diff --git "a/trainer_state.json" "b/trainer_state.json" --- "a/trainer_state.json" +++ "b/trainer_state.json" @@ -1,16816 +1,18106 @@ { "best_metric": null, "best_model_checkpoint": null, - "epoch": 0.9994610049580405, - "global_step": 280000, + "epoch": 0.9991549435800566, + "global_step": 301500, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, - "learning_rate": 4.9982152482054324e-05, - "loss": 3.7407, + "learning_rate": 4.9983430266275624e-05, + "loss": 3.5378, "step": 100 }, { "epoch": 0.0, - "learning_rate": 4.9964304964108645e-05, - "loss": 3.683, + "learning_rate": 4.9966860532551245e-05, + "loss": 3.514, "step": 200 }, { "epoch": 0.0, - "learning_rate": 4.9946457446162966e-05, - "loss": 3.6456, + "learning_rate": 4.995029079882687e-05, + "loss": 3.5069, "step": 300 }, { "epoch": 0.0, - "learning_rate": 4.992860992821729e-05, - "loss": 3.6417, + "learning_rate": 4.993372106510248e-05, + "loss": 3.5127, "step": 400 }, { "epoch": 0.0, - "learning_rate": 4.991076241027161e-05, - "loss": 3.6261, + "learning_rate": 4.991715133137811e-05, + "loss": 3.4982, "step": 500 }, { "epoch": 0.0, - "learning_rate": 4.989291489232592e-05, - "loss": 3.6141, + "learning_rate": 4.990058159765373e-05, + "loss": 3.4956, "step": 600 }, { "epoch": 0.0, - "learning_rate": 4.9875067374380244e-05, - "loss": 3.6185, + "learning_rate": 4.9884011863929346e-05, + "loss": 3.5026, "step": 700 }, { "epoch": 0.0, - "learning_rate": 4.9857219856434565e-05, - "loss": 3.6048, + "learning_rate": 4.9867442130204974e-05, + "loss": 3.4841, "step": 800 }, { "epoch": 0.0, - "learning_rate": 4.9839372338488887e-05, - "loss": 3.5957, + "learning_rate": 4.985087239648059e-05, + "loss": 3.4838, "step": 900 }, { "epoch": 0.0, - "learning_rate": 4.982152482054321e-05, - "loss": 3.5951, + "learning_rate": 4.983430266275621e-05, + "loss": 3.4808, "step": 1000 }, { "epoch": 0.0, - "learning_rate": 4.980367730259753e-05, - "loss": 3.5995, + "learning_rate": 4.981773292903183e-05, + "loss": 3.4918, "step": 1100 }, { "epoch": 0.0, - "learning_rate": 4.978582978465185e-05, - "loss": 3.5947, + "learning_rate": 4.980116319530745e-05, + "loss": 3.4975, "step": 1200 }, { "epoch": 0.0, - "learning_rate": 4.976798226670617e-05, - "loss": 3.5807, + "learning_rate": 4.9784593461583075e-05, + "loss": 3.4854, "step": 1300 }, { "epoch": 0.0, - "learning_rate": 4.975013474876049e-05, - "loss": 3.5755, + "learning_rate": 4.9768023727858696e-05, + "loss": 3.4789, "step": 1400 }, { - "epoch": 0.01, - "learning_rate": 4.9732287230814814e-05, - "loss": 3.5745, + "epoch": 0.0, + "learning_rate": 4.975145399413432e-05, + "loss": 3.4906, "step": 1500 }, { "epoch": 0.01, - "learning_rate": 4.9714439712869135e-05, - "loss": 3.561, + "learning_rate": 4.973488426040994e-05, + "loss": 3.4578, "step": 1600 }, { "epoch": 0.01, - "learning_rate": 4.969659219492345e-05, - "loss": 3.551, + "learning_rate": 4.971831452668556e-05, + "loss": 3.4764, "step": 1700 }, { "epoch": 0.01, - "learning_rate": 4.967874467697777e-05, - "loss": 3.5547, + "learning_rate": 4.970174479296118e-05, + "loss": 3.4731, "step": 1800 }, { "epoch": 0.01, - "learning_rate": 4.966089715903209e-05, - "loss": 3.5605, + "learning_rate": 4.96851750592368e-05, + "loss": 3.4722, "step": 1900 }, { "epoch": 0.01, - "learning_rate": 4.964304964108641e-05, - "loss": 3.5592, + "learning_rate": 4.9668605325512425e-05, + "loss": 3.4678, "step": 2000 }, { "epoch": 0.01, - "learning_rate": 4.9625202123140734e-05, - "loss": 3.5509, + "learning_rate": 4.9652035591788046e-05, + "loss": 3.469, "step": 2100 }, { "epoch": 0.01, - "learning_rate": 4.9607354605195056e-05, - "loss": 3.5405, + "learning_rate": 4.963546585806366e-05, + "loss": 3.4704, "step": 2200 }, { "epoch": 0.01, - "learning_rate": 4.958950708724938e-05, - "loss": 3.5333, + "learning_rate": 4.961889612433929e-05, + "loss": 3.4727, "step": 2300 }, { "epoch": 0.01, - "learning_rate": 4.95716595693037e-05, - "loss": 3.5285, + "learning_rate": 4.9602326390614904e-05, + "loss": 3.4653, "step": 2400 }, { "epoch": 0.01, - "learning_rate": 4.955381205135802e-05, - "loss": 3.5414, + "learning_rate": 4.9585756656890526e-05, + "loss": 3.4668, "step": 2500 }, { "epoch": 0.01, - "learning_rate": 4.953596453341234e-05, - "loss": 3.5267, + "learning_rate": 4.956918692316615e-05, + "loss": 3.4759, "step": 2600 }, { "epoch": 0.01, - "learning_rate": 4.951811701546666e-05, - "loss": 3.5223, + "learning_rate": 4.955261718944177e-05, + "loss": 3.4657, "step": 2700 }, { "epoch": 0.01, - "learning_rate": 4.950026949752098e-05, - "loss": 3.5173, + "learning_rate": 4.953604745571739e-05, + "loss": 3.4667, "step": 2800 }, { "epoch": 0.01, - "learning_rate": 4.9482421979575304e-05, - "loss": 3.5204, + "learning_rate": 4.9519477721993005e-05, + "loss": 3.4546, "step": 2900 }, { "epoch": 0.01, - "learning_rate": 4.9464574461629625e-05, - "loss": 3.5212, + "learning_rate": 4.950290798826863e-05, + "loss": 3.4739, "step": 3000 }, { "epoch": 0.01, - "learning_rate": 4.9446726943683947e-05, - "loss": 3.5148, + "learning_rate": 4.9486338254544254e-05, + "loss": 3.4613, "step": 3100 }, { "epoch": 0.01, - "learning_rate": 4.942887942573827e-05, - "loss": 3.5149, + "learning_rate": 4.946976852081987e-05, + "loss": 3.4704, "step": 3200 }, { "epoch": 0.01, - "learning_rate": 4.941103190779259e-05, - "loss": 3.5063, + "learning_rate": 4.94531987870955e-05, + "loss": 3.4573, "step": 3300 }, { "epoch": 0.01, - "learning_rate": 4.939318438984691e-05, - "loss": 3.5003, + "learning_rate": 4.943662905337111e-05, + "loss": 3.4579, "step": 3400 }, { "epoch": 0.01, - "learning_rate": 4.937533687190123e-05, - "loss": 3.5132, + "learning_rate": 4.9420059319646733e-05, + "loss": 3.458, "step": 3500 }, { "epoch": 0.01, - "learning_rate": 4.935748935395555e-05, - "loss": 3.5084, + "learning_rate": 4.9403489585922355e-05, + "loss": 3.4552, "step": 3600 }, { "epoch": 0.01, - "learning_rate": 4.933964183600987e-05, - "loss": 3.5029, + "learning_rate": 4.9386919852197976e-05, + "loss": 3.4614, "step": 3700 }, { "epoch": 0.01, - "learning_rate": 4.932179431806419e-05, - "loss": 3.5006, + "learning_rate": 4.93703501184736e-05, + "loss": 3.4539, "step": 3800 }, { "epoch": 0.01, - "learning_rate": 4.930394680011851e-05, - "loss": 3.4971, + "learning_rate": 4.935378038474922e-05, + "loss": 3.4479, "step": 3900 }, { "epoch": 0.01, - "learning_rate": 4.928609928217283e-05, - "loss": 3.495, + "learning_rate": 4.933721065102484e-05, + "loss": 3.4557, "step": 4000 }, { "epoch": 0.01, - "learning_rate": 4.926825176422715e-05, - "loss": 3.4947, + "learning_rate": 4.932064091730046e-05, + "loss": 3.4528, "step": 4100 }, { "epoch": 0.01, - "learning_rate": 4.925040424628147e-05, - "loss": 3.4926, + "learning_rate": 4.9304071183576084e-05, + "loss": 3.4577, "step": 4200 }, { - "epoch": 0.02, - "learning_rate": 4.9232556728335794e-05, - "loss": 3.4775, + "epoch": 0.01, + "learning_rate": 4.9287501449851705e-05, + "loss": 3.4513, "step": 4300 }, { - "epoch": 0.02, - "learning_rate": 4.9214709210390116e-05, - "loss": 3.4794, + "epoch": 0.01, + "learning_rate": 4.927093171612732e-05, + "loss": 3.4553, "step": 4400 }, { - "epoch": 0.02, - "learning_rate": 4.919686169244444e-05, - "loss": 3.4885, + "epoch": 0.01, + "learning_rate": 4.925436198240295e-05, + "loss": 3.4578, "step": 4500 }, { "epoch": 0.02, - "learning_rate": 4.917901417449876e-05, - "loss": 3.481, + "learning_rate": 4.923779224867856e-05, + "loss": 3.4565, "step": 4600 }, { "epoch": 0.02, - "learning_rate": 4.916116665655308e-05, - "loss": 3.4833, + "learning_rate": 4.9221222514954184e-05, + "loss": 3.4428, "step": 4700 }, { "epoch": 0.02, - "learning_rate": 4.9143319138607394e-05, - "loss": 3.4837, + "learning_rate": 4.920465278122981e-05, + "loss": 3.4565, "step": 4800 }, { "epoch": 0.02, - "learning_rate": 4.9125471620661715e-05, - "loss": 3.4811, + "learning_rate": 4.918808304750543e-05, + "loss": 3.4515, "step": 4900 }, { "epoch": 0.02, - "learning_rate": 4.9107624102716036e-05, - "loss": 3.4701, + "learning_rate": 4.917151331378105e-05, + "loss": 3.4574, "step": 5000 }, { "epoch": 0.02, - "learning_rate": 4.908977658477036e-05, - "loss": 3.4793, + "learning_rate": 4.915494358005667e-05, + "loss": 3.448, "step": 5100 }, { "epoch": 0.02, - "learning_rate": 4.907192906682468e-05, - "loss": 3.4697, + "learning_rate": 4.913837384633229e-05, + "loss": 3.4357, "step": 5200 }, { "epoch": 0.02, - "learning_rate": 4.9054081548879e-05, - "loss": 3.4811, + "learning_rate": 4.912180411260791e-05, + "loss": 3.4416, "step": 5300 }, { "epoch": 0.02, - "learning_rate": 4.903623403093332e-05, - "loss": 3.4576, + "learning_rate": 4.9105234378883535e-05, + "loss": 3.4606, "step": 5400 }, { "epoch": 0.02, - "learning_rate": 4.901838651298764e-05, - "loss": 3.4695, + "learning_rate": 4.9088664645159156e-05, + "loss": 3.4433, "step": 5500 }, { "epoch": 0.02, - "learning_rate": 4.900053899504196e-05, - "loss": 3.4782, + "learning_rate": 4.907209491143477e-05, + "loss": 3.4473, "step": 5600 }, { "epoch": 0.02, - "learning_rate": 4.8982691477096285e-05, - "loss": 3.4732, + "learning_rate": 4.90555251777104e-05, + "loss": 3.4431, "step": 5700 }, { "epoch": 0.02, - "learning_rate": 4.8964843959150606e-05, - "loss": 3.4601, + "learning_rate": 4.903895544398602e-05, + "loss": 3.4304, "step": 5800 }, { "epoch": 0.02, - "learning_rate": 4.894699644120492e-05, - "loss": 3.4604, + "learning_rate": 4.9022385710261635e-05, + "loss": 3.4333, "step": 5900 }, { "epoch": 0.02, - "learning_rate": 4.892914892325924e-05, - "loss": 3.46, + "learning_rate": 4.900581597653726e-05, + "loss": 3.4405, "step": 6000 }, { "epoch": 0.02, - "learning_rate": 4.891130140531356e-05, - "loss": 3.4513, + "learning_rate": 4.898924624281288e-05, + "loss": 3.45, "step": 6100 }, { "epoch": 0.02, - "learning_rate": 4.8893453887367884e-05, - "loss": 3.461, + "learning_rate": 4.89726765090885e-05, + "loss": 3.4323, "step": 6200 }, { "epoch": 0.02, - "learning_rate": 4.8875606369422205e-05, - "loss": 3.4633, + "learning_rate": 4.895610677536413e-05, + "loss": 3.4531, "step": 6300 }, { "epoch": 0.02, - "learning_rate": 4.8857758851476526e-05, - "loss": 3.4612, + "learning_rate": 4.893953704163974e-05, + "loss": 3.4347, "step": 6400 }, { "epoch": 0.02, - "learning_rate": 4.883991133353085e-05, - "loss": 3.4529, + "learning_rate": 4.8922967307915364e-05, + "loss": 3.4276, "step": 6500 }, { "epoch": 0.02, - "learning_rate": 4.882206381558517e-05, - "loss": 3.4606, + "learning_rate": 4.8906397574190985e-05, + "loss": 3.4396, "step": 6600 }, { "epoch": 0.02, - "learning_rate": 4.880421629763949e-05, - "loss": 3.4569, + "learning_rate": 4.888982784046661e-05, + "loss": 3.4336, "step": 6700 }, { "epoch": 0.02, - "learning_rate": 4.878636877969381e-05, - "loss": 3.4519, + "learning_rate": 4.887325810674223e-05, + "loss": 3.4227, "step": 6800 }, { "epoch": 0.02, - "learning_rate": 4.876852126174813e-05, - "loss": 3.4599, + "learning_rate": 4.885668837301785e-05, + "loss": 3.4389, "step": 6900 }, { "epoch": 0.02, - "learning_rate": 4.875067374380245e-05, - "loss": 3.4456, + "learning_rate": 4.884011863929347e-05, + "loss": 3.436, "step": 7000 }, { - "epoch": 0.03, - "learning_rate": 4.873282622585677e-05, - "loss": 3.4546, + "epoch": 0.02, + "learning_rate": 4.8823548905569086e-05, + "loss": 3.4434, "step": 7100 }, { - "epoch": 0.03, - "learning_rate": 4.871497870791109e-05, - "loss": 3.4449, + "epoch": 0.02, + "learning_rate": 4.8806979171844714e-05, + "loss": 3.4485, "step": 7200 }, { - "epoch": 0.03, - "learning_rate": 4.869713118996541e-05, - "loss": 3.4492, + "epoch": 0.02, + "learning_rate": 4.8790409438120336e-05, + "loss": 3.4207, "step": 7300 }, { - "epoch": 0.03, - "learning_rate": 4.867928367201973e-05, - "loss": 3.4504, + "epoch": 0.02, + "learning_rate": 4.877383970439595e-05, + "loss": 3.4238, "step": 7400 }, { - "epoch": 0.03, - "learning_rate": 4.866143615407405e-05, - "loss": 3.4437, + "epoch": 0.02, + "learning_rate": 4.875726997067158e-05, + "loss": 3.4369, "step": 7500 }, { "epoch": 0.03, - "learning_rate": 4.8643588636128374e-05, - "loss": 3.4374, + "learning_rate": 4.874070023694719e-05, + "loss": 3.4345, "step": 7600 }, { "epoch": 0.03, - "learning_rate": 4.86257411181827e-05, - "loss": 3.4463, + "learning_rate": 4.8724130503222815e-05, + "loss": 3.4325, "step": 7700 }, { "epoch": 0.03, - "learning_rate": 4.860789360023702e-05, - "loss": 3.4402, + "learning_rate": 4.8707560769498436e-05, + "loss": 3.4475, "step": 7800 }, { "epoch": 0.03, - "learning_rate": 4.859004608229134e-05, - "loss": 3.4325, + "learning_rate": 4.869099103577406e-05, + "loss": 3.427, "step": 7900 }, { "epoch": 0.03, - "learning_rate": 4.857219856434566e-05, - "loss": 3.4439, + "learning_rate": 4.867442130204968e-05, + "loss": 3.4285, "step": 8000 }, { "epoch": 0.03, - "learning_rate": 4.855435104639998e-05, - "loss": 3.4435, + "learning_rate": 4.8657851568325294e-05, + "loss": 3.448, "step": 8100 }, { "epoch": 0.03, - "learning_rate": 4.85365035284543e-05, - "loss": 3.4351, + "learning_rate": 4.864128183460092e-05, + "loss": 3.432, "step": 8200 }, { "epoch": 0.03, - "learning_rate": 4.851865601050862e-05, - "loss": 3.4371, + "learning_rate": 4.8624712100876544e-05, + "loss": 3.4294, "step": 8300 }, { "epoch": 0.03, - "learning_rate": 4.8500808492562944e-05, - "loss": 3.4317, + "learning_rate": 4.860814236715216e-05, + "loss": 3.4335, "step": 8400 }, { "epoch": 0.03, - "learning_rate": 4.8482960974617265e-05, - "loss": 3.4308, + "learning_rate": 4.8591572633427786e-05, + "loss": 3.4329, "step": 8500 }, { "epoch": 0.03, - "learning_rate": 4.8465113456671586e-05, - "loss": 3.4413, + "learning_rate": 4.85750028997034e-05, + "loss": 3.4347, "step": 8600 }, { "epoch": 0.03, - "learning_rate": 4.844726593872591e-05, - "loss": 3.4359, + "learning_rate": 4.855843316597902e-05, + "loss": 3.4302, "step": 8700 }, { "epoch": 0.03, - "learning_rate": 4.842941842078023e-05, - "loss": 3.428, + "learning_rate": 4.8541863432254644e-05, + "loss": 3.4159, "step": 8800 }, { "epoch": 0.03, - "learning_rate": 4.841157090283455e-05, - "loss": 3.4366, + "learning_rate": 4.8525293698530266e-05, + "loss": 3.4263, "step": 8900 }, { "epoch": 0.03, - "learning_rate": 4.8393723384888864e-05, - "loss": 3.4242, + "learning_rate": 4.850872396480589e-05, + "loss": 3.4375, "step": 9000 }, { "epoch": 0.03, - "learning_rate": 4.8375875866943186e-05, - "loss": 3.4312, + "learning_rate": 4.849215423108151e-05, + "loss": 3.4262, "step": 9100 }, { "epoch": 0.03, - "learning_rate": 4.835802834899751e-05, - "loss": 3.4329, + "learning_rate": 4.847558449735713e-05, + "loss": 3.4365, "step": 9200 }, { "epoch": 0.03, - "learning_rate": 4.834018083105183e-05, - "loss": 3.4315, + "learning_rate": 4.845901476363275e-05, + "loss": 3.4249, "step": 9300 }, { "epoch": 0.03, - "learning_rate": 4.832233331310615e-05, - "loss": 3.419, + "learning_rate": 4.844244502990837e-05, + "loss": 3.4318, "step": 9400 }, { "epoch": 0.03, - "learning_rate": 4.830448579516047e-05, - "loss": 3.4264, + "learning_rate": 4.8425875296183994e-05, + "loss": 3.4298, "step": 9500 }, { "epoch": 0.03, - "learning_rate": 4.828663827721479e-05, - "loss": 3.4183, + "learning_rate": 4.840930556245961e-05, + "loss": 3.418, "step": 9600 }, { "epoch": 0.03, - "learning_rate": 4.826879075926911e-05, - "loss": 3.4186, + "learning_rate": 4.839273582873524e-05, + "loss": 3.4355, "step": 9700 }, { "epoch": 0.03, - "learning_rate": 4.8250943241323434e-05, - "loss": 3.4089, + "learning_rate": 4.837616609501085e-05, + "loss": 3.4177, "step": 9800 }, { - "epoch": 0.04, - "learning_rate": 4.8233095723377755e-05, - "loss": 3.4186, + "epoch": 0.03, + "learning_rate": 4.8359596361286473e-05, + "loss": 3.4327, "step": 9900 }, { - "epoch": 0.04, - "learning_rate": 4.8215248205432076e-05, - "loss": 3.417, + "epoch": 0.03, + "learning_rate": 4.83430266275621e-05, + "loss": 3.4235, "step": 10000 }, { - "epoch": 0.04, - "learning_rate": 4.819740068748639e-05, - "loss": 3.4059, + "epoch": 0.03, + "learning_rate": 4.8326456893837716e-05, + "loss": 3.4211, "step": 10100 }, { - "epoch": 0.04, - "learning_rate": 4.817955316954071e-05, - "loss": 3.414, + "epoch": 0.03, + "learning_rate": 4.830988716011334e-05, + "loss": 3.4231, "step": 10200 }, { - "epoch": 0.04, - "learning_rate": 4.816170565159503e-05, - "loss": 3.4068, + "epoch": 0.03, + "learning_rate": 4.829331742638896e-05, + "loss": 3.4216, "step": 10300 }, { - "epoch": 0.04, - "learning_rate": 4.8143858133649355e-05, - "loss": 3.4198, + "epoch": 0.03, + "learning_rate": 4.827674769266458e-05, + "loss": 3.424, "step": 10400 }, { - "epoch": 0.04, - "learning_rate": 4.8126010615703676e-05, - "loss": 3.4168, + "epoch": 0.03, + "learning_rate": 4.82601779589402e-05, + "loss": 3.4257, "step": 10500 }, { "epoch": 0.04, - "learning_rate": 4.8108163097758e-05, - "loss": 3.4076, + "learning_rate": 4.8243608225215824e-05, + "loss": 3.4235, "step": 10600 }, { "epoch": 0.04, - "learning_rate": 4.809031557981232e-05, - "loss": 3.4179, + "learning_rate": 4.8227038491491445e-05, + "loss": 3.4238, "step": 10700 }, { "epoch": 0.04, - "learning_rate": 4.807246806186664e-05, - "loss": 3.4181, + "learning_rate": 4.821046875776707e-05, + "loss": 3.4137, "step": 10800 }, { "epoch": 0.04, - "learning_rate": 4.805462054392096e-05, - "loss": 3.401, + "learning_rate": 4.819389902404269e-05, + "loss": 3.4133, "step": 10900 }, { "epoch": 0.04, - "learning_rate": 4.803677302597528e-05, - "loss": 3.414, + "learning_rate": 4.817732929031831e-05, + "loss": 3.4209, "step": 11000 }, { "epoch": 0.04, - "learning_rate": 4.80189255080296e-05, - "loss": 3.412, + "learning_rate": 4.8160759556593924e-05, + "loss": 3.4163, "step": 11100 }, { "epoch": 0.04, - "learning_rate": 4.800107799008392e-05, - "loss": 3.3987, + "learning_rate": 4.814418982286955e-05, + "loss": 3.415, "step": 11200 }, { "epoch": 0.04, - "learning_rate": 4.798323047213824e-05, - "loss": 3.4114, + "learning_rate": 4.812762008914517e-05, + "loss": 3.4154, "step": 11300 }, { "epoch": 0.04, - "learning_rate": 4.796538295419256e-05, - "loss": 3.4072, + "learning_rate": 4.811105035542079e-05, + "loss": 3.4228, "step": 11400 }, { "epoch": 0.04, - "learning_rate": 4.794753543624688e-05, - "loss": 3.4024, + "learning_rate": 4.809448062169642e-05, + "loss": 3.4223, "step": 11500 }, { "epoch": 0.04, - "learning_rate": 4.79296879183012e-05, - "loss": 3.3962, + "learning_rate": 4.807791088797203e-05, + "loss": 3.4198, "step": 11600 }, { "epoch": 0.04, - "learning_rate": 4.7911840400355524e-05, - "loss": 3.4084, + "learning_rate": 4.806134115424765e-05, + "loss": 3.425, "step": 11700 }, { "epoch": 0.04, - "learning_rate": 4.7893992882409845e-05, - "loss": 3.4085, + "learning_rate": 4.8044771420523275e-05, + "loss": 3.4335, "step": 11800 }, { "epoch": 0.04, - "learning_rate": 4.7876145364464166e-05, - "loss": 3.3944, + "learning_rate": 4.8028201686798896e-05, + "loss": 3.4286, "step": 11900 }, { "epoch": 0.04, - "learning_rate": 4.785829784651849e-05, - "loss": 3.4071, + "learning_rate": 4.801163195307452e-05, + "loss": 3.4065, "step": 12000 }, { "epoch": 0.04, - "learning_rate": 4.784045032857281e-05, - "loss": 3.4007, + "learning_rate": 4.799506221935014e-05, + "loss": 3.4247, "step": 12100 }, { "epoch": 0.04, - "learning_rate": 4.782260281062712e-05, - "loss": 3.3963, + "learning_rate": 4.797849248562576e-05, + "loss": 3.4133, "step": 12200 }, { "epoch": 0.04, - "learning_rate": 4.7804755292681444e-05, - "loss": 3.4013, + "learning_rate": 4.7961922751901375e-05, + "loss": 3.4108, "step": 12300 }, { "epoch": 0.04, - "learning_rate": 4.7786907774735765e-05, - "loss": 3.3886, + "learning_rate": 4.7945353018177e-05, + "loss": 3.4284, "step": 12400 }, { "epoch": 0.04, - "learning_rate": 4.7769060256790086e-05, - "loss": 3.3897, + "learning_rate": 4.7928783284452625e-05, + "loss": 3.4118, "step": 12500 }, { "epoch": 0.04, - "learning_rate": 4.775121273884441e-05, - "loss": 3.3999, + "learning_rate": 4.791221355072824e-05, + "loss": 3.4014, "step": 12600 }, { - "epoch": 0.05, - "learning_rate": 4.773336522089873e-05, - "loss": 3.3972, + "epoch": 0.04, + "learning_rate": 4.789564381700387e-05, + "loss": 3.4246, "step": 12700 }, { - "epoch": 0.05, - "learning_rate": 4.771551770295306e-05, - "loss": 3.3921, + "epoch": 0.04, + "learning_rate": 4.787907408327948e-05, + "loss": 3.415, "step": 12800 }, { - "epoch": 0.05, - "learning_rate": 4.769767018500738e-05, - "loss": 3.3902, + "epoch": 0.04, + "learning_rate": 4.7862504349555104e-05, + "loss": 3.4196, "step": 12900 }, { - "epoch": 0.05, - "learning_rate": 4.76798226670617e-05, - "loss": 3.3933, + "epoch": 0.04, + "learning_rate": 4.7845934615830725e-05, + "loss": 3.402, "step": 13000 }, { - "epoch": 0.05, - "learning_rate": 4.7661975149116014e-05, - "loss": 3.3873, + "epoch": 0.04, + "learning_rate": 4.782936488210635e-05, + "loss": 3.4146, "step": 13100 }, { - "epoch": 0.05, - "learning_rate": 4.7644127631170335e-05, - "loss": 3.3896, + "epoch": 0.04, + "learning_rate": 4.781279514838197e-05, + "loss": 3.4131, "step": 13200 }, { - "epoch": 0.05, - "learning_rate": 4.7626280113224656e-05, - "loss": 3.3915, + "epoch": 0.04, + "learning_rate": 4.779622541465758e-05, + "loss": 3.4164, "step": 13300 }, { - "epoch": 0.05, - "learning_rate": 4.760843259527898e-05, - "loss": 3.3964, + "epoch": 0.04, + "learning_rate": 4.777965568093321e-05, + "loss": 3.4111, "step": 13400 }, { - "epoch": 0.05, - "learning_rate": 4.75905850773333e-05, - "loss": 3.3892, + "epoch": 0.04, + "learning_rate": 4.776308594720883e-05, + "loss": 3.4213, "step": 13500 }, { "epoch": 0.05, - "learning_rate": 4.757273755938762e-05, - "loss": 3.3968, + "learning_rate": 4.774651621348445e-05, + "loss": 3.4171, "step": 13600 }, { "epoch": 0.05, - "learning_rate": 4.755489004144194e-05, - "loss": 3.3826, + "learning_rate": 4.7729946479760076e-05, + "loss": 3.4094, "step": 13700 }, { "epoch": 0.05, - "learning_rate": 4.753704252349626e-05, - "loss": 3.3823, + "learning_rate": 4.771337674603569e-05, + "loss": 3.4074, "step": 13800 }, { "epoch": 0.05, - "learning_rate": 4.7519195005550584e-05, - "loss": 3.393, + "learning_rate": 4.769680701231131e-05, + "loss": 3.4065, "step": 13900 }, { "epoch": 0.05, - "learning_rate": 4.7501347487604905e-05, - "loss": 3.3895, + "learning_rate": 4.768023727858694e-05, + "loss": 3.4266, "step": 14000 }, { "epoch": 0.05, - "learning_rate": 4.7483499969659226e-05, - "loss": 3.386, + "learning_rate": 4.7663667544862555e-05, + "loss": 3.4083, "step": 14100 }, { "epoch": 0.05, - "learning_rate": 4.746565245171354e-05, - "loss": 3.3859, + "learning_rate": 4.7647097811138176e-05, + "loss": 3.4123, "step": 14200 }, { "epoch": 0.05, - "learning_rate": 4.744780493376786e-05, - "loss": 3.3874, + "learning_rate": 4.76305280774138e-05, + "loss": 3.4197, "step": 14300 }, { "epoch": 0.05, - "learning_rate": 4.742995741582218e-05, - "loss": 3.3776, + "learning_rate": 4.761395834368942e-05, + "loss": 3.4043, "step": 14400 }, { "epoch": 0.05, - "learning_rate": 4.7412109897876504e-05, - "loss": 3.3787, + "learning_rate": 4.759738860996504e-05, + "loss": 3.4132, "step": 14500 }, { "epoch": 0.05, - "learning_rate": 4.7394262379930825e-05, - "loss": 3.3793, + "learning_rate": 4.758081887624066e-05, + "loss": 3.407, "step": 14600 }, { "epoch": 0.05, - "learning_rate": 4.7376414861985146e-05, - "loss": 3.3718, + "learning_rate": 4.7564249142516284e-05, + "loss": 3.4026, "step": 14700 }, { "epoch": 0.05, - "learning_rate": 4.735856734403947e-05, - "loss": 3.3769, + "learning_rate": 4.75476794087919e-05, + "loss": 3.4, "step": 14800 }, { "epoch": 0.05, - "learning_rate": 4.734071982609379e-05, - "loss": 3.3869, + "learning_rate": 4.7531109675067526e-05, + "loss": 3.4033, "step": 14900 }, { "epoch": 0.05, - "learning_rate": 4.732287230814811e-05, - "loss": 3.3763, + "learning_rate": 4.751453994134315e-05, + "loss": 3.4167, "step": 15000 }, { "epoch": 0.05, - "learning_rate": 4.730502479020243e-05, - "loss": 3.3748, + "learning_rate": 4.749797020761876e-05, + "loss": 3.4197, "step": 15100 }, { "epoch": 0.05, - "learning_rate": 4.728717727225675e-05, - "loss": 3.3861, + "learning_rate": 4.748140047389439e-05, + "loss": 3.4082, "step": 15200 }, { "epoch": 0.05, - "learning_rate": 4.726932975431107e-05, - "loss": 3.3771, + "learning_rate": 4.7464830740170006e-05, + "loss": 3.4074, "step": 15300 }, { "epoch": 0.05, - "learning_rate": 4.725148223636539e-05, - "loss": 3.3799, + "learning_rate": 4.744826100644563e-05, + "loss": 3.4169, "step": 15400 }, { - "epoch": 0.06, - "learning_rate": 4.723363471841971e-05, - "loss": 3.385, + "epoch": 0.05, + "learning_rate": 4.743169127272125e-05, + "loss": 3.4184, "step": 15500 }, { - "epoch": 0.06, - "learning_rate": 4.721578720047403e-05, - "loss": 3.3789, + "epoch": 0.05, + "learning_rate": 4.741512153899687e-05, + "loss": 3.4086, "step": 15600 }, { - "epoch": 0.06, - "learning_rate": 4.719793968252835e-05, - "loss": 3.3697, + "epoch": 0.05, + "learning_rate": 4.739855180527249e-05, + "loss": 3.4219, "step": 15700 }, { - "epoch": 0.06, - "learning_rate": 4.718009216458267e-05, - "loss": 3.3763, + "epoch": 0.05, + "learning_rate": 4.738198207154811e-05, + "loss": 3.4063, "step": 15800 }, { - "epoch": 0.06, - "learning_rate": 4.7162244646636994e-05, - "loss": 3.3736, + "epoch": 0.05, + "learning_rate": 4.7365412337823734e-05, + "loss": 3.4125, "step": 15900 }, { - "epoch": 0.06, - "learning_rate": 4.7144397128691315e-05, - "loss": 3.375, + "epoch": 0.05, + "learning_rate": 4.7348842604099356e-05, + "loss": 3.4047, "step": 16000 }, { - "epoch": 0.06, - "learning_rate": 4.712654961074564e-05, - "loss": 3.3701, + "epoch": 0.05, + "learning_rate": 4.733227287037498e-05, + "loss": 3.3953, "step": 16100 }, { - "epoch": 0.06, - "learning_rate": 4.710870209279996e-05, - "loss": 3.3719, + "epoch": 0.05, + "learning_rate": 4.73157031366506e-05, + "loss": 3.4067, "step": 16200 }, { - "epoch": 0.06, - "learning_rate": 4.709085457485428e-05, - "loss": 3.3794, + "epoch": 0.05, + "learning_rate": 4.7299133402926213e-05, + "loss": 3.3954, "step": 16300 }, { - "epoch": 0.06, - "learning_rate": 4.7073007056908594e-05, - "loss": 3.3706, + "epoch": 0.05, + "learning_rate": 4.728256366920184e-05, + "loss": 3.4103, "step": 16400 }, { - "epoch": 0.06, - "learning_rate": 4.7055159538962915e-05, - "loss": 3.3823, + "epoch": 0.05, + "learning_rate": 4.7265993935477456e-05, + "loss": 3.4191, "step": 16500 }, { "epoch": 0.06, - "learning_rate": 4.7037312021017236e-05, - "loss": 3.3648, + "learning_rate": 4.724942420175308e-05, + "loss": 3.4117, "step": 16600 }, { "epoch": 0.06, - "learning_rate": 4.701946450307156e-05, - "loss": 3.3694, + "learning_rate": 4.7232854468028706e-05, + "loss": 3.4006, "step": 16700 }, { "epoch": 0.06, - "learning_rate": 4.700161698512588e-05, - "loss": 3.3593, + "learning_rate": 4.721628473430432e-05, + "loss": 3.3984, "step": 16800 }, { "epoch": 0.06, - "learning_rate": 4.69837694671802e-05, - "loss": 3.3631, + "learning_rate": 4.719971500057994e-05, + "loss": 3.3922, "step": 16900 }, { "epoch": 0.06, - "learning_rate": 4.696592194923452e-05, - "loss": 3.3773, + "learning_rate": 4.7183145266855564e-05, + "loss": 3.4097, "step": 17000 }, { "epoch": 0.06, - "learning_rate": 4.694807443128884e-05, - "loss": 3.368, + "learning_rate": 4.7166575533131185e-05, + "loss": 3.392, "step": 17100 }, { "epoch": 0.06, - "learning_rate": 4.693022691334316e-05, - "loss": 3.3651, + "learning_rate": 4.715000579940681e-05, + "loss": 3.4108, "step": 17200 }, { "epoch": 0.06, - "learning_rate": 4.6912379395397484e-05, - "loss": 3.3726, + "learning_rate": 4.713343606568243e-05, + "loss": 3.4029, "step": 17300 }, { "epoch": 0.06, - "learning_rate": 4.6894531877451806e-05, - "loss": 3.3633, + "learning_rate": 4.711686633195805e-05, + "loss": 3.4124, "step": 17400 }, { "epoch": 0.06, - "learning_rate": 4.687668435950612e-05, - "loss": 3.3696, + "learning_rate": 4.7100296598233664e-05, + "loss": 3.4116, "step": 17500 }, { "epoch": 0.06, - "learning_rate": 4.685883684156044e-05, - "loss": 3.3669, + "learning_rate": 4.708372686450929e-05, + "loss": 3.3832, "step": 17600 }, { "epoch": 0.06, - "learning_rate": 4.684098932361476e-05, - "loss": 3.3671, + "learning_rate": 4.7067157130784914e-05, + "loss": 3.4012, "step": 17700 }, { "epoch": 0.06, - "learning_rate": 4.6823141805669084e-05, - "loss": 3.368, + "learning_rate": 4.705058739706053e-05, + "loss": 3.4056, "step": 17800 }, { "epoch": 0.06, - "learning_rate": 4.680529428772341e-05, - "loss": 3.3717, + "learning_rate": 4.703401766333616e-05, + "loss": 3.3942, "step": 17900 }, { "epoch": 0.06, - "learning_rate": 4.678744676977773e-05, - "loss": 3.3482, + "learning_rate": 4.701744792961177e-05, + "loss": 3.3928, "step": 18000 }, { "epoch": 0.06, - "learning_rate": 4.6769599251832054e-05, - "loss": 3.3694, + "learning_rate": 4.700087819588739e-05, + "loss": 3.4021, "step": 18100 }, { "epoch": 0.06, - "learning_rate": 4.6751751733886375e-05, - "loss": 3.3442, + "learning_rate": 4.6984308462163015e-05, + "loss": 3.4048, "step": 18200 }, { - "epoch": 0.07, - "learning_rate": 4.67339042159407e-05, - "loss": 3.3578, + "epoch": 0.06, + "learning_rate": 4.6967738728438636e-05, + "loss": 3.4163, "step": 18300 }, { - "epoch": 0.07, - "learning_rate": 4.671605669799501e-05, - "loss": 3.3744, + "epoch": 0.06, + "learning_rate": 4.695116899471426e-05, + "loss": 3.4177, "step": 18400 }, { - "epoch": 0.07, - "learning_rate": 4.669820918004933e-05, - "loss": 3.3605, + "epoch": 0.06, + "learning_rate": 4.693459926098987e-05, + "loss": 3.396, "step": 18500 }, { - "epoch": 0.07, - "learning_rate": 4.6680361662103654e-05, - "loss": 3.3602, + "epoch": 0.06, + "learning_rate": 4.69180295272655e-05, + "loss": 3.4118, "step": 18600 }, { - "epoch": 0.07, - "learning_rate": 4.6662514144157975e-05, - "loss": 3.3636, + "epoch": 0.06, + "learning_rate": 4.690145979354112e-05, + "loss": 3.4093, "step": 18700 }, { - "epoch": 0.07, - "learning_rate": 4.6644666626212296e-05, - "loss": 3.3624, + "epoch": 0.06, + "learning_rate": 4.6884890059816737e-05, + "loss": 3.3996, "step": 18800 }, { - "epoch": 0.07, - "learning_rate": 4.662681910826662e-05, - "loss": 3.3529, + "epoch": 0.06, + "learning_rate": 4.6868320326092365e-05, + "loss": 3.3824, "step": 18900 }, { - "epoch": 0.07, - "learning_rate": 4.660897159032094e-05, - "loss": 3.3654, + "epoch": 0.06, + "learning_rate": 4.685175059236798e-05, + "loss": 3.407, "step": 19000 }, { - "epoch": 0.07, - "learning_rate": 4.659112407237526e-05, - "loss": 3.3453, + "epoch": 0.06, + "learning_rate": 4.68351808586436e-05, + "loss": 3.3897, "step": 19100 }, { - "epoch": 0.07, - "learning_rate": 4.657327655442958e-05, - "loss": 3.3585, + "epoch": 0.06, + "learning_rate": 4.681861112491923e-05, + "loss": 3.4016, "step": 19200 }, { - "epoch": 0.07, - "learning_rate": 4.65554290364839e-05, - "loss": 3.3572, + "epoch": 0.06, + "learning_rate": 4.6802041391194844e-05, + "loss": 3.4079, "step": 19300 }, { - "epoch": 0.07, - "learning_rate": 4.653758151853822e-05, - "loss": 3.347, + "epoch": 0.06, + "learning_rate": 4.6785471657470465e-05, + "loss": 3.381, "step": 19400 }, { - "epoch": 0.07, - "learning_rate": 4.651973400059254e-05, - "loss": 3.3518, + "epoch": 0.06, + "learning_rate": 4.676890192374609e-05, + "loss": 3.3918, "step": 19500 }, { - "epoch": 0.07, - "learning_rate": 4.650188648264686e-05, - "loss": 3.3574, + "epoch": 0.06, + "learning_rate": 4.675233219002171e-05, + "loss": 3.401, "step": 19600 }, { "epoch": 0.07, - "learning_rate": 4.648403896470118e-05, - "loss": 3.3518, + "learning_rate": 4.673576245629733e-05, + "loss": 3.4038, "step": 19700 }, { "epoch": 0.07, - "learning_rate": 4.64661914467555e-05, - "loss": 3.3544, + "learning_rate": 4.671919272257295e-05, + "loss": 3.3924, "step": 19800 }, { "epoch": 0.07, - "learning_rate": 4.644834392880982e-05, - "loss": 3.34, + "learning_rate": 4.670262298884857e-05, + "loss": 3.3818, "step": 19900 }, { "epoch": 0.07, - "learning_rate": 4.6430496410864144e-05, - "loss": 3.3534, + "learning_rate": 4.668605325512419e-05, + "loss": 3.3995, "step": 20000 }, { "epoch": 0.07, - "learning_rate": 4.6412648892918465e-05, - "loss": 3.3596, + "learning_rate": 4.6669483521399816e-05, + "loss": 3.3896, "step": 20100 }, { "epoch": 0.07, - "learning_rate": 4.6394801374972786e-05, - "loss": 3.3505, + "learning_rate": 4.665291378767544e-05, + "loss": 3.3971, "step": 20200 }, { "epoch": 0.07, - "learning_rate": 4.637695385702711e-05, - "loss": 3.3546, + "learning_rate": 4.663634405395105e-05, + "loss": 3.3955, "step": 20300 }, { "epoch": 0.07, - "learning_rate": 4.635910633908143e-05, - "loss": 3.3466, + "learning_rate": 4.661977432022668e-05, + "loss": 3.3989, "step": 20400 }, { "epoch": 0.07, - "learning_rate": 4.634125882113575e-05, - "loss": 3.351, + "learning_rate": 4.6603204586502295e-05, + "loss": 3.4087, "step": 20500 }, { "epoch": 0.07, - "learning_rate": 4.6323411303190064e-05, - "loss": 3.3457, + "learning_rate": 4.6586634852777916e-05, + "loss": 3.3976, "step": 20600 }, { "epoch": 0.07, - "learning_rate": 4.6305563785244385e-05, - "loss": 3.3432, + "learning_rate": 4.657006511905354e-05, + "loss": 3.3939, "step": 20700 }, { "epoch": 0.07, - "learning_rate": 4.628771626729871e-05, - "loss": 3.348, + "learning_rate": 4.655349538532916e-05, + "loss": 3.3986, "step": 20800 }, { "epoch": 0.07, - "learning_rate": 4.626986874935303e-05, - "loss": 3.3458, + "learning_rate": 4.653692565160478e-05, + "loss": 3.3876, "step": 20900 }, { "epoch": 0.07, - "learning_rate": 4.625202123140735e-05, - "loss": 3.3577, + "learning_rate": 4.65203559178804e-05, + "loss": 3.3986, "step": 21000 }, { - "epoch": 0.08, - "learning_rate": 4.623417371346167e-05, - "loss": 3.3427, + "epoch": 0.07, + "learning_rate": 4.6503786184156024e-05, + "loss": 3.3863, "step": 21100 }, { - "epoch": 0.08, - "learning_rate": 4.621632619551599e-05, - "loss": 3.349, + "epoch": 0.07, + "learning_rate": 4.6487216450431645e-05, + "loss": 3.3764, "step": 21200 }, { - "epoch": 0.08, - "learning_rate": 4.619847867757031e-05, - "loss": 3.3386, + "epoch": 0.07, + "learning_rate": 4.6470646716707266e-05, + "loss": 3.4007, "step": 21300 }, { - "epoch": 0.08, - "learning_rate": 4.6180631159624634e-05, - "loss": 3.3494, + "epoch": 0.07, + "learning_rate": 4.645407698298289e-05, + "loss": 3.3963, "step": 21400 }, { - "epoch": 0.08, - "learning_rate": 4.6162783641678955e-05, - "loss": 3.3534, + "epoch": 0.07, + "learning_rate": 4.64375072492585e-05, + "loss": 3.3888, "step": 21500 }, { - "epoch": 0.08, - "learning_rate": 4.6144936123733276e-05, - "loss": 3.3411, + "epoch": 0.07, + "learning_rate": 4.642093751553413e-05, + "loss": 3.3853, "step": 21600 }, { - "epoch": 0.08, - "learning_rate": 4.612708860578759e-05, - "loss": 3.3485, + "epoch": 0.07, + "learning_rate": 4.6404367781809746e-05, + "loss": 3.391, "step": 21700 }, { - "epoch": 0.08, - "learning_rate": 4.610924108784191e-05, - "loss": 3.3435, + "epoch": 0.07, + "learning_rate": 4.638779804808537e-05, + "loss": 3.389, "step": 21800 }, { - "epoch": 0.08, - "learning_rate": 4.609139356989623e-05, - "loss": 3.3327, + "epoch": 0.07, + "learning_rate": 4.6371228314360995e-05, + "loss": 3.3916, "step": 21900 }, { - "epoch": 0.08, - "learning_rate": 4.6073546051950554e-05, - "loss": 3.3438, + "epoch": 0.07, + "learning_rate": 4.635465858063661e-05, + "loss": 3.3929, "step": 22000 }, { - "epoch": 0.08, - "learning_rate": 4.6055698534004876e-05, - "loss": 3.345, + "epoch": 0.07, + "learning_rate": 4.633808884691223e-05, + "loss": 3.399, "step": 22100 }, { - "epoch": 0.08, - "learning_rate": 4.60378510160592e-05, - "loss": 3.3465, + "epoch": 0.07, + "learning_rate": 4.632151911318785e-05, + "loss": 3.3957, "step": 22200 }, { - "epoch": 0.08, - "learning_rate": 4.602000349811352e-05, - "loss": 3.3407, + "epoch": 0.07, + "learning_rate": 4.6304949379463474e-05, + "loss": 3.3903, "step": 22300 }, { - "epoch": 0.08, - "learning_rate": 4.600215598016784e-05, - "loss": 3.3409, + "epoch": 0.07, + "learning_rate": 4.6288379645739096e-05, + "loss": 3.3814, "step": 22400 }, { - "epoch": 0.08, - "learning_rate": 4.598430846222216e-05, - "loss": 3.3333, + "epoch": 0.07, + "learning_rate": 4.627180991201472e-05, + "loss": 3.3954, "step": 22500 }, { - "epoch": 0.08, - "learning_rate": 4.596646094427648e-05, - "loss": 3.3439, + "epoch": 0.07, + "learning_rate": 4.625524017829034e-05, + "loss": 3.3799, "step": 22600 }, { "epoch": 0.08, - "learning_rate": 4.59486134263308e-05, - "loss": 3.3357, + "learning_rate": 4.623867044456596e-05, + "loss": 3.3879, "step": 22700 }, { "epoch": 0.08, - "learning_rate": 4.593076590838512e-05, - "loss": 3.3429, + "learning_rate": 4.622210071084158e-05, + "loss": 3.3831, "step": 22800 }, { "epoch": 0.08, - "learning_rate": 4.591291839043944e-05, - "loss": 3.3325, + "learning_rate": 4.62055309771172e-05, + "loss": 3.38, "step": 22900 }, { "epoch": 0.08, - "learning_rate": 4.589507087249377e-05, - "loss": 3.3429, + "learning_rate": 4.618896124339282e-05, + "loss": 3.3887, "step": 23000 }, { "epoch": 0.08, - "learning_rate": 4.587722335454809e-05, - "loss": 3.3367, + "learning_rate": 4.6172391509668446e-05, + "loss": 3.3955, "step": 23100 }, { "epoch": 0.08, - "learning_rate": 4.585937583660241e-05, - "loss": 3.3421, + "learning_rate": 4.615582177594406e-05, + "loss": 3.3872, "step": 23200 }, { "epoch": 0.08, - "learning_rate": 4.584152831865673e-05, - "loss": 3.3329, + "learning_rate": 4.613925204221968e-05, + "loss": 3.3873, "step": 23300 }, { "epoch": 0.08, - "learning_rate": 4.582368080071105e-05, - "loss": 3.3413, + "learning_rate": 4.6122682308495304e-05, + "loss": 3.3933, "step": 23400 }, { "epoch": 0.08, - "learning_rate": 4.580583328276537e-05, - "loss": 3.3334, + "learning_rate": 4.6106112574770925e-05, + "loss": 3.3814, "step": 23500 }, { "epoch": 0.08, - "learning_rate": 4.5787985764819694e-05, - "loss": 3.343, + "learning_rate": 4.608954284104655e-05, + "loss": 3.3858, "step": 23600 }, { "epoch": 0.08, - "learning_rate": 4.577013824687401e-05, - "loss": 3.3429, + "learning_rate": 4.607297310732217e-05, + "loss": 3.38, "step": 23700 }, { "epoch": 0.08, - "learning_rate": 4.575229072892833e-05, - "loss": 3.3178, + "learning_rate": 4.605640337359779e-05, + "loss": 3.3847, "step": 23800 }, { - "epoch": 0.09, - "learning_rate": 4.573444321098265e-05, - "loss": 3.3151, + "epoch": 0.08, + "learning_rate": 4.603983363987341e-05, + "loss": 3.3922, "step": 23900 }, { - "epoch": 0.09, - "learning_rate": 4.571659569303697e-05, - "loss": 3.3287, + "epoch": 0.08, + "learning_rate": 4.6023263906149026e-05, + "loss": 3.3749, "step": 24000 }, { - "epoch": 0.09, - "learning_rate": 4.569874817509129e-05, - "loss": 3.3334, + "epoch": 0.08, + "learning_rate": 4.6006694172424654e-05, + "loss": 3.3809, "step": 24100 }, { - "epoch": 0.09, - "learning_rate": 4.5680900657145614e-05, - "loss": 3.3309, + "epoch": 0.08, + "learning_rate": 4.599012443870027e-05, + "loss": 3.4017, "step": 24200 }, { - "epoch": 0.09, - "learning_rate": 4.5663053139199936e-05, - "loss": 3.3352, + "epoch": 0.08, + "learning_rate": 4.597355470497589e-05, + "loss": 3.3997, "step": 24300 }, { - "epoch": 0.09, - "learning_rate": 4.564520562125426e-05, - "loss": 3.3387, + "epoch": 0.08, + "learning_rate": 4.595698497125152e-05, + "loss": 3.3871, "step": 24400 }, { - "epoch": 0.09, - "learning_rate": 4.562735810330858e-05, - "loss": 3.3391, + "epoch": 0.08, + "learning_rate": 4.594041523752713e-05, + "loss": 3.3821, "step": 24500 }, { - "epoch": 0.09, - "learning_rate": 4.56095105853629e-05, - "loss": 3.3272, + "epoch": 0.08, + "learning_rate": 4.5923845503802755e-05, + "loss": 3.3837, "step": 24600 }, { - "epoch": 0.09, - "learning_rate": 4.559166306741722e-05, - "loss": 3.3366, + "epoch": 0.08, + "learning_rate": 4.5907275770078376e-05, + "loss": 3.3859, "step": 24700 }, { - "epoch": 0.09, - "learning_rate": 4.5573815549471535e-05, - "loss": 3.347, + "epoch": 0.08, + "learning_rate": 4.5890706036354e-05, + "loss": 3.3932, "step": 24800 }, { - "epoch": 0.09, - "learning_rate": 4.5555968031525856e-05, - "loss": 3.3299, + "epoch": 0.08, + "learning_rate": 4.587413630262962e-05, + "loss": 3.3755, "step": 24900 }, { - "epoch": 0.09, - "learning_rate": 4.553812051358018e-05, - "loss": 3.3157, + "epoch": 0.08, + "learning_rate": 4.585756656890524e-05, + "loss": 3.3716, "step": 25000 }, { - "epoch": 0.09, - "learning_rate": 4.55202729956345e-05, - "loss": 3.3322, + "epoch": 0.08, + "learning_rate": 4.584099683518086e-05, + "loss": 3.3922, "step": 25100 }, { - "epoch": 0.09, - "learning_rate": 4.550242547768882e-05, - "loss": 3.3295, + "epoch": 0.08, + "learning_rate": 4.5824427101456477e-05, + "loss": 3.3916, "step": 25200 }, { - "epoch": 0.09, - "learning_rate": 4.548457795974314e-05, - "loss": 3.3302, + "epoch": 0.08, + "learning_rate": 4.5807857367732105e-05, + "loss": 3.3878, "step": 25300 }, { - "epoch": 0.09, - "learning_rate": 4.546673044179746e-05, - "loss": 3.3334, + "epoch": 0.08, + "learning_rate": 4.5791287634007726e-05, + "loss": 3.3905, "step": 25400 }, { - "epoch": 0.09, - "learning_rate": 4.5448882923851783e-05, - "loss": 3.3338, + "epoch": 0.08, + "learning_rate": 4.577471790028334e-05, + "loss": 3.3902, "step": 25500 }, { - "epoch": 0.09, - "learning_rate": 4.5431035405906105e-05, - "loss": 3.3273, + "epoch": 0.08, + "learning_rate": 4.575814816655897e-05, + "loss": 3.3897, "step": 25600 }, { "epoch": 0.09, - "learning_rate": 4.5413187887960426e-05, - "loss": 3.3285, + "learning_rate": 4.5741578432834584e-05, + "loss": 3.3895, "step": 25700 }, { "epoch": 0.09, - "learning_rate": 4.539534037001475e-05, - "loss": 3.3195, + "learning_rate": 4.5725008699110205e-05, + "loss": 3.3796, "step": 25800 }, { "epoch": 0.09, - "learning_rate": 4.537749285206906e-05, - "loss": 3.3251, + "learning_rate": 4.5708438965385834e-05, + "loss": 3.3945, "step": 25900 }, { "epoch": 0.09, - "learning_rate": 4.535964533412338e-05, - "loss": 3.3093, + "learning_rate": 4.569186923166145e-05, + "loss": 3.3824, "step": 26000 }, { "epoch": 0.09, - "learning_rate": 4.5341797816177704e-05, - "loss": 3.322, + "learning_rate": 4.567529949793707e-05, + "loss": 3.3792, "step": 26100 }, { "epoch": 0.09, - "learning_rate": 4.5323950298232025e-05, - "loss": 3.3246, + "learning_rate": 4.565872976421269e-05, + "loss": 3.3954, "step": 26200 }, { "epoch": 0.09, - "learning_rate": 4.5306102780286346e-05, - "loss": 3.3236, + "learning_rate": 4.564216003048831e-05, + "loss": 3.3757, "step": 26300 }, { "epoch": 0.09, - "learning_rate": 4.528825526234067e-05, - "loss": 3.3329, + "learning_rate": 4.5625590296763934e-05, + "loss": 3.3941, "step": 26400 }, { "epoch": 0.09, - "learning_rate": 4.527040774439499e-05, - "loss": 3.3213, + "learning_rate": 4.5609020563039556e-05, + "loss": 3.3836, "step": 26500 }, { "epoch": 0.09, - "learning_rate": 4.525256022644931e-05, - "loss": 3.3303, + "learning_rate": 4.559245082931518e-05, + "loss": 3.3842, "step": 26600 }, { - "epoch": 0.1, - "learning_rate": 4.523471270850363e-05, - "loss": 3.3204, + "epoch": 0.09, + "learning_rate": 4.557588109559079e-05, + "loss": 3.3851, "step": 26700 }, { - "epoch": 0.1, - "learning_rate": 4.521686519055795e-05, - "loss": 3.3152, + "epoch": 0.09, + "learning_rate": 4.555931136186642e-05, + "loss": 3.3826, "step": 26800 }, { - "epoch": 0.1, - "learning_rate": 4.5199017672612274e-05, - "loss": 3.3241, + "epoch": 0.09, + "learning_rate": 4.554274162814204e-05, + "loss": 3.3797, "step": 26900 }, { - "epoch": 0.1, - "learning_rate": 4.518117015466659e-05, - "loss": 3.3377, + "epoch": 0.09, + "learning_rate": 4.5526171894417656e-05, + "loss": 3.3837, "step": 27000 }, { - "epoch": 0.1, - "learning_rate": 4.516332263672091e-05, - "loss": 3.3238, + "epoch": 0.09, + "learning_rate": 4.5509602160693284e-05, + "loss": 3.3823, "step": 27100 }, { - "epoch": 0.1, - "learning_rate": 4.514547511877523e-05, - "loss": 3.3237, + "epoch": 0.09, + "learning_rate": 4.54930324269689e-05, + "loss": 3.3895, "step": 27200 }, { - "epoch": 0.1, - "learning_rate": 4.512762760082955e-05, - "loss": 3.3239, + "epoch": 0.09, + "learning_rate": 4.547646269324452e-05, + "loss": 3.3909, "step": 27300 }, { - "epoch": 0.1, - "learning_rate": 4.510978008288387e-05, - "loss": 3.3263, + "epoch": 0.09, + "learning_rate": 4.545989295952014e-05, + "loss": 3.3791, "step": 27400 }, { - "epoch": 0.1, - "learning_rate": 4.5091932564938194e-05, - "loss": 3.3262, + "epoch": 0.09, + "learning_rate": 4.5443323225795764e-05, + "loss": 3.3916, "step": 27500 }, { - "epoch": 0.1, - "learning_rate": 4.5074085046992515e-05, - "loss": 3.3081, + "epoch": 0.09, + "learning_rate": 4.5426753492071385e-05, + "loss": 3.389, "step": 27600 }, { - "epoch": 0.1, - "learning_rate": 4.505623752904684e-05, - "loss": 3.3272, + "epoch": 0.09, + "learning_rate": 4.5410183758347006e-05, + "loss": 3.3773, "step": 27700 }, { - "epoch": 0.1, - "learning_rate": 4.503839001110116e-05, - "loss": 3.3122, + "epoch": 0.09, + "learning_rate": 4.539361402462263e-05, + "loss": 3.3799, "step": 27800 }, { - "epoch": 0.1, - "learning_rate": 4.502054249315548e-05, - "loss": 3.3161, + "epoch": 0.09, + "learning_rate": 4.537704429089825e-05, + "loss": 3.3973, "step": 27900 }, { - "epoch": 0.1, - "learning_rate": 4.50026949752098e-05, - "loss": 3.3107, + "epoch": 0.09, + "learning_rate": 4.536047455717387e-05, + "loss": 3.378, "step": 28000 }, { - "epoch": 0.1, - "learning_rate": 4.498484745726412e-05, - "loss": 3.3158, + "epoch": 0.09, + "learning_rate": 4.534390482344949e-05, + "loss": 3.3853, "step": 28100 }, { - "epoch": 0.1, - "learning_rate": 4.496699993931844e-05, - "loss": 3.3233, + "epoch": 0.09, + "learning_rate": 4.532733508972511e-05, + "loss": 3.3843, "step": 28200 }, { - "epoch": 0.1, - "learning_rate": 4.4949152421372764e-05, - "loss": 3.3138, + "epoch": 0.09, + "learning_rate": 4.5310765356000735e-05, + "loss": 3.3835, "step": 28300 }, { - "epoch": 0.1, - "learning_rate": 4.4931304903427085e-05, - "loss": 3.3256, + "epoch": 0.09, + "learning_rate": 4.529419562227635e-05, + "loss": 3.3836, "step": 28400 }, { - "epoch": 0.1, - "learning_rate": 4.4913457385481406e-05, - "loss": 3.3257, + "epoch": 0.09, + "learning_rate": 4.527762588855197e-05, + "loss": 3.3765, "step": 28500 }, { - "epoch": 0.1, - "learning_rate": 4.489560986753573e-05, - "loss": 3.3036, + "epoch": 0.09, + "learning_rate": 4.526105615482759e-05, + "loss": 3.3806, "step": 28600 }, { "epoch": 0.1, - "learning_rate": 4.487776234959005e-05, - "loss": 3.3135, + "learning_rate": 4.5244486421103214e-05, + "loss": 3.3771, "step": 28700 }, { "epoch": 0.1, - "learning_rate": 4.485991483164437e-05, - "loss": 3.3065, + "learning_rate": 4.5227916687378836e-05, + "loss": 3.3696, "step": 28800 }, { "epoch": 0.1, - "learning_rate": 4.484206731369869e-05, - "loss": 3.3121, + "learning_rate": 4.521134695365446e-05, + "loss": 3.3746, "step": 28900 }, { "epoch": 0.1, - "learning_rate": 4.4824219795753006e-05, - "loss": 3.3169, + "learning_rate": 4.519477721993008e-05, + "loss": 3.3839, "step": 29000 }, { "epoch": 0.1, - "learning_rate": 4.480637227780733e-05, - "loss": 3.3133, + "learning_rate": 4.51782074862057e-05, + "loss": 3.3664, "step": 29100 }, { "epoch": 0.1, - "learning_rate": 4.478852475986165e-05, - "loss": 3.3112, + "learning_rate": 4.5161637752481315e-05, + "loss": 3.3917, "step": 29200 }, { "epoch": 0.1, - "learning_rate": 4.477067724191597e-05, - "loss": 3.3148, + "learning_rate": 4.514506801875694e-05, + "loss": 3.3744, "step": 29300 }, { "epoch": 0.1, - "learning_rate": 4.475282972397029e-05, - "loss": 3.3212, + "learning_rate": 4.512849828503256e-05, + "loss": 3.3841, "step": 29400 }, { - "epoch": 0.11, - "learning_rate": 4.473498220602461e-05, - "loss": 3.3157, + "epoch": 0.1, + "learning_rate": 4.511192855130818e-05, + "loss": 3.3814, "step": 29500 }, { - "epoch": 0.11, - "learning_rate": 4.471713468807893e-05, - "loss": 3.3135, + "epoch": 0.1, + "learning_rate": 4.509535881758381e-05, + "loss": 3.3754, "step": 29600 }, { - "epoch": 0.11, - "learning_rate": 4.4699287170133254e-05, - "loss": 3.3054, + "epoch": 0.1, + "learning_rate": 4.507878908385942e-05, + "loss": 3.3822, "step": 29700 }, { - "epoch": 0.11, - "learning_rate": 4.4681439652187575e-05, - "loss": 3.3126, + "epoch": 0.1, + "learning_rate": 4.5062219350135044e-05, + "loss": 3.3776, "step": 29800 }, { - "epoch": 0.11, - "learning_rate": 4.4663592134241897e-05, - "loss": 3.3028, + "epoch": 0.1, + "learning_rate": 4.5045649616410665e-05, + "loss": 3.3866, "step": 29900 }, { - "epoch": 0.11, - "learning_rate": 4.464574461629622e-05, - "loss": 3.308, + "epoch": 0.1, + "learning_rate": 4.502907988268629e-05, + "loss": 3.3715, "step": 30000 }, { - "epoch": 0.11, - "learning_rate": 4.462789709835053e-05, - "loss": 3.3179, + "epoch": 0.1, + "learning_rate": 4.501251014896191e-05, + "loss": 3.3865, "step": 30100 }, { - "epoch": 0.11, - "learning_rate": 4.4610049580404853e-05, - "loss": 3.3015, + "epoch": 0.1, + "learning_rate": 4.499594041523753e-05, + "loss": 3.3769, "step": 30200 }, { - "epoch": 0.11, - "learning_rate": 4.4592202062459175e-05, - "loss": 3.307, + "epoch": 0.1, + "learning_rate": 4.497937068151315e-05, + "loss": 3.3707, "step": 30300 }, { - "epoch": 0.11, - "learning_rate": 4.4574354544513496e-05, - "loss": 3.3124, + "epoch": 0.1, + "learning_rate": 4.4962800947788766e-05, + "loss": 3.3846, "step": 30400 }, { - "epoch": 0.11, - "learning_rate": 4.455650702656782e-05, - "loss": 3.3144, + "epoch": 0.1, + "learning_rate": 4.4946231214064394e-05, + "loss": 3.3746, "step": 30500 }, { - "epoch": 0.11, - "learning_rate": 4.453865950862214e-05, - "loss": 3.309, + "epoch": 0.1, + "learning_rate": 4.4929661480340015e-05, + "loss": 3.3792, "step": 30600 }, { - "epoch": 0.11, - "learning_rate": 4.452081199067646e-05, - "loss": 3.3127, + "epoch": 0.1, + "learning_rate": 4.491309174661563e-05, + "loss": 3.3696, "step": 30700 }, { - "epoch": 0.11, - "learning_rate": 4.450296447273078e-05, - "loss": 3.3143, + "epoch": 0.1, + "learning_rate": 4.489652201289126e-05, + "loss": 3.3778, "step": 30800 }, { - "epoch": 0.11, - "learning_rate": 4.44851169547851e-05, - "loss": 3.3118, + "epoch": 0.1, + "learning_rate": 4.487995227916687e-05, + "loss": 3.385, "step": 30900 }, { - "epoch": 0.11, - "learning_rate": 4.446726943683942e-05, - "loss": 3.3074, + "epoch": 0.1, + "learning_rate": 4.4863382545442495e-05, + "loss": 3.3735, "step": 31000 }, { - "epoch": 0.11, - "learning_rate": 4.4449421918893744e-05, - "loss": 3.3056, + "epoch": 0.1, + "learning_rate": 4.484681281171812e-05, + "loss": 3.3848, "step": 31100 }, { - "epoch": 0.11, - "learning_rate": 4.443157440094806e-05, - "loss": 3.3089, + "epoch": 0.1, + "learning_rate": 4.483024307799374e-05, + "loss": 3.3782, "step": 31200 }, { - "epoch": 0.11, - "learning_rate": 4.441372688300238e-05, - "loss": 3.2985, + "epoch": 0.1, + "learning_rate": 4.481367334426936e-05, + "loss": 3.3651, "step": 31300 }, { - "epoch": 0.11, - "learning_rate": 4.43958793650567e-05, - "loss": 3.3089, + "epoch": 0.1, + "learning_rate": 4.479710361054498e-05, + "loss": 3.3735, "step": 31400 }, { - "epoch": 0.11, - "learning_rate": 4.437803184711102e-05, - "loss": 3.2988, + "epoch": 0.1, + "learning_rate": 4.47805338768206e-05, + "loss": 3.3713, "step": 31500 }, { - "epoch": 0.11, - "learning_rate": 4.4360184329165344e-05, - "loss": 3.3006, + "epoch": 0.1, + "learning_rate": 4.476396414309622e-05, + "loss": 3.3738, "step": 31600 }, { "epoch": 0.11, - "learning_rate": 4.4342336811219665e-05, - "loss": 3.2906, + "learning_rate": 4.4747394409371845e-05, + "loss": 3.3613, "step": 31700 }, { "epoch": 0.11, - "learning_rate": 4.4324489293273986e-05, - "loss": 3.3017, + "learning_rate": 4.4730824675647466e-05, + "loss": 3.3718, "step": 31800 }, { "epoch": 0.11, - "learning_rate": 4.430664177532831e-05, - "loss": 3.3051, + "learning_rate": 4.471425494192308e-05, + "loss": 3.3817, "step": 31900 }, { "epoch": 0.11, - "learning_rate": 4.428879425738263e-05, - "loss": 3.3021, + "learning_rate": 4.469768520819871e-05, + "loss": 3.3815, "step": 32000 }, { "epoch": 0.11, - "learning_rate": 4.427094673943695e-05, - "loss": 3.2918, + "learning_rate": 4.468111547447433e-05, + "loss": 3.3879, "step": 32100 }, { "epoch": 0.11, - "learning_rate": 4.425309922149127e-05, - "loss": 3.287, + "learning_rate": 4.4664545740749945e-05, + "loss": 3.3864, "step": 32200 }, { - "epoch": 0.12, - "learning_rate": 4.4235251703545585e-05, - "loss": 3.3062, + "epoch": 0.11, + "learning_rate": 4.4647976007025574e-05, + "loss": 3.3723, "step": 32300 }, { - "epoch": 0.12, - "learning_rate": 4.421740418559991e-05, - "loss": 3.3002, + "epoch": 0.11, + "learning_rate": 4.463140627330119e-05, + "loss": 3.3721, "step": 32400 }, { - "epoch": 0.12, - "learning_rate": 4.419955666765423e-05, - "loss": 3.2958, + "epoch": 0.11, + "learning_rate": 4.461483653957681e-05, + "loss": 3.3773, "step": 32500 }, { - "epoch": 0.12, - "learning_rate": 4.418170914970855e-05, - "loss": 3.2979, + "epoch": 0.11, + "learning_rate": 4.459826680585243e-05, + "loss": 3.3717, "step": 32600 }, { - "epoch": 0.12, - "learning_rate": 4.416386163176287e-05, - "loss": 3.3097, + "epoch": 0.11, + "learning_rate": 4.458169707212805e-05, + "loss": 3.3851, "step": 32700 }, { - "epoch": 0.12, - "learning_rate": 4.414601411381719e-05, - "loss": 3.3087, + "epoch": 0.11, + "learning_rate": 4.4565127338403674e-05, + "loss": 3.3856, "step": 32800 }, { - "epoch": 0.12, - "learning_rate": 4.412816659587151e-05, - "loss": 3.3063, + "epoch": 0.11, + "learning_rate": 4.4548557604679296e-05, + "loss": 3.3751, "step": 32900 }, { - "epoch": 0.12, - "learning_rate": 4.4110319077925834e-05, - "loss": 3.296, + "epoch": 0.11, + "learning_rate": 4.453198787095492e-05, + "loss": 3.3739, "step": 33000 }, { - "epoch": 0.12, - "learning_rate": 4.4092471559980155e-05, - "loss": 3.3057, + "epoch": 0.11, + "learning_rate": 4.451541813723054e-05, + "loss": 3.3709, "step": 33100 }, { - "epoch": 0.12, - "learning_rate": 4.4074624042034476e-05, - "loss": 3.304, + "epoch": 0.11, + "learning_rate": 4.449884840350616e-05, + "loss": 3.3816, "step": 33200 }, { - "epoch": 0.12, - "learning_rate": 4.40567765240888e-05, - "loss": 3.3036, + "epoch": 0.11, + "learning_rate": 4.448227866978178e-05, + "loss": 3.3694, "step": 33300 }, { - "epoch": 0.12, - "learning_rate": 4.403892900614312e-05, - "loss": 3.2955, + "epoch": 0.11, + "learning_rate": 4.4465708936057396e-05, + "loss": 3.3802, "step": 33400 }, { - "epoch": 0.12, - "learning_rate": 4.402108148819744e-05, - "loss": 3.2951, + "epoch": 0.11, + "learning_rate": 4.4449139202333024e-05, + "loss": 3.3768, "step": 33500 }, { - "epoch": 0.12, - "learning_rate": 4.400323397025176e-05, - "loss": 3.3081, + "epoch": 0.11, + "learning_rate": 4.443256946860864e-05, + "loss": 3.3724, "step": 33600 }, { - "epoch": 0.12, - "learning_rate": 4.398538645230608e-05, - "loss": 3.3035, + "epoch": 0.11, + "learning_rate": 4.441599973488426e-05, + "loss": 3.3795, "step": 33700 }, { - "epoch": 0.12, - "learning_rate": 4.3967538934360404e-05, - "loss": 3.2993, + "epoch": 0.11, + "learning_rate": 4.439943000115988e-05, + "loss": 3.3822, "step": 33800 }, { - "epoch": 0.12, - "learning_rate": 4.3949691416414725e-05, - "loss": 3.301, + "epoch": 0.11, + "learning_rate": 4.4382860267435504e-05, + "loss": 3.3826, "step": 33900 }, { - "epoch": 0.12, - "learning_rate": 4.3931843898469046e-05, - "loss": 3.3091, + "epoch": 0.11, + "learning_rate": 4.4366290533711125e-05, + "loss": 3.3671, "step": 34000 }, { - "epoch": 0.12, - "learning_rate": 4.391399638052337e-05, - "loss": 3.3008, + "epoch": 0.11, + "learning_rate": 4.4349720799986746e-05, + "loss": 3.3808, "step": 34100 }, { - "epoch": 0.12, - "learning_rate": 4.389614886257769e-05, - "loss": 3.3015, + "epoch": 0.11, + "learning_rate": 4.433315106626237e-05, + "loss": 3.389, "step": 34200 }, { - "epoch": 0.12, - "learning_rate": 4.3878301344632e-05, - "loss": 3.2972, + "epoch": 0.11, + "learning_rate": 4.431658133253799e-05, + "loss": 3.368, "step": 34300 }, { - "epoch": 0.12, - "learning_rate": 4.3860453826686324e-05, - "loss": 3.2759, + "epoch": 0.11, + "learning_rate": 4.4300011598813604e-05, + "loss": 3.3826, "step": 34400 }, { - "epoch": 0.12, - "learning_rate": 4.3842606308740645e-05, - "loss": 3.2943, + "epoch": 0.11, + "learning_rate": 4.428344186508923e-05, + "loss": 3.3844, "step": 34500 }, { - "epoch": 0.12, - "learning_rate": 4.3824758790794967e-05, - "loss": 3.2969, + "epoch": 0.11, + "learning_rate": 4.4266872131364854e-05, + "loss": 3.3868, "step": 34600 }, { - "epoch": 0.12, - "learning_rate": 4.380691127284929e-05, - "loss": 3.2927, + "epoch": 0.11, + "learning_rate": 4.425030239764047e-05, + "loss": 3.3844, "step": 34700 }, { "epoch": 0.12, - "learning_rate": 4.378906375490361e-05, - "loss": 3.2968, + "learning_rate": 4.42337326639161e-05, + "loss": 3.3686, "step": 34800 }, { "epoch": 0.12, - "learning_rate": 4.377121623695793e-05, - "loss": 3.2967, + "learning_rate": 4.421716293019171e-05, + "loss": 3.3795, "step": 34900 }, { "epoch": 0.12, - "learning_rate": 4.375336871901225e-05, - "loss": 3.2878, + "learning_rate": 4.420059319646733e-05, + "loss": 3.3693, "step": 35000 }, { - "epoch": 0.13, - "learning_rate": 4.373552120106657e-05, - "loss": 3.2921, + "epoch": 0.12, + "learning_rate": 4.4184023462742954e-05, + "loss": 3.3739, "step": 35100 }, { - "epoch": 0.13, - "learning_rate": 4.3717673683120894e-05, - "loss": 3.2968, + "epoch": 0.12, + "learning_rate": 4.4167453729018576e-05, + "loss": 3.359, "step": 35200 }, { - "epoch": 0.13, - "learning_rate": 4.369982616517521e-05, - "loss": 3.2967, + "epoch": 0.12, + "learning_rate": 4.41508839952942e-05, + "loss": 3.3732, "step": 35300 }, { - "epoch": 0.13, - "learning_rate": 4.368197864722953e-05, - "loss": 3.2861, + "epoch": 0.12, + "learning_rate": 4.413431426156982e-05, + "loss": 3.3698, "step": 35400 }, { - "epoch": 0.13, - "learning_rate": 4.366413112928385e-05, - "loss": 3.301, + "epoch": 0.12, + "learning_rate": 4.411774452784544e-05, + "loss": 3.3687, "step": 35500 }, { - "epoch": 0.13, - "learning_rate": 4.364628361133817e-05, - "loss": 3.2894, + "epoch": 0.12, + "learning_rate": 4.410117479412106e-05, + "loss": 3.3669, "step": 35600 }, { - "epoch": 0.13, - "learning_rate": 4.362843609339249e-05, - "loss": 3.2926, + "epoch": 0.12, + "learning_rate": 4.408460506039668e-05, + "loss": 3.3867, "step": 35700 }, { - "epoch": 0.13, - "learning_rate": 4.3610588575446814e-05, - "loss": 3.2872, + "epoch": 0.12, + "learning_rate": 4.4068035326672305e-05, + "loss": 3.3566, "step": 35800 }, { - "epoch": 0.13, - "learning_rate": 4.3592741057501136e-05, - "loss": 3.2906, + "epoch": 0.12, + "learning_rate": 4.405146559294792e-05, + "loss": 3.371, "step": 35900 }, { - "epoch": 0.13, - "learning_rate": 4.357489353955546e-05, - "loss": 3.2923, + "epoch": 0.12, + "learning_rate": 4.403489585922355e-05, + "loss": 3.3756, "step": 36000 }, { - "epoch": 0.13, - "learning_rate": 4.355704602160978e-05, - "loss": 3.2902, + "epoch": 0.12, + "learning_rate": 4.401832612549916e-05, + "loss": 3.3673, "step": 36100 }, { - "epoch": 0.13, - "learning_rate": 4.35391985036641e-05, - "loss": 3.2868, + "epoch": 0.12, + "learning_rate": 4.4001756391774784e-05, + "loss": 3.3673, "step": 36200 }, { - "epoch": 0.13, - "learning_rate": 4.352135098571842e-05, - "loss": 3.2892, + "epoch": 0.12, + "learning_rate": 4.398518665805041e-05, + "loss": 3.3583, "step": 36300 }, { - "epoch": 0.13, - "learning_rate": 4.3503503467772735e-05, - "loss": 3.2966, + "epoch": 0.12, + "learning_rate": 4.396861692432603e-05, + "loss": 3.3653, "step": 36400 }, { - "epoch": 0.13, - "learning_rate": 4.3485655949827056e-05, - "loss": 3.2849, + "epoch": 0.12, + "learning_rate": 4.395204719060165e-05, + "loss": 3.3724, "step": 36500 }, { - "epoch": 0.13, - "learning_rate": 4.346780843188138e-05, - "loss": 3.3056, + "epoch": 0.12, + "learning_rate": 4.393547745687727e-05, + "loss": 3.3672, "step": 36600 }, { - "epoch": 0.13, - "learning_rate": 4.34499609139357e-05, - "loss": 3.2742, + "epoch": 0.12, + "learning_rate": 4.391890772315289e-05, + "loss": 3.3697, "step": 36700 }, { - "epoch": 0.13, - "learning_rate": 4.343211339599002e-05, - "loss": 3.2888, + "epoch": 0.12, + "learning_rate": 4.390233798942851e-05, + "loss": 3.3775, "step": 36800 }, { - "epoch": 0.13, - "learning_rate": 4.341426587804434e-05, - "loss": 3.2945, + "epoch": 0.12, + "learning_rate": 4.3885768255704134e-05, + "loss": 3.3677, "step": 36900 }, { - "epoch": 0.13, - "learning_rate": 4.339641836009866e-05, - "loss": 3.2942, + "epoch": 0.12, + "learning_rate": 4.3869198521979755e-05, + "loss": 3.3621, "step": 37000 }, { - "epoch": 0.13, - "learning_rate": 4.3378570842152983e-05, - "loss": 3.2757, + "epoch": 0.12, + "learning_rate": 4.385262878825537e-05, + "loss": 3.3668, "step": 37100 }, { - "epoch": 0.13, - "learning_rate": 4.3360723324207305e-05, - "loss": 3.2871, + "epoch": 0.12, + "learning_rate": 4.3836059054531e-05, + "loss": 3.3578, "step": 37200 }, { - "epoch": 0.13, - "learning_rate": 4.3342875806261626e-05, - "loss": 3.2863, + "epoch": 0.12, + "learning_rate": 4.381948932080662e-05, + "loss": 3.3661, "step": 37300 }, { - "epoch": 0.13, - "learning_rate": 4.332502828831595e-05, - "loss": 3.2871, + "epoch": 0.12, + "learning_rate": 4.3802919587082235e-05, + "loss": 3.356, "step": 37400 }, { - "epoch": 0.13, - "learning_rate": 4.330718077037026e-05, - "loss": 3.2846, + "epoch": 0.12, + "learning_rate": 4.378634985335786e-05, + "loss": 3.3655, "step": 37500 }, { - "epoch": 0.13, - "learning_rate": 4.328933325242458e-05, - "loss": 3.3068, + "epoch": 0.12, + "learning_rate": 4.376978011963348e-05, + "loss": 3.3662, "step": 37600 }, { - "epoch": 0.13, - "learning_rate": 4.3271485734478904e-05, - "loss": 3.2804, + "epoch": 0.12, + "learning_rate": 4.37532103859091e-05, + "loss": 3.358, "step": 37700 }, { "epoch": 0.13, - "learning_rate": 4.3253638216533225e-05, - "loss": 3.29, + "learning_rate": 4.373664065218473e-05, + "loss": 3.3672, "step": 37800 }, { - "epoch": 0.14, - "learning_rate": 4.3235790698587546e-05, - "loss": 3.2784, + "epoch": 0.13, + "learning_rate": 4.372007091846034e-05, + "loss": 3.3619, "step": 37900 }, { - "epoch": 0.14, - "learning_rate": 4.321794318064187e-05, - "loss": 3.2793, + "epoch": 0.13, + "learning_rate": 4.370350118473596e-05, + "loss": 3.3664, "step": 38000 }, { - "epoch": 0.14, - "learning_rate": 4.320009566269619e-05, - "loss": 3.2868, + "epoch": 0.13, + "learning_rate": 4.3686931451011585e-05, + "loss": 3.3591, "step": 38100 }, { - "epoch": 0.14, - "learning_rate": 4.318224814475051e-05, - "loss": 3.2905, + "epoch": 0.13, + "learning_rate": 4.3670361717287206e-05, + "loss": 3.3668, "step": 38200 }, { - "epoch": 0.14, - "learning_rate": 4.316440062680484e-05, - "loss": 3.2765, + "epoch": 0.13, + "learning_rate": 4.365379198356283e-05, + "loss": 3.3798, "step": 38300 }, { - "epoch": 0.14, - "learning_rate": 4.314655310885915e-05, - "loss": 3.2898, + "epoch": 0.13, + "learning_rate": 4.363722224983845e-05, + "loss": 3.3659, "step": 38400 }, { - "epoch": 0.14, - "learning_rate": 4.3128705590913474e-05, - "loss": 3.2873, + "epoch": 0.13, + "learning_rate": 4.362065251611407e-05, + "loss": 3.3577, "step": 38500 }, { - "epoch": 0.14, - "learning_rate": 4.3110858072967795e-05, - "loss": 3.2932, + "epoch": 0.13, + "learning_rate": 4.3604082782389685e-05, + "loss": 3.3606, "step": 38600 }, { - "epoch": 0.14, - "learning_rate": 4.3093010555022116e-05, - "loss": 3.2866, + "epoch": 0.13, + "learning_rate": 4.3587513048665314e-05, + "loss": 3.3677, "step": 38700 }, { - "epoch": 0.14, - "learning_rate": 4.307516303707644e-05, - "loss": 3.2681, + "epoch": 0.13, + "learning_rate": 4.3570943314940935e-05, + "loss": 3.3597, "step": 38800 }, { - "epoch": 0.14, - "learning_rate": 4.305731551913076e-05, - "loss": 3.2918, + "epoch": 0.13, + "learning_rate": 4.355437358121655e-05, + "loss": 3.3561, "step": 38900 }, { - "epoch": 0.14, - "learning_rate": 4.303946800118508e-05, - "loss": 3.287, + "epoch": 0.13, + "learning_rate": 4.353780384749217e-05, + "loss": 3.3694, "step": 39000 }, { - "epoch": 0.14, - "learning_rate": 4.30216204832394e-05, - "loss": 3.2836, + "epoch": 0.13, + "learning_rate": 4.352123411376779e-05, + "loss": 3.359, "step": 39100 }, { - "epoch": 0.14, - "learning_rate": 4.300377296529372e-05, - "loss": 3.296, + "epoch": 0.13, + "learning_rate": 4.3504664380043414e-05, + "loss": 3.3635, "step": 39200 }, { - "epoch": 0.14, - "learning_rate": 4.298592544734804e-05, - "loss": 3.2813, + "epoch": 0.13, + "learning_rate": 4.3488094646319036e-05, + "loss": 3.362, "step": 39300 }, { - "epoch": 0.14, - "learning_rate": 4.2968077929402365e-05, - "loss": 3.2812, + "epoch": 0.13, + "learning_rate": 4.347152491259466e-05, + "loss": 3.3827, "step": 39400 }, { - "epoch": 0.14, - "learning_rate": 4.295023041145668e-05, - "loss": 3.2739, + "epoch": 0.13, + "learning_rate": 4.345495517887028e-05, + "loss": 3.3742, "step": 39500 }, { - "epoch": 0.14, - "learning_rate": 4.2932382893511e-05, - "loss": 3.2857, + "epoch": 0.13, + "learning_rate": 4.343838544514589e-05, + "loss": 3.3614, "step": 39600 }, { - "epoch": 0.14, - "learning_rate": 4.291453537556532e-05, - "loss": 3.2675, + "epoch": 0.13, + "learning_rate": 4.342181571142152e-05, + "loss": 3.3722, "step": 39700 }, { - "epoch": 0.14, - "learning_rate": 4.289668785761964e-05, - "loss": 3.2912, + "epoch": 0.13, + "learning_rate": 4.340524597769714e-05, + "loss": 3.3692, "step": 39800 }, { - "epoch": 0.14, - "learning_rate": 4.2878840339673964e-05, - "loss": 3.2903, + "epoch": 0.13, + "learning_rate": 4.338867624397276e-05, + "loss": 3.3579, "step": 39900 }, { - "epoch": 0.14, - "learning_rate": 4.2860992821728285e-05, - "loss": 3.2731, + "epoch": 0.13, + "learning_rate": 4.3372106510248386e-05, + "loss": 3.3648, "step": 40000 }, { - "epoch": 0.14, - "learning_rate": 4.2843145303782606e-05, - "loss": 3.2787, + "epoch": 0.13, + "learning_rate": 4.3355536776524e-05, + "loss": 3.3643, "step": 40100 }, { - "epoch": 0.14, - "learning_rate": 4.282529778583693e-05, - "loss": 3.2805, + "epoch": 0.13, + "learning_rate": 4.333896704279962e-05, + "loss": 3.3631, "step": 40200 }, { - "epoch": 0.14, - "learning_rate": 4.280745026789125e-05, - "loss": 3.2824, + "epoch": 0.13, + "learning_rate": 4.3322397309075244e-05, + "loss": 3.3611, "step": 40300 }, { - "epoch": 0.14, - "learning_rate": 4.278960274994557e-05, - "loss": 3.2723, + "epoch": 0.13, + "learning_rate": 4.3305827575350865e-05, + "loss": 3.3628, "step": 40400 }, { - "epoch": 0.14, - "learning_rate": 4.277175523199989e-05, - "loss": 3.2795, + "epoch": 0.13, + "learning_rate": 4.3289257841626486e-05, + "loss": 3.3738, "step": 40500 }, { - "epoch": 0.14, - "learning_rate": 4.2753907714054206e-05, - "loss": 3.2767, + "epoch": 0.13, + "learning_rate": 4.327268810790211e-05, + "loss": 3.3649, "step": 40600 }, { - "epoch": 0.15, - "learning_rate": 4.273606019610853e-05, - "loss": 3.2745, + "epoch": 0.13, + "learning_rate": 4.325611837417773e-05, + "loss": 3.359, "step": 40700 }, { - "epoch": 0.15, - "learning_rate": 4.271821267816285e-05, - "loss": 3.2878, + "epoch": 0.14, + "learning_rate": 4.323954864045335e-05, + "loss": 3.3587, "step": 40800 }, { - "epoch": 0.15, - "learning_rate": 4.270036516021717e-05, - "loss": 3.2769, + "epoch": 0.14, + "learning_rate": 4.322297890672897e-05, + "loss": 3.3606, "step": 40900 }, { - "epoch": 0.15, - "learning_rate": 4.268251764227149e-05, - "loss": 3.2763, + "epoch": 0.14, + "learning_rate": 4.3206409173004594e-05, + "loss": 3.3781, "step": 41000 }, { - "epoch": 0.15, - "learning_rate": 4.266467012432581e-05, - "loss": 3.2742, + "epoch": 0.14, + "learning_rate": 4.318983943928021e-05, + "loss": 3.3546, "step": 41100 }, { - "epoch": 0.15, - "learning_rate": 4.264682260638013e-05, - "loss": 3.2815, + "epoch": 0.14, + "learning_rate": 4.317326970555584e-05, + "loss": 3.3595, "step": 41200 }, { - "epoch": 0.15, - "learning_rate": 4.2628975088434454e-05, - "loss": 3.2771, + "epoch": 0.14, + "learning_rate": 4.315669997183145e-05, + "loss": 3.3702, "step": 41300 }, { - "epoch": 0.15, - "learning_rate": 4.2611127570488775e-05, - "loss": 3.2757, + "epoch": 0.14, + "learning_rate": 4.314013023810707e-05, + "loss": 3.3741, "step": 41400 }, { - "epoch": 0.15, - "learning_rate": 4.2593280052543097e-05, - "loss": 3.2711, + "epoch": 0.14, + "learning_rate": 4.31235605043827e-05, + "loss": 3.3655, "step": 41500 }, { - "epoch": 0.15, - "learning_rate": 4.257543253459742e-05, - "loss": 3.2862, + "epoch": 0.14, + "learning_rate": 4.3106990770658316e-05, + "loss": 3.3779, "step": 41600 }, { - "epoch": 0.15, - "learning_rate": 4.255758501665173e-05, - "loss": 3.2724, + "epoch": 0.14, + "learning_rate": 4.309042103693394e-05, + "loss": 3.3575, "step": 41700 }, { - "epoch": 0.15, - "learning_rate": 4.2539737498706053e-05, - "loss": 3.2646, + "epoch": 0.14, + "learning_rate": 4.307385130320956e-05, + "loss": 3.3653, "step": 41800 }, { - "epoch": 0.15, - "learning_rate": 4.2521889980760375e-05, - "loss": 3.2712, + "epoch": 0.14, + "learning_rate": 4.305728156948518e-05, + "loss": 3.3474, "step": 41900 }, { - "epoch": 0.15, - "learning_rate": 4.2504042462814696e-05, - "loss": 3.2665, + "epoch": 0.14, + "learning_rate": 4.30407118357608e-05, + "loss": 3.3698, "step": 42000 }, { - "epoch": 0.15, - "learning_rate": 4.248619494486902e-05, - "loss": 3.2707, + "epoch": 0.14, + "learning_rate": 4.302414210203642e-05, + "loss": 3.3659, "step": 42100 }, { - "epoch": 0.15, - "learning_rate": 4.246834742692334e-05, - "loss": 3.2683, + "epoch": 0.14, + "learning_rate": 4.3007572368312045e-05, + "loss": 3.3652, "step": 42200 }, { - "epoch": 0.15, - "learning_rate": 4.245049990897766e-05, - "loss": 3.269, + "epoch": 0.14, + "learning_rate": 4.299100263458766e-05, + "loss": 3.3659, "step": 42300 }, { - "epoch": 0.15, - "learning_rate": 4.243265239103198e-05, - "loss": 3.2778, + "epoch": 0.14, + "learning_rate": 4.297443290086329e-05, + "loss": 3.3692, "step": 42400 }, { - "epoch": 0.15, - "learning_rate": 4.24148048730863e-05, - "loss": 3.278, + "epoch": 0.14, + "learning_rate": 4.295786316713891e-05, + "loss": 3.3607, "step": 42500 }, { - "epoch": 0.15, - "learning_rate": 4.239695735514062e-05, - "loss": 3.2824, + "epoch": 0.14, + "learning_rate": 4.2941293433414524e-05, + "loss": 3.3552, "step": 42600 }, { - "epoch": 0.15, - "learning_rate": 4.2379109837194944e-05, - "loss": 3.281, + "epoch": 0.14, + "learning_rate": 4.292472369969015e-05, + "loss": 3.3682, "step": 42700 }, { - "epoch": 0.15, - "learning_rate": 4.236126231924926e-05, - "loss": 3.2729, + "epoch": 0.14, + "learning_rate": 4.290815396596577e-05, + "loss": 3.3593, "step": 42800 }, { - "epoch": 0.15, - "learning_rate": 4.234341480130358e-05, - "loss": 3.2573, + "epoch": 0.14, + "learning_rate": 4.289158423224139e-05, + "loss": 3.3651, "step": 42900 }, { - "epoch": 0.15, - "learning_rate": 4.23255672833579e-05, - "loss": 3.2702, + "epoch": 0.14, + "learning_rate": 4.2875014498517016e-05, + "loss": 3.3516, "step": 43000 }, { - "epoch": 0.15, - "learning_rate": 4.230771976541222e-05, - "loss": 3.2717, + "epoch": 0.14, + "learning_rate": 4.285844476479263e-05, + "loss": 3.3787, "step": 43100 }, { - "epoch": 0.15, - "learning_rate": 4.2289872247466544e-05, - "loss": 3.272, + "epoch": 0.14, + "learning_rate": 4.284187503106825e-05, + "loss": 3.3641, "step": 43200 }, { - "epoch": 0.15, - "learning_rate": 4.2272024729520865e-05, - "loss": 3.27, + "epoch": 0.14, + "learning_rate": 4.2825305297343874e-05, + "loss": 3.3722, "step": 43300 }, { - "epoch": 0.15, - "learning_rate": 4.2254177211575186e-05, - "loss": 3.2691, + "epoch": 0.14, + "learning_rate": 4.2808735563619495e-05, + "loss": 3.3714, "step": 43400 }, { - "epoch": 0.16, - "learning_rate": 4.2236329693629514e-05, - "loss": 3.2669, + "epoch": 0.14, + "learning_rate": 4.279216582989512e-05, + "loss": 3.35, "step": 43500 }, { - "epoch": 0.16, - "learning_rate": 4.2218482175683835e-05, - "loss": 3.2667, + "epoch": 0.14, + "learning_rate": 4.277559609617074e-05, + "loss": 3.3641, "step": 43600 }, { - "epoch": 0.16, - "learning_rate": 4.220063465773815e-05, - "loss": 3.2748, + "epoch": 0.14, + "learning_rate": 4.275902636244636e-05, + "loss": 3.3642, "step": 43700 }, { - "epoch": 0.16, - "learning_rate": 4.218278713979247e-05, - "loss": 3.2748, + "epoch": 0.15, + "learning_rate": 4.2742456628721975e-05, + "loss": 3.3644, "step": 43800 }, { - "epoch": 0.16, - "learning_rate": 4.216493962184679e-05, - "loss": 3.2826, + "epoch": 0.15, + "learning_rate": 4.27258868949976e-05, + "loss": 3.3621, "step": 43900 }, { - "epoch": 0.16, - "learning_rate": 4.214709210390111e-05, - "loss": 3.2705, + "epoch": 0.15, + "learning_rate": 4.2709317161273224e-05, + "loss": 3.3665, "step": 44000 }, { - "epoch": 0.16, - "learning_rate": 4.2129244585955435e-05, - "loss": 3.2655, + "epoch": 0.15, + "learning_rate": 4.269274742754884e-05, + "loss": 3.3653, "step": 44100 }, { - "epoch": 0.16, - "learning_rate": 4.2111397068009756e-05, - "loss": 3.2734, + "epoch": 0.15, + "learning_rate": 4.267617769382446e-05, + "loss": 3.3556, "step": 44200 }, { - "epoch": 0.16, - "learning_rate": 4.209354955006408e-05, - "loss": 3.2776, + "epoch": 0.15, + "learning_rate": 4.265960796010008e-05, + "loss": 3.3414, "step": 44300 }, { - "epoch": 0.16, - "learning_rate": 4.20757020321184e-05, - "loss": 3.2645, + "epoch": 0.15, + "learning_rate": 4.26430382263757e-05, + "loss": 3.3707, "step": 44400 }, { - "epoch": 0.16, - "learning_rate": 4.205785451417272e-05, - "loss": 3.2725, + "epoch": 0.15, + "learning_rate": 4.2626468492651325e-05, + "loss": 3.3754, "step": 44500 }, { - "epoch": 0.16, - "learning_rate": 4.204000699622704e-05, - "loss": 3.2716, + "epoch": 0.15, + "learning_rate": 4.2609898758926946e-05, + "loss": 3.3685, "step": 44600 }, { - "epoch": 0.16, - "learning_rate": 4.202215947828136e-05, - "loss": 3.2762, + "epoch": 0.15, + "learning_rate": 4.259332902520257e-05, + "loss": 3.3681, "step": 44700 }, { - "epoch": 0.16, - "learning_rate": 4.2004311960335676e-05, - "loss": 3.2684, + "epoch": 0.15, + "learning_rate": 4.257675929147818e-05, + "loss": 3.3646, "step": 44800 }, { - "epoch": 0.16, - "learning_rate": 4.198646444239e-05, - "loss": 3.2674, + "epoch": 0.15, + "learning_rate": 4.256018955775381e-05, + "loss": 3.3509, "step": 44900 }, { - "epoch": 0.16, - "learning_rate": 4.196861692444432e-05, - "loss": 3.2665, + "epoch": 0.15, + "learning_rate": 4.254361982402943e-05, + "loss": 3.3567, "step": 45000 }, { - "epoch": 0.16, - "learning_rate": 4.195076940649864e-05, - "loss": 3.2688, + "epoch": 0.15, + "learning_rate": 4.252705009030505e-05, + "loss": 3.3648, "step": 45100 }, { - "epoch": 0.16, - "learning_rate": 4.193292188855296e-05, - "loss": 3.2697, + "epoch": 0.15, + "learning_rate": 4.2510480356580675e-05, + "loss": 3.3566, "step": 45200 }, { - "epoch": 0.16, - "learning_rate": 4.191507437060728e-05, - "loss": 3.2651, + "epoch": 0.15, + "learning_rate": 4.249391062285629e-05, + "loss": 3.3473, "step": 45300 }, { - "epoch": 0.16, - "learning_rate": 4.1897226852661604e-05, - "loss": 3.2675, + "epoch": 0.15, + "learning_rate": 4.247734088913191e-05, + "loss": 3.3616, "step": 45400 }, { - "epoch": 0.16, - "learning_rate": 4.1879379334715925e-05, - "loss": 3.2694, + "epoch": 0.15, + "learning_rate": 4.246077115540753e-05, + "loss": 3.3543, "step": 45500 }, { - "epoch": 0.16, - "learning_rate": 4.1861531816770246e-05, - "loss": 3.259, + "epoch": 0.15, + "learning_rate": 4.2444201421683154e-05, + "loss": 3.3596, "step": 45600 }, { - "epoch": 0.16, - "learning_rate": 4.184368429882457e-05, - "loss": 3.2559, + "epoch": 0.15, + "learning_rate": 4.2427631687958776e-05, + "loss": 3.3504, "step": 45700 }, { - "epoch": 0.16, - "learning_rate": 4.182583678087889e-05, - "loss": 3.2644, + "epoch": 0.15, + "learning_rate": 4.24110619542344e-05, + "loss": 3.3509, "step": 45800 }, { - "epoch": 0.16, - "learning_rate": 4.18079892629332e-05, - "loss": 3.262, + "epoch": 0.15, + "learning_rate": 4.239449222051002e-05, + "loss": 3.3641, "step": 45900 }, { - "epoch": 0.16, - "learning_rate": 4.1790141744987524e-05, - "loss": 3.2608, + "epoch": 0.15, + "learning_rate": 4.237792248678564e-05, + "loss": 3.366, "step": 46000 }, { - "epoch": 0.16, - "learning_rate": 4.1772294227041845e-05, - "loss": 3.2681, + "epoch": 0.15, + "learning_rate": 4.236135275306126e-05, + "loss": 3.3578, "step": 46100 }, { - "epoch": 0.16, - "learning_rate": 4.1754446709096167e-05, - "loss": 3.2638, + "epoch": 0.15, + "learning_rate": 4.234478301933688e-05, + "loss": 3.3682, "step": 46200 }, { - "epoch": 0.17, - "learning_rate": 4.173659919115049e-05, - "loss": 3.2739, + "epoch": 0.15, + "learning_rate": 4.23282132856125e-05, + "loss": 3.3578, "step": 46300 }, { - "epoch": 0.17, - "learning_rate": 4.171875167320481e-05, - "loss": 3.2654, + "epoch": 0.15, + "learning_rate": 4.2311643551888126e-05, + "loss": 3.3676, "step": 46400 }, { - "epoch": 0.17, - "learning_rate": 4.170090415525913e-05, - "loss": 3.2615, + "epoch": 0.15, + "learning_rate": 4.229507381816375e-05, + "loss": 3.3432, "step": 46500 }, { - "epoch": 0.17, - "learning_rate": 4.168305663731345e-05, - "loss": 3.2737, + "epoch": 0.15, + "learning_rate": 4.227850408443936e-05, + "loss": 3.3726, "step": 46600 }, { - "epoch": 0.17, - "learning_rate": 4.166520911936777e-05, - "loss": 3.2663, + "epoch": 0.15, + "learning_rate": 4.226193435071499e-05, + "loss": 3.3437, "step": 46700 }, { - "epoch": 0.17, - "learning_rate": 4.1647361601422094e-05, - "loss": 3.2674, + "epoch": 0.16, + "learning_rate": 4.2245364616990605e-05, + "loss": 3.3589, "step": 46800 }, { - "epoch": 0.17, - "learning_rate": 4.1629514083476415e-05, - "loss": 3.2739, + "epoch": 0.16, + "learning_rate": 4.2228794883266226e-05, + "loss": 3.3523, "step": 46900 }, { - "epoch": 0.17, - "learning_rate": 4.161166656553073e-05, - "loss": 3.2629, + "epoch": 0.16, + "learning_rate": 4.221222514954185e-05, + "loss": 3.3557, "step": 47000 }, { - "epoch": 0.17, - "learning_rate": 4.159381904758505e-05, - "loss": 3.2602, + "epoch": 0.16, + "learning_rate": 4.219565541581747e-05, + "loss": 3.3583, "step": 47100 }, { - "epoch": 0.17, - "learning_rate": 4.157597152963937e-05, - "loss": 3.2646, + "epoch": 0.16, + "learning_rate": 4.217908568209309e-05, + "loss": 3.3515, "step": 47200 }, { - "epoch": 0.17, - "learning_rate": 4.155812401169369e-05, - "loss": 3.2624, + "epoch": 0.16, + "learning_rate": 4.216251594836871e-05, + "loss": 3.3537, "step": 47300 }, { - "epoch": 0.17, - "learning_rate": 4.1540276493748014e-05, - "loss": 3.2685, + "epoch": 0.16, + "learning_rate": 4.2145946214644334e-05, + "loss": 3.3638, "step": 47400 }, { - "epoch": 0.17, - "learning_rate": 4.1522428975802336e-05, - "loss": 3.2636, + "epoch": 0.16, + "learning_rate": 4.2129376480919955e-05, + "loss": 3.3708, "step": 47500 }, { - "epoch": 0.17, - "learning_rate": 4.150458145785666e-05, - "loss": 3.2607, + "epoch": 0.16, + "learning_rate": 4.211280674719558e-05, + "loss": 3.3518, "step": 47600 }, { - "epoch": 0.17, - "learning_rate": 4.148673393991098e-05, - "loss": 3.2638, + "epoch": 0.16, + "learning_rate": 4.20962370134712e-05, + "loss": 3.3519, "step": 47700 }, { - "epoch": 0.17, - "learning_rate": 4.14688864219653e-05, - "loss": 3.2577, + "epoch": 0.16, + "learning_rate": 4.207966727974681e-05, + "loss": 3.3561, "step": 47800 }, { - "epoch": 0.17, - "learning_rate": 4.145103890401962e-05, - "loss": 3.261, + "epoch": 0.16, + "learning_rate": 4.206309754602244e-05, + "loss": 3.362, "step": 47900 }, { - "epoch": 0.17, - "learning_rate": 4.143319138607394e-05, - "loss": 3.2588, + "epoch": 0.16, + "learning_rate": 4.2046527812298056e-05, + "loss": 3.3666, "step": 48000 }, { - "epoch": 0.17, - "learning_rate": 4.1415343868128256e-05, - "loss": 3.2549, + "epoch": 0.16, + "learning_rate": 4.202995807857368e-05, + "loss": 3.3634, "step": 48100 }, { - "epoch": 0.17, - "learning_rate": 4.139749635018258e-05, - "loss": 3.2592, + "epoch": 0.16, + "learning_rate": 4.2013388344849306e-05, + "loss": 3.36, "step": 48200 }, { - "epoch": 0.17, - "learning_rate": 4.13796488322369e-05, - "loss": 3.2629, + "epoch": 0.16, + "learning_rate": 4.199681861112492e-05, + "loss": 3.3616, "step": 48300 }, { - "epoch": 0.17, - "learning_rate": 4.136180131429122e-05, - "loss": 3.2573, + "epoch": 0.16, + "learning_rate": 4.198024887740054e-05, + "loss": 3.3535, "step": 48400 }, { - "epoch": 0.17, - "learning_rate": 4.134395379634554e-05, - "loss": 3.2529, + "epoch": 0.16, + "learning_rate": 4.196367914367616e-05, + "loss": 3.3517, "step": 48500 }, { - "epoch": 0.17, - "learning_rate": 4.132610627839987e-05, - "loss": 3.2614, + "epoch": 0.16, + "learning_rate": 4.1947109409951785e-05, + "loss": 3.3619, "step": 48600 }, { - "epoch": 0.17, - "learning_rate": 4.130825876045419e-05, - "loss": 3.2549, + "epoch": 0.16, + "learning_rate": 4.1930539676227406e-05, + "loss": 3.3597, "step": 48700 }, { - "epoch": 0.17, - "learning_rate": 4.129041124250851e-05, - "loss": 3.269, + "epoch": 0.16, + "learning_rate": 4.191396994250303e-05, + "loss": 3.3536, "step": 48800 }, { - "epoch": 0.17, - "learning_rate": 4.127256372456283e-05, - "loss": 3.2494, + "epoch": 0.16, + "learning_rate": 4.189740020877865e-05, + "loss": 3.3646, "step": 48900 }, { - "epoch": 0.17, - "learning_rate": 4.125471620661715e-05, - "loss": 3.2605, + "epoch": 0.16, + "learning_rate": 4.1880830475054264e-05, + "loss": 3.3594, "step": 49000 }, { - "epoch": 0.18, - "learning_rate": 4.123686868867147e-05, - "loss": 3.2663, + "epoch": 0.16, + "learning_rate": 4.186426074132989e-05, + "loss": 3.3587, "step": 49100 }, { - "epoch": 0.18, - "learning_rate": 4.121902117072579e-05, - "loss": 3.2548, + "epoch": 0.16, + "learning_rate": 4.1847691007605513e-05, + "loss": 3.3618, "step": 49200 }, { - "epoch": 0.18, - "learning_rate": 4.120117365278011e-05, - "loss": 3.261, + "epoch": 0.16, + "learning_rate": 4.183112127388113e-05, + "loss": 3.3501, "step": 49300 }, { - "epoch": 0.18, - "learning_rate": 4.118332613483443e-05, - "loss": 3.2708, + "epoch": 0.16, + "learning_rate": 4.181455154015675e-05, + "loss": 3.3584, "step": 49400 }, { - "epoch": 0.18, - "learning_rate": 4.116547861688875e-05, - "loss": 3.2595, + "epoch": 0.16, + "learning_rate": 4.179798180643237e-05, + "loss": 3.3569, "step": 49500 }, { - "epoch": 0.18, - "learning_rate": 4.1147631098943074e-05, - "loss": 3.2552, + "epoch": 0.16, + "learning_rate": 4.178141207270799e-05, + "loss": 3.3504, "step": 49600 }, { - "epoch": 0.18, - "learning_rate": 4.1129783580997395e-05, - "loss": 3.2636, + "epoch": 0.16, + "learning_rate": 4.1764842338983614e-05, + "loss": 3.3556, "step": 49700 }, { - "epoch": 0.18, - "learning_rate": 4.111193606305172e-05, - "loss": 3.2634, + "epoch": 0.17, + "learning_rate": 4.1748272605259235e-05, + "loss": 3.357, "step": 49800 }, { - "epoch": 0.18, - "learning_rate": 4.109408854510604e-05, - "loss": 3.2582, + "epoch": 0.17, + "learning_rate": 4.173170287153486e-05, + "loss": 3.3402, "step": 49900 }, { - "epoch": 0.18, - "learning_rate": 4.107624102716036e-05, - "loss": 3.2588, + "epoch": 0.17, + "learning_rate": 4.171513313781047e-05, + "loss": 3.3407, "step": 50000 }, { - "epoch": 0.18, - "learning_rate": 4.1058393509214674e-05, - "loss": 3.2475, + "epoch": 0.17, + "learning_rate": 4.16985634040861e-05, + "loss": 3.3431, "step": 50100 }, { - "epoch": 0.18, - "learning_rate": 4.1040545991268995e-05, - "loss": 3.2559, + "epoch": 0.17, + "learning_rate": 4.168199367036172e-05, + "loss": 3.3394, "step": 50200 }, { - "epoch": 0.18, - "learning_rate": 4.1022698473323316e-05, - "loss": 3.2576, + "epoch": 0.17, + "learning_rate": 4.1665423936637336e-05, + "loss": 3.3449, "step": 50300 }, { - "epoch": 0.18, - "learning_rate": 4.100485095537764e-05, - "loss": 3.2441, + "epoch": 0.17, + "learning_rate": 4.1648854202912964e-05, + "loss": 3.3435, "step": 50400 }, { - "epoch": 0.18, - "learning_rate": 4.098700343743196e-05, - "loss": 3.2724, + "epoch": 0.17, + "learning_rate": 4.163228446918858e-05, + "loss": 3.371, "step": 50500 }, { - "epoch": 0.18, - "learning_rate": 4.096915591948628e-05, - "loss": 3.2662, + "epoch": 0.17, + "learning_rate": 4.16157147354642e-05, + "loss": 3.3492, "step": 50600 }, { - "epoch": 0.18, - "learning_rate": 4.09513084015406e-05, - "loss": 3.2613, + "epoch": 0.17, + "learning_rate": 4.159914500173983e-05, + "loss": 3.3462, "step": 50700 }, { - "epoch": 0.18, - "learning_rate": 4.093346088359492e-05, - "loss": 3.2515, + "epoch": 0.17, + "learning_rate": 4.158257526801544e-05, + "loss": 3.3562, "step": 50800 }, { - "epoch": 0.18, - "learning_rate": 4.091561336564924e-05, - "loss": 3.252, + "epoch": 0.17, + "learning_rate": 4.1566005534291065e-05, + "loss": 3.346, "step": 50900 }, { - "epoch": 0.18, - "learning_rate": 4.0897765847703565e-05, - "loss": 3.257, + "epoch": 0.17, + "learning_rate": 4.1549435800566686e-05, + "loss": 3.3605, "step": 51000 }, { - "epoch": 0.18, - "learning_rate": 4.0879918329757886e-05, - "loss": 3.2425, + "epoch": 0.17, + "learning_rate": 4.153286606684231e-05, + "loss": 3.3543, "step": 51100 }, { - "epoch": 0.18, - "learning_rate": 4.08620708118122e-05, - "loss": 3.2636, + "epoch": 0.17, + "learning_rate": 4.151629633311793e-05, + "loss": 3.3502, "step": 51200 }, { - "epoch": 0.18, - "learning_rate": 4.084422329386652e-05, - "loss": 3.2591, + "epoch": 0.17, + "learning_rate": 4.149972659939355e-05, + "loss": 3.3494, "step": 51300 }, { - "epoch": 0.18, - "learning_rate": 4.082637577592084e-05, - "loss": 3.2429, + "epoch": 0.17, + "learning_rate": 4.148315686566917e-05, + "loss": 3.3549, "step": 51400 }, { - "epoch": 0.18, - "learning_rate": 4.0808528257975164e-05, - "loss": 3.2564, + "epoch": 0.17, + "learning_rate": 4.146658713194479e-05, + "loss": 3.3679, "step": 51500 }, { - "epoch": 0.18, - "learning_rate": 4.0790680740029485e-05, - "loss": 3.2513, + "epoch": 0.17, + "learning_rate": 4.1450017398220415e-05, + "loss": 3.3514, "step": 51600 }, { - "epoch": 0.18, - "learning_rate": 4.0772833222083806e-05, - "loss": 3.2503, + "epoch": 0.17, + "learning_rate": 4.1433447664496037e-05, + "loss": 3.3521, "step": 51700 }, { - "epoch": 0.18, - "learning_rate": 4.075498570413813e-05, - "loss": 3.2456, + "epoch": 0.17, + "learning_rate": 4.141687793077165e-05, + "loss": 3.3588, "step": 51800 }, { - "epoch": 0.19, - "learning_rate": 4.073713818619245e-05, - "loss": 3.2661, + "epoch": 0.17, + "learning_rate": 4.140030819704728e-05, + "loss": 3.3486, "step": 51900 }, { - "epoch": 0.19, - "learning_rate": 4.071929066824677e-05, - "loss": 3.2524, + "epoch": 0.17, + "learning_rate": 4.1383738463322894e-05, + "loss": 3.3494, "step": 52000 }, { - "epoch": 0.19, - "learning_rate": 4.070144315030109e-05, - "loss": 3.2568, + "epoch": 0.17, + "learning_rate": 4.1367168729598516e-05, + "loss": 3.3549, "step": 52100 }, { - "epoch": 0.19, - "learning_rate": 4.068359563235541e-05, - "loss": 3.2559, + "epoch": 0.17, + "learning_rate": 4.135059899587414e-05, + "loss": 3.3449, "step": 52200 }, { - "epoch": 0.19, - "learning_rate": 4.066574811440973e-05, - "loss": 3.2617, + "epoch": 0.17, + "learning_rate": 4.133402926214976e-05, + "loss": 3.3437, "step": 52300 }, { - "epoch": 0.19, - "learning_rate": 4.064790059646405e-05, - "loss": 3.2535, + "epoch": 0.17, + "learning_rate": 4.131745952842538e-05, + "loss": 3.3581, "step": 52400 }, { - "epoch": 0.19, - "learning_rate": 4.063005307851837e-05, - "loss": 3.2596, + "epoch": 0.17, + "learning_rate": 4.1300889794701e-05, + "loss": 3.3456, "step": 52500 }, { - "epoch": 0.19, - "learning_rate": 4.061220556057269e-05, - "loss": 3.2557, + "epoch": 0.17, + "learning_rate": 4.128432006097662e-05, + "loss": 3.3528, "step": 52600 }, { - "epoch": 0.19, - "learning_rate": 4.059435804262701e-05, - "loss": 3.2484, + "epoch": 0.17, + "learning_rate": 4.1267750327252244e-05, + "loss": 3.3532, "step": 52700 }, { - "epoch": 0.19, - "learning_rate": 4.057651052468133e-05, - "loss": 3.25, + "epoch": 0.17, + "learning_rate": 4.1251180593527866e-05, + "loss": 3.3497, "step": 52800 }, { - "epoch": 0.19, - "learning_rate": 4.0558663006735654e-05, - "loss": 3.2516, + "epoch": 0.18, + "learning_rate": 4.123461085980349e-05, + "loss": 3.3606, "step": 52900 }, { - "epoch": 0.19, - "learning_rate": 4.0540815488789975e-05, - "loss": 3.2562, + "epoch": 0.18, + "learning_rate": 4.12180411260791e-05, + "loss": 3.3414, "step": 53000 }, { - "epoch": 0.19, - "learning_rate": 4.0522967970844296e-05, - "loss": 3.2425, + "epoch": 0.18, + "learning_rate": 4.120147139235473e-05, + "loss": 3.3491, "step": 53100 }, { - "epoch": 0.19, - "learning_rate": 4.050512045289862e-05, - "loss": 3.2618, + "epoch": 0.18, + "learning_rate": 4.1184901658630345e-05, + "loss": 3.352, "step": 53200 }, { - "epoch": 0.19, - "learning_rate": 4.048727293495294e-05, - "loss": 3.2514, + "epoch": 0.18, + "learning_rate": 4.1168331924905966e-05, + "loss": 3.3549, "step": 53300 }, { - "epoch": 0.19, - "learning_rate": 4.046942541700725e-05, - "loss": 3.2506, + "epoch": 0.18, + "learning_rate": 4.1151762191181595e-05, + "loss": 3.3632, "step": 53400 }, { - "epoch": 0.19, - "learning_rate": 4.0451577899061575e-05, - "loss": 3.2516, + "epoch": 0.18, + "learning_rate": 4.113519245745721e-05, + "loss": 3.3477, "step": 53500 }, { - "epoch": 0.19, - "learning_rate": 4.0433730381115896e-05, - "loss": 3.25, + "epoch": 0.18, + "learning_rate": 4.111862272373283e-05, + "loss": 3.3553, "step": 53600 }, { - "epoch": 0.19, - "learning_rate": 4.0415882863170224e-05, - "loss": 3.2458, + "epoch": 0.18, + "learning_rate": 4.110205299000845e-05, + "loss": 3.3426, "step": 53700 }, { - "epoch": 0.19, - "learning_rate": 4.0398035345224545e-05, - "loss": 3.2558, + "epoch": 0.18, + "learning_rate": 4.1085483256284074e-05, + "loss": 3.3422, "step": 53800 }, { - "epoch": 0.19, - "learning_rate": 4.0380187827278866e-05, - "loss": 3.2375, + "epoch": 0.18, + "learning_rate": 4.1068913522559695e-05, + "loss": 3.3405, "step": 53900 }, { - "epoch": 0.19, - "learning_rate": 4.036234030933319e-05, - "loss": 3.2506, + "epoch": 0.18, + "learning_rate": 4.105234378883532e-05, + "loss": 3.3615, "step": 54000 }, { - "epoch": 0.19, - "learning_rate": 4.034449279138751e-05, - "loss": 3.2392, + "epoch": 0.18, + "learning_rate": 4.103577405511094e-05, + "loss": 3.362, "step": 54100 }, { - "epoch": 0.19, - "learning_rate": 4.032664527344183e-05, - "loss": 3.238, + "epoch": 0.18, + "learning_rate": 4.101920432138655e-05, + "loss": 3.3421, "step": 54200 }, { - "epoch": 0.19, - "learning_rate": 4.0308797755496144e-05, - "loss": 3.2503, + "epoch": 0.18, + "learning_rate": 4.100263458766218e-05, + "loss": 3.345, "step": 54300 }, { - "epoch": 0.19, - "learning_rate": 4.0290950237550465e-05, - "loss": 3.2592, + "epoch": 0.18, + "learning_rate": 4.09860648539378e-05, + "loss": 3.3491, "step": 54400 }, { - "epoch": 0.19, - "learning_rate": 4.027310271960479e-05, - "loss": 3.2358, + "epoch": 0.18, + "learning_rate": 4.096949512021342e-05, + "loss": 3.3449, "step": 54500 }, { - "epoch": 0.19, - "learning_rate": 4.025525520165911e-05, - "loss": 3.2475, + "epoch": 0.18, + "learning_rate": 4.095292538648904e-05, + "loss": 3.3471, "step": 54600 }, { - "epoch": 0.2, - "learning_rate": 4.023740768371343e-05, - "loss": 3.2453, + "epoch": 0.18, + "learning_rate": 4.093635565276466e-05, + "loss": 3.3436, "step": 54700 }, { - "epoch": 0.2, - "learning_rate": 4.021956016576775e-05, - "loss": 3.2432, + "epoch": 0.18, + "learning_rate": 4.091978591904028e-05, + "loss": 3.3628, "step": 54800 }, { - "epoch": 0.2, - "learning_rate": 4.020171264782207e-05, - "loss": 3.2349, + "epoch": 0.18, + "learning_rate": 4.09032161853159e-05, + "loss": 3.3518, "step": 54900 }, { - "epoch": 0.2, - "learning_rate": 4.018386512987639e-05, - "loss": 3.2391, + "epoch": 0.18, + "learning_rate": 4.0886646451591525e-05, + "loss": 3.3411, "step": 55000 }, { - "epoch": 0.2, - "learning_rate": 4.0166017611930714e-05, - "loss": 3.2473, + "epoch": 0.18, + "learning_rate": 4.0870076717867146e-05, + "loss": 3.3333, "step": 55100 }, { - "epoch": 0.2, - "learning_rate": 4.0148170093985035e-05, - "loss": 3.2396, + "epoch": 0.18, + "learning_rate": 4.085350698414277e-05, + "loss": 3.3354, "step": 55200 }, { - "epoch": 0.2, - "learning_rate": 4.0130322576039356e-05, - "loss": 3.2514, + "epoch": 0.18, + "learning_rate": 4.083693725041839e-05, + "loss": 3.3366, "step": 55300 }, { - "epoch": 0.2, - "learning_rate": 4.011247505809367e-05, - "loss": 3.2478, + "epoch": 0.18, + "learning_rate": 4.082036751669401e-05, + "loss": 3.3402, "step": 55400 }, { - "epoch": 0.2, - "learning_rate": 4.009462754014799e-05, - "loss": 3.2567, + "epoch": 0.18, + "learning_rate": 4.0803797782969625e-05, + "loss": 3.3381, "step": 55500 }, { - "epoch": 0.2, - "learning_rate": 4.007678002220231e-05, - "loss": 3.2369, + "epoch": 0.18, + "learning_rate": 4.0787228049245253e-05, + "loss": 3.3444, "step": 55600 }, { - "epoch": 0.2, - "learning_rate": 4.0058932504256634e-05, - "loss": 3.2442, + "epoch": 0.18, + "learning_rate": 4.077065831552087e-05, + "loss": 3.3459, "step": 55700 }, { - "epoch": 0.2, - "learning_rate": 4.0041084986310956e-05, - "loss": 3.244, + "epoch": 0.18, + "learning_rate": 4.075408858179649e-05, + "loss": 3.3572, "step": 55800 }, { - "epoch": 0.2, - "learning_rate": 4.002323746836528e-05, - "loss": 3.2536, + "epoch": 0.19, + "learning_rate": 4.073751884807212e-05, + "loss": 3.344, "step": 55900 }, { - "epoch": 0.2, - "learning_rate": 4.00053899504196e-05, - "loss": 3.2429, + "epoch": 0.19, + "learning_rate": 4.072094911434773e-05, + "loss": 3.3549, "step": 56000 }, { - "epoch": 0.2, - "learning_rate": 3.998754243247392e-05, - "loss": 3.2452, + "epoch": 0.19, + "learning_rate": 4.0704379380623354e-05, + "loss": 3.3556, "step": 56100 }, { - "epoch": 0.2, - "learning_rate": 3.996969491452824e-05, - "loss": 3.2461, + "epoch": 0.19, + "learning_rate": 4.0687809646898975e-05, + "loss": 3.3489, "step": 56200 }, { - "epoch": 0.2, - "learning_rate": 3.995184739658256e-05, - "loss": 3.2517, + "epoch": 0.19, + "learning_rate": 4.06712399131746e-05, + "loss": 3.3473, "step": 56300 }, { - "epoch": 0.2, - "learning_rate": 3.993399987863688e-05, - "loss": 3.2455, + "epoch": 0.19, + "learning_rate": 4.065467017945022e-05, + "loss": 3.342, "step": 56400 }, { - "epoch": 0.2, - "learning_rate": 3.99161523606912e-05, - "loss": 3.2474, + "epoch": 0.19, + "learning_rate": 4.063810044572584e-05, + "loss": 3.3423, "step": 56500 }, { - "epoch": 0.2, - "learning_rate": 3.989830484274552e-05, - "loss": 3.2518, + "epoch": 0.19, + "learning_rate": 4.062153071200146e-05, + "loss": 3.3532, "step": 56600 }, { - "epoch": 0.2, - "learning_rate": 3.988045732479984e-05, - "loss": 3.2396, + "epoch": 0.19, + "learning_rate": 4.0604960978277076e-05, + "loss": 3.336, "step": 56700 }, { - "epoch": 0.2, - "learning_rate": 3.986260980685416e-05, - "loss": 3.2508, + "epoch": 0.19, + "learning_rate": 4.0588391244552704e-05, + "loss": 3.3547, "step": 56800 }, { - "epoch": 0.2, - "learning_rate": 3.984476228890848e-05, - "loss": 3.2512, + "epoch": 0.19, + "learning_rate": 4.0571821510828326e-05, + "loss": 3.3524, "step": 56900 }, { - "epoch": 0.2, - "learning_rate": 3.9826914770962804e-05, - "loss": 3.2502, + "epoch": 0.19, + "learning_rate": 4.055525177710394e-05, + "loss": 3.3477, "step": 57000 }, { - "epoch": 0.2, - "learning_rate": 3.9809067253017125e-05, - "loss": 3.2456, + "epoch": 0.19, + "learning_rate": 4.053868204337957e-05, + "loss": 3.3553, "step": 57100 }, { - "epoch": 0.2, - "learning_rate": 3.9791219735071446e-05, - "loss": 3.2379, + "epoch": 0.19, + "learning_rate": 4.052211230965518e-05, + "loss": 3.3433, "step": 57200 }, { - "epoch": 0.2, - "learning_rate": 3.977337221712577e-05, - "loss": 3.2399, + "epoch": 0.19, + "learning_rate": 4.0505542575930805e-05, + "loss": 3.3486, "step": 57300 }, { - "epoch": 0.2, - "learning_rate": 3.975552469918009e-05, - "loss": 3.2315, + "epoch": 0.19, + "learning_rate": 4.0488972842206426e-05, + "loss": 3.3543, "step": 57400 }, { - "epoch": 0.21, - "learning_rate": 3.97376771812344e-05, - "loss": 3.2416, + "epoch": 0.19, + "learning_rate": 4.047240310848205e-05, + "loss": 3.3474, "step": 57500 }, { - "epoch": 0.21, - "learning_rate": 3.9719829663288724e-05, - "loss": 3.2437, + "epoch": 0.19, + "learning_rate": 4.045583337475767e-05, + "loss": 3.3409, "step": 57600 }, { - "epoch": 0.21, - "learning_rate": 3.9701982145343045e-05, - "loss": 3.2365, + "epoch": 0.19, + "learning_rate": 4.043926364103329e-05, + "loss": 3.3515, "step": 57700 }, { - "epoch": 0.21, - "learning_rate": 3.9684134627397366e-05, - "loss": 3.2492, + "epoch": 0.19, + "learning_rate": 4.042269390730891e-05, + "loss": 3.353, "step": 57800 }, { - "epoch": 0.21, - "learning_rate": 3.966628710945169e-05, - "loss": 3.2328, + "epoch": 0.19, + "learning_rate": 4.0406124173584534e-05, + "loss": 3.3503, "step": 57900 }, { - "epoch": 0.21, - "learning_rate": 3.964843959150601e-05, - "loss": 3.2414, + "epoch": 0.19, + "learning_rate": 4.0389554439860155e-05, + "loss": 3.3446, "step": 58000 }, { - "epoch": 0.21, - "learning_rate": 3.963059207356033e-05, - "loss": 3.2385, + "epoch": 0.19, + "learning_rate": 4.0372984706135777e-05, + "loss": 3.3571, "step": 58100 }, { - "epoch": 0.21, - "learning_rate": 3.961274455561465e-05, - "loss": 3.2499, + "epoch": 0.19, + "learning_rate": 4.035641497241139e-05, + "loss": 3.3467, "step": 58200 }, { - "epoch": 0.21, - "learning_rate": 3.959489703766897e-05, - "loss": 3.2378, + "epoch": 0.19, + "learning_rate": 4.033984523868702e-05, + "loss": 3.3667, "step": 58300 }, { - "epoch": 0.21, - "learning_rate": 3.9577049519723294e-05, - "loss": 3.2313, + "epoch": 0.19, + "learning_rate": 4.032327550496264e-05, + "loss": 3.3492, "step": 58400 }, { - "epoch": 0.21, - "learning_rate": 3.9559202001777615e-05, - "loss": 3.2325, + "epoch": 0.19, + "learning_rate": 4.0306705771238256e-05, + "loss": 3.3445, "step": 58500 }, { - "epoch": 0.21, - "learning_rate": 3.954135448383193e-05, - "loss": 3.2489, + "epoch": 0.19, + "learning_rate": 4.0290136037513884e-05, + "loss": 3.3567, "step": 58600 }, { - "epoch": 0.21, - "learning_rate": 3.952350696588625e-05, - "loss": 3.2339, + "epoch": 0.19, + "learning_rate": 4.02735663037895e-05, + "loss": 3.3497, "step": 58700 }, { - "epoch": 0.21, - "learning_rate": 3.950565944794058e-05, - "loss": 3.2303, + "epoch": 0.19, + "learning_rate": 4.025699657006512e-05, + "loss": 3.3386, "step": 58800 }, { - "epoch": 0.21, - "learning_rate": 3.94878119299949e-05, - "loss": 3.2359, + "epoch": 0.2, + "learning_rate": 4.024042683634074e-05, + "loss": 3.3426, "step": 58900 }, { - "epoch": 0.21, - "learning_rate": 3.946996441204922e-05, - "loss": 3.2349, + "epoch": 0.2, + "learning_rate": 4.022385710261636e-05, + "loss": 3.3341, "step": 59000 }, { - "epoch": 0.21, - "learning_rate": 3.945211689410354e-05, - "loss": 3.2357, + "epoch": 0.2, + "learning_rate": 4.0207287368891984e-05, + "loss": 3.3402, "step": 59100 }, { - "epoch": 0.21, - "learning_rate": 3.9434269376157863e-05, - "loss": 3.2402, + "epoch": 0.2, + "learning_rate": 4.0190717635167606e-05, + "loss": 3.3455, "step": 59200 }, { - "epoch": 0.21, - "learning_rate": 3.9416421858212185e-05, - "loss": 3.2331, + "epoch": 0.2, + "learning_rate": 4.017414790144323e-05, + "loss": 3.3532, "step": 59300 }, { - "epoch": 0.21, - "learning_rate": 3.9398574340266506e-05, - "loss": 3.2475, + "epoch": 0.2, + "learning_rate": 4.015757816771885e-05, + "loss": 3.3383, "step": 59400 }, { - "epoch": 0.21, - "learning_rate": 3.938072682232082e-05, - "loss": 3.2459, + "epoch": 0.2, + "learning_rate": 4.014100843399447e-05, + "loss": 3.3416, "step": 59500 }, { - "epoch": 0.21, - "learning_rate": 3.936287930437514e-05, - "loss": 3.2448, + "epoch": 0.2, + "learning_rate": 4.012443870027009e-05, + "loss": 3.3453, "step": 59600 }, { - "epoch": 0.21, - "learning_rate": 3.934503178642946e-05, - "loss": 3.2372, + "epoch": 0.2, + "learning_rate": 4.0107868966545707e-05, + "loss": 3.3432, "step": 59700 }, { - "epoch": 0.21, - "learning_rate": 3.9327184268483784e-05, - "loss": 3.2316, + "epoch": 0.2, + "learning_rate": 4.009129923282133e-05, + "loss": 3.3476, "step": 59800 }, { - "epoch": 0.21, - "learning_rate": 3.9309336750538105e-05, - "loss": 3.2376, + "epoch": 0.2, + "learning_rate": 4.007472949909695e-05, + "loss": 3.3514, "step": 59900 }, { - "epoch": 0.21, - "learning_rate": 3.9291489232592426e-05, - "loss": 3.2347, + "epoch": 0.2, + "learning_rate": 4.005815976537257e-05, + "loss": 3.3329, "step": 60000 }, { - "epoch": 0.21, - "learning_rate": 3.927364171464675e-05, - "loss": 3.2399, + "epoch": 0.2, + "learning_rate": 4.004159003164819e-05, + "loss": 3.3428, "step": 60100 }, { - "epoch": 0.21, - "learning_rate": 3.925579419670107e-05, - "loss": 3.2386, + "epoch": 0.2, + "learning_rate": 4.0025020297923814e-05, + "loss": 3.3456, "step": 60200 }, { - "epoch": 0.22, - "learning_rate": 3.923794667875539e-05, - "loss": 3.2273, + "epoch": 0.2, + "learning_rate": 4.0008450564199435e-05, + "loss": 3.3509, "step": 60300 }, { - "epoch": 0.22, - "learning_rate": 3.922009916080971e-05, - "loss": 3.2385, + "epoch": 0.2, + "learning_rate": 3.999188083047506e-05, + "loss": 3.3497, "step": 60400 }, { - "epoch": 0.22, - "learning_rate": 3.920225164286403e-05, - "loss": 3.241, + "epoch": 0.2, + "learning_rate": 3.997531109675068e-05, + "loss": 3.3476, "step": 60500 }, { - "epoch": 0.22, - "learning_rate": 3.918440412491835e-05, - "loss": 3.2461, + "epoch": 0.2, + "learning_rate": 3.99587413630263e-05, + "loss": 3.3376, "step": 60600 }, { - "epoch": 0.22, - "learning_rate": 3.916655660697267e-05, - "loss": 3.245, + "epoch": 0.2, + "learning_rate": 3.9942171629301914e-05, + "loss": 3.3388, "step": 60700 }, { - "epoch": 0.22, - "learning_rate": 3.914870908902699e-05, - "loss": 3.2381, + "epoch": 0.2, + "learning_rate": 3.992560189557754e-05, + "loss": 3.3375, "step": 60800 }, { - "epoch": 0.22, - "learning_rate": 3.913086157108131e-05, - "loss": 3.2372, + "epoch": 0.2, + "learning_rate": 3.990903216185316e-05, + "loss": 3.3422, "step": 60900 }, { - "epoch": 0.22, - "learning_rate": 3.911301405313563e-05, - "loss": 3.2422, + "epoch": 0.2, + "learning_rate": 3.989246242812878e-05, + "loss": 3.3523, "step": 61000 }, { - "epoch": 0.22, - "learning_rate": 3.909516653518995e-05, - "loss": 3.2313, + "epoch": 0.2, + "learning_rate": 3.987589269440441e-05, + "loss": 3.3427, "step": 61100 }, { - "epoch": 0.22, - "learning_rate": 3.9077319017244274e-05, - "loss": 3.2289, + "epoch": 0.2, + "learning_rate": 3.985932296068002e-05, + "loss": 3.3457, "step": 61200 }, { - "epoch": 0.22, - "learning_rate": 3.9059471499298595e-05, - "loss": 3.2361, + "epoch": 0.2, + "learning_rate": 3.984275322695564e-05, + "loss": 3.3377, "step": 61300 }, { - "epoch": 0.22, - "learning_rate": 3.904162398135292e-05, - "loss": 3.2443, + "epoch": 0.2, + "learning_rate": 3.9826183493231265e-05, + "loss": 3.3534, "step": 61400 }, { - "epoch": 0.22, - "learning_rate": 3.902377646340724e-05, - "loss": 3.2354, + "epoch": 0.2, + "learning_rate": 3.9809613759506886e-05, + "loss": 3.3395, "step": 61500 }, { - "epoch": 0.22, - "learning_rate": 3.900592894546156e-05, - "loss": 3.2232, + "epoch": 0.2, + "learning_rate": 3.979304402578251e-05, + "loss": 3.3397, "step": 61600 }, { - "epoch": 0.22, - "learning_rate": 3.8988081427515874e-05, - "loss": 3.2294, + "epoch": 0.2, + "learning_rate": 3.977647429205813e-05, + "loss": 3.3347, "step": 61700 }, { - "epoch": 0.22, - "learning_rate": 3.8970233909570195e-05, - "loss": 3.2402, + "epoch": 0.2, + "learning_rate": 3.975990455833375e-05, + "loss": 3.3465, "step": 61800 }, { - "epoch": 0.22, - "learning_rate": 3.8952386391624516e-05, - "loss": 3.2346, + "epoch": 0.21, + "learning_rate": 3.9743334824609365e-05, + "loss": 3.3446, "step": 61900 }, { - "epoch": 0.22, - "learning_rate": 3.893453887367884e-05, - "loss": 3.2415, + "epoch": 0.21, + "learning_rate": 3.9726765090884993e-05, + "loss": 3.328, "step": 62000 }, { - "epoch": 0.22, - "learning_rate": 3.891669135573316e-05, - "loss": 3.2274, + "epoch": 0.21, + "learning_rate": 3.9710195357160615e-05, + "loss": 3.3345, "step": 62100 }, { - "epoch": 0.22, - "learning_rate": 3.889884383778748e-05, - "loss": 3.2359, + "epoch": 0.21, + "learning_rate": 3.969362562343623e-05, + "loss": 3.3504, "step": 62200 }, { - "epoch": 0.22, - "learning_rate": 3.88809963198418e-05, - "loss": 3.2241, + "epoch": 0.21, + "learning_rate": 3.967705588971186e-05, + "loss": 3.3307, "step": 62300 }, { - "epoch": 0.22, - "learning_rate": 3.886314880189612e-05, - "loss": 3.2454, + "epoch": 0.21, + "learning_rate": 3.966048615598747e-05, + "loss": 3.3406, "step": 62400 }, { - "epoch": 0.22, - "learning_rate": 3.884530128395044e-05, - "loss": 3.2244, + "epoch": 0.21, + "learning_rate": 3.9643916422263094e-05, + "loss": 3.3441, "step": 62500 }, { - "epoch": 0.22, - "learning_rate": 3.8827453766004764e-05, - "loss": 3.232, + "epoch": 0.21, + "learning_rate": 3.962734668853872e-05, + "loss": 3.3492, "step": 62600 }, { - "epoch": 0.22, - "learning_rate": 3.8809606248059086e-05, - "loss": 3.2295, + "epoch": 0.21, + "learning_rate": 3.961077695481434e-05, + "loss": 3.3458, "step": 62700 }, { - "epoch": 0.22, - "learning_rate": 3.87917587301134e-05, - "loss": 3.2317, + "epoch": 0.21, + "learning_rate": 3.959420722108996e-05, + "loss": 3.343, "step": 62800 }, { - "epoch": 0.22, - "learning_rate": 3.877391121216772e-05, - "loss": 3.2304, + "epoch": 0.21, + "learning_rate": 3.957763748736558e-05, + "loss": 3.3499, "step": 62900 }, { - "epoch": 0.22, - "learning_rate": 3.875606369422204e-05, - "loss": 3.2319, + "epoch": 0.21, + "learning_rate": 3.95610677536412e-05, + "loss": 3.35, "step": 63000 }, { - "epoch": 0.23, - "learning_rate": 3.8738216176276364e-05, - "loss": 3.2235, + "epoch": 0.21, + "learning_rate": 3.954449801991682e-05, + "loss": 3.33, "step": 63100 }, { - "epoch": 0.23, - "learning_rate": 3.8720368658330685e-05, - "loss": 3.2325, + "epoch": 0.21, + "learning_rate": 3.9527928286192444e-05, + "loss": 3.3379, "step": 63200 }, { - "epoch": 0.23, - "learning_rate": 3.8702521140385006e-05, - "loss": 3.2338, + "epoch": 0.21, + "learning_rate": 3.9511358552468066e-05, + "loss": 3.3411, "step": 63300 }, { - "epoch": 0.23, - "learning_rate": 3.868467362243933e-05, - "loss": 3.2267, + "epoch": 0.21, + "learning_rate": 3.949478881874368e-05, + "loss": 3.3388, "step": 63400 }, { - "epoch": 0.23, - "learning_rate": 3.866682610449365e-05, - "loss": 3.2399, + "epoch": 0.21, + "learning_rate": 3.947821908501931e-05, + "loss": 3.3367, "step": 63500 }, + { + "epoch": 0.21, + "learning_rate": 3.946164935129493e-05, + "loss": 3.3421, + "step": 63600 + }, + { + "epoch": 0.21, + "learning_rate": 3.9445079617570545e-05, + "loss": 3.3445, + "step": 63700 + }, + { + "epoch": 0.21, + "learning_rate": 3.942850988384617e-05, + "loss": 3.3475, + "step": 63800 + }, + { + "epoch": 0.21, + "learning_rate": 3.941194015012179e-05, + "loss": 3.3425, + "step": 63900 + }, + { + "epoch": 0.21, + "learning_rate": 3.939537041639741e-05, + "loss": 3.3314, + "step": 64000 + }, + { + "epoch": 0.21, + "learning_rate": 3.937880068267303e-05, + "loss": 3.349, + "step": 64100 + }, + { + "epoch": 0.21, + "learning_rate": 3.936223094894865e-05, + "loss": 3.3572, + "step": 64200 + }, + { + "epoch": 0.21, + "learning_rate": 3.9345661215224274e-05, + "loss": 3.3469, + "step": 64300 + }, + { + "epoch": 0.21, + "learning_rate": 3.9329091481499895e-05, + "loss": 3.3494, + "step": 64400 + }, + { + "epoch": 0.21, + "learning_rate": 3.9312521747775517e-05, + "loss": 3.3446, + "step": 64500 + }, + { + "epoch": 0.21, + "learning_rate": 3.929595201405114e-05, + "loss": 3.3409, + "step": 64600 + }, + { + "epoch": 0.21, + "learning_rate": 3.927938228032676e-05, + "loss": 3.3349, + "step": 64700 + }, + { + "epoch": 0.21, + "learning_rate": 3.926281254660238e-05, + "loss": 3.3382, + "step": 64800 + }, + { + "epoch": 0.22, + "learning_rate": 3.9246242812877996e-05, + "loss": 3.3367, + "step": 64900 + }, + { + "epoch": 0.22, + "learning_rate": 3.922967307915362e-05, + "loss": 3.3396, + "step": 65000 + }, + { + "epoch": 0.22, + "learning_rate": 3.921310334542924e-05, + "loss": 3.3513, + "step": 65100 + }, + { + "epoch": 0.22, + "learning_rate": 3.919653361170486e-05, + "loss": 3.3427, + "step": 65200 + }, + { + "epoch": 0.22, + "learning_rate": 3.917996387798048e-05, + "loss": 3.3574, + "step": 65300 + }, + { + "epoch": 0.22, + "learning_rate": 3.91633941442561e-05, + "loss": 3.3354, + "step": 65400 + }, + { + "epoch": 0.22, + "learning_rate": 3.9146824410531724e-05, + "loss": 3.3383, + "step": 65500 + }, + { + "epoch": 0.22, + "learning_rate": 3.9130254676807346e-05, + "loss": 3.3502, + "step": 65600 + }, + { + "epoch": 0.22, + "learning_rate": 3.911368494308297e-05, + "loss": 3.333, + "step": 65700 + }, + { + "epoch": 0.22, + "learning_rate": 3.909711520935859e-05, + "loss": 3.328, + "step": 65800 + }, + { + "epoch": 0.22, + "learning_rate": 3.9080545475634204e-05, + "loss": 3.3307, + "step": 65900 + }, + { + "epoch": 0.22, + "learning_rate": 3.906397574190983e-05, + "loss": 3.3385, + "step": 66000 + }, + { + "epoch": 0.22, + "learning_rate": 3.9047406008185447e-05, + "loss": 3.3348, + "step": 66100 + }, + { + "epoch": 0.22, + "learning_rate": 3.903083627446107e-05, + "loss": 3.3486, + "step": 66200 + }, + { + "epoch": 0.22, + "learning_rate": 3.9014266540736696e-05, + "loss": 3.3428, + "step": 66300 + }, + { + "epoch": 0.22, + "learning_rate": 3.899769680701231e-05, + "loss": 3.3343, + "step": 66400 + }, + { + "epoch": 0.22, + "learning_rate": 3.898112707328793e-05, + "loss": 3.3468, + "step": 66500 + }, + { + "epoch": 0.22, + "learning_rate": 3.8964557339563554e-05, + "loss": 3.3333, + "step": 66600 + }, + { + "epoch": 0.22, + "learning_rate": 3.8947987605839175e-05, + "loss": 3.3464, + "step": 66700 + }, + { + "epoch": 0.22, + "learning_rate": 3.89314178721148e-05, + "loss": 3.3235, + "step": 66800 + }, + { + "epoch": 0.22, + "learning_rate": 3.891484813839042e-05, + "loss": 3.3444, + "step": 66900 + }, + { + "epoch": 0.22, + "learning_rate": 3.889827840466604e-05, + "loss": 3.3375, + "step": 67000 + }, + { + "epoch": 0.22, + "learning_rate": 3.888170867094166e-05, + "loss": 3.3301, + "step": 67100 + }, + { + "epoch": 0.22, + "learning_rate": 3.886513893721728e-05, + "loss": 3.3401, + "step": 67200 + }, + { + "epoch": 0.22, + "learning_rate": 3.8848569203492904e-05, + "loss": 3.3465, + "step": 67300 + }, + { + "epoch": 0.22, + "learning_rate": 3.883199946976852e-05, + "loss": 3.3431, + "step": 67400 + }, + { + "epoch": 0.22, + "learning_rate": 3.881542973604415e-05, + "loss": 3.3283, + "step": 67500 + }, + { + "epoch": 0.22, + "learning_rate": 3.879886000231976e-05, + "loss": 3.3269, + "step": 67600 + }, + { + "epoch": 0.22, + "learning_rate": 3.878229026859538e-05, + "loss": 3.3296, + "step": 67700 + }, + { + "epoch": 0.22, + "learning_rate": 3.876572053487101e-05, + "loss": 3.3422, + "step": 67800 + }, + { + "epoch": 0.23, + "learning_rate": 3.8749150801146626e-05, + "loss": 3.3324, + "step": 67900 + }, + { + "epoch": 0.23, + "learning_rate": 3.873258106742225e-05, + "loss": 3.3241, + "step": 68000 + }, + { + "epoch": 0.23, + "learning_rate": 3.871601133369787e-05, + "loss": 3.3203, + "step": 68100 + }, + { + "epoch": 0.23, + "learning_rate": 3.869944159997349e-05, + "loss": 3.3279, + "step": 68200 + }, + { + "epoch": 0.23, + "learning_rate": 3.868287186624911e-05, + "loss": 3.3448, + "step": 68300 + }, + { + "epoch": 0.23, + "learning_rate": 3.8666302132524733e-05, + "loss": 3.3417, + "step": 68400 + }, + { + "epoch": 0.23, + "learning_rate": 3.8649732398800355e-05, + "loss": 3.3459, + "step": 68500 + }, + { + "epoch": 0.23, + "learning_rate": 3.863316266507597e-05, + "loss": 3.3312, + "step": 68600 + }, + { + "epoch": 0.23, + "learning_rate": 3.86165929313516e-05, + "loss": 3.3411, + "step": 68700 + }, + { + "epoch": 0.23, + "learning_rate": 3.860002319762722e-05, + "loss": 3.3326, + "step": 68800 + }, { "epoch": 0.23, - "learning_rate": 3.864897858654797e-05, - "loss": 3.2321, - "step": 63600 + "learning_rate": 3.8583453463902834e-05, + "loss": 3.341, + "step": 68900 }, { "epoch": 0.23, - "learning_rate": 3.863113106860229e-05, - "loss": 3.2343, - "step": 63700 + "learning_rate": 3.856688373017846e-05, + "loss": 3.3319, + "step": 69000 }, { "epoch": 0.23, - "learning_rate": 3.861328355065661e-05, - "loss": 3.2331, - "step": 63800 + "learning_rate": 3.855031399645408e-05, + "loss": 3.3394, + "step": 69100 }, { "epoch": 0.23, - "learning_rate": 3.8595436032710933e-05, - "loss": 3.2438, - "step": 63900 + "learning_rate": 3.85337442627297e-05, + "loss": 3.3334, + "step": 69200 }, { "epoch": 0.23, - "learning_rate": 3.8577588514765255e-05, - "loss": 3.2308, - "step": 64000 + "learning_rate": 3.851717452900532e-05, + "loss": 3.3329, + "step": 69300 }, { "epoch": 0.23, - "learning_rate": 3.8559740996819576e-05, - "loss": 3.2332, - "step": 64100 + "learning_rate": 3.850060479528094e-05, + "loss": 3.328, + "step": 69400 }, { "epoch": 0.23, - "learning_rate": 3.85418934788739e-05, - "loss": 3.2332, - "step": 64200 + "learning_rate": 3.848403506155656e-05, + "loss": 3.3484, + "step": 69500 }, { "epoch": 0.23, - "learning_rate": 3.852404596092822e-05, - "loss": 3.228, - "step": 64300 + "learning_rate": 3.8467465327832184e-05, + "loss": 3.343, + "step": 69600 }, { "epoch": 0.23, - "learning_rate": 3.850619844298254e-05, - "loss": 3.2265, - "step": 64400 + "learning_rate": 3.8450895594107806e-05, + "loss": 3.3432, + "step": 69700 }, { "epoch": 0.23, - "learning_rate": 3.848835092503686e-05, - "loss": 3.2292, - "step": 64500 + "learning_rate": 3.843432586038343e-05, + "loss": 3.3366, + "step": 69800 }, { "epoch": 0.23, - "learning_rate": 3.847050340709118e-05, - "loss": 3.2245, - "step": 64600 + "learning_rate": 3.841775612665905e-05, + "loss": 3.3426, + "step": 69900 }, { "epoch": 0.23, - "learning_rate": 3.84526558891455e-05, - "loss": 3.2212, - "step": 64700 + "learning_rate": 3.840118639293467e-05, + "loss": 3.3544, + "step": 70000 }, { "epoch": 0.23, - "learning_rate": 3.843480837119982e-05, - "loss": 3.2171, - "step": 64800 + "learning_rate": 3.8384616659210285e-05, + "loss": 3.3428, + "step": 70100 }, { "epoch": 0.23, - "learning_rate": 3.841696085325414e-05, - "loss": 3.2272, - "step": 64900 + "learning_rate": 3.8368046925485906e-05, + "loss": 3.3457, + "step": 70200 }, { "epoch": 0.23, - "learning_rate": 3.839911333530846e-05, - "loss": 3.2249, - "step": 65000 + "learning_rate": 3.8351477191761535e-05, + "loss": 3.3327, + "step": 70300 }, { "epoch": 0.23, - "learning_rate": 3.838126581736278e-05, - "loss": 3.2415, - "step": 65100 + "learning_rate": 3.833490745803715e-05, + "loss": 3.338, + "step": 70400 }, { "epoch": 0.23, - "learning_rate": 3.83634182994171e-05, - "loss": 3.2278, - "step": 65200 + "learning_rate": 3.831833772431277e-05, + "loss": 3.3289, + "step": 70500 }, { "epoch": 0.23, - "learning_rate": 3.8345570781471424e-05, - "loss": 3.2369, - "step": 65300 + "learning_rate": 3.830176799058839e-05, + "loss": 3.3466, + "step": 70600 }, { "epoch": 0.23, - "learning_rate": 3.8327723263525745e-05, - "loss": 3.2392, - "step": 65400 + "learning_rate": 3.8285198256864014e-05, + "loss": 3.3504, + "step": 70700 }, { "epoch": 0.23, - "learning_rate": 3.8309875745580066e-05, - "loss": 3.2245, - "step": 65500 + "learning_rate": 3.8268628523139635e-05, + "loss": 3.3219, + "step": 70800 }, { "epoch": 0.23, - "learning_rate": 3.829202822763439e-05, - "loss": 3.2161, - "step": 65600 + "learning_rate": 3.8252058789415257e-05, + "loss": 3.333, + "step": 70900 }, { - "epoch": 0.23, - "learning_rate": 3.827418070968871e-05, - "loss": 3.2149, - "step": 65700 + "epoch": 0.24, + "learning_rate": 3.823548905569088e-05, + "loss": 3.3356, + "step": 71000 }, { - "epoch": 0.23, - "learning_rate": 3.825633319174303e-05, - "loss": 3.2189, - "step": 65800 + "epoch": 0.24, + "learning_rate": 3.821891932196649e-05, + "loss": 3.3308, + "step": 71100 }, { "epoch": 0.24, - "learning_rate": 3.8238485673797344e-05, - "loss": 3.2208, - "step": 65900 + "learning_rate": 3.820234958824212e-05, + "loss": 3.3325, + "step": 71200 }, { "epoch": 0.24, - "learning_rate": 3.8220638155851665e-05, - "loss": 3.2292, - "step": 66000 + "learning_rate": 3.818577985451774e-05, + "loss": 3.3262, + "step": 71300 }, { "epoch": 0.24, - "learning_rate": 3.820279063790599e-05, - "loss": 3.2217, - "step": 66100 + "learning_rate": 3.816921012079336e-05, + "loss": 3.3406, + "step": 71400 }, { "epoch": 0.24, - "learning_rate": 3.818494311996031e-05, - "loss": 3.2367, - "step": 66200 + "learning_rate": 3.8152640387068985e-05, + "loss": 3.3236, + "step": 71500 }, { "epoch": 0.24, - "learning_rate": 3.816709560201463e-05, - "loss": 3.2293, - "step": 66300 + "learning_rate": 3.81360706533446e-05, + "loss": 3.3329, + "step": 71600 }, { "epoch": 0.24, - "learning_rate": 3.814924808406895e-05, - "loss": 3.2348, - "step": 66400 + "learning_rate": 3.811950091962022e-05, + "loss": 3.3484, + "step": 71700 }, { "epoch": 0.24, - "learning_rate": 3.813140056612327e-05, - "loss": 3.2264, - "step": 66500 + "learning_rate": 3.810293118589584e-05, + "loss": 3.3376, + "step": 71800 }, { "epoch": 0.24, - "learning_rate": 3.811355304817759e-05, - "loss": 3.2269, - "step": 66600 + "learning_rate": 3.8086361452171464e-05, + "loss": 3.3271, + "step": 71900 }, { "epoch": 0.24, - "learning_rate": 3.8095705530231914e-05, - "loss": 3.2238, - "step": 66700 + "learning_rate": 3.8069791718447086e-05, + "loss": 3.335, + "step": 72000 }, { "epoch": 0.24, - "learning_rate": 3.8077858012286235e-05, - "loss": 3.2139, - "step": 66800 + "learning_rate": 3.805322198472271e-05, + "loss": 3.3288, + "step": 72100 }, { "epoch": 0.24, - "learning_rate": 3.8060010494340556e-05, - "loss": 3.2273, - "step": 66900 + "learning_rate": 3.803665225099833e-05, + "loss": 3.3366, + "step": 72200 }, { "epoch": 0.24, - "learning_rate": 3.804216297639487e-05, - "loss": 3.2227, - "step": 67000 + "learning_rate": 3.802008251727395e-05, + "loss": 3.3329, + "step": 72300 }, { "epoch": 0.24, - "learning_rate": 3.802431545844919e-05, - "loss": 3.2286, - "step": 67100 + "learning_rate": 3.800351278354957e-05, + "loss": 3.3367, + "step": 72400 }, { "epoch": 0.24, - "learning_rate": 3.800646794050351e-05, - "loss": 3.2239, - "step": 67200 + "learning_rate": 3.798694304982519e-05, + "loss": 3.337, + "step": 72500 }, { "epoch": 0.24, - "learning_rate": 3.7988620422557834e-05, - "loss": 3.2305, - "step": 67300 + "learning_rate": 3.797037331610081e-05, + "loss": 3.3255, + "step": 72600 }, { "epoch": 0.24, - "learning_rate": 3.7970772904612156e-05, - "loss": 3.2262, - "step": 67400 + "learning_rate": 3.7953803582376436e-05, + "loss": 3.3435, + "step": 72700 }, { "epoch": 0.24, - "learning_rate": 3.795292538666648e-05, - "loss": 3.2251, - "step": 67500 + "learning_rate": 3.793723384865205e-05, + "loss": 3.3137, + "step": 72800 }, { "epoch": 0.24, - "learning_rate": 3.79350778687208e-05, - "loss": 3.2298, - "step": 67600 + "learning_rate": 3.792066411492767e-05, + "loss": 3.3252, + "step": 72900 }, { "epoch": 0.24, - "learning_rate": 3.791723035077512e-05, - "loss": 3.2203, - "step": 67700 + "learning_rate": 3.79040943812033e-05, + "loss": 3.3268, + "step": 73000 }, { "epoch": 0.24, - "learning_rate": 3.789938283282944e-05, - "loss": 3.2336, - "step": 67800 + "learning_rate": 3.7887524647478915e-05, + "loss": 3.3427, + "step": 73100 }, { "epoch": 0.24, - "learning_rate": 3.788153531488376e-05, - "loss": 3.2192, - "step": 67900 + "learning_rate": 3.787095491375454e-05, + "loss": 3.3262, + "step": 73200 }, { "epoch": 0.24, - "learning_rate": 3.786368779693808e-05, - "loss": 3.2247, - "step": 68000 + "learning_rate": 3.785438518003016e-05, + "loss": 3.3233, + "step": 73300 }, { "epoch": 0.24, - "learning_rate": 3.78458402789924e-05, - "loss": 3.2307, - "step": 68100 + "learning_rate": 3.783781544630578e-05, + "loss": 3.3429, + "step": 73400 }, { "epoch": 0.24, - "learning_rate": 3.782799276104672e-05, - "loss": 3.2261, - "step": 68200 + "learning_rate": 3.78212457125814e-05, + "loss": 3.3269, + "step": 73500 }, { "epoch": 0.24, - "learning_rate": 3.781014524310104e-05, - "loss": 3.2249, - "step": 68300 + "learning_rate": 3.780467597885702e-05, + "loss": 3.3382, + "step": 73600 }, { "epoch": 0.24, - "learning_rate": 3.779229772515536e-05, - "loss": 3.224, - "step": 68400 + "learning_rate": 3.7788106245132644e-05, + "loss": 3.3293, + "step": 73700 }, { "epoch": 0.24, - "learning_rate": 3.777445020720968e-05, - "loss": 3.2109, - "step": 68500 + "learning_rate": 3.777153651140826e-05, + "loss": 3.327, + "step": 73800 }, { "epoch": 0.24, - "learning_rate": 3.7756602689264003e-05, - "loss": 3.2233, - "step": 68600 + "learning_rate": 3.775496677768389e-05, + "loss": 3.3373, + "step": 73900 }, { "epoch": 0.25, - "learning_rate": 3.7738755171318325e-05, - "loss": 3.2304, - "step": 68700 + "learning_rate": 3.773839704395951e-05, + "loss": 3.3305, + "step": 74000 }, { "epoch": 0.25, - "learning_rate": 3.7720907653372646e-05, - "loss": 3.2246, - "step": 68800 + "learning_rate": 3.772182731023512e-05, + "loss": 3.3295, + "step": 74100 }, { "epoch": 0.25, - "learning_rate": 3.770306013542697e-05, - "loss": 3.2211, - "step": 68900 + "learning_rate": 3.770525757651075e-05, + "loss": 3.3324, + "step": 74200 }, { "epoch": 0.25, - "learning_rate": 3.768521261748129e-05, - "loss": 3.2249, - "step": 69000 + "learning_rate": 3.7688687842786366e-05, + "loss": 3.3251, + "step": 74300 }, { "epoch": 0.25, - "learning_rate": 3.766736509953561e-05, - "loss": 3.2292, - "step": 69100 + "learning_rate": 3.767211810906199e-05, + "loss": 3.3369, + "step": 74400 }, { "epoch": 0.25, - "learning_rate": 3.764951758158993e-05, - "loss": 3.2233, - "step": 69200 + "learning_rate": 3.7655548375337616e-05, + "loss": 3.3277, + "step": 74500 }, { "epoch": 0.25, - "learning_rate": 3.763167006364425e-05, - "loss": 3.2202, - "step": 69300 + "learning_rate": 3.763897864161323e-05, + "loss": 3.3361, + "step": 74600 }, { "epoch": 0.25, - "learning_rate": 3.761382254569857e-05, - "loss": 3.221, - "step": 69400 + "learning_rate": 3.762240890788885e-05, + "loss": 3.3335, + "step": 74700 }, { "epoch": 0.25, - "learning_rate": 3.7595975027752894e-05, - "loss": 3.2251, - "step": 69500 + "learning_rate": 3.7605839174164473e-05, + "loss": 3.3243, + "step": 74800 }, { "epoch": 0.25, - "learning_rate": 3.7578127509807216e-05, - "loss": 3.2197, - "step": 69600 + "learning_rate": 3.7589269440440095e-05, + "loss": 3.3218, + "step": 74900 }, { "epoch": 0.25, - "learning_rate": 3.756027999186154e-05, - "loss": 3.2191, - "step": 69700 + "learning_rate": 3.7572699706715716e-05, + "loss": 3.3278, + "step": 75000 }, { "epoch": 0.25, - "learning_rate": 3.754243247391586e-05, - "loss": 3.2162, - "step": 69800 + "learning_rate": 3.755612997299134e-05, + "loss": 3.3378, + "step": 75100 }, { "epoch": 0.25, - "learning_rate": 3.752458495597018e-05, - "loss": 3.2299, - "step": 69900 + "learning_rate": 3.753956023926696e-05, + "loss": 3.3288, + "step": 75200 }, { "epoch": 0.25, - "learning_rate": 3.75067374380245e-05, - "loss": 3.2284, - "step": 70000 + "learning_rate": 3.7522990505542574e-05, + "loss": 3.3317, + "step": 75300 }, { "epoch": 0.25, - "learning_rate": 3.7488889920078815e-05, - "loss": 3.2244, - "step": 70100 + "learning_rate": 3.7506420771818196e-05, + "loss": 3.3267, + "step": 75400 }, { "epoch": 0.25, - "learning_rate": 3.7471042402133136e-05, - "loss": 3.2153, - "step": 70200 + "learning_rate": 3.7489851038093824e-05, + "loss": 3.334, + "step": 75500 }, { "epoch": 0.25, - "learning_rate": 3.745319488418746e-05, - "loss": 3.219, - "step": 70300 + "learning_rate": 3.747328130436944e-05, + "loss": 3.3286, + "step": 75600 }, { "epoch": 0.25, - "learning_rate": 3.743534736624178e-05, - "loss": 3.2128, - "step": 70400 + "learning_rate": 3.745671157064506e-05, + "loss": 3.3298, + "step": 75700 }, { "epoch": 0.25, - "learning_rate": 3.74174998482961e-05, - "loss": 3.2108, - "step": 70500 + "learning_rate": 3.744014183692068e-05, + "loss": 3.3359, + "step": 75800 }, { "epoch": 0.25, - "learning_rate": 3.739965233035042e-05, - "loss": 3.212, - "step": 70600 + "learning_rate": 3.74235721031963e-05, + "loss": 3.3261, + "step": 75900 }, { "epoch": 0.25, - "learning_rate": 3.738180481240474e-05, - "loss": 3.2274, - "step": 70700 + "learning_rate": 3.7407002369471924e-05, + "loss": 3.3361, + "step": 76000 }, { "epoch": 0.25, - "learning_rate": 3.7363957294459063e-05, - "loss": 3.2198, - "step": 70800 + "learning_rate": 3.7390432635747546e-05, + "loss": 3.3195, + "step": 76100 }, { "epoch": 0.25, - "learning_rate": 3.7346109776513385e-05, - "loss": 3.2129, - "step": 70900 + "learning_rate": 3.737386290202317e-05, + "loss": 3.322, + "step": 76200 }, { "epoch": 0.25, - "learning_rate": 3.7328262258567706e-05, - "loss": 3.2202, - "step": 71000 + "learning_rate": 3.735729316829878e-05, + "loss": 3.3272, + "step": 76300 }, { "epoch": 0.25, - "learning_rate": 3.731041474062203e-05, - "loss": 3.2313, - "step": 71100 + "learning_rate": 3.734072343457441e-05, + "loss": 3.3348, + "step": 76400 }, { "epoch": 0.25, - "learning_rate": 3.729256722267634e-05, - "loss": 3.2285, - "step": 71200 + "learning_rate": 3.732415370085003e-05, + "loss": 3.3327, + "step": 76500 }, { "epoch": 0.25, - "learning_rate": 3.727471970473066e-05, - "loss": 3.2223, - "step": 71300 + "learning_rate": 3.7307583967125646e-05, + "loss": 3.3307, + "step": 76600 }, { "epoch": 0.25, - "learning_rate": 3.7256872186784984e-05, - "loss": 3.2238, - "step": 71400 + "learning_rate": 3.7291014233401275e-05, + "loss": 3.3319, + "step": 76700 + }, + { + "epoch": 0.25, + "learning_rate": 3.727444449967689e-05, + "loss": 3.3302, + "step": 76800 + }, + { + "epoch": 0.25, + "learning_rate": 3.725787476595251e-05, + "loss": 3.3277, + "step": 76900 }, { "epoch": 0.26, - "learning_rate": 3.7239024668839305e-05, - "loss": 3.2137, - "step": 71500 + "learning_rate": 3.724130503222813e-05, + "loss": 3.3357, + "step": 77000 }, { "epoch": 0.26, - "learning_rate": 3.7221177150893626e-05, - "loss": 3.2143, - "step": 71600 + "learning_rate": 3.7224735298503754e-05, + "loss": 3.3164, + "step": 77100 }, { "epoch": 0.26, - "learning_rate": 3.720332963294795e-05, - "loss": 3.2349, - "step": 71700 + "learning_rate": 3.7208165564779375e-05, + "loss": 3.3329, + "step": 77200 }, { "epoch": 0.26, - "learning_rate": 3.718548211500227e-05, - "loss": 3.2104, - "step": 71800 + "learning_rate": 3.7191595831054997e-05, + "loss": 3.3211, + "step": 77300 }, { "epoch": 0.26, - "learning_rate": 3.716763459705659e-05, - "loss": 3.2148, - "step": 71900 + "learning_rate": 3.717502609733062e-05, + "loss": 3.3378, + "step": 77400 }, { "epoch": 0.26, - "learning_rate": 3.714978707911091e-05, - "loss": 3.2198, - "step": 72000 + "learning_rate": 3.715845636360624e-05, + "loss": 3.3201, + "step": 77500 }, { "epoch": 0.26, - "learning_rate": 3.713193956116523e-05, - "loss": 3.2108, - "step": 72100 + "learning_rate": 3.714188662988186e-05, + "loss": 3.3286, + "step": 77600 }, { "epoch": 0.26, - "learning_rate": 3.7114092043219554e-05, - "loss": 3.233, - "step": 72200 + "learning_rate": 3.712531689615748e-05, + "loss": 3.3313, + "step": 77700 }, { "epoch": 0.26, - "learning_rate": 3.709624452527387e-05, - "loss": 3.2216, - "step": 72300 + "learning_rate": 3.71087471624331e-05, + "loss": 3.3267, + "step": 77800 }, { "epoch": 0.26, - "learning_rate": 3.707839700732819e-05, - "loss": 3.2229, - "step": 72400 + "learning_rate": 3.7092177428708725e-05, + "loss": 3.3384, + "step": 77900 }, { "epoch": 0.26, - "learning_rate": 3.706054948938251e-05, - "loss": 3.2057, - "step": 72500 + "learning_rate": 3.707560769498434e-05, + "loss": 3.3209, + "step": 78000 }, { "epoch": 0.26, - "learning_rate": 3.704270197143683e-05, - "loss": 3.2162, - "step": 72600 + "learning_rate": 3.705903796125996e-05, + "loss": 3.3313, + "step": 78100 }, { "epoch": 0.26, - "learning_rate": 3.702485445349115e-05, - "loss": 3.2222, - "step": 72700 + "learning_rate": 3.704246822753559e-05, + "loss": 3.3279, + "step": 78200 }, { "epoch": 0.26, - "learning_rate": 3.7007006935545474e-05, - "loss": 3.2151, - "step": 72800 + "learning_rate": 3.7025898493811205e-05, + "loss": 3.3292, + "step": 78300 }, { "epoch": 0.26, - "learning_rate": 3.6989159417599795e-05, - "loss": 3.2211, - "step": 72900 + "learning_rate": 3.7009328760086826e-05, + "loss": 3.3328, + "step": 78400 }, { "epoch": 0.26, - "learning_rate": 3.6971311899654117e-05, - "loss": 3.2262, - "step": 73000 + "learning_rate": 3.699275902636245e-05, + "loss": 3.3348, + "step": 78500 }, { "epoch": 0.26, - "learning_rate": 3.695346438170844e-05, - "loss": 3.2177, - "step": 73100 + "learning_rate": 3.697618929263807e-05, + "loss": 3.3162, + "step": 78600 + }, + { + "epoch": 0.26, + "learning_rate": 3.695961955891369e-05, + "loss": 3.3426, + "step": 78700 + }, + { + "epoch": 0.26, + "learning_rate": 3.694304982518931e-05, + "loss": 3.3336, + "step": 78800 + }, + { + "epoch": 0.26, + "learning_rate": 3.692648009146493e-05, + "loss": 3.3339, + "step": 78900 + }, + { + "epoch": 0.26, + "learning_rate": 3.6909910357740555e-05, + "loss": 3.3258, + "step": 79000 }, { "epoch": 0.26, - "learning_rate": 3.693561686376276e-05, - "loss": 3.2231, - "step": 73200 + "learning_rate": 3.6893340624016176e-05, + "loss": 3.3128, + "step": 79100 }, { "epoch": 0.26, - "learning_rate": 3.691776934581708e-05, - "loss": 3.2081, - "step": 73300 + "learning_rate": 3.68767708902918e-05, + "loss": 3.3304, + "step": 79200 }, { "epoch": 0.26, - "learning_rate": 3.6899921827871395e-05, - "loss": 3.2246, - "step": 73400 + "learning_rate": 3.686020115656741e-05, + "loss": 3.3341, + "step": 79300 }, { "epoch": 0.26, - "learning_rate": 3.6882074309925716e-05, - "loss": 3.1978, - "step": 73500 + "learning_rate": 3.684363142284304e-05, + "loss": 3.3222, + "step": 79400 }, { "epoch": 0.26, - "learning_rate": 3.686422679198004e-05, - "loss": 3.2097, - "step": 73600 + "learning_rate": 3.6827061689118655e-05, + "loss": 3.3322, + "step": 79500 }, { "epoch": 0.26, - "learning_rate": 3.684637927403436e-05, - "loss": 3.2218, - "step": 73700 + "learning_rate": 3.681049195539428e-05, + "loss": 3.3301, + "step": 79600 }, { "epoch": 0.26, - "learning_rate": 3.682853175608868e-05, - "loss": 3.2295, - "step": 73800 + "learning_rate": 3.6793922221669905e-05, + "loss": 3.3371, + "step": 79700 }, { "epoch": 0.26, - "learning_rate": 3.6810684238143e-05, - "loss": 3.2122, - "step": 73900 + "learning_rate": 3.677735248794552e-05, + "loss": 3.3345, + "step": 79800 }, { "epoch": 0.26, - "learning_rate": 3.679283672019732e-05, - "loss": 3.2145, - "step": 74000 + "learning_rate": 3.676078275422114e-05, + "loss": 3.3223, + "step": 79900 }, { - "epoch": 0.26, - "learning_rate": 3.677498920225165e-05, - "loss": 3.2179, - "step": 74100 + "epoch": 0.27, + "learning_rate": 3.674421302049676e-05, + "loss": 3.3365, + "step": 80000 }, { - "epoch": 0.26, - "learning_rate": 3.675714168430597e-05, - "loss": 3.2065, - "step": 74200 + "epoch": 0.27, + "learning_rate": 3.6727643286772384e-05, + "loss": 3.3213, + "step": 80100 }, { "epoch": 0.27, - "learning_rate": 3.6739294166360286e-05, - "loss": 3.2118, - "step": 74300 + "learning_rate": 3.6711073553048006e-05, + "loss": 3.321, + "step": 80200 }, { "epoch": 0.27, - "learning_rate": 3.672144664841461e-05, - "loss": 3.2117, - "step": 74400 + "learning_rate": 3.669450381932363e-05, + "loss": 3.3389, + "step": 80300 }, { "epoch": 0.27, - "learning_rate": 3.670359913046893e-05, - "loss": 3.2128, - "step": 74500 + "learning_rate": 3.667793408559925e-05, + "loss": 3.3182, + "step": 80400 }, { "epoch": 0.27, - "learning_rate": 3.668575161252325e-05, - "loss": 3.2147, - "step": 74600 + "learning_rate": 3.666136435187486e-05, + "loss": 3.3248, + "step": 80500 }, { "epoch": 0.27, - "learning_rate": 3.666790409457757e-05, - "loss": 3.2222, - "step": 74700 + "learning_rate": 3.6644794618150485e-05, + "loss": 3.3301, + "step": 80600 }, { "epoch": 0.27, - "learning_rate": 3.665005657663189e-05, - "loss": 3.2151, - "step": 74800 + "learning_rate": 3.662822488442611e-05, + "loss": 3.3352, + "step": 80700 }, { "epoch": 0.27, - "learning_rate": 3.663220905868621e-05, - "loss": 3.2122, - "step": 74900 + "learning_rate": 3.661165515070173e-05, + "loss": 3.32, + "step": 80800 }, { "epoch": 0.27, - "learning_rate": 3.6614361540740534e-05, - "loss": 3.2109, - "step": 75000 + "learning_rate": 3.659508541697735e-05, + "loss": 3.3307, + "step": 80900 }, { "epoch": 0.27, - "learning_rate": 3.6596514022794855e-05, - "loss": 3.2131, - "step": 75100 + "learning_rate": 3.657851568325297e-05, + "loss": 3.3326, + "step": 81000 }, { "epoch": 0.27, - "learning_rate": 3.6578666504849177e-05, - "loss": 3.2207, - "step": 75200 + "learning_rate": 3.656194594952859e-05, + "loss": 3.3224, + "step": 81100 }, { "epoch": 0.27, - "learning_rate": 3.65608189869035e-05, - "loss": 3.221, - "step": 75300 + "learning_rate": 3.6545376215804213e-05, + "loss": 3.332, + "step": 81200 }, { "epoch": 0.27, - "learning_rate": 3.654297146895781e-05, - "loss": 3.2127, - "step": 75400 + "learning_rate": 3.6528806482079835e-05, + "loss": 3.327, + "step": 81300 }, { "epoch": 0.27, - "learning_rate": 3.6525123951012133e-05, - "loss": 3.2003, - "step": 75500 + "learning_rate": 3.6512236748355456e-05, + "loss": 3.324, + "step": 81400 }, { "epoch": 0.27, - "learning_rate": 3.6507276433066455e-05, - "loss": 3.2035, - "step": 75600 + "learning_rate": 3.649566701463107e-05, + "loss": 3.3348, + "step": 81500 }, { "epoch": 0.27, - "learning_rate": 3.6489428915120776e-05, - "loss": 3.2141, - "step": 75700 + "learning_rate": 3.64790972809067e-05, + "loss": 3.3276, + "step": 81600 }, { "epoch": 0.27, - "learning_rate": 3.64715813971751e-05, - "loss": 3.2125, - "step": 75800 + "learning_rate": 3.646252754718232e-05, + "loss": 3.3214, + "step": 81700 }, { "epoch": 0.27, - "learning_rate": 3.645373387922942e-05, - "loss": 3.2175, - "step": 75900 + "learning_rate": 3.6445957813457936e-05, + "loss": 3.3261, + "step": 81800 }, { "epoch": 0.27, - "learning_rate": 3.643588636128374e-05, - "loss": 3.203, - "step": 76000 + "learning_rate": 3.6429388079733564e-05, + "loss": 3.3127, + "step": 81900 }, { "epoch": 0.27, - "learning_rate": 3.641803884333806e-05, - "loss": 3.2078, - "step": 76100 + "learning_rate": 3.641281834600918e-05, + "loss": 3.336, + "step": 82000 }, { "epoch": 0.27, - "learning_rate": 3.640019132539238e-05, - "loss": 3.2044, - "step": 76200 + "learning_rate": 3.63962486122848e-05, + "loss": 3.3286, + "step": 82100 }, { "epoch": 0.27, - "learning_rate": 3.63823438074467e-05, - "loss": 3.2201, - "step": 76300 + "learning_rate": 3.637967887856043e-05, + "loss": 3.3243, + "step": 82200 }, { "epoch": 0.27, - "learning_rate": 3.6364496289501024e-05, - "loss": 3.2205, - "step": 76400 + "learning_rate": 3.636310914483604e-05, + "loss": 3.3281, + "step": 82300 }, { "epoch": 0.27, - "learning_rate": 3.634664877155534e-05, - "loss": 3.2133, - "step": 76500 + "learning_rate": 3.6346539411111664e-05, + "loss": 3.3248, + "step": 82400 }, { "epoch": 0.27, - "learning_rate": 3.632880125360966e-05, - "loss": 3.2058, - "step": 76600 + "learning_rate": 3.6329969677387286e-05, + "loss": 3.3247, + "step": 82500 }, { "epoch": 0.27, - "learning_rate": 3.631095373566398e-05, - "loss": 3.2128, - "step": 76700 + "learning_rate": 3.631339994366291e-05, + "loss": 3.3305, + "step": 82600 }, { "epoch": 0.27, - "learning_rate": 3.62931062177183e-05, - "loss": 3.205, - "step": 76800 + "learning_rate": 3.629683020993853e-05, + "loss": 3.3295, + "step": 82700 }, { "epoch": 0.27, - "learning_rate": 3.6275258699772624e-05, - "loss": 3.2111, - "step": 76900 + "learning_rate": 3.628026047621415e-05, + "loss": 3.3252, + "step": 82800 }, { "epoch": 0.27, - "learning_rate": 3.6257411181826945e-05, - "loss": 3.2086, - "step": 77000 + "learning_rate": 3.626369074248977e-05, + "loss": 3.3288, + "step": 82900 }, { "epoch": 0.28, - "learning_rate": 3.6239563663881266e-05, - "loss": 3.2096, - "step": 77100 + "learning_rate": 3.6247121008765386e-05, + "loss": 3.3223, + "step": 83000 }, { "epoch": 0.28, - "learning_rate": 3.622171614593559e-05, - "loss": 3.2087, - "step": 77200 + "learning_rate": 3.6230551275041015e-05, + "loss": 3.3214, + "step": 83100 }, { "epoch": 0.28, - "learning_rate": 3.620386862798991e-05, - "loss": 3.2071, - "step": 77300 + "learning_rate": 3.6213981541316636e-05, + "loss": 3.3156, + "step": 83200 }, { "epoch": 0.28, - "learning_rate": 3.618602111004423e-05, - "loss": 3.2031, - "step": 77400 + "learning_rate": 3.619741180759225e-05, + "loss": 3.3288, + "step": 83300 }, { "epoch": 0.28, - "learning_rate": 3.616817359209855e-05, - "loss": 3.217, - "step": 77500 + "learning_rate": 3.618084207386788e-05, + "loss": 3.3246, + "step": 83400 }, { "epoch": 0.28, - "learning_rate": 3.6150326074152865e-05, - "loss": 3.2035, - "step": 77600 + "learning_rate": 3.6164272340143494e-05, + "loss": 3.321, + "step": 83500 }, { "epoch": 0.28, - "learning_rate": 3.6132478556207187e-05, - "loss": 3.2132, - "step": 77700 + "learning_rate": 3.6147702606419115e-05, + "loss": 3.3119, + "step": 83600 }, { "epoch": 0.28, - "learning_rate": 3.611463103826151e-05, - "loss": 3.2061, - "step": 77800 + "learning_rate": 3.613113287269474e-05, + "loss": 3.3268, + "step": 83700 }, { "epoch": 0.28, - "learning_rate": 3.609678352031583e-05, - "loss": 3.2052, - "step": 77900 + "learning_rate": 3.611456313897036e-05, + "loss": 3.3184, + "step": 83800 }, { "epoch": 0.28, - "learning_rate": 3.607893600237015e-05, - "loss": 3.2055, - "step": 78000 + "learning_rate": 3.609799340524598e-05, + "loss": 3.3316, + "step": 83900 }, { "epoch": 0.28, - "learning_rate": 3.606108848442447e-05, - "loss": 3.2191, - "step": 78100 + "learning_rate": 3.60814236715216e-05, + "loss": 3.3364, + "step": 84000 }, { "epoch": 0.28, - "learning_rate": 3.604324096647879e-05, - "loss": 3.2187, - "step": 78200 + "learning_rate": 3.606485393779722e-05, + "loss": 3.3271, + "step": 84100 }, { "epoch": 0.28, - "learning_rate": 3.6025393448533114e-05, - "loss": 3.2327, - "step": 78300 + "learning_rate": 3.6048284204072844e-05, + "loss": 3.3219, + "step": 84200 }, { "epoch": 0.28, - "learning_rate": 3.6007545930587435e-05, - "loss": 3.2236, - "step": 78400 + "learning_rate": 3.6031714470348465e-05, + "loss": 3.3314, + "step": 84300 }, { "epoch": 0.28, - "learning_rate": 3.5989698412641756e-05, - "loss": 3.2076, - "step": 78500 + "learning_rate": 3.601514473662409e-05, + "loss": 3.3187, + "step": 84400 }, { "epoch": 0.28, - "learning_rate": 3.597185089469608e-05, - "loss": 3.218, - "step": 78600 + "learning_rate": 3.59985750028997e-05, + "loss": 3.3342, + "step": 84500 }, { "epoch": 0.28, - "learning_rate": 3.595400337675039e-05, - "loss": 3.2154, - "step": 78700 + "learning_rate": 3.598200526917533e-05, + "loss": 3.3324, + "step": 84600 }, { "epoch": 0.28, - "learning_rate": 3.593615585880471e-05, - "loss": 3.2137, - "step": 78800 + "learning_rate": 3.5965435535450945e-05, + "loss": 3.3324, + "step": 84700 }, { "epoch": 0.28, - "learning_rate": 3.5918308340859034e-05, - "loss": 3.2104, - "step": 78900 + "learning_rate": 3.5948865801726566e-05, + "loss": 3.3141, + "step": 84800 }, { "epoch": 0.28, - "learning_rate": 3.5900460822913356e-05, - "loss": 3.2039, - "step": 79000 + "learning_rate": 3.5932296068002194e-05, + "loss": 3.3204, + "step": 84900 }, { "epoch": 0.28, - "learning_rate": 3.588261330496768e-05, - "loss": 3.2103, - "step": 79100 + "learning_rate": 3.591572633427781e-05, + "loss": 3.3396, + "step": 85000 }, { "epoch": 0.28, - "learning_rate": 3.5864765787022005e-05, - "loss": 3.2076, - "step": 79200 + "learning_rate": 3.589915660055343e-05, + "loss": 3.3219, + "step": 85100 }, { "epoch": 0.28, - "learning_rate": 3.5846918269076326e-05, - "loss": 3.2081, - "step": 79300 + "learning_rate": 3.588258686682905e-05, + "loss": 3.3259, + "step": 85200 }, { "epoch": 0.28, - "learning_rate": 3.582907075113065e-05, - "loss": 3.2105, - "step": 79400 + "learning_rate": 3.586601713310467e-05, + "loss": 3.3202, + "step": 85300 }, { "epoch": 0.28, - "learning_rate": 3.581122323318497e-05, - "loss": 3.2127, - "step": 79500 + "learning_rate": 3.5849447399380295e-05, + "loss": 3.3128, + "step": 85400 }, { "epoch": 0.28, - "learning_rate": 3.579337571523928e-05, - "loss": 3.2102, - "step": 79600 + "learning_rate": 3.5832877665655916e-05, + "loss": 3.3232, + "step": 85500 }, { "epoch": 0.28, - "learning_rate": 3.5775528197293604e-05, - "loss": 3.2093, - "step": 79700 + "learning_rate": 3.581630793193154e-05, + "loss": 3.3121, + "step": 85600 }, { "epoch": 0.28, - "learning_rate": 3.5757680679347925e-05, - "loss": 3.2027, - "step": 79800 + "learning_rate": 3.579973819820715e-05, + "loss": 3.3264, + "step": 85700 + }, + { + "epoch": 0.28, + "learning_rate": 3.5783168464482774e-05, + "loss": 3.327, + "step": 85800 + }, + { + "epoch": 0.28, + "learning_rate": 3.57665987307584e-05, + "loss": 3.3227, + "step": 85900 + }, + { + "epoch": 0.28, + "learning_rate": 3.575002899703402e-05, + "loss": 3.3195, + "step": 86000 }, { "epoch": 0.29, - "learning_rate": 3.5739833161402247e-05, - "loss": 3.2085, - "step": 79900 + "learning_rate": 3.573345926330964e-05, + "loss": 3.3264, + "step": 86100 }, { "epoch": 0.29, - "learning_rate": 3.572198564345657e-05, - "loss": 3.2054, - "step": 80000 + "learning_rate": 3.571688952958526e-05, + "loss": 3.3231, + "step": 86200 }, { "epoch": 0.29, - "learning_rate": 3.570413812551089e-05, - "loss": 3.2153, - "step": 80100 + "learning_rate": 3.570031979586088e-05, + "loss": 3.3213, + "step": 86300 }, { "epoch": 0.29, - "learning_rate": 3.568629060756521e-05, - "loss": 3.2129, - "step": 80200 + "learning_rate": 3.56837500621365e-05, + "loss": 3.321, + "step": 86400 }, { "epoch": 0.29, - "learning_rate": 3.566844308961953e-05, - "loss": 3.2036, - "step": 80300 + "learning_rate": 3.5667180328412124e-05, + "loss": 3.316, + "step": 86500 }, { "epoch": 0.29, - "learning_rate": 3.565059557167385e-05, - "loss": 3.2055, - "step": 80400 + "learning_rate": 3.5650610594687746e-05, + "loss": 3.3286, + "step": 86600 }, { "epoch": 0.29, - "learning_rate": 3.5632748053728174e-05, - "loss": 3.2037, - "step": 80500 + "learning_rate": 3.563404086096336e-05, + "loss": 3.3299, + "step": 86700 }, { "epoch": 0.29, - "learning_rate": 3.561490053578249e-05, - "loss": 3.2048, - "step": 80600 + "learning_rate": 3.561747112723899e-05, + "loss": 3.3066, + "step": 86800 }, { "epoch": 0.29, - "learning_rate": 3.559705301783681e-05, - "loss": 3.2023, - "step": 80700 + "learning_rate": 3.560090139351461e-05, + "loss": 3.3381, + "step": 86900 }, { "epoch": 0.29, - "learning_rate": 3.557920549989113e-05, - "loss": 3.2066, - "step": 80800 + "learning_rate": 3.5584331659790225e-05, + "loss": 3.322, + "step": 87000 }, { "epoch": 0.29, - "learning_rate": 3.556135798194545e-05, - "loss": 3.1991, - "step": 80900 + "learning_rate": 3.556776192606585e-05, + "loss": 3.3231, + "step": 87100 }, { "epoch": 0.29, - "learning_rate": 3.554351046399977e-05, - "loss": 3.2057, - "step": 81000 + "learning_rate": 3.555119219234147e-05, + "loss": 3.3151, + "step": 87200 }, { "epoch": 0.29, - "learning_rate": 3.5525662946054094e-05, - "loss": 3.2209, - "step": 81100 + "learning_rate": 3.553462245861709e-05, + "loss": 3.3262, + "step": 87300 }, { "epoch": 0.29, - "learning_rate": 3.5507815428108416e-05, - "loss": 3.1992, - "step": 81200 + "learning_rate": 3.551805272489272e-05, + "loss": 3.3438, + "step": 87400 }, { "epoch": 0.29, - "learning_rate": 3.548996791016274e-05, - "loss": 3.213, - "step": 81300 + "learning_rate": 3.550148299116833e-05, + "loss": 3.3167, + "step": 87500 }, { "epoch": 0.29, - "learning_rate": 3.547212039221706e-05, - "loss": 3.2035, - "step": 81400 + "learning_rate": 3.5484913257443954e-05, + "loss": 3.3166, + "step": 87600 }, { "epoch": 0.29, - "learning_rate": 3.545427287427138e-05, - "loss": 3.2083, - "step": 81500 + "learning_rate": 3.5468343523719575e-05, + "loss": 3.331, + "step": 87700 }, { "epoch": 0.29, - "learning_rate": 3.54364253563257e-05, - "loss": 3.2081, - "step": 81600 + "learning_rate": 3.5451773789995196e-05, + "loss": 3.3276, + "step": 87800 }, { "epoch": 0.29, - "learning_rate": 3.5418577838380015e-05, - "loss": 3.2116, - "step": 81700 + "learning_rate": 3.543520405627082e-05, + "loss": 3.3279, + "step": 87900 }, { "epoch": 0.29, - "learning_rate": 3.5400730320434336e-05, - "loss": 3.1954, - "step": 81800 + "learning_rate": 3.541863432254644e-05, + "loss": 3.3187, + "step": 88000 }, { "epoch": 0.29, - "learning_rate": 3.538288280248866e-05, - "loss": 3.2057, - "step": 81900 + "learning_rate": 3.540206458882206e-05, + "loss": 3.3198, + "step": 88100 }, { "epoch": 0.29, - "learning_rate": 3.536503528454298e-05, - "loss": 3.2036, - "step": 82000 + "learning_rate": 3.5385494855097676e-05, + "loss": 3.3261, + "step": 88200 }, { "epoch": 0.29, - "learning_rate": 3.53471877665973e-05, - "loss": 3.1973, - "step": 82100 + "learning_rate": 3.5368925121373304e-05, + "loss": 3.3199, + "step": 88300 }, { "epoch": 0.29, - "learning_rate": 3.532934024865162e-05, - "loss": 3.2046, - "step": 82200 + "learning_rate": 3.5352355387648925e-05, + "loss": 3.3075, + "step": 88400 }, { "epoch": 0.29, - "learning_rate": 3.531149273070594e-05, - "loss": 3.2108, - "step": 82300 + "learning_rate": 3.533578565392454e-05, + "loss": 3.3158, + "step": 88500 }, { "epoch": 0.29, - "learning_rate": 3.529364521276026e-05, - "loss": 3.2081, - "step": 82400 + "learning_rate": 3.531921592020017e-05, + "loss": 3.3367, + "step": 88600 }, { "epoch": 0.29, - "learning_rate": 3.5275797694814585e-05, - "loss": 3.191, - "step": 82500 + "learning_rate": 3.530264618647578e-05, + "loss": 3.3163, + "step": 88700 }, { "epoch": 0.29, - "learning_rate": 3.5257950176868906e-05, - "loss": 3.1992, - "step": 82600 + "learning_rate": 3.5286076452751404e-05, + "loss": 3.324, + "step": 88800 + }, + { + "epoch": 0.29, + "learning_rate": 3.5269506719027026e-05, + "loss": 3.3144, + "step": 88900 + }, + { + "epoch": 0.29, + "learning_rate": 3.525293698530265e-05, + "loss": 3.3271, + "step": 89000 }, { "epoch": 0.3, - "learning_rate": 3.524010265892323e-05, - "loss": 3.2197, - "step": 82700 + "learning_rate": 3.523636725157827e-05, + "loss": 3.3152, + "step": 89100 }, { "epoch": 0.3, - "learning_rate": 3.522225514097754e-05, - "loss": 3.2107, - "step": 82800 + "learning_rate": 3.521979751785389e-05, + "loss": 3.3138, + "step": 89200 }, { "epoch": 0.3, - "learning_rate": 3.520440762303186e-05, - "loss": 3.1993, - "step": 82900 + "learning_rate": 3.520322778412951e-05, + "loss": 3.3274, + "step": 89300 + }, + { + "epoch": 0.3, + "learning_rate": 3.518665805040513e-05, + "loss": 3.3101, + "step": 89400 + }, + { + "epoch": 0.3, + "learning_rate": 3.5170088316680755e-05, + "loss": 3.3247, + "step": 89500 + }, + { + "epoch": 0.3, + "learning_rate": 3.5153518582956376e-05, + "loss": 3.313, + "step": 89600 + }, + { + "epoch": 0.3, + "learning_rate": 3.513694884923199e-05, + "loss": 3.3177, + "step": 89700 }, { "epoch": 0.3, - "learning_rate": 3.5186560105086184e-05, - "loss": 3.199, - "step": 83000 + "learning_rate": 3.512037911550762e-05, + "loss": 3.3164, + "step": 89800 }, { "epoch": 0.3, - "learning_rate": 3.5168712587140505e-05, - "loss": 3.1956, - "step": 83100 + "learning_rate": 3.5103809381783234e-05, + "loss": 3.3345, + "step": 89900 }, { "epoch": 0.3, - "learning_rate": 3.5150865069194826e-05, - "loss": 3.2043, - "step": 83200 + "learning_rate": 3.5087239648058855e-05, + "loss": 3.33, + "step": 90000 }, { "epoch": 0.3, - "learning_rate": 3.513301755124915e-05, - "loss": 3.2078, - "step": 83300 + "learning_rate": 3.5070669914334483e-05, + "loss": 3.3201, + "step": 90100 }, { "epoch": 0.3, - "learning_rate": 3.511517003330347e-05, - "loss": 3.2137, - "step": 83400 + "learning_rate": 3.50541001806101e-05, + "loss": 3.3233, + "step": 90200 }, { "epoch": 0.3, - "learning_rate": 3.509732251535779e-05, - "loss": 3.199, - "step": 83500 + "learning_rate": 3.503753044688572e-05, + "loss": 3.3317, + "step": 90300 }, { "epoch": 0.3, - "learning_rate": 3.507947499741211e-05, - "loss": 3.2039, - "step": 83600 + "learning_rate": 3.502096071316134e-05, + "loss": 3.3202, + "step": 90400 }, { "epoch": 0.3, - "learning_rate": 3.506162747946643e-05, - "loss": 3.198, - "step": 83700 + "learning_rate": 3.500439097943696e-05, + "loss": 3.313, + "step": 90500 }, { "epoch": 0.3, - "learning_rate": 3.5043779961520754e-05, - "loss": 3.2042, - "step": 83800 + "learning_rate": 3.4987821245712584e-05, + "loss": 3.3079, + "step": 90600 }, { "epoch": 0.3, - "learning_rate": 3.502593244357507e-05, - "loss": 3.2009, - "step": 83900 + "learning_rate": 3.4971251511988205e-05, + "loss": 3.3235, + "step": 90700 }, { "epoch": 0.3, - "learning_rate": 3.500808492562939e-05, - "loss": 3.2067, - "step": 84000 + "learning_rate": 3.495468177826383e-05, + "loss": 3.3296, + "step": 90800 }, { "epoch": 0.3, - "learning_rate": 3.499023740768371e-05, - "loss": 3.1993, - "step": 84100 + "learning_rate": 3.493811204453944e-05, + "loss": 3.3169, + "step": 90900 }, { "epoch": 0.3, - "learning_rate": 3.497238988973803e-05, - "loss": 3.1963, - "step": 84200 + "learning_rate": 3.492154231081506e-05, + "loss": 3.3343, + "step": 91000 }, { "epoch": 0.3, - "learning_rate": 3.495454237179236e-05, - "loss": 3.1982, - "step": 84300 + "learning_rate": 3.490497257709069e-05, + "loss": 3.3168, + "step": 91100 }, { "epoch": 0.3, - "learning_rate": 3.493669485384668e-05, - "loss": 3.2002, - "step": 84400 + "learning_rate": 3.4888402843366306e-05, + "loss": 3.3215, + "step": 91200 }, { "epoch": 0.3, - "learning_rate": 3.4918847335901e-05, - "loss": 3.2029, - "step": 84500 + "learning_rate": 3.487183310964193e-05, + "loss": 3.3127, + "step": 91300 }, { "epoch": 0.3, - "learning_rate": 3.490099981795532e-05, - "loss": 3.205, - "step": 84600 + "learning_rate": 3.485526337591755e-05, + "loss": 3.3259, + "step": 91400 }, { "epoch": 0.3, - "learning_rate": 3.4883152300009645e-05, - "loss": 3.207, - "step": 84700 + "learning_rate": 3.483869364219317e-05, + "loss": 3.3221, + "step": 91500 }, { "epoch": 0.3, - "learning_rate": 3.486530478206396e-05, - "loss": 3.1985, - "step": 84800 + "learning_rate": 3.482212390846879e-05, + "loss": 3.3094, + "step": 91600 }, { "epoch": 0.3, - "learning_rate": 3.484745726411828e-05, - "loss": 3.2031, - "step": 84900 + "learning_rate": 3.480555417474441e-05, + "loss": 3.3338, + "step": 91700 }, { "epoch": 0.3, - "learning_rate": 3.48296097461726e-05, - "loss": 3.196, - "step": 85000 + "learning_rate": 3.4788984441020035e-05, + "loss": 3.3133, + "step": 91800 }, { "epoch": 0.3, - "learning_rate": 3.481176222822692e-05, - "loss": 3.2066, - "step": 85100 + "learning_rate": 3.4772414707295656e-05, + "loss": 3.3013, + "step": 91900 }, { "epoch": 0.3, - "learning_rate": 3.4793914710281244e-05, - "loss": 3.1914, - "step": 85200 + "learning_rate": 3.475584497357128e-05, + "loss": 3.3232, + "step": 92000 }, { - "epoch": 0.3, - "learning_rate": 3.4776067192335565e-05, - "loss": 3.1956, - "step": 85300 + "epoch": 0.31, + "learning_rate": 3.47392752398469e-05, + "loss": 3.3117, + "step": 92100 }, { - "epoch": 0.3, - "learning_rate": 3.4758219674389886e-05, - "loss": 3.2075, - "step": 85400 + "epoch": 0.31, + "learning_rate": 3.4722705506122514e-05, + "loss": 3.3029, + "step": 92200 }, { "epoch": 0.31, - "learning_rate": 3.474037215644421e-05, - "loss": 3.2062, - "step": 85500 + "learning_rate": 3.470613577239814e-05, + "loss": 3.3109, + "step": 92300 }, { "epoch": 0.31, - "learning_rate": 3.472252463849853e-05, - "loss": 3.2061, - "step": 85600 + "learning_rate": 3.468956603867376e-05, + "loss": 3.3227, + "step": 92400 }, { "epoch": 0.31, - "learning_rate": 3.470467712055285e-05, - "loss": 3.1826, - "step": 85700 + "learning_rate": 3.467299630494938e-05, + "loss": 3.3202, + "step": 92500 }, { "epoch": 0.31, - "learning_rate": 3.468682960260717e-05, - "loss": 3.2049, - "step": 85800 + "learning_rate": 3.4656426571225007e-05, + "loss": 3.3221, + "step": 92600 }, { "epoch": 0.31, - "learning_rate": 3.4668982084661486e-05, - "loss": 3.1949, - "step": 85900 + "learning_rate": 3.463985683750062e-05, + "loss": 3.3167, + "step": 92700 }, { "epoch": 0.31, - "learning_rate": 3.465113456671581e-05, - "loss": 3.1964, - "step": 86000 + "learning_rate": 3.462328710377624e-05, + "loss": 3.3083, + "step": 92800 }, { "epoch": 0.31, - "learning_rate": 3.463328704877013e-05, - "loss": 3.1957, - "step": 86100 + "learning_rate": 3.4606717370051864e-05, + "loss": 3.3309, + "step": 92900 }, { "epoch": 0.31, - "learning_rate": 3.461543953082445e-05, - "loss": 3.208, - "step": 86200 + "learning_rate": 3.4590147636327486e-05, + "loss": 3.3098, + "step": 93000 }, { "epoch": 0.31, - "learning_rate": 3.459759201287877e-05, - "loss": 3.2012, - "step": 86300 + "learning_rate": 3.457357790260311e-05, + "loss": 3.3244, + "step": 93100 }, { "epoch": 0.31, - "learning_rate": 3.457974449493309e-05, - "loss": 3.2049, - "step": 86400 + "learning_rate": 3.455700816887873e-05, + "loss": 3.3074, + "step": 93200 }, { "epoch": 0.31, - "learning_rate": 3.456189697698741e-05, - "loss": 3.1999, - "step": 86500 + "learning_rate": 3.454043843515435e-05, + "loss": 3.3182, + "step": 93300 }, { "epoch": 0.31, - "learning_rate": 3.4544049459041734e-05, - "loss": 3.2121, - "step": 86600 + "learning_rate": 3.4523868701429965e-05, + "loss": 3.3184, + "step": 93400 }, { "epoch": 0.31, - "learning_rate": 3.4526201941096055e-05, - "loss": 3.1929, - "step": 86700 + "learning_rate": 3.450729896770559e-05, + "loss": 3.3168, + "step": 93500 }, { "epoch": 0.31, - "learning_rate": 3.4508354423150376e-05, - "loss": 3.1931, - "step": 86800 + "learning_rate": 3.4490729233981214e-05, + "loss": 3.3325, + "step": 93600 }, { "epoch": 0.31, - "learning_rate": 3.44905069052047e-05, - "loss": 3.199, - "step": 86900 + "learning_rate": 3.447415950025683e-05, + "loss": 3.3161, + "step": 93700 }, { "epoch": 0.31, - "learning_rate": 3.447265938725901e-05, - "loss": 3.1988, - "step": 87000 + "learning_rate": 3.445758976653246e-05, + "loss": 3.3101, + "step": 93800 }, { "epoch": 0.31, - "learning_rate": 3.445481186931333e-05, - "loss": 3.2025, - "step": 87100 + "learning_rate": 3.444102003280807e-05, + "loss": 3.3196, + "step": 93900 }, { "epoch": 0.31, - "learning_rate": 3.4436964351367655e-05, - "loss": 3.1974, - "step": 87200 + "learning_rate": 3.4424450299083694e-05, + "loss": 3.3231, + "step": 94000 }, { "epoch": 0.31, - "learning_rate": 3.4419116833421976e-05, - "loss": 3.1996, - "step": 87300 + "learning_rate": 3.4407880565359315e-05, + "loss": 3.3216, + "step": 94100 }, { "epoch": 0.31, - "learning_rate": 3.44012693154763e-05, - "loss": 3.2088, - "step": 87400 + "learning_rate": 3.4391310831634936e-05, + "loss": 3.3124, + "step": 94200 }, { "epoch": 0.31, - "learning_rate": 3.438342179753062e-05, - "loss": 3.195, - "step": 87500 + "learning_rate": 3.437474109791056e-05, + "loss": 3.3241, + "step": 94300 }, { "epoch": 0.31, - "learning_rate": 3.436557427958494e-05, - "loss": 3.1997, - "step": 87600 + "learning_rate": 3.435817136418618e-05, + "loss": 3.319, + "step": 94400 }, { "epoch": 0.31, - "learning_rate": 3.434772676163926e-05, - "loss": 3.1923, - "step": 87700 + "learning_rate": 3.43416016304618e-05, + "loss": 3.2995, + "step": 94500 }, { "epoch": 0.31, - "learning_rate": 3.432987924369358e-05, - "loss": 3.1949, - "step": 87800 + "learning_rate": 3.432503189673742e-05, + "loss": 3.3217, + "step": 94600 }, { "epoch": 0.31, - "learning_rate": 3.43120317257479e-05, - "loss": 3.1873, - "step": 87900 + "learning_rate": 3.4308462163013044e-05, + "loss": 3.3154, + "step": 94700 }, { "epoch": 0.31, - "learning_rate": 3.4294184207802224e-05, - "loss": 3.19, - "step": 88000 + "learning_rate": 3.4291892429288665e-05, + "loss": 3.3202, + "step": 94800 }, { "epoch": 0.31, - "learning_rate": 3.427633668985654e-05, - "loss": 3.1959, - "step": 88100 + "learning_rate": 3.427532269556428e-05, + "loss": 3.3167, + "step": 94900 }, { "epoch": 0.31, - "learning_rate": 3.425848917191086e-05, - "loss": 3.193, - "step": 88200 + "learning_rate": 3.425875296183991e-05, + "loss": 3.3108, + "step": 95000 }, { "epoch": 0.32, - "learning_rate": 3.424064165396518e-05, - "loss": 3.1955, - "step": 88300 + "learning_rate": 3.424218322811553e-05, + "loss": 3.3242, + "step": 95100 }, { "epoch": 0.32, - "learning_rate": 3.42227941360195e-05, - "loss": 3.2041, - "step": 88400 + "learning_rate": 3.4225613494391144e-05, + "loss": 3.3243, + "step": 95200 }, { "epoch": 0.32, - "learning_rate": 3.4204946618073824e-05, - "loss": 3.2018, - "step": 88500 + "learning_rate": 3.420904376066677e-05, + "loss": 3.3262, + "step": 95300 }, { "epoch": 0.32, - "learning_rate": 3.4187099100128145e-05, - "loss": 3.1969, - "step": 88600 + "learning_rate": 3.419247402694239e-05, + "loss": 3.3114, + "step": 95400 }, { "epoch": 0.32, - "learning_rate": 3.4169251582182466e-05, - "loss": 3.2031, - "step": 88700 + "learning_rate": 3.417590429321801e-05, + "loss": 3.3174, + "step": 95500 }, { "epoch": 0.32, - "learning_rate": 3.415140406423679e-05, - "loss": 3.1977, - "step": 88800 + "learning_rate": 3.415933455949363e-05, + "loss": 3.3146, + "step": 95600 }, { "epoch": 0.32, - "learning_rate": 3.413355654629111e-05, - "loss": 3.194, - "step": 88900 + "learning_rate": 3.414276482576925e-05, + "loss": 3.3133, + "step": 95700 }, { "epoch": 0.32, - "learning_rate": 3.411570902834543e-05, - "loss": 3.2014, - "step": 89000 + "learning_rate": 3.412619509204487e-05, + "loss": 3.323, + "step": 95800 }, { "epoch": 0.32, - "learning_rate": 3.409786151039975e-05, - "loss": 3.2058, - "step": 89100 + "learning_rate": 3.4109625358320495e-05, + "loss": 3.3273, + "step": 95900 }, { "epoch": 0.32, - "learning_rate": 3.4080013992454065e-05, - "loss": 3.192, - "step": 89200 + "learning_rate": 3.4093055624596116e-05, + "loss": 3.3172, + "step": 96000 }, { "epoch": 0.32, - "learning_rate": 3.4062166474508387e-05, - "loss": 3.1989, - "step": 89300 + "learning_rate": 3.407648589087174e-05, + "loss": 3.3245, + "step": 96100 }, { "epoch": 0.32, - "learning_rate": 3.4044318956562715e-05, - "loss": 3.1973, - "step": 89400 + "learning_rate": 3.405991615714735e-05, + "loss": 3.3142, + "step": 96200 }, { "epoch": 0.32, - "learning_rate": 3.4026471438617036e-05, - "loss": 3.1904, - "step": 89500 + "learning_rate": 3.404334642342298e-05, + "loss": 3.3036, + "step": 96300 }, { "epoch": 0.32, - "learning_rate": 3.400862392067136e-05, - "loss": 3.2079, - "step": 89600 + "learning_rate": 3.4026776689698595e-05, + "loss": 3.3287, + "step": 96400 }, { "epoch": 0.32, - "learning_rate": 3.399077640272568e-05, - "loss": 3.1984, - "step": 89700 + "learning_rate": 3.401020695597422e-05, + "loss": 3.3317, + "step": 96500 }, { "epoch": 0.32, - "learning_rate": 3.397292888478e-05, - "loss": 3.1931, - "step": 89800 + "learning_rate": 3.399363722224984e-05, + "loss": 3.3327, + "step": 96600 }, { "epoch": 0.32, - "learning_rate": 3.395508136683432e-05, - "loss": 3.1983, - "step": 89900 + "learning_rate": 3.397706748852546e-05, + "loss": 3.3192, + "step": 96700 }, { "epoch": 0.32, - "learning_rate": 3.393723384888864e-05, - "loss": 3.1876, - "step": 90000 + "learning_rate": 3.396049775480108e-05, + "loss": 3.323, + "step": 96800 }, { "epoch": 0.32, - "learning_rate": 3.3919386330942956e-05, - "loss": 3.1858, - "step": 90100 + "learning_rate": 3.39439280210767e-05, + "loss": 3.3148, + "step": 96900 }, { "epoch": 0.32, - "learning_rate": 3.390153881299728e-05, - "loss": 3.199, - "step": 90200 + "learning_rate": 3.3927358287352324e-05, + "loss": 3.3175, + "step": 97000 }, { "epoch": 0.32, - "learning_rate": 3.38836912950516e-05, - "loss": 3.1927, - "step": 90300 + "learning_rate": 3.3910788553627945e-05, + "loss": 3.3094, + "step": 97100 }, { "epoch": 0.32, - "learning_rate": 3.386584377710592e-05, - "loss": 3.1933, - "step": 90400 + "learning_rate": 3.389421881990357e-05, + "loss": 3.3154, + "step": 97200 }, { "epoch": 0.32, - "learning_rate": 3.384799625916024e-05, - "loss": 3.1944, - "step": 90500 + "learning_rate": 3.387764908617919e-05, + "loss": 3.3227, + "step": 97300 }, { "epoch": 0.32, - "learning_rate": 3.383014874121456e-05, - "loss": 3.1942, - "step": 90600 + "learning_rate": 3.38610793524548e-05, + "loss": 3.3228, + "step": 97400 }, { "epoch": 0.32, - "learning_rate": 3.3812301223268884e-05, - "loss": 3.1957, - "step": 90700 + "learning_rate": 3.384450961873043e-05, + "loss": 3.3391, + "step": 97500 }, { "epoch": 0.32, - "learning_rate": 3.3794453705323205e-05, - "loss": 3.2017, - "step": 90800 + "learning_rate": 3.3827939885006046e-05, + "loss": 3.3152, + "step": 97600 }, { "epoch": 0.32, - "learning_rate": 3.3776606187377526e-05, - "loss": 3.1949, - "step": 90900 + "learning_rate": 3.381137015128167e-05, + "loss": 3.3209, + "step": 97700 }, { "epoch": 0.32, - "learning_rate": 3.375875866943185e-05, - "loss": 3.1931, - "step": 91000 + "learning_rate": 3.3794800417557296e-05, + "loss": 3.3245, + "step": 97800 + }, + { + "epoch": 0.32, + "learning_rate": 3.377823068383291e-05, + "loss": 3.319, + "step": 97900 + }, + { + "epoch": 0.32, + "learning_rate": 3.376166095010853e-05, + "loss": 3.3214, + "step": 98000 }, { "epoch": 0.33, - "learning_rate": 3.374091115148617e-05, - "loss": 3.1982, - "step": 91100 + "learning_rate": 3.374509121638415e-05, + "loss": 3.3194, + "step": 98100 }, { "epoch": 0.33, - "learning_rate": 3.372306363354048e-05, - "loss": 3.197, - "step": 91200 + "learning_rate": 3.3728521482659775e-05, + "loss": 3.325, + "step": 98200 }, { "epoch": 0.33, - "learning_rate": 3.3705216115594804e-05, - "loss": 3.1994, - "step": 91300 + "learning_rate": 3.3711951748935396e-05, + "loss": 3.3147, + "step": 98300 }, { "epoch": 0.33, - "learning_rate": 3.3687368597649125e-05, - "loss": 3.1895, - "step": 91400 + "learning_rate": 3.369538201521102e-05, + "loss": 3.316, + "step": 98400 }, { "epoch": 0.33, - "learning_rate": 3.3669521079703446e-05, - "loss": 3.1949, - "step": 91500 + "learning_rate": 3.367881228148664e-05, + "loss": 3.3197, + "step": 98500 }, { "epoch": 0.33, - "learning_rate": 3.365167356175777e-05, - "loss": 3.1834, - "step": 91600 + "learning_rate": 3.3662242547762254e-05, + "loss": 3.3247, + "step": 98600 }, { "epoch": 0.33, - "learning_rate": 3.363382604381209e-05, - "loss": 3.2041, - "step": 91700 + "learning_rate": 3.364567281403788e-05, + "loss": 3.307, + "step": 98700 }, { "epoch": 0.33, - "learning_rate": 3.361597852586641e-05, - "loss": 3.1961, - "step": 91800 + "learning_rate": 3.3629103080313504e-05, + "loss": 3.3046, + "step": 98800 }, { "epoch": 0.33, - "learning_rate": 3.359813100792073e-05, - "loss": 3.202, - "step": 91900 + "learning_rate": 3.361253334658912e-05, + "loss": 3.3116, + "step": 98900 }, { "epoch": 0.33, - "learning_rate": 3.358028348997505e-05, - "loss": 3.1896, - "step": 92000 + "learning_rate": 3.3595963612864747e-05, + "loss": 3.3149, + "step": 99000 }, { "epoch": 0.33, - "learning_rate": 3.3562435972029374e-05, - "loss": 3.1877, - "step": 92100 + "learning_rate": 3.357939387914036e-05, + "loss": 3.3129, + "step": 99100 }, { "epoch": 0.33, - "learning_rate": 3.3544588454083695e-05, - "loss": 3.1968, - "step": 92200 + "learning_rate": 3.356282414541598e-05, + "loss": 3.3213, + "step": 99200 }, { "epoch": 0.33, - "learning_rate": 3.352674093613801e-05, - "loss": 3.1971, - "step": 92300 + "learning_rate": 3.354625441169161e-05, + "loss": 3.3049, + "step": 99300 }, { "epoch": 0.33, - "learning_rate": 3.350889341819233e-05, - "loss": 3.1927, - "step": 92400 + "learning_rate": 3.3529684677967226e-05, + "loss": 3.3232, + "step": 99400 }, { "epoch": 0.33, - "learning_rate": 3.349104590024665e-05, - "loss": 3.1933, - "step": 92500 + "learning_rate": 3.351311494424285e-05, + "loss": 3.3017, + "step": 99500 }, { "epoch": 0.33, - "learning_rate": 3.347319838230097e-05, - "loss": 3.1876, - "step": 92600 + "learning_rate": 3.349654521051847e-05, + "loss": 3.3062, + "step": 99600 }, { "epoch": 0.33, - "learning_rate": 3.3455350864355294e-05, - "loss": 3.2015, - "step": 92700 + "learning_rate": 3.347997547679409e-05, + "loss": 3.3099, + "step": 99700 }, { "epoch": 0.33, - "learning_rate": 3.3437503346409615e-05, - "loss": 3.192, - "step": 92800 + "learning_rate": 3.346340574306971e-05, + "loss": 3.3173, + "step": 99800 + }, + { + "epoch": 0.33, + "learning_rate": 3.344683600934533e-05, + "loss": 3.311, + "step": 99900 + }, + { + "epoch": 0.33, + "learning_rate": 3.3430266275620954e-05, + "loss": 3.3054, + "step": 100000 + }, + { + "epoch": 0.33, + "learning_rate": 3.341369654189657e-05, + "loss": 3.3117, + "step": 100100 + }, + { + "epoch": 0.33, + "learning_rate": 3.33971268081722e-05, + "loss": 3.3128, + "step": 100200 + }, + { + "epoch": 0.33, + "learning_rate": 3.338055707444782e-05, + "loss": 3.3185, + "step": 100300 }, { "epoch": 0.33, - "learning_rate": 3.341965582846394e-05, - "loss": 3.1929, - "step": 92900 + "learning_rate": 3.3363987340723434e-05, + "loss": 3.3179, + "step": 100400 }, { "epoch": 0.33, - "learning_rate": 3.340180831051826e-05, - "loss": 3.1975, - "step": 93000 + "learning_rate": 3.334741760699906e-05, + "loss": 3.3199, + "step": 100500 }, { "epoch": 0.33, - "learning_rate": 3.338396079257258e-05, - "loss": 3.1777, - "step": 93100 + "learning_rate": 3.3330847873274676e-05, + "loss": 3.3197, + "step": 100600 }, { "epoch": 0.33, - "learning_rate": 3.33661132746269e-05, - "loss": 3.1965, - "step": 93200 + "learning_rate": 3.33142781395503e-05, + "loss": 3.3131, + "step": 100700 }, { "epoch": 0.33, - "learning_rate": 3.334826575668122e-05, - "loss": 3.2012, - "step": 93300 + "learning_rate": 3.329770840582592e-05, + "loss": 3.3167, + "step": 100800 }, { "epoch": 0.33, - "learning_rate": 3.3330418238735536e-05, - "loss": 3.1856, - "step": 93400 + "learning_rate": 3.328113867210154e-05, + "loss": 3.3213, + "step": 100900 }, { "epoch": 0.33, - "learning_rate": 3.331257072078986e-05, - "loss": 3.1913, - "step": 93500 + "learning_rate": 3.326456893837716e-05, + "loss": 3.3154, + "step": 101000 }, { - "epoch": 0.33, - "learning_rate": 3.329472320284418e-05, - "loss": 3.1869, - "step": 93600 + "epoch": 0.34, + "learning_rate": 3.3247999204652784e-05, + "loss": 3.3147, + "step": 101100 }, { - "epoch": 0.33, - "learning_rate": 3.32768756848985e-05, - "loss": 3.1958, - "step": 93700 + "epoch": 0.34, + "learning_rate": 3.3231429470928405e-05, + "loss": 3.3099, + "step": 101200 }, { - "epoch": 0.33, - "learning_rate": 3.325902816695282e-05, - "loss": 3.1823, - "step": 93800 + "epoch": 0.34, + "learning_rate": 3.321485973720403e-05, + "loss": 3.3015, + "step": 101300 }, { "epoch": 0.34, - "learning_rate": 3.324118064900714e-05, - "loss": 3.1861, - "step": 93900 + "learning_rate": 3.319829000347964e-05, + "loss": 3.3198, + "step": 101400 }, { "epoch": 0.34, - "learning_rate": 3.322333313106146e-05, - "loss": 3.1862, - "step": 94000 + "learning_rate": 3.318172026975527e-05, + "loss": 3.3168, + "step": 101500 }, { "epoch": 0.34, - "learning_rate": 3.3205485613115785e-05, - "loss": 3.1894, - "step": 94100 + "learning_rate": 3.3165150536030884e-05, + "loss": 3.3087, + "step": 101600 }, { "epoch": 0.34, - "learning_rate": 3.3187638095170106e-05, - "loss": 3.1948, - "step": 94200 + "learning_rate": 3.3148580802306506e-05, + "loss": 3.3162, + "step": 101700 }, { "epoch": 0.34, - "learning_rate": 3.316979057722443e-05, - "loss": 3.1956, - "step": 94300 + "learning_rate": 3.313201106858213e-05, + "loss": 3.3189, + "step": 101800 }, { "epoch": 0.34, - "learning_rate": 3.315194305927875e-05, - "loss": 3.193, - "step": 94400 + "learning_rate": 3.311544133485775e-05, + "loss": 3.3242, + "step": 101900 }, { "epoch": 0.34, - "learning_rate": 3.313409554133307e-05, - "loss": 3.1913, - "step": 94500 + "learning_rate": 3.309887160113337e-05, + "loss": 3.3201, + "step": 102000 }, { "epoch": 0.34, - "learning_rate": 3.311624802338739e-05, - "loss": 3.1936, - "step": 94600 + "learning_rate": 3.308230186740899e-05, + "loss": 3.3104, + "step": 102100 }, { "epoch": 0.34, - "learning_rate": 3.309840050544171e-05, - "loss": 3.1901, - "step": 94700 + "learning_rate": 3.306573213368461e-05, + "loss": 3.3114, + "step": 102200 }, { "epoch": 0.34, - "learning_rate": 3.308055298749603e-05, - "loss": 3.185, - "step": 94800 + "learning_rate": 3.3049162399960235e-05, + "loss": 3.3129, + "step": 102300 }, { "epoch": 0.34, - "learning_rate": 3.3062705469550354e-05, - "loss": 3.1804, - "step": 94900 + "learning_rate": 3.3032592666235856e-05, + "loss": 3.3086, + "step": 102400 }, { "epoch": 0.34, - "learning_rate": 3.3044857951604675e-05, - "loss": 3.1918, - "step": 95000 + "learning_rate": 3.301602293251148e-05, + "loss": 3.3129, + "step": 102500 }, { "epoch": 0.34, - "learning_rate": 3.3027010433659e-05, - "loss": 3.1877, - "step": 95100 + "learning_rate": 3.299945319878709e-05, + "loss": 3.3133, + "step": 102600 }, { "epoch": 0.34, - "learning_rate": 3.300916291571332e-05, - "loss": 3.1929, - "step": 95200 + "learning_rate": 3.298288346506272e-05, + "loss": 3.3229, + "step": 102700 }, { "epoch": 0.34, - "learning_rate": 3.299131539776764e-05, - "loss": 3.1901, - "step": 95300 + "learning_rate": 3.2966313731338335e-05, + "loss": 3.3265, + "step": 102800 }, { "epoch": 0.34, - "learning_rate": 3.2973467879821954e-05, - "loss": 3.184, - "step": 95400 + "learning_rate": 3.294974399761396e-05, + "loss": 3.3209, + "step": 102900 }, { "epoch": 0.34, - "learning_rate": 3.2955620361876275e-05, - "loss": 3.1849, - "step": 95500 + "learning_rate": 3.2933174263889585e-05, + "loss": 3.3068, + "step": 103000 }, { "epoch": 0.34, - "learning_rate": 3.2937772843930596e-05, - "loss": 3.1807, - "step": 95600 + "learning_rate": 3.29166045301652e-05, + "loss": 3.3195, + "step": 103100 }, { "epoch": 0.34, - "learning_rate": 3.291992532598492e-05, - "loss": 3.1867, - "step": 95700 + "learning_rate": 3.290003479644082e-05, + "loss": 3.3051, + "step": 103200 }, { "epoch": 0.34, - "learning_rate": 3.290207780803924e-05, - "loss": 3.1801, - "step": 95800 + "learning_rate": 3.288346506271644e-05, + "loss": 3.3192, + "step": 103300 }, { "epoch": 0.34, - "learning_rate": 3.288423029009356e-05, - "loss": 3.1965, - "step": 95900 + "learning_rate": 3.2866895328992064e-05, + "loss": 3.3028, + "step": 103400 }, { "epoch": 0.34, - "learning_rate": 3.286638277214788e-05, - "loss": 3.1914, - "step": 96000 + "learning_rate": 3.2850325595267685e-05, + "loss": 3.2945, + "step": 103500 }, { "epoch": 0.34, - "learning_rate": 3.28485352542022e-05, - "loss": 3.1939, - "step": 96100 + "learning_rate": 3.283375586154331e-05, + "loss": 3.3052, + "step": 103600 }, { "epoch": 0.34, - "learning_rate": 3.283068773625652e-05, - "loss": 3.1946, - "step": 96200 + "learning_rate": 3.281718612781893e-05, + "loss": 3.315, + "step": 103700 }, { "epoch": 0.34, - "learning_rate": 3.2812840218310844e-05, - "loss": 3.1872, - "step": 96300 + "learning_rate": 3.280061639409455e-05, + "loss": 3.3231, + "step": 103800 }, { "epoch": 0.34, - "learning_rate": 3.2794992700365166e-05, - "loss": 3.1952, - "step": 96400 + "learning_rate": 3.278404666037017e-05, + "loss": 3.3184, + "step": 103900 }, { "epoch": 0.34, - "learning_rate": 3.277714518241948e-05, - "loss": 3.1887, - "step": 96500 + "learning_rate": 3.276747692664579e-05, + "loss": 3.3128, + "step": 104000 }, { "epoch": 0.34, - "learning_rate": 3.27592976644738e-05, - "loss": 3.1982, - "step": 96600 + "learning_rate": 3.275090719292141e-05, + "loss": 3.3073, + "step": 104100 }, { "epoch": 0.35, - "learning_rate": 3.274145014652812e-05, - "loss": 3.1852, - "step": 96700 + "learning_rate": 3.2734337459197036e-05, + "loss": 3.3116, + "step": 104200 }, { "epoch": 0.35, - "learning_rate": 3.2723602628582444e-05, - "loss": 3.1913, - "step": 96800 + "learning_rate": 3.271776772547265e-05, + "loss": 3.3108, + "step": 104300 }, { "epoch": 0.35, - "learning_rate": 3.2705755110636765e-05, - "loss": 3.1825, - "step": 96900 + "learning_rate": 3.270119799174827e-05, + "loss": 3.3114, + "step": 104400 }, { "epoch": 0.35, - "learning_rate": 3.2687907592691086e-05, - "loss": 3.1858, - "step": 97000 + "learning_rate": 3.26846282580239e-05, + "loss": 3.3061, + "step": 104500 }, { "epoch": 0.35, - "learning_rate": 3.267006007474541e-05, - "loss": 3.1744, - "step": 97100 + "learning_rate": 3.2668058524299515e-05, + "loss": 3.3151, + "step": 104600 }, { "epoch": 0.35, - "learning_rate": 3.265221255679973e-05, - "loss": 3.1955, - "step": 97200 + "learning_rate": 3.2651488790575136e-05, + "loss": 3.3037, + "step": 104700 }, { "epoch": 0.35, - "learning_rate": 3.263436503885405e-05, - "loss": 3.1837, - "step": 97300 + "learning_rate": 3.263491905685076e-05, + "loss": 3.308, + "step": 104800 }, { "epoch": 0.35, - "learning_rate": 3.261651752090837e-05, - "loss": 3.1948, - "step": 97400 + "learning_rate": 3.261834932312638e-05, + "loss": 3.3096, + "step": 104900 }, { "epoch": 0.35, - "learning_rate": 3.259867000296269e-05, - "loss": 3.1888, - "step": 97500 + "learning_rate": 3.2601779589402e-05, + "loss": 3.3151, + "step": 105000 }, { "epoch": 0.35, - "learning_rate": 3.258082248501701e-05, - "loss": 3.1876, - "step": 97600 + "learning_rate": 3.258520985567762e-05, + "loss": 3.3104, + "step": 105100 }, { "epoch": 0.35, - "learning_rate": 3.256297496707133e-05, - "loss": 3.1911, - "step": 97700 + "learning_rate": 3.2568640121953244e-05, + "loss": 3.3078, + "step": 105200 }, { "epoch": 0.35, - "learning_rate": 3.254512744912565e-05, - "loss": 3.1842, - "step": 97800 + "learning_rate": 3.255207038822886e-05, + "loss": 3.3137, + "step": 105300 }, { "epoch": 0.35, - "learning_rate": 3.252727993117997e-05, - "loss": 3.1834, - "step": 97900 + "learning_rate": 3.2535500654504487e-05, + "loss": 3.3231, + "step": 105400 }, { "epoch": 0.35, - "learning_rate": 3.250943241323429e-05, - "loss": 3.1923, - "step": 98000 + "learning_rate": 3.251893092078011e-05, + "loss": 3.3048, + "step": 105500 }, { "epoch": 0.35, - "learning_rate": 3.249158489528861e-05, - "loss": 3.1894, - "step": 98100 + "learning_rate": 3.250236118705572e-05, + "loss": 3.3142, + "step": 105600 }, { "epoch": 0.35, - "learning_rate": 3.2473737377342934e-05, - "loss": 3.1983, - "step": 98200 + "learning_rate": 3.248579145333135e-05, + "loss": 3.3189, + "step": 105700 }, { "epoch": 0.35, - "learning_rate": 3.2455889859397255e-05, - "loss": 3.1864, - "step": 98300 + "learning_rate": 3.2469221719606966e-05, + "loss": 3.3046, + "step": 105800 }, { "epoch": 0.35, - "learning_rate": 3.2438042341451576e-05, - "loss": 3.1806, - "step": 98400 + "learning_rate": 3.245265198588259e-05, + "loss": 3.3154, + "step": 105900 }, { "epoch": 0.35, - "learning_rate": 3.24201948235059e-05, - "loss": 3.1775, - "step": 98500 + "learning_rate": 3.243608225215821e-05, + "loss": 3.305, + "step": 106000 }, { "epoch": 0.35, - "learning_rate": 3.240234730556022e-05, - "loss": 3.1936, - "step": 98600 + "learning_rate": 3.241951251843383e-05, + "loss": 3.3095, + "step": 106100 }, { "epoch": 0.35, - "learning_rate": 3.238449978761453e-05, - "loss": 3.1856, - "step": 98700 + "learning_rate": 3.240294278470945e-05, + "loss": 3.3065, + "step": 106200 }, { "epoch": 0.35, - "learning_rate": 3.2366652269668855e-05, - "loss": 3.1838, - "step": 98800 + "learning_rate": 3.238637305098507e-05, + "loss": 3.3192, + "step": 106300 }, { "epoch": 0.35, - "learning_rate": 3.2348804751723176e-05, - "loss": 3.189, - "step": 98900 + "learning_rate": 3.2369803317260694e-05, + "loss": 3.3202, + "step": 106400 }, { "epoch": 0.35, - "learning_rate": 3.23309572337775e-05, - "loss": 3.1893, - "step": 99000 + "learning_rate": 3.2353233583536316e-05, + "loss": 3.3266, + "step": 106500 }, { "epoch": 0.35, - "learning_rate": 3.231310971583182e-05, - "loss": 3.1957, - "step": 99100 + "learning_rate": 3.233666384981193e-05, + "loss": 3.3065, + "step": 106600 }, { "epoch": 0.35, - "learning_rate": 3.229526219788614e-05, - "loss": 3.182, - "step": 99200 + "learning_rate": 3.232009411608756e-05, + "loss": 3.3059, + "step": 106700 }, { "epoch": 0.35, - "learning_rate": 3.227741467994046e-05, - "loss": 3.1881, - "step": 99300 + "learning_rate": 3.2303524382363174e-05, + "loss": 3.3187, + "step": 106800 }, { "epoch": 0.35, - "learning_rate": 3.225956716199478e-05, - "loss": 3.1905, - "step": 99400 + "learning_rate": 3.2286954648638795e-05, + "loss": 3.3006, + "step": 106900 + }, + { + "epoch": 0.35, + "learning_rate": 3.227038491491442e-05, + "loss": 3.3092, + "step": 107000 + }, + { + "epoch": 0.35, + "learning_rate": 3.225381518119004e-05, + "loss": 3.2996, + "step": 107100 }, { "epoch": 0.36, - "learning_rate": 3.22417196440491e-05, - "loss": 3.1915, - "step": 99500 + "learning_rate": 3.223724544746566e-05, + "loss": 3.3104, + "step": 107200 }, { "epoch": 0.36, - "learning_rate": 3.2223872126103424e-05, - "loss": 3.1876, - "step": 99600 + "learning_rate": 3.222067571374128e-05, + "loss": 3.3, + "step": 107300 }, { "epoch": 0.36, - "learning_rate": 3.2206024608157745e-05, - "loss": 3.1734, - "step": 99700 + "learning_rate": 3.22041059800169e-05, + "loss": 3.3112, + "step": 107400 }, { "epoch": 0.36, - "learning_rate": 3.218817709021207e-05, - "loss": 3.195, - "step": 99800 + "learning_rate": 3.2187536246292524e-05, + "loss": 3.3132, + "step": 107500 }, { "epoch": 0.36, - "learning_rate": 3.217032957226639e-05, - "loss": 3.1828, - "step": 99900 + "learning_rate": 3.2170966512568145e-05, + "loss": 3.3181, + "step": 107600 }, { "epoch": 0.36, - "learning_rate": 3.215248205432071e-05, - "loss": 3.1863, - "step": 100000 + "learning_rate": 3.215439677884377e-05, + "loss": 3.3147, + "step": 107700 }, { "epoch": 0.36, - "learning_rate": 3.213463453637503e-05, - "loss": 3.1943, - "step": 100100 + "learning_rate": 3.213782704511938e-05, + "loss": 3.3159, + "step": 107800 }, { "epoch": 0.36, - "learning_rate": 3.211678701842935e-05, - "loss": 3.1823, - "step": 100200 + "learning_rate": 3.212125731139501e-05, + "loss": 3.3144, + "step": 107900 }, { "epoch": 0.36, - "learning_rate": 3.209893950048367e-05, - "loss": 3.1952, - "step": 100300 + "learning_rate": 3.210468757767063e-05, + "loss": 3.3088, + "step": 108000 }, { "epoch": 0.36, - "learning_rate": 3.2081091982537994e-05, - "loss": 3.1992, - "step": 100400 + "learning_rate": 3.2088117843946246e-05, + "loss": 3.317, + "step": 108100 }, { "epoch": 0.36, - "learning_rate": 3.2063244464592315e-05, - "loss": 3.185, - "step": 100500 + "learning_rate": 3.2071548110221874e-05, + "loss": 3.3117, + "step": 108200 }, { "epoch": 0.36, - "learning_rate": 3.2045396946646636e-05, - "loss": 3.1754, - "step": 100600 + "learning_rate": 3.205497837649749e-05, + "loss": 3.3121, + "step": 108300 }, { "epoch": 0.36, - "learning_rate": 3.202754942870095e-05, - "loss": 3.1963, - "step": 100700 + "learning_rate": 3.203840864277311e-05, + "loss": 3.3206, + "step": 108400 }, { "epoch": 0.36, - "learning_rate": 3.200970191075527e-05, - "loss": 3.1811, - "step": 100800 + "learning_rate": 3.202183890904873e-05, + "loss": 3.3157, + "step": 108500 }, { "epoch": 0.36, - "learning_rate": 3.199185439280959e-05, - "loss": 3.1861, - "step": 100900 + "learning_rate": 3.200526917532435e-05, + "loss": 3.311, + "step": 108600 }, { "epoch": 0.36, - "learning_rate": 3.1974006874863914e-05, - "loss": 3.1857, - "step": 101000 + "learning_rate": 3.1988699441599975e-05, + "loss": 3.3001, + "step": 108700 }, { "epoch": 0.36, - "learning_rate": 3.1956159356918236e-05, - "loss": 3.1833, - "step": 101100 + "learning_rate": 3.1972129707875596e-05, + "loss": 3.304, + "step": 108800 }, { "epoch": 0.36, - "learning_rate": 3.193831183897256e-05, - "loss": 3.1765, - "step": 101200 + "learning_rate": 3.195555997415122e-05, + "loss": 3.3021, + "step": 108900 }, { "epoch": 0.36, - "learning_rate": 3.192046432102688e-05, - "loss": 3.1888, - "step": 101300 + "learning_rate": 3.193899024042684e-05, + "loss": 3.303, + "step": 109000 }, { "epoch": 0.36, - "learning_rate": 3.19026168030812e-05, - "loss": 3.1849, - "step": 101400 + "learning_rate": 3.192242050670246e-05, + "loss": 3.3237, + "step": 109100 }, { "epoch": 0.36, - "learning_rate": 3.188476928513552e-05, - "loss": 3.1889, - "step": 101500 + "learning_rate": 3.190585077297808e-05, + "loss": 3.31, + "step": 109200 }, { "epoch": 0.36, - "learning_rate": 3.186692176718984e-05, - "loss": 3.1834, - "step": 101600 + "learning_rate": 3.18892810392537e-05, + "loss": 3.3169, + "step": 109300 }, { "epoch": 0.36, - "learning_rate": 3.184907424924416e-05, - "loss": 3.1961, - "step": 101700 + "learning_rate": 3.1872711305529325e-05, + "loss": 3.3045, + "step": 109400 }, { "epoch": 0.36, - "learning_rate": 3.183122673129848e-05, - "loss": 3.1824, - "step": 101800 + "learning_rate": 3.185614157180494e-05, + "loss": 3.3158, + "step": 109500 }, { "epoch": 0.36, - "learning_rate": 3.18133792133528e-05, - "loss": 3.1749, - "step": 101900 + "learning_rate": 3.183957183808056e-05, + "loss": 3.3187, + "step": 109600 }, { "epoch": 0.36, - "learning_rate": 3.179553169540712e-05, - "loss": 3.1869, - "step": 102000 + "learning_rate": 3.182300210435619e-05, + "loss": 3.2998, + "step": 109700 }, { "epoch": 0.36, - "learning_rate": 3.177768417746144e-05, - "loss": 3.1784, - "step": 102100 + "learning_rate": 3.1806432370631804e-05, + "loss": 3.3015, + "step": 109800 }, { "epoch": 0.36, - "learning_rate": 3.175983665951576e-05, - "loss": 3.1858, - "step": 102200 + "learning_rate": 3.1789862636907425e-05, + "loss": 3.3058, + "step": 109900 + }, + { + "epoch": 0.36, + "learning_rate": 3.177329290318305e-05, + "loss": 3.3215, + "step": 110000 + }, + { + "epoch": 0.36, + "learning_rate": 3.175672316945867e-05, + "loss": 3.3004, + "step": 110100 }, { "epoch": 0.37, - "learning_rate": 3.1741989141570083e-05, - "loss": 3.1816, - "step": 102300 + "learning_rate": 3.174015343573429e-05, + "loss": 3.2953, + "step": 110200 }, { "epoch": 0.37, - "learning_rate": 3.1724141623624405e-05, - "loss": 3.1949, - "step": 102400 + "learning_rate": 3.172358370200991e-05, + "loss": 3.2975, + "step": 110300 + }, + { + "epoch": 0.37, + "learning_rate": 3.170701396828553e-05, + "loss": 3.3137, + "step": 110400 + }, + { + "epoch": 0.37, + "learning_rate": 3.169044423456115e-05, + "loss": 3.3093, + "step": 110500 + }, + { + "epoch": 0.37, + "learning_rate": 3.1673874500836776e-05, + "loss": 3.3037, + "step": 110600 + }, + { + "epoch": 0.37, + "learning_rate": 3.16573047671124e-05, + "loss": 3.3011, + "step": 110700 }, { "epoch": 0.37, - "learning_rate": 3.1706294105678726e-05, - "loss": 3.1826, - "step": 102500 + "learning_rate": 3.164073503338801e-05, + "loss": 3.2956, + "step": 110800 }, { "epoch": 0.37, - "learning_rate": 3.168844658773305e-05, - "loss": 3.1742, - "step": 102600 + "learning_rate": 3.162416529966364e-05, + "loss": 3.3024, + "step": 110900 }, { "epoch": 0.37, - "learning_rate": 3.167059906978737e-05, - "loss": 3.1824, - "step": 102700 + "learning_rate": 3.1607595565939255e-05, + "loss": 3.3085, + "step": 111000 }, { "epoch": 0.37, - "learning_rate": 3.165275155184169e-05, - "loss": 3.1865, - "step": 102800 + "learning_rate": 3.1591025832214876e-05, + "loss": 3.3161, + "step": 111100 }, { "epoch": 0.37, - "learning_rate": 3.1634904033896004e-05, - "loss": 3.1839, - "step": 102900 + "learning_rate": 3.1574456098490505e-05, + "loss": 3.3101, + "step": 111200 }, { "epoch": 0.37, - "learning_rate": 3.1617056515950325e-05, - "loss": 3.1776, - "step": 103000 + "learning_rate": 3.155788636476612e-05, + "loss": 3.3044, + "step": 111300 }, { "epoch": 0.37, - "learning_rate": 3.1599208998004646e-05, - "loss": 3.1801, - "step": 103100 + "learning_rate": 3.154131663104174e-05, + "loss": 3.3141, + "step": 111400 }, { "epoch": 0.37, - "learning_rate": 3.158136148005897e-05, - "loss": 3.179, - "step": 103200 + "learning_rate": 3.152474689731736e-05, + "loss": 3.3088, + "step": 111500 }, { "epoch": 0.37, - "learning_rate": 3.156351396211329e-05, - "loss": 3.1764, - "step": 103300 + "learning_rate": 3.1508177163592984e-05, + "loss": 3.3124, + "step": 111600 }, { "epoch": 0.37, - "learning_rate": 3.154566644416761e-05, - "loss": 3.1818, - "step": 103400 + "learning_rate": 3.1491607429868605e-05, + "loss": 3.3131, + "step": 111700 }, { "epoch": 0.37, - "learning_rate": 3.152781892622193e-05, - "loss": 3.1838, - "step": 103500 + "learning_rate": 3.147503769614422e-05, + "loss": 3.3061, + "step": 111800 }, { "epoch": 0.37, - "learning_rate": 3.150997140827625e-05, - "loss": 3.1836, - "step": 103600 + "learning_rate": 3.145846796241985e-05, + "loss": 3.3065, + "step": 111900 }, { "epoch": 0.37, - "learning_rate": 3.1492123890330574e-05, - "loss": 3.1758, - "step": 103700 + "learning_rate": 3.144189822869546e-05, + "loss": 3.301, + "step": 112000 }, { "epoch": 0.37, - "learning_rate": 3.1474276372384895e-05, - "loss": 3.1661, - "step": 103800 + "learning_rate": 3.1425328494971084e-05, + "loss": 3.313, + "step": 112100 }, { "epoch": 0.37, - "learning_rate": 3.145642885443921e-05, - "loss": 3.1747, - "step": 103900 + "learning_rate": 3.140875876124671e-05, + "loss": 3.3081, + "step": 112200 }, { "epoch": 0.37, - "learning_rate": 3.143858133649353e-05, - "loss": 3.176, - "step": 104000 + "learning_rate": 3.139218902752233e-05, + "loss": 3.3031, + "step": 112300 }, { "epoch": 0.37, - "learning_rate": 3.142073381854785e-05, - "loss": 3.1902, - "step": 104100 + "learning_rate": 3.137561929379795e-05, + "loss": 3.3074, + "step": 112400 }, { "epoch": 0.37, - "learning_rate": 3.140288630060217e-05, - "loss": 3.1771, - "step": 104200 + "learning_rate": 3.135904956007357e-05, + "loss": 3.3072, + "step": 112500 }, { "epoch": 0.37, - "learning_rate": 3.1385038782656494e-05, - "loss": 3.1798, - "step": 104300 + "learning_rate": 3.134247982634919e-05, + "loss": 3.3122, + "step": 112600 }, { "epoch": 0.37, - "learning_rate": 3.1367191264710815e-05, - "loss": 3.1878, - "step": 104400 + "learning_rate": 3.132591009262481e-05, + "loss": 3.303, + "step": 112700 }, { "epoch": 0.37, - "learning_rate": 3.134934374676514e-05, - "loss": 3.1735, - "step": 104500 + "learning_rate": 3.1309340358900434e-05, + "loss": 3.2882, + "step": 112800 }, { "epoch": 0.37, - "learning_rate": 3.133149622881946e-05, - "loss": 3.1817, - "step": 104600 + "learning_rate": 3.1292770625176056e-05, + "loss": 3.2878, + "step": 112900 }, { "epoch": 0.37, - "learning_rate": 3.1313648710873786e-05, - "loss": 3.1827, - "step": 104700 + "learning_rate": 3.127620089145167e-05, + "loss": 3.3077, + "step": 113000 }, { "epoch": 0.37, - "learning_rate": 3.12958011929281e-05, - "loss": 3.1848, - "step": 104800 + "learning_rate": 3.12596311577273e-05, + "loss": 3.3056, + "step": 113100 }, { - "epoch": 0.37, - "learning_rate": 3.127795367498242e-05, - "loss": 3.1793, - "step": 104900 + "epoch": 0.38, + "learning_rate": 3.124306142400292e-05, + "loss": 3.3048, + "step": 113200 }, { - "epoch": 0.37, - "learning_rate": 3.126010615703674e-05, - "loss": 3.1678, - "step": 105000 + "epoch": 0.38, + "learning_rate": 3.1226491690278535e-05, + "loss": 3.3073, + "step": 113300 }, { "epoch": 0.38, - "learning_rate": 3.1242258639091064e-05, - "loss": 3.1798, - "step": 105100 + "learning_rate": 3.120992195655416e-05, + "loss": 3.3039, + "step": 113400 }, { "epoch": 0.38, - "learning_rate": 3.1224411121145385e-05, - "loss": 3.1751, - "step": 105200 + "learning_rate": 3.119335222282978e-05, + "loss": 3.3027, + "step": 113500 }, { "epoch": 0.38, - "learning_rate": 3.1206563603199706e-05, - "loss": 3.1837, - "step": 105300 + "learning_rate": 3.11767824891054e-05, + "loss": 3.3099, + "step": 113600 }, { "epoch": 0.38, - "learning_rate": 3.118871608525403e-05, - "loss": 3.1827, - "step": 105400 + "learning_rate": 3.116021275538102e-05, + "loss": 3.3214, + "step": 113700 }, { "epoch": 0.38, - "learning_rate": 3.117086856730835e-05, - "loss": 3.177, - "step": 105500 + "learning_rate": 3.114364302165664e-05, + "loss": 3.3078, + "step": 113800 }, { "epoch": 0.38, - "learning_rate": 3.115302104936267e-05, - "loss": 3.182, - "step": 105600 + "learning_rate": 3.1127073287932264e-05, + "loss": 3.3039, + "step": 113900 }, { "epoch": 0.38, - "learning_rate": 3.113517353141699e-05, - "loss": 3.1821, - "step": 105700 + "learning_rate": 3.1110503554207885e-05, + "loss": 3.314, + "step": 114000 }, { "epoch": 0.38, - "learning_rate": 3.111732601347131e-05, - "loss": 3.1817, - "step": 105800 + "learning_rate": 3.109393382048351e-05, + "loss": 3.3034, + "step": 114100 }, { "epoch": 0.38, - "learning_rate": 3.109947849552563e-05, - "loss": 3.1897, - "step": 105900 + "learning_rate": 3.107736408675913e-05, + "loss": 3.2986, + "step": 114200 }, { "epoch": 0.38, - "learning_rate": 3.108163097757995e-05, - "loss": 3.18, - "step": 106000 + "learning_rate": 3.106079435303475e-05, + "loss": 3.3099, + "step": 114300 }, { "epoch": 0.38, - "learning_rate": 3.106378345963427e-05, - "loss": 3.1789, - "step": 106100 + "learning_rate": 3.104422461931037e-05, + "loss": 3.2958, + "step": 114400 }, { "epoch": 0.38, - "learning_rate": 3.104593594168859e-05, - "loss": 3.1803, - "step": 106200 + "learning_rate": 3.1027654885585986e-05, + "loss": 3.3054, + "step": 114500 }, { "epoch": 0.38, - "learning_rate": 3.102808842374291e-05, - "loss": 3.1841, - "step": 106300 + "learning_rate": 3.1011085151861614e-05, + "loss": 3.299, + "step": 114600 }, { "epoch": 0.38, - "learning_rate": 3.101024090579723e-05, - "loss": 3.1794, - "step": 106400 + "learning_rate": 3.099451541813723e-05, + "loss": 3.3178, + "step": 114700 }, { "epoch": 0.38, - "learning_rate": 3.0992393387851554e-05, - "loss": 3.1802, - "step": 106500 + "learning_rate": 3.097794568441285e-05, + "loss": 3.2923, + "step": 114800 }, { "epoch": 0.38, - "learning_rate": 3.0974545869905875e-05, - "loss": 3.1803, - "step": 106600 + "learning_rate": 3.096137595068848e-05, + "loss": 3.3082, + "step": 114900 }, { "epoch": 0.38, - "learning_rate": 3.0956698351960197e-05, - "loss": 3.1841, - "step": 106700 + "learning_rate": 3.094480621696409e-05, + "loss": 3.3059, + "step": 115000 }, { "epoch": 0.38, - "learning_rate": 3.093885083401452e-05, - "loss": 3.1906, - "step": 106800 + "learning_rate": 3.0928236483239715e-05, + "loss": 3.3035, + "step": 115100 }, { "epoch": 0.38, - "learning_rate": 3.092100331606884e-05, - "loss": 3.1667, - "step": 106900 + "learning_rate": 3.0911666749515336e-05, + "loss": 3.2962, + "step": 115200 }, { "epoch": 0.38, - "learning_rate": 3.0903155798123153e-05, - "loss": 3.1667, - "step": 107000 + "learning_rate": 3.089509701579096e-05, + "loss": 3.3004, + "step": 115300 }, { "epoch": 0.38, - "learning_rate": 3.0885308280177475e-05, - "loss": 3.1781, - "step": 107100 + "learning_rate": 3.087852728206658e-05, + "loss": 3.2886, + "step": 115400 }, { "epoch": 0.38, - "learning_rate": 3.0867460762231796e-05, - "loss": 3.1685, - "step": 107200 + "learning_rate": 3.08619575483422e-05, + "loss": 3.3008, + "step": 115500 }, { "epoch": 0.38, - "learning_rate": 3.084961324428612e-05, - "loss": 3.183, - "step": 107300 + "learning_rate": 3.084538781461782e-05, + "loss": 3.3072, + "step": 115600 }, { "epoch": 0.38, - "learning_rate": 3.083176572634044e-05, - "loss": 3.1784, - "step": 107400 + "learning_rate": 3.0828818080893443e-05, + "loss": 3.3158, + "step": 115700 }, { "epoch": 0.38, - "learning_rate": 3.081391820839476e-05, - "loss": 3.1784, - "step": 107500 + "learning_rate": 3.0812248347169065e-05, + "loss": 3.3263, + "step": 115800 }, { "epoch": 0.38, - "learning_rate": 3.079607069044908e-05, - "loss": 3.1713, - "step": 107600 + "learning_rate": 3.0795678613444686e-05, + "loss": 3.3183, + "step": 115900 }, { "epoch": 0.38, - "learning_rate": 3.07782231725034e-05, - "loss": 3.1695, - "step": 107700 + "learning_rate": 3.07791088797203e-05, + "loss": 3.3044, + "step": 116000 }, { "epoch": 0.38, - "learning_rate": 3.076037565455772e-05, - "loss": 3.1845, - "step": 107800 + "learning_rate": 3.076253914599593e-05, + "loss": 3.3049, + "step": 116100 }, { "epoch": 0.39, - "learning_rate": 3.0742528136612044e-05, - "loss": 3.1801, - "step": 107900 + "learning_rate": 3.0745969412271544e-05, + "loss": 3.3092, + "step": 116200 }, { "epoch": 0.39, - "learning_rate": 3.0724680618666366e-05, - "loss": 3.173, - "step": 108000 + "learning_rate": 3.0729399678547165e-05, + "loss": 3.3161, + "step": 116300 }, { "epoch": 0.39, - "learning_rate": 3.070683310072068e-05, - "loss": 3.186, - "step": 108100 + "learning_rate": 3.0712829944822794e-05, + "loss": 3.3024, + "step": 116400 }, { "epoch": 0.39, - "learning_rate": 3.0688985582775e-05, - "loss": 3.1778, - "step": 108200 + "learning_rate": 3.069626021109841e-05, + "loss": 3.3033, + "step": 116500 }, { "epoch": 0.39, - "learning_rate": 3.067113806482932e-05, - "loss": 3.1775, - "step": 108300 + "learning_rate": 3.067969047737403e-05, + "loss": 3.2878, + "step": 116600 }, { "epoch": 0.39, - "learning_rate": 3.0653290546883644e-05, - "loss": 3.1814, - "step": 108400 + "learning_rate": 3.066312074364965e-05, + "loss": 3.3144, + "step": 116700 }, { "epoch": 0.39, - "learning_rate": 3.0635443028937965e-05, - "loss": 3.1738, - "step": 108500 + "learning_rate": 3.064655100992527e-05, + "loss": 3.3086, + "step": 116800 }, { "epoch": 0.39, - "learning_rate": 3.0617595510992286e-05, - "loss": 3.174, - "step": 108600 + "learning_rate": 3.0629981276200894e-05, + "loss": 3.3005, + "step": 116900 }, { "epoch": 0.39, - "learning_rate": 3.059974799304661e-05, - "loss": 3.1722, - "step": 108700 + "learning_rate": 3.061341154247651e-05, + "loss": 3.2935, + "step": 117000 }, { "epoch": 0.39, - "learning_rate": 3.058190047510093e-05, - "loss": 3.1826, - "step": 108800 + "learning_rate": 3.059684180875214e-05, + "loss": 3.307, + "step": 117100 }, { "epoch": 0.39, - "learning_rate": 3.056405295715525e-05, - "loss": 3.1868, - "step": 108900 + "learning_rate": 3.058027207502775e-05, + "loss": 3.2984, + "step": 117200 }, { "epoch": 0.39, - "learning_rate": 3.054620543920957e-05, - "loss": 3.1711, - "step": 109000 + "learning_rate": 3.056370234130337e-05, + "loss": 3.3104, + "step": 117300 }, { "epoch": 0.39, - "learning_rate": 3.052835792126389e-05, - "loss": 3.1725, - "step": 109100 + "learning_rate": 3.0547132607579e-05, + "loss": 3.3, + "step": 117400 }, { "epoch": 0.39, - "learning_rate": 3.051051040331821e-05, - "loss": 3.1806, - "step": 109200 + "learning_rate": 3.0530562873854616e-05, + "loss": 3.3153, + "step": 117500 }, { "epoch": 0.39, - "learning_rate": 3.049266288537253e-05, - "loss": 3.173, - "step": 109300 + "learning_rate": 3.0513993140130238e-05, + "loss": 3.3047, + "step": 117600 }, { "epoch": 0.39, - "learning_rate": 3.0474815367426852e-05, - "loss": 3.1737, - "step": 109400 + "learning_rate": 3.0497423406405863e-05, + "loss": 3.312, + "step": 117700 }, { "epoch": 0.39, - "learning_rate": 3.045696784948117e-05, - "loss": 3.1746, - "step": 109500 + "learning_rate": 3.048085367268148e-05, + "loss": 3.3066, + "step": 117800 }, { "epoch": 0.39, - "learning_rate": 3.043912033153549e-05, - "loss": 3.1836, - "step": 109600 + "learning_rate": 3.04642839389571e-05, + "loss": 3.3156, + "step": 117900 }, { "epoch": 0.39, - "learning_rate": 3.0421272813589813e-05, - "loss": 3.1702, - "step": 109700 + "learning_rate": 3.0447714205232724e-05, + "loss": 3.2915, + "step": 118000 }, { "epoch": 0.39, - "learning_rate": 3.0403425295644137e-05, - "loss": 3.1786, - "step": 109800 + "learning_rate": 3.0431144471508345e-05, + "loss": 3.2989, + "step": 118100 }, { "epoch": 0.39, - "learning_rate": 3.038557777769846e-05, - "loss": 3.1777, - "step": 109900 + "learning_rate": 3.0414574737783963e-05, + "loss": 3.2989, + "step": 118200 }, { "epoch": 0.39, - "learning_rate": 3.036773025975278e-05, - "loss": 3.1665, - "step": 110000 + "learning_rate": 3.0398005004059588e-05, + "loss": 3.2925, + "step": 118300 }, { "epoch": 0.39, - "learning_rate": 3.03498827418071e-05, - "loss": 3.1714, - "step": 110100 + "learning_rate": 3.0381435270335206e-05, + "loss": 3.316, + "step": 118400 }, { "epoch": 0.39, - "learning_rate": 3.0332035223861422e-05, - "loss": 3.1686, - "step": 110200 + "learning_rate": 3.0364865536610828e-05, + "loss": 3.3056, + "step": 118500 }, { "epoch": 0.39, - "learning_rate": 3.0314187705915743e-05, - "loss": 3.1825, - "step": 110300 + "learning_rate": 3.034829580288645e-05, + "loss": 3.301, + "step": 118600 }, { "epoch": 0.39, - "learning_rate": 3.029634018797006e-05, - "loss": 3.1717, - "step": 110400 + "learning_rate": 3.033172606916207e-05, + "loss": 3.3109, + "step": 118700 }, { "epoch": 0.39, - "learning_rate": 3.0278492670024382e-05, - "loss": 3.1677, - "step": 110500 + "learning_rate": 3.031515633543769e-05, + "loss": 3.3054, + "step": 118800 }, { "epoch": 0.39, - "learning_rate": 3.0260645152078704e-05, - "loss": 3.1867, - "step": 110600 + "learning_rate": 3.0298586601713313e-05, + "loss": 3.3163, + "step": 118900 + }, + { + "epoch": 0.39, + "learning_rate": 3.028201686798893e-05, + "loss": 3.3041, + "step": 119000 + }, + { + "epoch": 0.39, + "learning_rate": 3.0265447134264553e-05, + "loss": 3.303, + "step": 119100 }, { "epoch": 0.4, - "learning_rate": 3.0242797634133025e-05, - "loss": 3.1777, - "step": 110700 + "learning_rate": 3.0248877400540178e-05, + "loss": 3.2931, + "step": 119200 }, { "epoch": 0.4, - "learning_rate": 3.0224950116187346e-05, - "loss": 3.1676, - "step": 110800 + "learning_rate": 3.0232307666815796e-05, + "loss": 3.3056, + "step": 119300 }, { "epoch": 0.4, - "learning_rate": 3.0207102598241664e-05, - "loss": 3.1766, - "step": 110900 + "learning_rate": 3.0215737933091414e-05, + "loss": 3.3065, + "step": 119400 }, { "epoch": 0.4, - "learning_rate": 3.0189255080295985e-05, - "loss": 3.182, - "step": 111000 + "learning_rate": 3.019916819936704e-05, + "loss": 3.3067, + "step": 119500 }, { "epoch": 0.4, - "learning_rate": 3.0171407562350306e-05, - "loss": 3.1774, - "step": 111100 + "learning_rate": 3.0182598465642657e-05, + "loss": 3.3103, + "step": 119600 }, { "epoch": 0.4, - "learning_rate": 3.0153560044404628e-05, - "loss": 3.1772, - "step": 111200 + "learning_rate": 3.016602873191828e-05, + "loss": 3.2999, + "step": 119700 }, { "epoch": 0.4, - "learning_rate": 3.013571252645895e-05, - "loss": 3.1702, - "step": 111300 + "learning_rate": 3.0149458998193903e-05, + "loss": 3.3203, + "step": 119800 }, { "epoch": 0.4, - "learning_rate": 3.011786500851327e-05, - "loss": 3.1825, - "step": 111400 + "learning_rate": 3.013288926446952e-05, + "loss": 3.3062, + "step": 119900 }, { "epoch": 0.4, - "learning_rate": 3.0100017490567588e-05, - "loss": 3.1681, - "step": 111500 + "learning_rate": 3.011631953074514e-05, + "loss": 3.3034, + "step": 120000 }, { "epoch": 0.4, - "learning_rate": 3.008216997262191e-05, - "loss": 3.169, - "step": 111600 + "learning_rate": 3.0099749797020764e-05, + "loss": 3.3057, + "step": 120100 }, { "epoch": 0.4, - "learning_rate": 3.006432245467623e-05, - "loss": 3.1804, - "step": 111700 + "learning_rate": 3.0083180063296386e-05, + "loss": 3.298, + "step": 120200 }, { "epoch": 0.4, - "learning_rate": 3.004647493673055e-05, - "loss": 3.1663, - "step": 111800 + "learning_rate": 3.0066610329572004e-05, + "loss": 3.3028, + "step": 120300 }, { "epoch": 0.4, - "learning_rate": 3.0028627418784873e-05, - "loss": 3.1746, - "step": 111900 + "learning_rate": 3.005004059584763e-05, + "loss": 3.3102, + "step": 120400 }, { "epoch": 0.4, - "learning_rate": 3.001077990083919e-05, - "loss": 3.1804, - "step": 112000 + "learning_rate": 3.0033470862123247e-05, + "loss": 3.2998, + "step": 120500 + }, + { + "epoch": 0.4, + "learning_rate": 3.0016901128398868e-05, + "loss": 3.3043, + "step": 120600 + }, + { + "epoch": 0.4, + "learning_rate": 3.000033139467449e-05, + "loss": 3.3097, + "step": 120700 + }, + { + "epoch": 0.4, + "learning_rate": 2.998376166095011e-05, + "loss": 3.2932, + "step": 120800 + }, + { + "epoch": 0.4, + "learning_rate": 2.996719192722573e-05, + "loss": 3.295, + "step": 120900 + }, + { + "epoch": 0.4, + "learning_rate": 2.9950622193501354e-05, + "loss": 3.2985, + "step": 121000 }, { "epoch": 0.4, - "learning_rate": 2.9992932382893512e-05, - "loss": 3.1722, - "step": 112100 + "learning_rate": 2.9934052459776972e-05, + "loss": 3.3072, + "step": 121100 }, { "epoch": 0.4, - "learning_rate": 2.9975084864947833e-05, - "loss": 3.1668, - "step": 112200 + "learning_rate": 2.9917482726052594e-05, + "loss": 3.3072, + "step": 121200 }, { "epoch": 0.4, - "learning_rate": 2.9957237347002154e-05, - "loss": 3.1858, - "step": 112300 + "learning_rate": 2.990091299232822e-05, + "loss": 3.2897, + "step": 121300 }, { "epoch": 0.4, - "learning_rate": 2.9939389829056475e-05, - "loss": 3.1693, - "step": 112400 + "learning_rate": 2.9884343258603837e-05, + "loss": 3.2973, + "step": 121400 }, { "epoch": 0.4, - "learning_rate": 2.9921542311110797e-05, - "loss": 3.1751, - "step": 112500 + "learning_rate": 2.9867773524879455e-05, + "loss": 3.2913, + "step": 121500 }, { "epoch": 0.4, - "learning_rate": 2.9903694793165114e-05, - "loss": 3.1793, - "step": 112600 + "learning_rate": 2.985120379115508e-05, + "loss": 3.2964, + "step": 121600 }, { "epoch": 0.4, - "learning_rate": 2.9885847275219436e-05, - "loss": 3.1691, - "step": 112700 + "learning_rate": 2.98346340574307e-05, + "loss": 3.3007, + "step": 121700 }, { "epoch": 0.4, - "learning_rate": 2.9867999757273757e-05, - "loss": 3.1719, - "step": 112800 + "learning_rate": 2.981806432370632e-05, + "loss": 3.2948, + "step": 121800 }, { "epoch": 0.4, - "learning_rate": 2.9850152239328078e-05, - "loss": 3.1794, - "step": 112900 + "learning_rate": 2.9801494589981944e-05, + "loss": 3.3018, + "step": 121900 }, { "epoch": 0.4, - "learning_rate": 2.98323047213824e-05, - "loss": 3.1732, - "step": 113000 + "learning_rate": 2.9784924856257562e-05, + "loss": 3.3179, + "step": 122000 }, { "epoch": 0.4, - "learning_rate": 2.9814457203436717e-05, - "loss": 3.179, - "step": 113100 + "learning_rate": 2.976835512253318e-05, + "loss": 3.3006, + "step": 122100 }, { "epoch": 0.4, - "learning_rate": 2.9796609685491038e-05, - "loss": 3.1804, - "step": 113200 + "learning_rate": 2.97517853888088e-05, + "loss": 3.3017, + "step": 122200 }, { - "epoch": 0.4, - "learning_rate": 2.977876216754536e-05, - "loss": 3.1677, - "step": 113300 + "epoch": 0.41, + "learning_rate": 2.9735215655084426e-05, + "loss": 3.3056, + "step": 122300 }, { - "epoch": 0.4, - "learning_rate": 2.976091464959968e-05, - "loss": 3.1814, - "step": 113400 + "epoch": 0.41, + "learning_rate": 2.9718645921360044e-05, + "loss": 3.3028, + "step": 122400 }, { "epoch": 0.41, - "learning_rate": 2.9743067131654002e-05, - "loss": 3.1702, - "step": 113500 + "learning_rate": 2.9702076187635663e-05, + "loss": 3.2979, + "step": 122500 }, { "epoch": 0.41, - "learning_rate": 2.9725219613708323e-05, - "loss": 3.1731, - "step": 113600 + "learning_rate": 2.9685506453911287e-05, + "loss": 3.3089, + "step": 122600 }, { "epoch": 0.41, - "learning_rate": 2.970737209576264e-05, - "loss": 3.1791, - "step": 113700 + "learning_rate": 2.966893672018691e-05, + "loss": 3.3045, + "step": 122700 }, { "epoch": 0.41, - "learning_rate": 2.9689524577816962e-05, - "loss": 3.1714, - "step": 113800 + "learning_rate": 2.9652366986462527e-05, + "loss": 3.3037, + "step": 122800 }, { "epoch": 0.41, - "learning_rate": 2.9671677059871283e-05, - "loss": 3.1621, - "step": 113900 + "learning_rate": 2.9635797252738152e-05, + "loss": 3.3018, + "step": 122900 }, { "epoch": 0.41, - "learning_rate": 2.9653829541925605e-05, - "loss": 3.1793, - "step": 114000 + "learning_rate": 2.961922751901377e-05, + "loss": 3.2884, + "step": 123000 }, { "epoch": 0.41, - "learning_rate": 2.9635982023979926e-05, - "loss": 3.1705, - "step": 114100 + "learning_rate": 2.9602657785289388e-05, + "loss": 3.3108, + "step": 123100 }, { "epoch": 0.41, - "learning_rate": 2.9618134506034244e-05, - "loss": 3.1746, - "step": 114200 + "learning_rate": 2.9586088051565013e-05, + "loss": 3.3018, + "step": 123200 }, { "epoch": 0.41, - "learning_rate": 2.9600286988088565e-05, - "loss": 3.1647, - "step": 114300 + "learning_rate": 2.9569518317840634e-05, + "loss": 3.299, + "step": 123300 }, { "epoch": 0.41, - "learning_rate": 2.9582439470142886e-05, - "loss": 3.1754, - "step": 114400 + "learning_rate": 2.9552948584116252e-05, + "loss": 3.3073, + "step": 123400 }, { "epoch": 0.41, - "learning_rate": 2.9564591952197207e-05, - "loss": 3.1798, - "step": 114500 + "learning_rate": 2.9536378850391877e-05, + "loss": 3.3112, + "step": 123500 }, { "epoch": 0.41, - "learning_rate": 2.954674443425153e-05, - "loss": 3.1742, - "step": 114600 + "learning_rate": 2.9519809116667495e-05, + "loss": 3.3004, + "step": 123600 }, { "epoch": 0.41, - "learning_rate": 2.952889691630585e-05, - "loss": 3.1638, - "step": 114700 + "learning_rate": 2.9503239382943117e-05, + "loss": 3.2962, + "step": 123700 }, { "epoch": 0.41, - "learning_rate": 2.9511049398360168e-05, - "loss": 3.1612, - "step": 114800 + "learning_rate": 2.948666964921874e-05, + "loss": 3.3026, + "step": 123800 }, { "epoch": 0.41, - "learning_rate": 2.9493201880414496e-05, - "loss": 3.1709, - "step": 114900 + "learning_rate": 2.947009991549436e-05, + "loss": 3.3034, + "step": 123900 }, { "epoch": 0.41, - "learning_rate": 2.9475354362468817e-05, - "loss": 3.1716, - "step": 115000 + "learning_rate": 2.9453530181769978e-05, + "loss": 3.3162, + "step": 124000 }, { "epoch": 0.41, - "learning_rate": 2.9457506844523135e-05, - "loss": 3.1649, - "step": 115100 + "learning_rate": 2.9436960448045603e-05, + "loss": 3.3043, + "step": 124100 }, { "epoch": 0.41, - "learning_rate": 2.9439659326577456e-05, - "loss": 3.1702, - "step": 115200 + "learning_rate": 2.942039071432122e-05, + "loss": 3.3121, + "step": 124200 }, { "epoch": 0.41, - "learning_rate": 2.9421811808631777e-05, - "loss": 3.1728, - "step": 115300 + "learning_rate": 2.9403820980596842e-05, + "loss": 3.3003, + "step": 124300 }, { "epoch": 0.41, - "learning_rate": 2.9403964290686098e-05, - "loss": 3.1636, - "step": 115400 + "learning_rate": 2.9387251246872467e-05, + "loss": 3.3004, + "step": 124400 }, { "epoch": 0.41, - "learning_rate": 2.938611677274042e-05, - "loss": 3.1749, - "step": 115500 + "learning_rate": 2.9370681513148085e-05, + "loss": 3.2974, + "step": 124500 }, { "epoch": 0.41, - "learning_rate": 2.936826925479474e-05, - "loss": 3.1665, - "step": 115600 + "learning_rate": 2.9354111779423703e-05, + "loss": 3.3003, + "step": 124600 }, { "epoch": 0.41, - "learning_rate": 2.935042173684906e-05, - "loss": 3.1793, - "step": 115700 + "learning_rate": 2.9337542045699328e-05, + "loss": 3.2996, + "step": 124700 }, { "epoch": 0.41, - "learning_rate": 2.933257421890338e-05, - "loss": 3.173, - "step": 115800 + "learning_rate": 2.932097231197495e-05, + "loss": 3.3008, + "step": 124800 }, { "epoch": 0.41, - "learning_rate": 2.93147267009577e-05, - "loss": 3.1683, - "step": 115900 + "learning_rate": 2.9304402578250568e-05, + "loss": 3.3039, + "step": 124900 }, { "epoch": 0.41, - "learning_rate": 2.9296879183012022e-05, - "loss": 3.1758, - "step": 116000 + "learning_rate": 2.9287832844526192e-05, + "loss": 3.3138, + "step": 125000 }, { "epoch": 0.41, - "learning_rate": 2.9279031665066343e-05, - "loss": 3.1732, - "step": 116100 + "learning_rate": 2.927126311080181e-05, + "loss": 3.2872, + "step": 125100 }, { "epoch": 0.41, - "learning_rate": 2.926118414712066e-05, - "loss": 3.1741, - "step": 116200 + "learning_rate": 2.925469337707743e-05, + "loss": 3.3055, + "step": 125200 }, { "epoch": 0.42, - "learning_rate": 2.9243336629174982e-05, - "loss": 3.1762, - "step": 116300 + "learning_rate": 2.9238123643353053e-05, + "loss": 3.3003, + "step": 125300 }, { "epoch": 0.42, - "learning_rate": 2.9225489111229304e-05, - "loss": 3.1749, - "step": 116400 + "learning_rate": 2.9221553909628675e-05, + "loss": 3.2977, + "step": 125400 }, { "epoch": 0.42, - "learning_rate": 2.9207641593283625e-05, - "loss": 3.1662, - "step": 116500 + "learning_rate": 2.9204984175904293e-05, + "loss": 3.297, + "step": 125500 }, { "epoch": 0.42, - "learning_rate": 2.9189794075337946e-05, - "loss": 3.1723, - "step": 116600 + "learning_rate": 2.9188414442179918e-05, + "loss": 3.3013, + "step": 125600 }, { "epoch": 0.42, - "learning_rate": 2.9171946557392267e-05, - "loss": 3.1796, - "step": 116700 + "learning_rate": 2.9171844708455536e-05, + "loss": 3.3002, + "step": 125700 }, { "epoch": 0.42, - "learning_rate": 2.9154099039446585e-05, - "loss": 3.1739, - "step": 116800 + "learning_rate": 2.9155274974731157e-05, + "loss": 3.3054, + "step": 125800 }, { "epoch": 0.42, - "learning_rate": 2.9136251521500906e-05, - "loss": 3.1753, - "step": 116900 + "learning_rate": 2.9138705241006782e-05, + "loss": 3.3099, + "step": 125900 }, { "epoch": 0.42, - "learning_rate": 2.9118404003555228e-05, - "loss": 3.1769, - "step": 117000 + "learning_rate": 2.91221355072824e-05, + "loss": 3.3053, + "step": 126000 }, { "epoch": 0.42, - "learning_rate": 2.910055648560955e-05, - "loss": 3.165, - "step": 117100 + "learning_rate": 2.910556577355802e-05, + "loss": 3.3099, + "step": 126100 }, { "epoch": 0.42, - "learning_rate": 2.908270896766387e-05, - "loss": 3.1617, - "step": 117200 + "learning_rate": 2.9088996039833643e-05, + "loss": 3.2849, + "step": 126200 }, { "epoch": 0.42, - "learning_rate": 2.9064861449718188e-05, - "loss": 3.1577, - "step": 117300 + "learning_rate": 2.907242630610926e-05, + "loss": 3.3061, + "step": 126300 }, { "epoch": 0.42, - "learning_rate": 2.904701393177251e-05, - "loss": 3.1666, - "step": 117400 + "learning_rate": 2.9055856572384883e-05, + "loss": 3.3076, + "step": 126400 }, { "epoch": 0.42, - "learning_rate": 2.902916641382683e-05, - "loss": 3.1775, - "step": 117500 + "learning_rate": 2.9039286838660508e-05, + "loss": 3.306, + "step": 126500 }, { "epoch": 0.42, - "learning_rate": 2.901131889588115e-05, - "loss": 3.1714, - "step": 117600 + "learning_rate": 2.9022717104936126e-05, + "loss": 3.3118, + "step": 126600 }, { "epoch": 0.42, - "learning_rate": 2.8993471377935473e-05, - "loss": 3.1781, - "step": 117700 + "learning_rate": 2.9006147371211744e-05, + "loss": 3.2876, + "step": 126700 }, { "epoch": 0.42, - "learning_rate": 2.8975623859989794e-05, - "loss": 3.1724, - "step": 117800 + "learning_rate": 2.898957763748737e-05, + "loss": 3.3001, + "step": 126800 }, { "epoch": 0.42, - "learning_rate": 2.895777634204411e-05, - "loss": 3.1674, - "step": 117900 + "learning_rate": 2.897300790376299e-05, + "loss": 3.2971, + "step": 126900 }, { "epoch": 0.42, - "learning_rate": 2.8939928824098433e-05, - "loss": 3.1537, - "step": 118000 + "learning_rate": 2.8956438170038608e-05, + "loss": 3.3094, + "step": 127000 }, { "epoch": 0.42, - "learning_rate": 2.8922081306152754e-05, - "loss": 3.1687, - "step": 118100 + "learning_rate": 2.8939868436314233e-05, + "loss": 3.3123, + "step": 127100 }, { "epoch": 0.42, - "learning_rate": 2.8904233788207075e-05, - "loss": 3.1711, - "step": 118200 + "learning_rate": 2.892329870258985e-05, + "loss": 3.2966, + "step": 127200 }, { "epoch": 0.42, - "learning_rate": 2.8886386270261397e-05, - "loss": 3.1675, - "step": 118300 + "learning_rate": 2.890672896886547e-05, + "loss": 3.3004, + "step": 127300 }, { "epoch": 0.42, - "learning_rate": 2.8868538752315714e-05, - "loss": 3.1691, - "step": 118400 + "learning_rate": 2.889015923514109e-05, + "loss": 3.295, + "step": 127400 }, { "epoch": 0.42, - "learning_rate": 2.8850691234370036e-05, - "loss": 3.1676, - "step": 118500 + "learning_rate": 2.8873589501416716e-05, + "loss": 3.2953, + "step": 127500 }, { "epoch": 0.42, - "learning_rate": 2.8832843716424357e-05, - "loss": 3.1704, - "step": 118600 + "learning_rate": 2.8857019767692334e-05, + "loss": 3.2945, + "step": 127600 }, { "epoch": 0.42, - "learning_rate": 2.8814996198478678e-05, - "loss": 3.1751, - "step": 118700 + "learning_rate": 2.8840450033967952e-05, + "loss": 3.287, + "step": 127700 }, { "epoch": 0.42, - "learning_rate": 2.8797148680533e-05, - "loss": 3.1686, - "step": 118800 + "learning_rate": 2.8823880300243577e-05, + "loss": 3.2975, + "step": 127800 }, { "epoch": 0.42, - "learning_rate": 2.877930116258732e-05, - "loss": 3.1745, - "step": 118900 + "learning_rate": 2.8807310566519198e-05, + "loss": 3.3091, + "step": 127900 }, { "epoch": 0.42, - "learning_rate": 2.8761453644641638e-05, - "loss": 3.1722, - "step": 119000 + "learning_rate": 2.8790740832794816e-05, + "loss": 3.3129, + "step": 128000 + }, + { + "epoch": 0.42, + "learning_rate": 2.877417109907044e-05, + "loss": 3.2858, + "step": 128100 + }, + { + "epoch": 0.42, + "learning_rate": 2.875760136534606e-05, + "loss": 3.3042, + "step": 128200 }, { "epoch": 0.43, - "learning_rate": 2.874360612669596e-05, - "loss": 3.173, - "step": 119100 + "learning_rate": 2.8741031631621677e-05, + "loss": 3.2994, + "step": 128300 }, { "epoch": 0.43, - "learning_rate": 2.872575860875028e-05, - "loss": 3.1789, - "step": 119200 + "learning_rate": 2.8724461897897302e-05, + "loss": 3.3014, + "step": 128400 }, { "epoch": 0.43, - "learning_rate": 2.8707911090804602e-05, - "loss": 3.1645, - "step": 119300 + "learning_rate": 2.8707892164172923e-05, + "loss": 3.3026, + "step": 128500 }, { "epoch": 0.43, - "learning_rate": 2.8690063572858923e-05, - "loss": 3.1638, - "step": 119400 + "learning_rate": 2.869132243044854e-05, + "loss": 3.3076, + "step": 128600 }, { "epoch": 0.43, - "learning_rate": 2.867221605491324e-05, - "loss": 3.1653, - "step": 119500 + "learning_rate": 2.8674752696724166e-05, + "loss": 3.2989, + "step": 128700 }, { "epoch": 0.43, - "learning_rate": 2.8654368536967562e-05, - "loss": 3.1658, - "step": 119600 + "learning_rate": 2.8658182962999784e-05, + "loss": 3.3039, + "step": 128800 }, { "epoch": 0.43, - "learning_rate": 2.8636521019021883e-05, - "loss": 3.1646, - "step": 119700 + "learning_rate": 2.8641613229275406e-05, + "loss": 3.2934, + "step": 128900 }, { "epoch": 0.43, - "learning_rate": 2.8618673501076205e-05, - "loss": 3.1551, - "step": 119800 + "learning_rate": 2.862504349555103e-05, + "loss": 3.2969, + "step": 129000 }, { "epoch": 0.43, - "learning_rate": 2.8600825983130526e-05, - "loss": 3.1762, - "step": 119900 + "learning_rate": 2.860847376182665e-05, + "loss": 3.3093, + "step": 129100 }, { "epoch": 0.43, - "learning_rate": 2.8582978465184847e-05, - "loss": 3.1667, - "step": 120000 + "learning_rate": 2.8591904028102267e-05, + "loss": 3.2908, + "step": 129200 }, { "epoch": 0.43, - "learning_rate": 2.856513094723917e-05, - "loss": 3.1683, - "step": 120100 + "learning_rate": 2.8575334294377892e-05, + "loss": 3.297, + "step": 129300 }, { "epoch": 0.43, - "learning_rate": 2.8547283429293493e-05, - "loss": 3.167, - "step": 120200 + "learning_rate": 2.855876456065351e-05, + "loss": 3.3002, + "step": 129400 }, { "epoch": 0.43, - "learning_rate": 2.8529435911347814e-05, - "loss": 3.1718, - "step": 120300 + "learning_rate": 2.854219482692913e-05, + "loss": 3.2863, + "step": 129500 }, { "epoch": 0.43, - "learning_rate": 2.8511588393402132e-05, - "loss": 3.1668, - "step": 120400 + "learning_rate": 2.8525625093204756e-05, + "loss": 3.298, + "step": 129600 }, { "epoch": 0.43, - "learning_rate": 2.8493740875456453e-05, - "loss": 3.166, - "step": 120500 + "learning_rate": 2.8509055359480374e-05, + "loss": 3.3069, + "step": 129700 }, { "epoch": 0.43, - "learning_rate": 2.8475893357510774e-05, - "loss": 3.1744, - "step": 120600 + "learning_rate": 2.8492485625755992e-05, + "loss": 3.3084, + "step": 129800 }, { "epoch": 0.43, - "learning_rate": 2.8458045839565096e-05, - "loss": 3.1705, - "step": 120700 + "learning_rate": 2.8475915892031617e-05, + "loss": 3.2898, + "step": 129900 }, { "epoch": 0.43, - "learning_rate": 2.8440198321619417e-05, - "loss": 3.1767, - "step": 120800 + "learning_rate": 2.845934615830724e-05, + "loss": 3.292, + "step": 130000 }, { "epoch": 0.43, - "learning_rate": 2.8422350803673735e-05, - "loss": 3.1658, - "step": 120900 + "learning_rate": 2.8442776424582857e-05, + "loss": 3.3084, + "step": 130100 }, { "epoch": 0.43, - "learning_rate": 2.8404503285728056e-05, - "loss": 3.1652, - "step": 121000 + "learning_rate": 2.842620669085848e-05, + "loss": 3.3206, + "step": 130200 }, { "epoch": 0.43, - "learning_rate": 2.8386655767782377e-05, - "loss": 3.1733, - "step": 121100 + "learning_rate": 2.84096369571341e-05, + "loss": 3.2766, + "step": 130300 }, { "epoch": 0.43, - "learning_rate": 2.8368808249836698e-05, - "loss": 3.1682, - "step": 121200 + "learning_rate": 2.839306722340972e-05, + "loss": 3.2894, + "step": 130400 }, { "epoch": 0.43, - "learning_rate": 2.835096073189102e-05, - "loss": 3.171, - "step": 121300 + "learning_rate": 2.8376497489685343e-05, + "loss": 3.2809, + "step": 130500 }, { "epoch": 0.43, - "learning_rate": 2.833311321394534e-05, - "loss": 3.1674, - "step": 121400 + "learning_rate": 2.8359927755960964e-05, + "loss": 3.2963, + "step": 130600 }, { "epoch": 0.43, - "learning_rate": 2.831526569599966e-05, - "loss": 3.1685, - "step": 121500 + "learning_rate": 2.8343358022236582e-05, + "loss": 3.2833, + "step": 130700 + }, + { + "epoch": 0.43, + "learning_rate": 2.8326788288512207e-05, + "loss": 3.3102, + "step": 130800 + }, + { + "epoch": 0.43, + "learning_rate": 2.8310218554787825e-05, + "loss": 3.2951, + "step": 130900 + }, + { + "epoch": 0.43, + "learning_rate": 2.8293648821063447e-05, + "loss": 3.2916, + "step": 131000 + }, + { + "epoch": 0.43, + "learning_rate": 2.827707908733907e-05, + "loss": 3.3017, + "step": 131100 + }, + { + "epoch": 0.43, + "learning_rate": 2.826050935361469e-05, + "loss": 3.295, + "step": 131200 + }, + { + "epoch": 0.44, + "learning_rate": 2.8243939619890308e-05, + "loss": 3.2942, + "step": 131300 }, { - "epoch": 0.43, - "learning_rate": 2.829741817805398e-05, - "loss": 3.1667, - "step": 121600 + "epoch": 0.44, + "learning_rate": 2.8227369886165932e-05, + "loss": 3.2774, + "step": 131400 }, { - "epoch": 0.43, - "learning_rate": 2.82795706601083e-05, - "loss": 3.1745, - "step": 121700 + "epoch": 0.44, + "learning_rate": 2.821080015244155e-05, + "loss": 3.2939, + "step": 131500 }, { - "epoch": 0.43, - "learning_rate": 2.8261723142162622e-05, - "loss": 3.1614, - "step": 121800 + "epoch": 0.44, + "learning_rate": 2.8194230418717172e-05, + "loss": 3.284, + "step": 131600 }, { "epoch": 0.44, - "learning_rate": 2.8243875624216943e-05, - "loss": 3.1576, - "step": 121900 + "learning_rate": 2.8177660684992797e-05, + "loss": 3.2989, + "step": 131700 }, { "epoch": 0.44, - "learning_rate": 2.822602810627126e-05, - "loss": 3.1671, - "step": 122000 + "learning_rate": 2.8161090951268415e-05, + "loss": 3.2836, + "step": 131800 }, { "epoch": 0.44, - "learning_rate": 2.8208180588325582e-05, - "loss": 3.1648, - "step": 122100 + "learning_rate": 2.8144521217544033e-05, + "loss": 3.306, + "step": 131900 }, { "epoch": 0.44, - "learning_rate": 2.8190333070379904e-05, - "loss": 3.1652, - "step": 122200 + "learning_rate": 2.8127951483819658e-05, + "loss": 3.2928, + "step": 132000 }, { "epoch": 0.44, - "learning_rate": 2.8172485552434225e-05, - "loss": 3.1621, - "step": 122300 + "learning_rate": 2.811138175009528e-05, + "loss": 3.2873, + "step": 132100 }, { "epoch": 0.44, - "learning_rate": 2.8154638034488546e-05, - "loss": 3.1717, - "step": 122400 + "learning_rate": 2.8094812016370897e-05, + "loss": 3.3073, + "step": 132200 }, { "epoch": 0.44, - "learning_rate": 2.8136790516542867e-05, - "loss": 3.1683, - "step": 122500 + "learning_rate": 2.8078242282646522e-05, + "loss": 3.3014, + "step": 132300 }, { "epoch": 0.44, - "learning_rate": 2.8118942998597185e-05, - "loss": 3.1694, - "step": 122600 + "learning_rate": 2.806167254892214e-05, + "loss": 3.3077, + "step": 132400 }, { "epoch": 0.44, - "learning_rate": 2.8101095480651506e-05, - "loss": 3.157, - "step": 122700 + "learning_rate": 2.8045102815197762e-05, + "loss": 3.2962, + "step": 132500 }, { "epoch": 0.44, - "learning_rate": 2.8083247962705828e-05, - "loss": 3.158, - "step": 122800 + "learning_rate": 2.802853308147338e-05, + "loss": 3.2964, + "step": 132600 }, { "epoch": 0.44, - "learning_rate": 2.806540044476015e-05, - "loss": 3.1588, - "step": 122900 + "learning_rate": 2.8011963347749005e-05, + "loss": 3.2947, + "step": 132700 }, { "epoch": 0.44, - "learning_rate": 2.804755292681447e-05, - "loss": 3.1657, - "step": 123000 + "learning_rate": 2.7995393614024623e-05, + "loss": 3.3046, + "step": 132800 }, { "epoch": 0.44, - "learning_rate": 2.8029705408868788e-05, - "loss": 3.1677, - "step": 123100 + "learning_rate": 2.797882388030024e-05, + "loss": 3.2973, + "step": 132900 }, { "epoch": 0.44, - "learning_rate": 2.801185789092311e-05, - "loss": 3.1747, - "step": 123200 + "learning_rate": 2.7962254146575866e-05, + "loss": 3.2993, + "step": 133000 }, { "epoch": 0.44, - "learning_rate": 2.799401037297743e-05, - "loss": 3.1635, - "step": 123300 + "learning_rate": 2.7945684412851487e-05, + "loss": 3.287, + "step": 133100 }, { "epoch": 0.44, - "learning_rate": 2.797616285503175e-05, - "loss": 3.1595, - "step": 123400 + "learning_rate": 2.7929114679127105e-05, + "loss": 3.3165, + "step": 133200 }, { "epoch": 0.44, - "learning_rate": 2.7958315337086073e-05, - "loss": 3.1673, - "step": 123500 + "learning_rate": 2.791254494540273e-05, + "loss": 3.3075, + "step": 133300 }, { "epoch": 0.44, - "learning_rate": 2.7940467819140394e-05, - "loss": 3.1655, - "step": 123600 + "learning_rate": 2.7895975211678348e-05, + "loss": 3.2942, + "step": 133400 }, { "epoch": 0.44, - "learning_rate": 2.792262030119471e-05, - "loss": 3.1681, - "step": 123700 + "learning_rate": 2.787940547795397e-05, + "loss": 3.3023, + "step": 133500 }, { "epoch": 0.44, - "learning_rate": 2.7904772783249033e-05, - "loss": 3.1654, - "step": 123800 + "learning_rate": 2.786283574422959e-05, + "loss": 3.2893, + "step": 133600 }, { "epoch": 0.44, - "learning_rate": 2.7886925265303354e-05, - "loss": 3.1772, - "step": 123900 + "learning_rate": 2.7846266010505213e-05, + "loss": 3.2927, + "step": 133700 }, { "epoch": 0.44, - "learning_rate": 2.7869077747357675e-05, - "loss": 3.1584, - "step": 124000 + "learning_rate": 2.782969627678083e-05, + "loss": 3.2997, + "step": 133800 }, { "epoch": 0.44, - "learning_rate": 2.7851230229411997e-05, - "loss": 3.1604, - "step": 124100 + "learning_rate": 2.7813126543056456e-05, + "loss": 3.2947, + "step": 133900 }, { "epoch": 0.44, - "learning_rate": 2.7833382711466314e-05, - "loss": 3.1598, - "step": 124200 + "learning_rate": 2.7796556809332074e-05, + "loss": 3.3037, + "step": 134000 }, { "epoch": 0.44, - "learning_rate": 2.7815535193520636e-05, - "loss": 3.1602, - "step": 124300 + "learning_rate": 2.7779987075607695e-05, + "loss": 3.2895, + "step": 134100 }, { "epoch": 0.44, - "learning_rate": 2.7797687675574957e-05, - "loss": 3.1685, - "step": 124400 + "learning_rate": 2.776341734188332e-05, + "loss": 3.3041, + "step": 134200 }, { - "epoch": 0.44, - "learning_rate": 2.7779840157629278e-05, - "loss": 3.1513, - "step": 124500 + "epoch": 0.45, + "learning_rate": 2.7746847608158938e-05, + "loss": 3.3082, + "step": 134300 }, { - "epoch": 0.44, - "learning_rate": 2.77619926396836e-05, - "loss": 3.1557, - "step": 124600 + "epoch": 0.45, + "learning_rate": 2.7730277874434556e-05, + "loss": 3.3116, + "step": 134400 }, { "epoch": 0.45, - "learning_rate": 2.774414512173792e-05, - "loss": 3.1654, - "step": 124700 + "learning_rate": 2.771370814071018e-05, + "loss": 3.287, + "step": 134500 }, { "epoch": 0.45, - "learning_rate": 2.7726297603792238e-05, - "loss": 3.1719, - "step": 124800 + "learning_rate": 2.7697138406985802e-05, + "loss": 3.3, + "step": 134600 }, { "epoch": 0.45, - "learning_rate": 2.770845008584656e-05, - "loss": 3.1577, - "step": 124900 + "learning_rate": 2.768056867326142e-05, + "loss": 3.3129, + "step": 134700 }, { "epoch": 0.45, - "learning_rate": 2.769060256790088e-05, - "loss": 3.1579, - "step": 125000 + "learning_rate": 2.7663998939537045e-05, + "loss": 3.2982, + "step": 134800 }, { "epoch": 0.45, - "learning_rate": 2.7672755049955202e-05, - "loss": 3.1739, - "step": 125100 + "learning_rate": 2.7647429205812663e-05, + "loss": 3.307, + "step": 134900 }, { "epoch": 0.45, - "learning_rate": 2.7654907532009526e-05, - "loss": 3.17, - "step": 125200 + "learning_rate": 2.763085947208828e-05, + "loss": 3.3101, + "step": 135000 }, { "epoch": 0.45, - "learning_rate": 2.7637060014063848e-05, - "loss": 3.1576, - "step": 125300 + "learning_rate": 2.7614289738363906e-05, + "loss": 3.3056, + "step": 135100 }, { "epoch": 0.45, - "learning_rate": 2.761921249611817e-05, - "loss": 3.1589, - "step": 125400 + "learning_rate": 2.7597720004639528e-05, + "loss": 3.2811, + "step": 135200 }, { "epoch": 0.45, - "learning_rate": 2.760136497817249e-05, - "loss": 3.1724, - "step": 125500 + "learning_rate": 2.7581150270915146e-05, + "loss": 3.3042, + "step": 135300 }, { "epoch": 0.45, - "learning_rate": 2.758351746022681e-05, - "loss": 3.1706, - "step": 125600 + "learning_rate": 2.756458053719077e-05, + "loss": 3.2883, + "step": 135400 }, { "epoch": 0.45, - "learning_rate": 2.756566994228113e-05, - "loss": 3.1634, - "step": 125700 + "learning_rate": 2.754801080346639e-05, + "loss": 3.2926, + "step": 135500 }, { "epoch": 0.45, - "learning_rate": 2.754782242433545e-05, - "loss": 3.162, - "step": 125800 + "learning_rate": 2.753144106974201e-05, + "loss": 3.2904, + "step": 135600 }, { "epoch": 0.45, - "learning_rate": 2.752997490638977e-05, - "loss": 3.1534, - "step": 125900 + "learning_rate": 2.7514871336017635e-05, + "loss": 3.2884, + "step": 135700 }, { "epoch": 0.45, - "learning_rate": 2.7512127388444093e-05, - "loss": 3.1611, - "step": 126000 + "learning_rate": 2.7498301602293253e-05, + "loss": 3.2853, + "step": 135800 }, { "epoch": 0.45, - "learning_rate": 2.7494279870498414e-05, - "loss": 3.1671, - "step": 126100 + "learning_rate": 2.748173186856887e-05, + "loss": 3.2871, + "step": 135900 }, { "epoch": 0.45, - "learning_rate": 2.7476432352552732e-05, - "loss": 3.157, - "step": 126200 + "learning_rate": 2.7465162134844496e-05, + "loss": 3.2896, + "step": 136000 }, { "epoch": 0.45, - "learning_rate": 2.7458584834607053e-05, - "loss": 3.1581, - "step": 126300 + "learning_rate": 2.7448592401120114e-05, + "loss": 3.2948, + "step": 136100 }, { "epoch": 0.45, - "learning_rate": 2.7440737316661374e-05, - "loss": 3.1556, - "step": 126400 + "learning_rate": 2.7432022667395736e-05, + "loss": 3.2945, + "step": 136200 }, { "epoch": 0.45, - "learning_rate": 2.7422889798715696e-05, - "loss": 3.1667, - "step": 126500 + "learning_rate": 2.741545293367136e-05, + "loss": 3.2969, + "step": 136300 }, { "epoch": 0.45, - "learning_rate": 2.7405042280770017e-05, - "loss": 3.1613, - "step": 126600 + "learning_rate": 2.739888319994698e-05, + "loss": 3.3025, + "step": 136400 }, { "epoch": 0.45, - "learning_rate": 2.7387194762824338e-05, - "loss": 3.1623, - "step": 126700 + "learning_rate": 2.7382313466222597e-05, + "loss": 3.2844, + "step": 136500 }, { "epoch": 0.45, - "learning_rate": 2.7369347244878656e-05, - "loss": 3.1496, - "step": 126800 + "learning_rate": 2.736574373249822e-05, + "loss": 3.2997, + "step": 136600 }, { "epoch": 0.45, - "learning_rate": 2.7351499726932977e-05, - "loss": 3.162, - "step": 126900 + "learning_rate": 2.7349173998773843e-05, + "loss": 3.2959, + "step": 136700 }, { "epoch": 0.45, - "learning_rate": 2.7333652208987298e-05, - "loss": 3.1639, - "step": 127000 + "learning_rate": 2.733260426504946e-05, + "loss": 3.2987, + "step": 136800 }, { "epoch": 0.45, - "learning_rate": 2.731580469104162e-05, - "loss": 3.1592, - "step": 127100 + "learning_rate": 2.7316034531325086e-05, + "loss": 3.2923, + "step": 136900 }, { "epoch": 0.45, - "learning_rate": 2.729795717309594e-05, - "loss": 3.1566, - "step": 127200 + "learning_rate": 2.7299464797600704e-05, + "loss": 3.2997, + "step": 137000 }, { "epoch": 0.45, - "learning_rate": 2.728010965515026e-05, - "loss": 3.1658, - "step": 127300 + "learning_rate": 2.7282895063876322e-05, + "loss": 3.297, + "step": 137100 }, { "epoch": 0.45, - "learning_rate": 2.726226213720458e-05, - "loss": 3.1633, - "step": 127400 + "learning_rate": 2.7266325330151947e-05, + "loss": 3.2881, + "step": 137200 }, { "epoch": 0.46, - "learning_rate": 2.72444146192589e-05, - "loss": 3.1633, - "step": 127500 + "learning_rate": 2.724975559642757e-05, + "loss": 3.2917, + "step": 137300 }, { "epoch": 0.46, - "learning_rate": 2.7226567101313222e-05, - "loss": 3.1606, - "step": 127600 + "learning_rate": 2.7233185862703187e-05, + "loss": 3.3049, + "step": 137400 }, { "epoch": 0.46, - "learning_rate": 2.7208719583367543e-05, - "loss": 3.1638, - "step": 127700 + "learning_rate": 2.721661612897881e-05, + "loss": 3.298, + "step": 137500 }, { "epoch": 0.46, - "learning_rate": 2.7190872065421865e-05, - "loss": 3.1594, - "step": 127800 + "learning_rate": 2.720004639525443e-05, + "loss": 3.2935, + "step": 137600 }, { "epoch": 0.46, - "learning_rate": 2.7173024547476182e-05, - "loss": 3.1618, - "step": 127900 + "learning_rate": 2.718347666153005e-05, + "loss": 3.2981, + "step": 137700 }, { "epoch": 0.46, - "learning_rate": 2.7155177029530504e-05, - "loss": 3.1506, - "step": 128000 + "learning_rate": 2.716690692780567e-05, + "loss": 3.2924, + "step": 137800 }, { "epoch": 0.46, - "learning_rate": 2.7137329511584825e-05, - "loss": 3.1667, - "step": 128100 + "learning_rate": 2.7150337194081294e-05, + "loss": 3.2931, + "step": 137900 }, { "epoch": 0.46, - "learning_rate": 2.7119481993639146e-05, - "loss": 3.1594, - "step": 128200 + "learning_rate": 2.7133767460356912e-05, + "loss": 3.2874, + "step": 138000 }, { "epoch": 0.46, - "learning_rate": 2.7101634475693467e-05, - "loss": 3.1693, - "step": 128300 + "learning_rate": 2.711719772663253e-05, + "loss": 3.302, + "step": 138100 }, { "epoch": 0.46, - "learning_rate": 2.7083786957747785e-05, - "loss": 3.1665, - "step": 128400 + "learning_rate": 2.7100627992908155e-05, + "loss": 3.2783, + "step": 138200 }, { "epoch": 0.46, - "learning_rate": 2.7065939439802106e-05, - "loss": 3.1481, - "step": 128500 + "learning_rate": 2.7084058259183776e-05, + "loss": 3.2954, + "step": 138300 }, { "epoch": 0.46, - "learning_rate": 2.7048091921856427e-05, - "loss": 3.1704, - "step": 128600 + "learning_rate": 2.7067488525459394e-05, + "loss": 3.2982, + "step": 138400 }, { "epoch": 0.46, - "learning_rate": 2.703024440391075e-05, - "loss": 3.1653, - "step": 128700 + "learning_rate": 2.705091879173502e-05, + "loss": 3.2864, + "step": 138500 }, { "epoch": 0.46, - "learning_rate": 2.701239688596507e-05, - "loss": 3.1743, - "step": 128800 + "learning_rate": 2.7034349058010637e-05, + "loss": 3.2909, + "step": 138600 }, { "epoch": 0.46, - "learning_rate": 2.699454936801939e-05, - "loss": 3.1577, - "step": 128900 + "learning_rate": 2.701777932428626e-05, + "loss": 3.2948, + "step": 138700 }, { "epoch": 0.46, - "learning_rate": 2.697670185007371e-05, - "loss": 3.1549, - "step": 129000 + "learning_rate": 2.7001209590561884e-05, + "loss": 3.3039, + "step": 138800 }, { "epoch": 0.46, - "learning_rate": 2.695885433212803e-05, - "loss": 3.1582, - "step": 129100 + "learning_rate": 2.6984639856837502e-05, + "loss": 3.2887, + "step": 138900 }, { "epoch": 0.46, - "learning_rate": 2.694100681418235e-05, - "loss": 3.1654, - "step": 129200 + "learning_rate": 2.696807012311312e-05, + "loss": 3.2984, + "step": 139000 }, { "epoch": 0.46, - "learning_rate": 2.6923159296236673e-05, - "loss": 3.1718, - "step": 129300 + "learning_rate": 2.6951500389388745e-05, + "loss": 3.2995, + "step": 139100 }, { "epoch": 0.46, - "learning_rate": 2.6905311778290994e-05, - "loss": 3.1534, - "step": 129400 + "learning_rate": 2.6934930655664363e-05, + "loss": 3.3007, + "step": 139200 }, { "epoch": 0.46, - "learning_rate": 2.688746426034531e-05, - "loss": 3.1474, - "step": 129500 + "learning_rate": 2.6918360921939984e-05, + "loss": 3.2884, + "step": 139300 }, { "epoch": 0.46, - "learning_rate": 2.6869616742399633e-05, - "loss": 3.1659, - "step": 129600 + "learning_rate": 2.690179118821561e-05, + "loss": 3.2854, + "step": 139400 }, { "epoch": 0.46, - "learning_rate": 2.6851769224453954e-05, - "loss": 3.1526, - "step": 129700 + "learning_rate": 2.6885221454491227e-05, + "loss": 3.2984, + "step": 139500 }, { "epoch": 0.46, - "learning_rate": 2.6833921706508275e-05, - "loss": 3.1733, - "step": 129800 + "learning_rate": 2.6868651720766845e-05, + "loss": 3.2921, + "step": 139600 }, { "epoch": 0.46, - "learning_rate": 2.6816074188562596e-05, - "loss": 3.1517, - "step": 129900 + "learning_rate": 2.685208198704247e-05, + "loss": 3.2915, + "step": 139700 }, { "epoch": 0.46, - "learning_rate": 2.6798226670616918e-05, - "loss": 3.1565, - "step": 130000 + "learning_rate": 2.683551225331809e-05, + "loss": 3.2999, + "step": 139800 }, { "epoch": 0.46, - "learning_rate": 2.6780379152671236e-05, - "loss": 3.16, - "step": 130100 + "learning_rate": 2.681894251959371e-05, + "loss": 3.3036, + "step": 139900 }, { "epoch": 0.46, - "learning_rate": 2.6762531634725557e-05, - "loss": 3.1737, - "step": 130200 + "learning_rate": 2.6802372785869335e-05, + "loss": 3.2935, + "step": 140000 + }, + { + "epoch": 0.46, + "learning_rate": 2.6785803052144953e-05, + "loss": 3.2907, + "step": 140100 + }, + { + "epoch": 0.46, + "learning_rate": 2.676923331842057e-05, + "loss": 3.2788, + "step": 140200 + }, + { + "epoch": 0.46, + "learning_rate": 2.6752663584696196e-05, + "loss": 3.2891, + "step": 140300 }, { "epoch": 0.47, - "learning_rate": 2.6744684116779885e-05, - "loss": 3.16, - "step": 130300 + "learning_rate": 2.6736093850971817e-05, + "loss": 3.3041, + "step": 140400 }, { "epoch": 0.47, - "learning_rate": 2.6726836598834203e-05, - "loss": 3.1614, - "step": 130400 + "learning_rate": 2.6719524117247435e-05, + "loss": 3.2928, + "step": 140500 }, { "epoch": 0.47, - "learning_rate": 2.6708989080888524e-05, - "loss": 3.1613, - "step": 130500 + "learning_rate": 2.670295438352306e-05, + "loss": 3.3077, + "step": 140600 }, { "epoch": 0.47, - "learning_rate": 2.6691141562942845e-05, - "loss": 3.1545, - "step": 130600 + "learning_rate": 2.6686384649798678e-05, + "loss": 3.2869, + "step": 140700 }, { "epoch": 0.47, - "learning_rate": 2.6673294044997166e-05, - "loss": 3.1672, - "step": 130700 + "learning_rate": 2.66698149160743e-05, + "loss": 3.2886, + "step": 140800 }, { "epoch": 0.47, - "learning_rate": 2.6655446527051487e-05, - "loss": 3.1642, - "step": 130800 + "learning_rate": 2.6653245182349924e-05, + "loss": 3.3035, + "step": 140900 }, { "epoch": 0.47, - "learning_rate": 2.663759900910581e-05, - "loss": 3.1541, - "step": 130900 + "learning_rate": 2.6636675448625542e-05, + "loss": 3.2928, + "step": 141000 }, { "epoch": 0.47, - "learning_rate": 2.6619751491160126e-05, - "loss": 3.1526, - "step": 131000 + "learning_rate": 2.662010571490116e-05, + "loss": 3.3072, + "step": 141100 }, { "epoch": 0.47, - "learning_rate": 2.6601903973214448e-05, - "loss": 3.1584, - "step": 131100 + "learning_rate": 2.6603535981176785e-05, + "loss": 3.306, + "step": 141200 }, { "epoch": 0.47, - "learning_rate": 2.658405645526877e-05, - "loss": 3.1569, - "step": 131200 + "learning_rate": 2.6586966247452403e-05, + "loss": 3.2948, + "step": 141300 }, { "epoch": 0.47, - "learning_rate": 2.656620893732309e-05, - "loss": 3.1637, - "step": 131300 + "learning_rate": 2.6570396513728025e-05, + "loss": 3.2868, + "step": 141400 }, { "epoch": 0.47, - "learning_rate": 2.654836141937741e-05, - "loss": 3.1638, - "step": 131400 + "learning_rate": 2.655382678000365e-05, + "loss": 3.2869, + "step": 141500 }, { "epoch": 0.47, - "learning_rate": 2.653051390143173e-05, - "loss": 3.1619, - "step": 131500 + "learning_rate": 2.6537257046279268e-05, + "loss": 3.3043, + "step": 141600 + }, + { + "epoch": 0.47, + "learning_rate": 2.6520687312554886e-05, + "loss": 3.2986, + "step": 141700 + }, + { + "epoch": 0.47, + "learning_rate": 2.650411757883051e-05, + "loss": 3.3005, + "step": 141800 + }, + { + "epoch": 0.47, + "learning_rate": 2.6487547845106132e-05, + "loss": 3.2924, + "step": 141900 + }, + { + "epoch": 0.47, + "learning_rate": 2.647097811138175e-05, + "loss": 3.3035, + "step": 142000 }, { "epoch": 0.47, - "learning_rate": 2.651266638348605e-05, - "loss": 3.1565, - "step": 131600 + "learning_rate": 2.6454408377657375e-05, + "loss": 3.301, + "step": 142100 }, { "epoch": 0.47, - "learning_rate": 2.649481886554037e-05, - "loss": 3.1536, - "step": 131700 + "learning_rate": 2.6437838643932993e-05, + "loss": 3.297, + "step": 142200 }, { "epoch": 0.47, - "learning_rate": 2.6476971347594693e-05, - "loss": 3.155, - "step": 131800 + "learning_rate": 2.642126891020861e-05, + "loss": 3.2985, + "step": 142300 }, { "epoch": 0.47, - "learning_rate": 2.6459123829649014e-05, - "loss": 3.1646, - "step": 131900 + "learning_rate": 2.6404699176484236e-05, + "loss": 3.2917, + "step": 142400 }, { "epoch": 0.47, - "learning_rate": 2.6441276311703332e-05, - "loss": 3.1573, - "step": 132000 + "learning_rate": 2.6388129442759858e-05, + "loss": 3.2863, + "step": 142500 }, { "epoch": 0.47, - "learning_rate": 2.6423428793757653e-05, - "loss": 3.1705, - "step": 132100 + "learning_rate": 2.6371559709035476e-05, + "loss": 3.3015, + "step": 142600 }, { "epoch": 0.47, - "learning_rate": 2.6405581275811974e-05, - "loss": 3.161, - "step": 132200 + "learning_rate": 2.63549899753111e-05, + "loss": 3.2924, + "step": 142700 }, { "epoch": 0.47, - "learning_rate": 2.6387733757866295e-05, - "loss": 3.1536, - "step": 132300 + "learning_rate": 2.633842024158672e-05, + "loss": 3.2887, + "step": 142800 }, { "epoch": 0.47, - "learning_rate": 2.6369886239920617e-05, - "loss": 3.168, - "step": 132400 + "learning_rate": 2.632185050786234e-05, + "loss": 3.2985, + "step": 142900 }, { "epoch": 0.47, - "learning_rate": 2.6352038721974938e-05, - "loss": 3.1695, - "step": 132500 + "learning_rate": 2.6305280774137958e-05, + "loss": 3.2949, + "step": 143000 }, { "epoch": 0.47, - "learning_rate": 2.6334191204029256e-05, - "loss": 3.1461, - "step": 132600 + "learning_rate": 2.6288711040413583e-05, + "loss": 3.2983, + "step": 143100 }, { "epoch": 0.47, - "learning_rate": 2.6316343686083577e-05, - "loss": 3.1602, - "step": 132700 + "learning_rate": 2.62721413066892e-05, + "loss": 3.292, + "step": 143200 }, { "epoch": 0.47, - "learning_rate": 2.6298496168137898e-05, - "loss": 3.1646, - "step": 132800 + "learning_rate": 2.6255571572964823e-05, + "loss": 3.2996, + "step": 143300 }, { - "epoch": 0.47, - "learning_rate": 2.628064865019222e-05, - "loss": 3.1667, - "step": 132900 + "epoch": 0.48, + "learning_rate": 2.6239001839240444e-05, + "loss": 3.294, + "step": 143400 }, { - "epoch": 0.47, - "learning_rate": 2.626280113224654e-05, - "loss": 3.1618, - "step": 133000 + "epoch": 0.48, + "learning_rate": 2.6222432105516066e-05, + "loss": 3.2952, + "step": 143500 }, { "epoch": 0.48, - "learning_rate": 2.624495361430086e-05, - "loss": 3.1527, - "step": 133100 + "learning_rate": 2.6205862371791684e-05, + "loss": 3.2972, + "step": 143600 }, { "epoch": 0.48, - "learning_rate": 2.622710609635518e-05, - "loss": 3.1602, - "step": 133200 + "learning_rate": 2.618929263806731e-05, + "loss": 3.2853, + "step": 143700 }, { "epoch": 0.48, - "learning_rate": 2.62092585784095e-05, - "loss": 3.1727, - "step": 133300 + "learning_rate": 2.6172722904342927e-05, + "loss": 3.2903, + "step": 143800 }, { "epoch": 0.48, - "learning_rate": 2.6191411060463822e-05, - "loss": 3.1501, - "step": 133400 + "learning_rate": 2.6156153170618548e-05, + "loss": 3.3031, + "step": 143900 }, { "epoch": 0.48, - "learning_rate": 2.6173563542518143e-05, - "loss": 3.1505, - "step": 133500 + "learning_rate": 2.6139583436894173e-05, + "loss": 3.3021, + "step": 144000 }, { "epoch": 0.48, - "learning_rate": 2.6155716024572465e-05, - "loss": 3.1689, - "step": 133600 + "learning_rate": 2.612301370316979e-05, + "loss": 3.2952, + "step": 144100 }, { "epoch": 0.48, - "learning_rate": 2.6137868506626782e-05, - "loss": 3.1533, - "step": 133700 + "learning_rate": 2.610644396944541e-05, + "loss": 3.2861, + "step": 144200 }, { "epoch": 0.48, - "learning_rate": 2.6120020988681104e-05, - "loss": 3.1625, - "step": 133800 + "learning_rate": 2.6089874235721034e-05, + "loss": 3.2972, + "step": 144300 }, { "epoch": 0.48, - "learning_rate": 2.6102173470735425e-05, - "loss": 3.1578, - "step": 133900 + "learning_rate": 2.6073304501996655e-05, + "loss": 3.2912, + "step": 144400 }, { "epoch": 0.48, - "learning_rate": 2.6084325952789746e-05, - "loss": 3.1581, - "step": 134000 + "learning_rate": 2.6056734768272273e-05, + "loss": 3.2879, + "step": 144500 }, { "epoch": 0.48, - "learning_rate": 2.6066478434844067e-05, - "loss": 3.1673, - "step": 134100 + "learning_rate": 2.60401650345479e-05, + "loss": 3.2874, + "step": 144600 }, { "epoch": 0.48, - "learning_rate": 2.6048630916898385e-05, - "loss": 3.1639, - "step": 134200 + "learning_rate": 2.6023595300823516e-05, + "loss": 3.3032, + "step": 144700 }, { "epoch": 0.48, - "learning_rate": 2.6030783398952706e-05, - "loss": 3.1584, - "step": 134300 + "learning_rate": 2.6007025567099134e-05, + "loss": 3.3037, + "step": 144800 }, { "epoch": 0.48, - "learning_rate": 2.6012935881007027e-05, - "loss": 3.1561, - "step": 134400 + "learning_rate": 2.599045583337476e-05, + "loss": 3.2904, + "step": 144900 }, { "epoch": 0.48, - "learning_rate": 2.599508836306135e-05, - "loss": 3.1571, - "step": 134500 + "learning_rate": 2.597388609965038e-05, + "loss": 3.2851, + "step": 145000 }, { "epoch": 0.48, - "learning_rate": 2.597724084511567e-05, - "loss": 3.158, - "step": 134600 + "learning_rate": 2.5957316365926e-05, + "loss": 3.2855, + "step": 145100 }, { "epoch": 0.48, - "learning_rate": 2.595939332716999e-05, - "loss": 3.1506, - "step": 134700 + "learning_rate": 2.5940746632201624e-05, + "loss": 3.2909, + "step": 145200 }, { "epoch": 0.48, - "learning_rate": 2.594154580922431e-05, - "loss": 3.1623, - "step": 134800 + "learning_rate": 2.5924176898477242e-05, + "loss": 3.2836, + "step": 145300 }, { "epoch": 0.48, - "learning_rate": 2.592369829127863e-05, - "loss": 3.1561, - "step": 134900 + "learning_rate": 2.5907607164752863e-05, + "loss": 3.2945, + "step": 145400 }, { "epoch": 0.48, - "learning_rate": 2.590585077333295e-05, - "loss": 3.1617, - "step": 135000 + "learning_rate": 2.5891037431028485e-05, + "loss": 3.2933, + "step": 145500 }, { "epoch": 0.48, - "learning_rate": 2.5888003255387273e-05, - "loss": 3.1482, - "step": 135100 + "learning_rate": 2.5874467697304106e-05, + "loss": 3.2878, + "step": 145600 }, { "epoch": 0.48, - "learning_rate": 2.5870155737441594e-05, - "loss": 3.1535, - "step": 135200 + "learning_rate": 2.5857897963579724e-05, + "loss": 3.2908, + "step": 145700 }, { "epoch": 0.48, - "learning_rate": 2.585230821949591e-05, - "loss": 3.1606, - "step": 135300 + "learning_rate": 2.584132822985535e-05, + "loss": 3.3071, + "step": 145800 }, { "epoch": 0.48, - "learning_rate": 2.583446070155024e-05, - "loss": 3.1615, - "step": 135400 + "learning_rate": 2.5824758496130967e-05, + "loss": 3.2979, + "step": 145900 }, { "epoch": 0.48, - "learning_rate": 2.581661318360456e-05, - "loss": 3.1529, - "step": 135500 + "learning_rate": 2.580818876240659e-05, + "loss": 3.2947, + "step": 146000 }, { "epoch": 0.48, - "learning_rate": 2.5798765665658882e-05, - "loss": 3.1498, - "step": 135600 + "learning_rate": 2.5791619028682214e-05, + "loss": 3.2876, + "step": 146100 }, { "epoch": 0.48, - "learning_rate": 2.57809181477132e-05, - "loss": 3.146, - "step": 135700 + "learning_rate": 2.577504929495783e-05, + "loss": 3.2871, + "step": 146200 }, { "epoch": 0.48, - "learning_rate": 2.576307062976752e-05, - "loss": 3.1705, - "step": 135800 + "learning_rate": 2.575847956123345e-05, + "loss": 3.2901, + "step": 146300 }, { "epoch": 0.49, - "learning_rate": 2.5745223111821842e-05, - "loss": 3.1565, - "step": 135900 + "learning_rate": 2.5741909827509075e-05, + "loss": 3.2882, + "step": 146400 }, { "epoch": 0.49, - "learning_rate": 2.5727375593876163e-05, - "loss": 3.1589, - "step": 136000 + "learning_rate": 2.5725340093784696e-05, + "loss": 3.2812, + "step": 146500 }, { "epoch": 0.49, - "learning_rate": 2.5709528075930485e-05, - "loss": 3.1657, - "step": 136100 + "learning_rate": 2.5708770360060314e-05, + "loss": 3.2955, + "step": 146600 }, { "epoch": 0.49, - "learning_rate": 2.5691680557984803e-05, - "loss": 3.1591, - "step": 136200 + "learning_rate": 2.569220062633594e-05, + "loss": 3.2957, + "step": 146700 }, { "epoch": 0.49, - "learning_rate": 2.5673833040039124e-05, - "loss": 3.1656, - "step": 136300 + "learning_rate": 2.5675630892611557e-05, + "loss": 3.286, + "step": 146800 }, { "epoch": 0.49, - "learning_rate": 2.5655985522093445e-05, - "loss": 3.1583, - "step": 136400 + "learning_rate": 2.5659061158887175e-05, + "loss": 3.285, + "step": 146900 }, { "epoch": 0.49, - "learning_rate": 2.5638138004147766e-05, - "loss": 3.157, - "step": 136500 + "learning_rate": 2.56424914251628e-05, + "loss": 3.2879, + "step": 147000 }, { "epoch": 0.49, - "learning_rate": 2.5620290486202087e-05, - "loss": 3.1524, - "step": 136600 + "learning_rate": 2.562592169143842e-05, + "loss": 3.2942, + "step": 147100 }, { "epoch": 0.49, - "learning_rate": 2.560244296825641e-05, - "loss": 3.1556, - "step": 136700 + "learning_rate": 2.560935195771404e-05, + "loss": 3.2856, + "step": 147200 }, { "epoch": 0.49, - "learning_rate": 2.5584595450310726e-05, - "loss": 3.1622, - "step": 136800 + "learning_rate": 2.5592782223989664e-05, + "loss": 3.2979, + "step": 147300 }, { "epoch": 0.49, - "learning_rate": 2.5566747932365048e-05, - "loss": 3.15, - "step": 136900 + "learning_rate": 2.5576212490265282e-05, + "loss": 3.2765, + "step": 147400 }, { "epoch": 0.49, - "learning_rate": 2.554890041441937e-05, - "loss": 3.157, - "step": 137000 + "learning_rate": 2.5559642756540904e-05, + "loss": 3.2969, + "step": 147500 }, { "epoch": 0.49, - "learning_rate": 2.553105289647369e-05, - "loss": 3.1574, - "step": 137100 + "learning_rate": 2.554307302281653e-05, + "loss": 3.2849, + "step": 147600 }, { "epoch": 0.49, - "learning_rate": 2.551320537852801e-05, - "loss": 3.1585, - "step": 137200 + "learning_rate": 2.5526503289092147e-05, + "loss": 3.2956, + "step": 147700 }, { "epoch": 0.49, - "learning_rate": 2.549535786058233e-05, - "loss": 3.1605, - "step": 137300 + "learning_rate": 2.5509933555367765e-05, + "loss": 3.3014, + "step": 147800 }, { "epoch": 0.49, - "learning_rate": 2.547751034263665e-05, - "loss": 3.1476, - "step": 137400 + "learning_rate": 2.549336382164339e-05, + "loss": 3.2756, + "step": 147900 }, { "epoch": 0.49, - "learning_rate": 2.545966282469097e-05, - "loss": 3.1449, - "step": 137500 + "learning_rate": 2.5476794087919008e-05, + "loss": 3.2808, + "step": 148000 }, { "epoch": 0.49, - "learning_rate": 2.5441815306745293e-05, - "loss": 3.1583, - "step": 137600 + "learning_rate": 2.546022435419463e-05, + "loss": 3.2833, + "step": 148100 }, { "epoch": 0.49, - "learning_rate": 2.5423967788799614e-05, - "loss": 3.1563, - "step": 137700 + "learning_rate": 2.5443654620470247e-05, + "loss": 3.2976, + "step": 148200 }, { "epoch": 0.49, - "learning_rate": 2.5406120270853935e-05, - "loss": 3.1353, - "step": 137800 + "learning_rate": 2.5427084886745872e-05, + "loss": 3.2927, + "step": 148300 }, { "epoch": 0.49, - "learning_rate": 2.5388272752908253e-05, - "loss": 3.1655, - "step": 137900 + "learning_rate": 2.541051515302149e-05, + "loss": 3.2825, + "step": 148400 }, { "epoch": 0.49, - "learning_rate": 2.5370425234962574e-05, - "loss": 3.1552, - "step": 138000 + "learning_rate": 2.5393945419297112e-05, + "loss": 3.2914, + "step": 148500 }, { "epoch": 0.49, - "learning_rate": 2.5352577717016895e-05, - "loss": 3.1541, - "step": 138100 + "learning_rate": 2.5377375685572737e-05, + "loss": 3.2856, + "step": 148600 }, { "epoch": 0.49, - "learning_rate": 2.5334730199071217e-05, - "loss": 3.1623, - "step": 138200 + "learning_rate": 2.5360805951848355e-05, + "loss": 3.2861, + "step": 148700 }, { "epoch": 0.49, - "learning_rate": 2.5316882681125538e-05, - "loss": 3.1473, - "step": 138300 + "learning_rate": 2.5344236218123973e-05, + "loss": 3.2758, + "step": 148800 }, { "epoch": 0.49, - "learning_rate": 2.5299035163179856e-05, - "loss": 3.1579, - "step": 138400 + "learning_rate": 2.5327666484399598e-05, + "loss": 3.2882, + "step": 148900 }, { "epoch": 0.49, - "learning_rate": 2.5281187645234177e-05, - "loss": 3.1629, - "step": 138500 + "learning_rate": 2.5311096750675216e-05, + "loss": 3.291, + "step": 149000 }, { "epoch": 0.49, - "learning_rate": 2.5263340127288498e-05, - "loss": 3.144, - "step": 138600 + "learning_rate": 2.5294527016950837e-05, + "loss": 3.2835, + "step": 149100 + }, + { + "epoch": 0.49, + "learning_rate": 2.5277957283226462e-05, + "loss": 3.2929, + "step": 149200 + }, + { + "epoch": 0.49, + "learning_rate": 2.526138754950208e-05, + "loss": 3.2892, + "step": 149300 }, { "epoch": 0.5, - "learning_rate": 2.524549260934282e-05, - "loss": 3.1604, - "step": 138700 + "learning_rate": 2.5244817815777698e-05, + "loss": 3.271, + "step": 149400 }, { "epoch": 0.5, - "learning_rate": 2.522764509139714e-05, - "loss": 3.1496, - "step": 138800 + "learning_rate": 2.5228248082053323e-05, + "loss": 3.2966, + "step": 149500 }, { "epoch": 0.5, - "learning_rate": 2.5209797573451462e-05, - "loss": 3.1497, - "step": 138900 + "learning_rate": 2.5211678348328945e-05, + "loss": 3.2979, + "step": 149600 }, { "epoch": 0.5, - "learning_rate": 2.519195005550578e-05, - "loss": 3.1447, - "step": 139000 + "learning_rate": 2.5195108614604563e-05, + "loss": 3.2853, + "step": 149700 }, { "epoch": 0.5, - "learning_rate": 2.51741025375601e-05, - "loss": 3.1546, - "step": 139100 + "learning_rate": 2.5178538880880188e-05, + "loss": 3.2897, + "step": 149800 }, { "epoch": 0.5, - "learning_rate": 2.5156255019614422e-05, - "loss": 3.1485, - "step": 139200 + "learning_rate": 2.5161969147155806e-05, + "loss": 3.2922, + "step": 149900 }, { "epoch": 0.5, - "learning_rate": 2.5138407501668743e-05, - "loss": 3.1453, - "step": 139300 + "learning_rate": 2.5145399413431424e-05, + "loss": 3.2803, + "step": 150000 }, { "epoch": 0.5, - "learning_rate": 2.5120559983723064e-05, - "loss": 3.1578, - "step": 139400 + "learning_rate": 2.512882967970705e-05, + "loss": 3.2895, + "step": 150100 }, { "epoch": 0.5, - "learning_rate": 2.5102712465777382e-05, - "loss": 3.1451, - "step": 139500 + "learning_rate": 2.511225994598267e-05, + "loss": 3.2965, + "step": 150200 }, { "epoch": 0.5, - "learning_rate": 2.5084864947831704e-05, - "loss": 3.1645, - "step": 139600 + "learning_rate": 2.5095690212258288e-05, + "loss": 3.2636, + "step": 150300 }, { "epoch": 0.5, - "learning_rate": 2.5067017429886025e-05, - "loss": 3.158, - "step": 139700 + "learning_rate": 2.5079120478533913e-05, + "loss": 3.2881, + "step": 150400 }, { "epoch": 0.5, - "learning_rate": 2.5049169911940346e-05, - "loss": 3.1573, - "step": 139800 + "learning_rate": 2.506255074480953e-05, + "loss": 3.2803, + "step": 150500 }, { "epoch": 0.5, - "learning_rate": 2.5031322393994667e-05, - "loss": 3.1553, - "step": 139900 + "learning_rate": 2.5045981011085152e-05, + "loss": 3.2805, + "step": 150600 }, { "epoch": 0.5, - "learning_rate": 2.501347487604899e-05, - "loss": 3.1643, - "step": 140000 + "learning_rate": 2.5029411277360777e-05, + "loss": 3.2854, + "step": 150700 }, { "epoch": 0.5, - "learning_rate": 2.499562735810331e-05, - "loss": 3.1625, - "step": 140100 + "learning_rate": 2.5012841543636395e-05, + "loss": 3.2914, + "step": 150800 }, { "epoch": 0.5, - "learning_rate": 2.497777984015763e-05, - "loss": 3.1536, - "step": 140200 + "learning_rate": 2.4996271809912017e-05, + "loss": 3.2876, + "step": 150900 }, { "epoch": 0.5, - "learning_rate": 2.4959932322211952e-05, - "loss": 3.1543, - "step": 140300 + "learning_rate": 2.4979702076187635e-05, + "loss": 3.2905, + "step": 151000 }, { "epoch": 0.5, - "learning_rate": 2.4942084804266273e-05, - "loss": 3.1544, - "step": 140400 + "learning_rate": 2.4963132342463256e-05, + "loss": 3.2992, + "step": 151100 }, { "epoch": 0.5, - "learning_rate": 2.492423728632059e-05, - "loss": 3.1462, - "step": 140500 + "learning_rate": 2.494656260873888e-05, + "loss": 3.2884, + "step": 151200 }, { "epoch": 0.5, - "learning_rate": 2.4906389768374912e-05, - "loss": 3.1531, - "step": 140600 + "learning_rate": 2.49299928750145e-05, + "loss": 3.2947, + "step": 151300 }, { "epoch": 0.5, - "learning_rate": 2.4888542250429233e-05, - "loss": 3.1485, - "step": 140700 + "learning_rate": 2.491342314129012e-05, + "loss": 3.3012, + "step": 151400 }, { "epoch": 0.5, - "learning_rate": 2.4870694732483555e-05, - "loss": 3.1589, - "step": 140800 + "learning_rate": 2.4896853407565742e-05, + "loss": 3.2898, + "step": 151500 }, { "epoch": 0.5, - "learning_rate": 2.4852847214537876e-05, - "loss": 3.1574, - "step": 140900 + "learning_rate": 2.488028367384136e-05, + "loss": 3.2881, + "step": 151600 }, { "epoch": 0.5, - "learning_rate": 2.4834999696592197e-05, - "loss": 3.1502, - "step": 141000 + "learning_rate": 2.4863713940116985e-05, + "loss": 3.2951, + "step": 151700 + }, + { + "epoch": 0.5, + "learning_rate": 2.4847144206392607e-05, + "loss": 3.2936, + "step": 151800 + }, + { + "epoch": 0.5, + "learning_rate": 2.4830574472668225e-05, + "loss": 3.2936, + "step": 151900 + }, + { + "epoch": 0.5, + "learning_rate": 2.4814004738943846e-05, + "loss": 3.2883, + "step": 152000 + }, + { + "epoch": 0.5, + "learning_rate": 2.4797435005219464e-05, + "loss": 3.2834, + "step": 152100 + }, + { + "epoch": 0.5, + "learning_rate": 2.478086527149509e-05, + "loss": 3.2974, + "step": 152200 }, { "epoch": 0.5, - "learning_rate": 2.4817152178646515e-05, - "loss": 3.1469, - "step": 141100 + "learning_rate": 2.476429553777071e-05, + "loss": 3.2838, + "step": 152300 }, { - "epoch": 0.5, - "learning_rate": 2.4799304660700836e-05, - "loss": 3.1593, - "step": 141200 + "epoch": 0.51, + "learning_rate": 2.474772580404633e-05, + "loss": 3.2967, + "step": 152400 }, { - "epoch": 0.5, - "learning_rate": 2.4781457142755157e-05, - "loss": 3.1551, - "step": 141300 + "epoch": 0.51, + "learning_rate": 2.473115607032195e-05, + "loss": 3.2877, + "step": 152500 }, { - "epoch": 0.5, - "learning_rate": 2.476360962480948e-05, - "loss": 3.1449, - "step": 141400 + "epoch": 0.51, + "learning_rate": 2.471458633659757e-05, + "loss": 3.2875, + "step": 152600 }, { "epoch": 0.51, - "learning_rate": 2.47457621068638e-05, - "loss": 3.1574, - "step": 141500 + "learning_rate": 2.4698016602873193e-05, + "loss": 3.2819, + "step": 152700 }, { "epoch": 0.51, - "learning_rate": 2.4727914588918118e-05, - "loss": 3.1582, - "step": 141600 + "learning_rate": 2.4681446869148815e-05, + "loss": 3.2896, + "step": 152800 }, { "epoch": 0.51, - "learning_rate": 2.471006707097244e-05, - "loss": 3.1487, - "step": 141700 + "learning_rate": 2.4664877135424436e-05, + "loss": 3.2978, + "step": 152900 }, { "epoch": 0.51, - "learning_rate": 2.4692219553026763e-05, - "loss": 3.1551, - "step": 141800 + "learning_rate": 2.4648307401700054e-05, + "loss": 3.2919, + "step": 153000 }, { "epoch": 0.51, - "learning_rate": 2.4674372035081085e-05, - "loss": 3.1461, - "step": 141900 + "learning_rate": 2.4631737667975676e-05, + "loss": 3.2998, + "step": 153100 }, { "epoch": 0.51, - "learning_rate": 2.4656524517135406e-05, - "loss": 3.154, - "step": 142000 + "learning_rate": 2.4615167934251297e-05, + "loss": 3.2886, + "step": 153200 }, { "epoch": 0.51, - "learning_rate": 2.4638676999189724e-05, - "loss": 3.1489, - "step": 142100 + "learning_rate": 2.459859820052692e-05, + "loss": 3.2825, + "step": 153300 }, { "epoch": 0.51, - "learning_rate": 2.4620829481244045e-05, - "loss": 3.1504, - "step": 142200 + "learning_rate": 2.458202846680254e-05, + "loss": 3.2859, + "step": 153400 }, { "epoch": 0.51, - "learning_rate": 2.4602981963298366e-05, - "loss": 3.1513, - "step": 142300 + "learning_rate": 2.456545873307816e-05, + "loss": 3.2858, + "step": 153500 }, { "epoch": 0.51, - "learning_rate": 2.4585134445352687e-05, - "loss": 3.1385, - "step": 142400 + "learning_rate": 2.454888899935378e-05, + "loss": 3.2882, + "step": 153600 }, { "epoch": 0.51, - "learning_rate": 2.456728692740701e-05, - "loss": 3.1467, - "step": 142500 + "learning_rate": 2.45323192656294e-05, + "loss": 3.2905, + "step": 153700 }, { "epoch": 0.51, - "learning_rate": 2.4549439409461326e-05, - "loss": 3.1568, - "step": 142600 + "learning_rate": 2.4515749531905026e-05, + "loss": 3.2871, + "step": 153800 }, { "epoch": 0.51, - "learning_rate": 2.4531591891515648e-05, - "loss": 3.151, - "step": 142700 + "learning_rate": 2.4499179798180644e-05, + "loss": 3.2845, + "step": 153900 }, { "epoch": 0.51, - "learning_rate": 2.451374437356997e-05, - "loss": 3.1601, - "step": 142800 + "learning_rate": 2.4482610064456265e-05, + "loss": 3.2841, + "step": 154000 }, { "epoch": 0.51, - "learning_rate": 2.449589685562429e-05, - "loss": 3.1511, - "step": 142900 + "learning_rate": 2.4466040330731887e-05, + "loss": 3.2847, + "step": 154100 }, { "epoch": 0.51, - "learning_rate": 2.447804933767861e-05, - "loss": 3.1465, - "step": 143000 + "learning_rate": 2.4449470597007505e-05, + "loss": 3.2922, + "step": 154200 }, { "epoch": 0.51, - "learning_rate": 2.446020181973293e-05, - "loss": 3.1618, - "step": 143100 + "learning_rate": 2.443290086328313e-05, + "loss": 3.3039, + "step": 154300 }, { "epoch": 0.51, - "learning_rate": 2.444235430178725e-05, - "loss": 3.1577, - "step": 143200 + "learning_rate": 2.441633112955875e-05, + "loss": 3.2935, + "step": 154400 }, { "epoch": 0.51, - "learning_rate": 2.442450678384157e-05, - "loss": 3.145, - "step": 143300 + "learning_rate": 2.439976139583437e-05, + "loss": 3.2822, + "step": 154500 }, { "epoch": 0.51, - "learning_rate": 2.4406659265895893e-05, - "loss": 3.1431, - "step": 143400 + "learning_rate": 2.438319166210999e-05, + "loss": 3.301, + "step": 154600 }, { "epoch": 0.51, - "learning_rate": 2.4388811747950214e-05, - "loss": 3.1461, - "step": 143500 + "learning_rate": 2.4366621928385612e-05, + "loss": 3.2923, + "step": 154700 }, { "epoch": 0.51, - "learning_rate": 2.4370964230004535e-05, - "loss": 3.1516, - "step": 143600 + "learning_rate": 2.4350052194661234e-05, + "loss": 3.2712, + "step": 154800 }, { "epoch": 0.51, - "learning_rate": 2.4353116712058853e-05, - "loss": 3.1535, - "step": 143700 + "learning_rate": 2.4333482460936855e-05, + "loss": 3.2886, + "step": 154900 }, { "epoch": 0.51, - "learning_rate": 2.4335269194113174e-05, - "loss": 3.1577, - "step": 143800 + "learning_rate": 2.4316912727212473e-05, + "loss": 3.2771, + "step": 155000 }, { "epoch": 0.51, - "learning_rate": 2.4317421676167495e-05, - "loss": 3.1458, - "step": 143900 + "learning_rate": 2.4300342993488095e-05, + "loss": 3.2888, + "step": 155100 }, { "epoch": 0.51, - "learning_rate": 2.4299574158221817e-05, - "loss": 3.1423, - "step": 144000 + "learning_rate": 2.4283773259763716e-05, + "loss": 3.2664, + "step": 155200 }, { "epoch": 0.51, - "learning_rate": 2.4281726640276138e-05, - "loss": 3.1374, - "step": 144100 + "learning_rate": 2.4267203526039338e-05, + "loss": 3.2847, + "step": 155300 }, { "epoch": 0.51, - "learning_rate": 2.4263879122330456e-05, - "loss": 3.1491, - "step": 144200 + "learning_rate": 2.425063379231496e-05, + "loss": 3.2771, + "step": 155400 }, { "epoch": 0.52, - "learning_rate": 2.424603160438478e-05, - "loss": 3.1562, - "step": 144300 + "learning_rate": 2.423406405859058e-05, + "loss": 3.2919, + "step": 155500 }, { "epoch": 0.52, - "learning_rate": 2.42281840864391e-05, - "loss": 3.1509, - "step": 144400 + "learning_rate": 2.42174943248662e-05, + "loss": 3.3008, + "step": 155600 }, { "epoch": 0.52, - "learning_rate": 2.4210336568493423e-05, - "loss": 3.149, - "step": 144500 + "learning_rate": 2.420092459114182e-05, + "loss": 3.285, + "step": 155700 }, { "epoch": 0.52, - "learning_rate": 2.4192489050547744e-05, - "loss": 3.1551, - "step": 144600 + "learning_rate": 2.418435485741744e-05, + "loss": 3.2908, + "step": 155800 }, { "epoch": 0.52, - "learning_rate": 2.4174641532602062e-05, - "loss": 3.1448, - "step": 144700 + "learning_rate": 2.4167785123693063e-05, + "loss": 3.2977, + "step": 155900 }, { "epoch": 0.52, - "learning_rate": 2.4156794014656383e-05, - "loss": 3.1538, - "step": 144800 + "learning_rate": 2.4151215389968685e-05, + "loss": 3.2769, + "step": 156000 }, { "epoch": 0.52, - "learning_rate": 2.4138946496710704e-05, - "loss": 3.141, - "step": 144900 + "learning_rate": 2.4134645656244306e-05, + "loss": 3.2821, + "step": 156100 }, { "epoch": 0.52, - "learning_rate": 2.4121098978765025e-05, - "loss": 3.1471, - "step": 145000 + "learning_rate": 2.4118075922519924e-05, + "loss": 3.2894, + "step": 156200 }, { "epoch": 0.52, - "learning_rate": 2.4103251460819347e-05, - "loss": 3.1497, - "step": 145100 + "learning_rate": 2.410150618879555e-05, + "loss": 3.2814, + "step": 156300 }, { "epoch": 0.52, - "learning_rate": 2.4085403942873664e-05, - "loss": 3.1368, - "step": 145200 + "learning_rate": 2.408493645507117e-05, + "loss": 3.2821, + "step": 156400 }, { "epoch": 0.52, - "learning_rate": 2.4067556424927986e-05, - "loss": 3.1538, - "step": 145300 + "learning_rate": 2.406836672134679e-05, + "loss": 3.2914, + "step": 156500 }, { "epoch": 0.52, - "learning_rate": 2.4049708906982307e-05, - "loss": 3.1395, - "step": 145400 + "learning_rate": 2.405179698762241e-05, + "loss": 3.3064, + "step": 156600 }, { "epoch": 0.52, - "learning_rate": 2.4031861389036628e-05, - "loss": 3.1433, - "step": 145500 + "learning_rate": 2.403522725389803e-05, + "loss": 3.2822, + "step": 156700 }, { "epoch": 0.52, - "learning_rate": 2.401401387109095e-05, - "loss": 3.1509, - "step": 145600 + "learning_rate": 2.4018657520173653e-05, + "loss": 3.2836, + "step": 156800 }, { "epoch": 0.52, - "learning_rate": 2.399616635314527e-05, - "loss": 3.148, - "step": 145700 + "learning_rate": 2.4002087786449274e-05, + "loss": 3.2855, + "step": 156900 }, { "epoch": 0.52, - "learning_rate": 2.397831883519959e-05, - "loss": 3.1434, - "step": 145800 + "learning_rate": 2.3985518052724896e-05, + "loss": 3.2925, + "step": 157000 }, { "epoch": 0.52, - "learning_rate": 2.396047131725391e-05, - "loss": 3.1372, - "step": 145900 + "learning_rate": 2.3968948319000514e-05, + "loss": 3.2881, + "step": 157100 }, { "epoch": 0.52, - "learning_rate": 2.394262379930823e-05, - "loss": 3.1442, - "step": 146000 + "learning_rate": 2.3952378585276135e-05, + "loss": 3.2888, + "step": 157200 }, { "epoch": 0.52, - "learning_rate": 2.3924776281362552e-05, - "loss": 3.1586, - "step": 146100 + "learning_rate": 2.3935808851551757e-05, + "loss": 3.2933, + "step": 157300 }, { "epoch": 0.52, - "learning_rate": 2.3906928763416873e-05, - "loss": 3.1477, - "step": 146200 + "learning_rate": 2.391923911782738e-05, + "loss": 3.2753, + "step": 157400 }, { "epoch": 0.52, - "learning_rate": 2.388908124547119e-05, - "loss": 3.152, - "step": 146300 + "learning_rate": 2.3902669384103e-05, + "loss": 3.2907, + "step": 157500 }, { "epoch": 0.52, - "learning_rate": 2.3871233727525512e-05, - "loss": 3.146, - "step": 146400 + "learning_rate": 2.3886099650378618e-05, + "loss": 3.2759, + "step": 157600 }, { "epoch": 0.52, - "learning_rate": 2.3853386209579833e-05, - "loss": 3.145, - "step": 146500 + "learning_rate": 2.386952991665424e-05, + "loss": 3.2871, + "step": 157700 }, { "epoch": 0.52, - "learning_rate": 2.3835538691634155e-05, - "loss": 3.15, - "step": 146600 + "learning_rate": 2.385296018292986e-05, + "loss": 3.2896, + "step": 157800 }, { "epoch": 0.52, - "learning_rate": 2.3817691173688476e-05, - "loss": 3.1492, - "step": 146700 + "learning_rate": 2.3836390449205482e-05, + "loss": 3.2737, + "step": 157900 }, { "epoch": 0.52, - "learning_rate": 2.3799843655742797e-05, - "loss": 3.1475, - "step": 146800 + "learning_rate": 2.3819820715481104e-05, + "loss": 3.2869, + "step": 158000 }, { "epoch": 0.52, - "learning_rate": 2.378199613779712e-05, - "loss": 3.1577, - "step": 146900 + "learning_rate": 2.3803250981756725e-05, + "loss": 3.2851, + "step": 158100 }, { "epoch": 0.52, - "learning_rate": 2.376414861985144e-05, - "loss": 3.1511, - "step": 147000 + "learning_rate": 2.3786681248032343e-05, + "loss": 3.2927, + "step": 158200 + }, + { + "epoch": 0.52, + "learning_rate": 2.3770111514307965e-05, + "loss": 3.2811, + "step": 158300 + }, + { + "epoch": 0.52, + "learning_rate": 2.375354178058359e-05, + "loss": 3.2817, + "step": 158400 }, { "epoch": 0.53, - "learning_rate": 2.374630110190576e-05, - "loss": 3.1618, - "step": 147100 + "learning_rate": 2.3736972046859208e-05, + "loss": 3.2755, + "step": 158500 }, { "epoch": 0.53, - "learning_rate": 2.3728453583960082e-05, - "loss": 3.1411, - "step": 147200 + "learning_rate": 2.372040231313483e-05, + "loss": 3.2903, + "step": 158600 }, { "epoch": 0.53, - "learning_rate": 2.37106060660144e-05, - "loss": 3.1617, - "step": 147300 + "learning_rate": 2.370383257941045e-05, + "loss": 3.2895, + "step": 158700 }, { "epoch": 0.53, - "learning_rate": 2.369275854806872e-05, - "loss": 3.1512, - "step": 147400 + "learning_rate": 2.368726284568607e-05, + "loss": 3.2662, + "step": 158800 }, { "epoch": 0.53, - "learning_rate": 2.3674911030123042e-05, - "loss": 3.1479, - "step": 147500 + "learning_rate": 2.3670693111961694e-05, + "loss": 3.2843, + "step": 158900 }, { "epoch": 0.53, - "learning_rate": 2.3657063512177363e-05, - "loss": 3.1534, - "step": 147600 + "learning_rate": 2.3654123378237315e-05, + "loss": 3.285, + "step": 159000 }, { "epoch": 0.53, - "learning_rate": 2.3639215994231685e-05, - "loss": 3.1604, - "step": 147700 + "learning_rate": 2.3637553644512933e-05, + "loss": 3.2847, + "step": 159100 }, { "epoch": 0.53, - "learning_rate": 2.3621368476286006e-05, - "loss": 3.1563, - "step": 147800 + "learning_rate": 2.3620983910788555e-05, + "loss": 3.2952, + "step": 159200 }, { "epoch": 0.53, - "learning_rate": 2.3603520958340324e-05, - "loss": 3.1431, - "step": 147900 + "learning_rate": 2.3604414177064176e-05, + "loss": 3.2964, + "step": 159300 }, { "epoch": 0.53, - "learning_rate": 2.3585673440394645e-05, - "loss": 3.1393, - "step": 148000 + "learning_rate": 2.3587844443339798e-05, + "loss": 3.2899, + "step": 159400 }, { "epoch": 0.53, - "learning_rate": 2.3567825922448966e-05, - "loss": 3.1561, - "step": 148100 + "learning_rate": 2.357127470961542e-05, + "loss": 3.2791, + "step": 159500 }, { "epoch": 0.53, - "learning_rate": 2.3549978404503287e-05, - "loss": 3.1551, - "step": 148200 + "learning_rate": 2.355470497589104e-05, + "loss": 3.2832, + "step": 159600 }, { "epoch": 0.53, - "learning_rate": 2.353213088655761e-05, - "loss": 3.1473, - "step": 148300 + "learning_rate": 2.353813524216666e-05, + "loss": 3.2758, + "step": 159700 }, { "epoch": 0.53, - "learning_rate": 2.3514283368611926e-05, - "loss": 3.1422, - "step": 148400 + "learning_rate": 2.352156550844228e-05, + "loss": 3.2839, + "step": 159800 }, { "epoch": 0.53, - "learning_rate": 2.3496435850666248e-05, - "loss": 3.1569, - "step": 148500 + "learning_rate": 2.35049957747179e-05, + "loss": 3.2769, + "step": 159900 }, { "epoch": 0.53, - "learning_rate": 2.347858833272057e-05, - "loss": 3.1521, - "step": 148600 + "learning_rate": 2.3488426040993523e-05, + "loss": 3.2795, + "step": 160000 }, { "epoch": 0.53, - "learning_rate": 2.346074081477489e-05, - "loss": 3.132, - "step": 148700 + "learning_rate": 2.3471856307269144e-05, + "loss": 3.2731, + "step": 160100 }, { "epoch": 0.53, - "learning_rate": 2.344289329682921e-05, - "loss": 3.1403, - "step": 148800 + "learning_rate": 2.3455286573544762e-05, + "loss": 3.2861, + "step": 160200 }, { "epoch": 0.53, - "learning_rate": 2.3425045778883532e-05, - "loss": 3.1383, - "step": 148900 + "learning_rate": 2.3438716839820384e-05, + "loss": 3.2805, + "step": 160300 }, { "epoch": 0.53, - "learning_rate": 2.340719826093785e-05, - "loss": 3.1493, - "step": 149000 + "learning_rate": 2.3422147106096005e-05, + "loss": 3.2756, + "step": 160400 }, { "epoch": 0.53, - "learning_rate": 2.338935074299217e-05, - "loss": 3.1327, - "step": 149100 + "learning_rate": 2.3405577372371627e-05, + "loss": 3.2833, + "step": 160500 }, { "epoch": 0.53, - "learning_rate": 2.3371503225046493e-05, - "loss": 3.1481, - "step": 149200 + "learning_rate": 2.338900763864725e-05, + "loss": 3.2805, + "step": 160600 }, { "epoch": 0.53, - "learning_rate": 2.3353655707100814e-05, - "loss": 3.1564, - "step": 149300 + "learning_rate": 2.337243790492287e-05, + "loss": 3.2825, + "step": 160700 }, { "epoch": 0.53, - "learning_rate": 2.3335808189155135e-05, - "loss": 3.1534, - "step": 149400 + "learning_rate": 2.3355868171198488e-05, + "loss": 3.2848, + "step": 160800 }, { "epoch": 0.53, - "learning_rate": 2.3317960671209456e-05, - "loss": 3.1362, - "step": 149500 + "learning_rate": 2.333929843747411e-05, + "loss": 3.2831, + "step": 160900 }, { "epoch": 0.53, - "learning_rate": 2.3300113153263778e-05, - "loss": 3.1492, - "step": 149600 + "learning_rate": 2.3322728703749734e-05, + "loss": 3.2864, + "step": 161000 }, { "epoch": 0.53, - "learning_rate": 2.32822656353181e-05, - "loss": 3.1443, - "step": 149700 + "learning_rate": 2.3306158970025352e-05, + "loss": 3.2941, + "step": 161100 }, { "epoch": 0.53, - "learning_rate": 2.326441811737242e-05, - "loss": 3.1455, - "step": 149800 + "learning_rate": 2.3289589236300974e-05, + "loss": 3.2851, + "step": 161200 + }, + { + "epoch": 0.53, + "learning_rate": 2.3273019502576595e-05, + "loss": 3.2845, + "step": 161300 + }, + { + "epoch": 0.53, + "learning_rate": 2.3256449768852213e-05, + "loss": 3.2823, + "step": 161400 }, { "epoch": 0.54, - "learning_rate": 2.324657059942674e-05, - "loss": 3.1487, - "step": 149900 + "learning_rate": 2.3239880035127838e-05, + "loss": 3.2893, + "step": 161500 }, { "epoch": 0.54, - "learning_rate": 2.322872308148106e-05, - "loss": 3.1553, - "step": 150000 + "learning_rate": 2.322331030140346e-05, + "loss": 3.277, + "step": 161600 }, { "epoch": 0.54, - "learning_rate": 2.321087556353538e-05, - "loss": 3.1468, - "step": 150100 + "learning_rate": 2.3206740567679078e-05, + "loss": 3.279, + "step": 161700 }, { "epoch": 0.54, - "learning_rate": 2.31930280455897e-05, - "loss": 3.1571, - "step": 150200 + "learning_rate": 2.31901708339547e-05, + "loss": 3.2878, + "step": 161800 }, { "epoch": 0.54, - "learning_rate": 2.3175180527644023e-05, - "loss": 3.1427, - "step": 150300 + "learning_rate": 2.317360110023032e-05, + "loss": 3.288, + "step": 161900 }, { "epoch": 0.54, - "learning_rate": 2.3157333009698344e-05, - "loss": 3.1484, - "step": 150400 + "learning_rate": 2.3157031366505942e-05, + "loss": 3.2729, + "step": 162000 + }, + { + "epoch": 0.54, + "learning_rate": 2.3140461632781564e-05, + "loss": 3.2861, + "step": 162100 + }, + { + "epoch": 0.54, + "learning_rate": 2.3123891899057185e-05, + "loss": 3.2831, + "step": 162200 + }, + { + "epoch": 0.54, + "learning_rate": 2.3107322165332803e-05, + "loss": 3.2861, + "step": 162300 + }, + { + "epoch": 0.54, + "learning_rate": 2.3090752431608425e-05, + "loss": 3.2863, + "step": 162400 }, { "epoch": 0.54, - "learning_rate": 2.3139485491752662e-05, - "loss": 3.1565, - "step": 150500 + "learning_rate": 2.3074182697884046e-05, + "loss": 3.2806, + "step": 162500 }, { "epoch": 0.54, - "learning_rate": 2.3121637973806983e-05, - "loss": 3.1449, - "step": 150600 + "learning_rate": 2.3057612964159668e-05, + "loss": 3.2929, + "step": 162600 }, { "epoch": 0.54, - "learning_rate": 2.3103790455861304e-05, - "loss": 3.1475, - "step": 150700 + "learning_rate": 2.304104323043529e-05, + "loss": 3.2824, + "step": 162700 }, { "epoch": 0.54, - "learning_rate": 2.3085942937915625e-05, - "loss": 3.1438, - "step": 150800 + "learning_rate": 2.3024473496710907e-05, + "loss": 3.2857, + "step": 162800 }, { "epoch": 0.54, - "learning_rate": 2.3068095419969947e-05, - "loss": 3.1451, - "step": 150900 + "learning_rate": 2.300790376298653e-05, + "loss": 3.2773, + "step": 162900 }, { "epoch": 0.54, - "learning_rate": 2.3050247902024268e-05, - "loss": 3.1476, - "step": 151000 + "learning_rate": 2.299133402926215e-05, + "loss": 3.2766, + "step": 163000 }, { "epoch": 0.54, - "learning_rate": 2.3032400384078586e-05, - "loss": 3.1537, - "step": 151100 + "learning_rate": 2.297476429553777e-05, + "loss": 3.2782, + "step": 163100 }, { "epoch": 0.54, - "learning_rate": 2.3014552866132907e-05, - "loss": 3.1404, - "step": 151200 + "learning_rate": 2.2958194561813393e-05, + "loss": 3.2789, + "step": 163200 }, { "epoch": 0.54, - "learning_rate": 2.2996705348187228e-05, - "loss": 3.1485, - "step": 151300 + "learning_rate": 2.2941624828089014e-05, + "loss": 3.2865, + "step": 163300 }, { "epoch": 0.54, - "learning_rate": 2.297885783024155e-05, - "loss": 3.1497, - "step": 151400 + "learning_rate": 2.2925055094364632e-05, + "loss": 3.2794, + "step": 163400 }, { "epoch": 0.54, - "learning_rate": 2.296101031229587e-05, - "loss": 3.1362, - "step": 151500 + "learning_rate": 2.2908485360640254e-05, + "loss": 3.2685, + "step": 163500 }, { "epoch": 0.54, - "learning_rate": 2.294316279435019e-05, - "loss": 3.149, - "step": 151600 + "learning_rate": 2.289191562691588e-05, + "loss": 3.2993, + "step": 163600 }, { "epoch": 0.54, - "learning_rate": 2.292531527640451e-05, - "loss": 3.1543, - "step": 151700 + "learning_rate": 2.2875345893191497e-05, + "loss": 3.2837, + "step": 163700 }, { "epoch": 0.54, - "learning_rate": 2.290746775845883e-05, - "loss": 3.1371, - "step": 151800 + "learning_rate": 2.285877615946712e-05, + "loss": 3.2783, + "step": 163800 }, { "epoch": 0.54, - "learning_rate": 2.2889620240513152e-05, - "loss": 3.1447, - "step": 151900 + "learning_rate": 2.284220642574274e-05, + "loss": 3.2909, + "step": 163900 }, { "epoch": 0.54, - "learning_rate": 2.2871772722567477e-05, - "loss": 3.1381, - "step": 152000 + "learning_rate": 2.2825636692018358e-05, + "loss": 3.2844, + "step": 164000 }, { "epoch": 0.54, - "learning_rate": 2.2853925204621794e-05, - "loss": 3.1429, - "step": 152100 + "learning_rate": 2.2809066958293983e-05, + "loss": 3.2822, + "step": 164100 }, { "epoch": 0.54, - "learning_rate": 2.2836077686676116e-05, - "loss": 3.1374, - "step": 152200 + "learning_rate": 2.2792497224569604e-05, + "loss": 3.2899, + "step": 164200 }, { "epoch": 0.54, - "learning_rate": 2.2818230168730437e-05, - "loss": 3.1429, - "step": 152300 + "learning_rate": 2.2775927490845222e-05, + "loss": 3.282, + "step": 164300 }, { "epoch": 0.54, - "learning_rate": 2.2800382650784758e-05, - "loss": 3.1483, - "step": 152400 + "learning_rate": 2.2759357757120844e-05, + "loss": 3.2589, + "step": 164400 }, { - "epoch": 0.54, - "learning_rate": 2.278253513283908e-05, - "loss": 3.1569, - "step": 152500 + "epoch": 0.55, + "learning_rate": 2.2742788023396465e-05, + "loss": 3.2706, + "step": 164500 }, { - "epoch": 0.54, - "learning_rate": 2.2764687614893397e-05, - "loss": 3.1503, - "step": 152600 + "epoch": 0.55, + "learning_rate": 2.2726218289672087e-05, + "loss": 3.2807, + "step": 164600 }, { "epoch": 0.55, - "learning_rate": 2.2746840096947718e-05, - "loss": 3.1438, - "step": 152700 + "learning_rate": 2.2709648555947708e-05, + "loss": 3.2747, + "step": 164700 }, { "epoch": 0.55, - "learning_rate": 2.272899257900204e-05, - "loss": 3.1524, - "step": 152800 + "learning_rate": 2.269307882222333e-05, + "loss": 3.2863, + "step": 164800 }, { "epoch": 0.55, - "learning_rate": 2.271114506105636e-05, - "loss": 3.1395, - "step": 152900 + "learning_rate": 2.2676509088498948e-05, + "loss": 3.287, + "step": 164900 }, { "epoch": 0.55, - "learning_rate": 2.2693297543110682e-05, - "loss": 3.1324, - "step": 153000 + "learning_rate": 2.265993935477457e-05, + "loss": 3.2848, + "step": 165000 }, { "epoch": 0.55, - "learning_rate": 2.2675450025165003e-05, - "loss": 3.1454, - "step": 153100 + "learning_rate": 2.264336962105019e-05, + "loss": 3.2724, + "step": 165100 }, { "epoch": 0.55, - "learning_rate": 2.265760250721932e-05, - "loss": 3.1415, - "step": 153200 + "learning_rate": 2.2626799887325812e-05, + "loss": 3.2838, + "step": 165200 }, { "epoch": 0.55, - "learning_rate": 2.2639754989273642e-05, - "loss": 3.1491, - "step": 153300 + "learning_rate": 2.2610230153601434e-05, + "loss": 3.2744, + "step": 165300 }, { "epoch": 0.55, - "learning_rate": 2.2621907471327963e-05, - "loss": 3.1466, - "step": 153400 + "learning_rate": 2.259366041987705e-05, + "loss": 3.2855, + "step": 165400 }, { "epoch": 0.55, - "learning_rate": 2.2604059953382285e-05, - "loss": 3.138, - "step": 153500 + "learning_rate": 2.2577090686152673e-05, + "loss": 3.2843, + "step": 165500 }, { "epoch": 0.55, - "learning_rate": 2.2586212435436606e-05, - "loss": 3.1346, - "step": 153600 + "learning_rate": 2.2560520952428295e-05, + "loss": 3.2717, + "step": 165600 }, { "epoch": 0.55, - "learning_rate": 2.2568364917490924e-05, - "loss": 3.1359, - "step": 153700 + "learning_rate": 2.2543951218703916e-05, + "loss": 3.2861, + "step": 165700 }, { "epoch": 0.55, - "learning_rate": 2.2550517399545245e-05, - "loss": 3.1422, - "step": 153800 + "learning_rate": 2.2527381484979538e-05, + "loss": 3.2767, + "step": 165800 }, { "epoch": 0.55, - "learning_rate": 2.2532669881599566e-05, - "loss": 3.1424, - "step": 153900 + "learning_rate": 2.251081175125516e-05, + "loss": 3.2805, + "step": 165900 }, { "epoch": 0.55, - "learning_rate": 2.2514822363653887e-05, - "loss": 3.151, - "step": 154000 + "learning_rate": 2.2494242017530777e-05, + "loss": 3.2862, + "step": 166000 }, { "epoch": 0.55, - "learning_rate": 2.249697484570821e-05, - "loss": 3.1424, - "step": 154100 + "learning_rate": 2.24776722838064e-05, + "loss": 3.2846, + "step": 166100 }, { "epoch": 0.55, - "learning_rate": 2.247912732776253e-05, - "loss": 3.1473, - "step": 154200 + "learning_rate": 2.2461102550082023e-05, + "loss": 3.2897, + "step": 166200 }, { "epoch": 0.55, - "learning_rate": 2.2461279809816848e-05, - "loss": 3.1499, - "step": 154300 + "learning_rate": 2.244453281635764e-05, + "loss": 3.2737, + "step": 166300 }, { "epoch": 0.55, - "learning_rate": 2.244343229187117e-05, - "loss": 3.1278, - "step": 154400 + "learning_rate": 2.2427963082633263e-05, + "loss": 3.2872, + "step": 166400 }, { "epoch": 0.55, - "learning_rate": 2.2425584773925493e-05, - "loss": 3.1382, - "step": 154500 + "learning_rate": 2.2411393348908884e-05, + "loss": 3.2867, + "step": 166500 }, { "epoch": 0.55, - "learning_rate": 2.2407737255979815e-05, - "loss": 3.1428, - "step": 154600 + "learning_rate": 2.2394823615184506e-05, + "loss": 3.294, + "step": 166600 }, { "epoch": 0.55, - "learning_rate": 2.2389889738034132e-05, - "loss": 3.1401, - "step": 154700 + "learning_rate": 2.2378253881460127e-05, + "loss": 3.2776, + "step": 166700 }, { "epoch": 0.55, - "learning_rate": 2.2372042220088454e-05, - "loss": 3.143, - "step": 154800 + "learning_rate": 2.236168414773575e-05, + "loss": 3.2909, + "step": 166800 }, { "epoch": 0.55, - "learning_rate": 2.2354194702142775e-05, - "loss": 3.1422, - "step": 154900 + "learning_rate": 2.2345114414011367e-05, + "loss": 3.2777, + "step": 166900 }, { "epoch": 0.55, - "learning_rate": 2.2336347184197096e-05, - "loss": 3.1308, - "step": 155000 + "learning_rate": 2.232854468028699e-05, + "loss": 3.2889, + "step": 167000 }, { "epoch": 0.55, - "learning_rate": 2.2318499666251417e-05, - "loss": 3.1505, - "step": 155100 + "learning_rate": 2.231197494656261e-05, + "loss": 3.2854, + "step": 167100 }, { "epoch": 0.55, - "learning_rate": 2.2300652148305735e-05, - "loss": 3.1294, - "step": 155200 + "learning_rate": 2.229540521283823e-05, + "loss": 3.2827, + "step": 167200 }, { "epoch": 0.55, - "learning_rate": 2.2282804630360056e-05, - "loss": 3.1498, - "step": 155300 + "learning_rate": 2.2278835479113853e-05, + "loss": 3.3006, + "step": 167300 }, { "epoch": 0.55, - "learning_rate": 2.2264957112414378e-05, - "loss": 3.1362, - "step": 155400 + "learning_rate": 2.2262265745389474e-05, + "loss": 3.2783, + "step": 167400 }, { "epoch": 0.56, - "learning_rate": 2.22471095944687e-05, - "loss": 3.1456, - "step": 155500 + "learning_rate": 2.2245696011665092e-05, + "loss": 3.2888, + "step": 167500 }, { "epoch": 0.56, - "learning_rate": 2.222926207652302e-05, - "loss": 3.1446, - "step": 155600 + "learning_rate": 2.2229126277940714e-05, + "loss": 3.272, + "step": 167600 }, { "epoch": 0.56, - "learning_rate": 2.221141455857734e-05, - "loss": 3.145, - "step": 155700 + "learning_rate": 2.2212556544216335e-05, + "loss": 3.2821, + "step": 167700 }, { "epoch": 0.56, - "learning_rate": 2.219356704063166e-05, - "loss": 3.1433, - "step": 155800 + "learning_rate": 2.2195986810491957e-05, + "loss": 3.2795, + "step": 167800 }, { "epoch": 0.56, - "learning_rate": 2.217571952268598e-05, - "loss": 3.1434, - "step": 155900 + "learning_rate": 2.2179417076767578e-05, + "loss": 3.2776, + "step": 167900 }, { "epoch": 0.56, - "learning_rate": 2.21578720047403e-05, - "loss": 3.153, - "step": 156000 + "learning_rate": 2.2162847343043196e-05, + "loss": 3.2793, + "step": 168000 }, { "epoch": 0.56, - "learning_rate": 2.2140024486794623e-05, - "loss": 3.1469, - "step": 156100 + "learning_rate": 2.2146277609318818e-05, + "loss": 3.2818, + "step": 168100 }, { "epoch": 0.56, - "learning_rate": 2.2122176968848944e-05, - "loss": 3.1394, - "step": 156200 + "learning_rate": 2.2129707875594443e-05, + "loss": 3.2793, + "step": 168200 }, { "epoch": 0.56, - "learning_rate": 2.2104329450903262e-05, - "loss": 3.1503, - "step": 156300 + "learning_rate": 2.211313814187006e-05, + "loss": 3.2892, + "step": 168300 }, { "epoch": 0.56, - "learning_rate": 2.2086481932957583e-05, - "loss": 3.1361, - "step": 156400 + "learning_rate": 2.2096568408145682e-05, + "loss": 3.2896, + "step": 168400 }, { "epoch": 0.56, - "learning_rate": 2.2068634415011904e-05, - "loss": 3.1457, - "step": 156500 + "learning_rate": 2.2079998674421304e-05, + "loss": 3.2771, + "step": 168500 }, { "epoch": 0.56, - "learning_rate": 2.2050786897066225e-05, - "loss": 3.1489, - "step": 156600 + "learning_rate": 2.206342894069692e-05, + "loss": 3.275, + "step": 168600 }, { "epoch": 0.56, - "learning_rate": 2.2032939379120547e-05, - "loss": 3.1399, - "step": 156700 + "learning_rate": 2.2046859206972547e-05, + "loss": 3.2791, + "step": 168700 }, { "epoch": 0.56, - "learning_rate": 2.2015091861174868e-05, - "loss": 3.153, - "step": 156800 + "learning_rate": 2.2030289473248168e-05, + "loss": 3.2656, + "step": 168800 }, { "epoch": 0.56, - "learning_rate": 2.1997244343229186e-05, - "loss": 3.1419, - "step": 156900 + "learning_rate": 2.2013719739523786e-05, + "loss": 3.2706, + "step": 168900 }, { "epoch": 0.56, - "learning_rate": 2.1979396825283507e-05, - "loss": 3.1406, - "step": 157000 + "learning_rate": 2.1997150005799408e-05, + "loss": 3.2837, + "step": 169000 }, { "epoch": 0.56, - "learning_rate": 2.196154930733783e-05, - "loss": 3.1391, - "step": 157100 + "learning_rate": 2.198058027207503e-05, + "loss": 3.2636, + "step": 169100 }, { "epoch": 0.56, - "learning_rate": 2.1943701789392153e-05, - "loss": 3.1358, - "step": 157200 + "learning_rate": 2.196401053835065e-05, + "loss": 3.2828, + "step": 169200 }, { "epoch": 0.56, - "learning_rate": 2.192585427144647e-05, - "loss": 3.1371, - "step": 157300 + "learning_rate": 2.1947440804626272e-05, + "loss": 3.2835, + "step": 169300 }, { "epoch": 0.56, - "learning_rate": 2.190800675350079e-05, - "loss": 3.1559, - "step": 157400 + "learning_rate": 2.1930871070901893e-05, + "loss": 3.283, + "step": 169400 }, { "epoch": 0.56, - "learning_rate": 2.1890159235555113e-05, - "loss": 3.1381, - "step": 157500 + "learning_rate": 2.191430133717751e-05, + "loss": 3.2923, + "step": 169500 }, { "epoch": 0.56, - "learning_rate": 2.1872311717609434e-05, - "loss": 3.1484, - "step": 157600 + "learning_rate": 2.1897731603453133e-05, + "loss": 3.2938, + "step": 169600 }, { "epoch": 0.56, - "learning_rate": 2.1854464199663755e-05, - "loss": 3.1469, - "step": 157700 + "learning_rate": 2.1881161869728754e-05, + "loss": 3.29, + "step": 169700 }, { "epoch": 0.56, - "learning_rate": 2.1836616681718077e-05, - "loss": 3.1485, - "step": 157800 + "learning_rate": 2.1864592136004376e-05, + "loss": 3.2878, + "step": 169800 }, { "epoch": 0.56, - "learning_rate": 2.1818769163772394e-05, - "loss": 3.135, - "step": 157900 + "learning_rate": 2.1848022402279997e-05, + "loss": 3.2827, + "step": 169900 }, { "epoch": 0.56, - "learning_rate": 2.1800921645826716e-05, - "loss": 3.1383, - "step": 158000 + "learning_rate": 2.183145266855562e-05, + "loss": 3.2757, + "step": 170000 }, { "epoch": 0.56, - "learning_rate": 2.1783074127881037e-05, - "loss": 3.137, - "step": 158100 + "learning_rate": 2.1814882934831237e-05, + "loss": 3.287, + "step": 170100 }, { "epoch": 0.56, - "learning_rate": 2.1765226609935358e-05, - "loss": 3.1306, - "step": 158200 + "learning_rate": 2.179831320110686e-05, + "loss": 3.2788, + "step": 170200 + }, + { + "epoch": 0.56, + "learning_rate": 2.178174346738248e-05, + "loss": 3.2798, + "step": 170300 + }, + { + "epoch": 0.56, + "learning_rate": 2.17651737336581e-05, + "loss": 3.2871, + "step": 170400 }, { "epoch": 0.57, - "learning_rate": 2.174737909198968e-05, - "loss": 3.1474, - "step": 158300 + "learning_rate": 2.1748603999933723e-05, + "loss": 3.286, + "step": 170500 }, { "epoch": 0.57, - "learning_rate": 2.1729531574043997e-05, - "loss": 3.1418, - "step": 158400 + "learning_rate": 2.173203426620934e-05, + "loss": 3.3001, + "step": 170600 }, { "epoch": 0.57, - "learning_rate": 2.1711684056098318e-05, - "loss": 3.1413, - "step": 158500 + "learning_rate": 2.1715464532484962e-05, + "loss": 3.2867, + "step": 170700 }, { "epoch": 0.57, - "learning_rate": 2.169383653815264e-05, - "loss": 3.1457, - "step": 158600 + "learning_rate": 2.1698894798760587e-05, + "loss": 3.29, + "step": 170800 }, { "epoch": 0.57, - "learning_rate": 2.167598902020696e-05, - "loss": 3.1425, - "step": 158700 + "learning_rate": 2.1682325065036205e-05, + "loss": 3.289, + "step": 170900 }, { "epoch": 0.57, - "learning_rate": 2.1658141502261282e-05, - "loss": 3.1423, - "step": 158800 + "learning_rate": 2.1665755331311827e-05, + "loss": 3.2888, + "step": 171000 }, { "epoch": 0.57, - "learning_rate": 2.1640293984315603e-05, - "loss": 3.1492, - "step": 158900 + "learning_rate": 2.1649185597587448e-05, + "loss": 3.2808, + "step": 171100 }, { "epoch": 0.57, - "learning_rate": 2.162244646636992e-05, - "loss": 3.1413, - "step": 159000 + "learning_rate": 2.1632615863863066e-05, + "loss": 3.2751, + "step": 171200 }, { "epoch": 0.57, - "learning_rate": 2.1604598948424242e-05, - "loss": 3.1367, - "step": 159100 + "learning_rate": 2.161604613013869e-05, + "loss": 3.2808, + "step": 171300 }, { "epoch": 0.57, - "learning_rate": 2.1586751430478563e-05, - "loss": 3.1354, - "step": 159200 + "learning_rate": 2.1599476396414313e-05, + "loss": 3.2784, + "step": 171400 }, { "epoch": 0.57, - "learning_rate": 2.1568903912532885e-05, - "loss": 3.1437, - "step": 159300 + "learning_rate": 2.158290666268993e-05, + "loss": 3.2842, + "step": 171500 }, { "epoch": 0.57, - "learning_rate": 2.1551056394587206e-05, - "loss": 3.1384, - "step": 159400 + "learning_rate": 2.1566336928965552e-05, + "loss": 3.2589, + "step": 171600 }, { "epoch": 0.57, - "learning_rate": 2.1533208876641524e-05, - "loss": 3.1438, - "step": 159500 + "learning_rate": 2.1549767195241174e-05, + "loss": 3.2719, + "step": 171700 }, { "epoch": 0.57, - "learning_rate": 2.1515361358695848e-05, - "loss": 3.1439, - "step": 159600 + "learning_rate": 2.1533197461516795e-05, + "loss": 3.2891, + "step": 171800 }, { "epoch": 0.57, - "learning_rate": 2.149751384075017e-05, - "loss": 3.1502, - "step": 159700 + "learning_rate": 2.1516627727792417e-05, + "loss": 3.2631, + "step": 171900 }, { "epoch": 0.57, - "learning_rate": 2.147966632280449e-05, - "loss": 3.1333, - "step": 159800 + "learning_rate": 2.1500057994068038e-05, + "loss": 3.2826, + "step": 172000 + }, + { + "epoch": 0.57, + "learning_rate": 2.1483488260343656e-05, + "loss": 3.2756, + "step": 172100 + }, + { + "epoch": 0.57, + "learning_rate": 2.1466918526619278e-05, + "loss": 3.2796, + "step": 172200 + }, + { + "epoch": 0.57, + "learning_rate": 2.14503487928949e-05, + "loss": 3.3116, + "step": 172300 + }, + { + "epoch": 0.57, + "learning_rate": 2.143377905917052e-05, + "loss": 3.2819, + "step": 172400 + }, + { + "epoch": 0.57, + "learning_rate": 2.1417209325446142e-05, + "loss": 3.2934, + "step": 172500 }, { "epoch": 0.57, - "learning_rate": 2.1461818804858812e-05, - "loss": 3.1407, - "step": 159900 + "learning_rate": 2.1400639591721763e-05, + "loss": 3.2748, + "step": 172600 }, { "epoch": 0.57, - "learning_rate": 2.144397128691313e-05, - "loss": 3.139, - "step": 160000 + "learning_rate": 2.138406985799738e-05, + "loss": 3.2857, + "step": 172700 }, { "epoch": 0.57, - "learning_rate": 2.142612376896745e-05, - "loss": 3.1496, - "step": 160100 + "learning_rate": 2.1367500124273003e-05, + "loss": 3.2928, + "step": 172800 }, { "epoch": 0.57, - "learning_rate": 2.1408276251021772e-05, - "loss": 3.1428, - "step": 160200 + "learning_rate": 2.1350930390548624e-05, + "loss": 3.2837, + "step": 172900 }, { "epoch": 0.57, - "learning_rate": 2.1390428733076093e-05, - "loss": 3.151, - "step": 160300 + "learning_rate": 2.1334360656824246e-05, + "loss": 3.2744, + "step": 173000 }, { "epoch": 0.57, - "learning_rate": 2.1372581215130415e-05, - "loss": 3.1388, - "step": 160400 + "learning_rate": 2.1317790923099867e-05, + "loss": 3.2811, + "step": 173100 }, { "epoch": 0.57, - "learning_rate": 2.1354733697184732e-05, - "loss": 3.1316, - "step": 160500 + "learning_rate": 2.1301221189375485e-05, + "loss": 3.288, + "step": 173200 }, { "epoch": 0.57, - "learning_rate": 2.1336886179239054e-05, - "loss": 3.1408, - "step": 160600 + "learning_rate": 2.1284651455651107e-05, + "loss": 3.2829, + "step": 173300 }, { "epoch": 0.57, - "learning_rate": 2.1319038661293375e-05, - "loss": 3.1318, - "step": 160700 + "learning_rate": 2.1268081721926732e-05, + "loss": 3.2829, + "step": 173400 }, { "epoch": 0.57, - "learning_rate": 2.1301191143347696e-05, - "loss": 3.1286, - "step": 160800 + "learning_rate": 2.125151198820235e-05, + "loss": 3.2831, + "step": 173500 }, { - "epoch": 0.57, - "learning_rate": 2.1283343625402017e-05, - "loss": 3.1391, - "step": 160900 + "epoch": 0.58, + "learning_rate": 2.123494225447797e-05, + "loss": 3.2837, + "step": 173600 }, { - "epoch": 0.57, - "learning_rate": 2.126549610745634e-05, - "loss": 3.1338, - "step": 161000 + "epoch": 0.58, + "learning_rate": 2.1218372520753593e-05, + "loss": 3.2809, + "step": 173700 }, { "epoch": 0.58, - "learning_rate": 2.1247648589510656e-05, - "loss": 3.1454, - "step": 161100 + "learning_rate": 2.120180278702921e-05, + "loss": 3.2842, + "step": 173800 }, { "epoch": 0.58, - "learning_rate": 2.1229801071564978e-05, - "loss": 3.1415, - "step": 161200 + "learning_rate": 2.1185233053304836e-05, + "loss": 3.2762, + "step": 173900 }, { "epoch": 0.58, - "learning_rate": 2.12119535536193e-05, - "loss": 3.1402, - "step": 161300 + "learning_rate": 2.1168663319580457e-05, + "loss": 3.289, + "step": 174000 }, { "epoch": 0.58, - "learning_rate": 2.119410603567362e-05, - "loss": 3.1334, - "step": 161400 + "learning_rate": 2.1152093585856075e-05, + "loss": 3.2765, + "step": 174100 }, { "epoch": 0.58, - "learning_rate": 2.117625851772794e-05, - "loss": 3.1313, - "step": 161500 + "learning_rate": 2.1135523852131697e-05, + "loss": 3.278, + "step": 174200 }, { "epoch": 0.58, - "learning_rate": 2.115841099978226e-05, - "loss": 3.1331, - "step": 161600 + "learning_rate": 2.1118954118407318e-05, + "loss": 3.2938, + "step": 174300 }, { "epoch": 0.58, - "learning_rate": 2.114056348183658e-05, - "loss": 3.1351, - "step": 161700 + "learning_rate": 2.110238438468294e-05, + "loss": 3.268, + "step": 174400 }, { "epoch": 0.58, - "learning_rate": 2.11227159638909e-05, - "loss": 3.1376, - "step": 161800 + "learning_rate": 2.108581465095856e-05, + "loss": 3.2875, + "step": 174500 }, { "epoch": 0.58, - "learning_rate": 2.1104868445945223e-05, - "loss": 3.1366, - "step": 161900 + "learning_rate": 2.1069244917234183e-05, + "loss": 3.2822, + "step": 174600 }, { "epoch": 0.58, - "learning_rate": 2.1087020927999544e-05, - "loss": 3.1301, - "step": 162000 + "learning_rate": 2.10526751835098e-05, + "loss": 3.2809, + "step": 174700 }, { "epoch": 0.58, - "learning_rate": 2.1069173410053865e-05, - "loss": 3.138, - "step": 162100 + "learning_rate": 2.1036105449785422e-05, + "loss": 3.2876, + "step": 174800 }, { "epoch": 0.58, - "learning_rate": 2.1051325892108186e-05, - "loss": 3.1339, - "step": 162200 + "learning_rate": 2.1019535716061044e-05, + "loss": 3.282, + "step": 174900 }, { "epoch": 0.58, - "learning_rate": 2.1033478374162507e-05, - "loss": 3.1481, - "step": 162300 + "learning_rate": 2.1002965982336665e-05, + "loss": 3.2731, + "step": 175000 }, { "epoch": 0.58, - "learning_rate": 2.101563085621683e-05, - "loss": 3.1351, - "step": 162400 + "learning_rate": 2.0986396248612287e-05, + "loss": 3.2717, + "step": 175100 }, { "epoch": 0.58, - "learning_rate": 2.099778333827115e-05, - "loss": 3.1413, - "step": 162500 + "learning_rate": 2.0969826514887908e-05, + "loss": 3.2753, + "step": 175200 }, { "epoch": 0.58, - "learning_rate": 2.0979935820325468e-05, - "loss": 3.1304, - "step": 162600 + "learning_rate": 2.0953256781163526e-05, + "loss": 3.2735, + "step": 175300 }, { "epoch": 0.58, - "learning_rate": 2.096208830237979e-05, - "loss": 3.1426, - "step": 162700 + "learning_rate": 2.0936687047439148e-05, + "loss": 3.291, + "step": 175400 }, { "epoch": 0.58, - "learning_rate": 2.094424078443411e-05, - "loss": 3.13, - "step": 162800 + "learning_rate": 2.092011731371477e-05, + "loss": 3.2831, + "step": 175500 }, { "epoch": 0.58, - "learning_rate": 2.092639326648843e-05, - "loss": 3.1346, - "step": 162900 + "learning_rate": 2.090354757999039e-05, + "loss": 3.2756, + "step": 175600 }, { "epoch": 0.58, - "learning_rate": 2.0908545748542753e-05, - "loss": 3.1332, - "step": 163000 + "learning_rate": 2.0886977846266012e-05, + "loss": 3.2659, + "step": 175700 }, { "epoch": 0.58, - "learning_rate": 2.0890698230597074e-05, - "loss": 3.1499, - "step": 163100 + "learning_rate": 2.087040811254163e-05, + "loss": 3.2736, + "step": 175800 }, { "epoch": 0.58, - "learning_rate": 2.087285071265139e-05, - "loss": 3.1348, - "step": 163200 + "learning_rate": 2.085383837881725e-05, + "loss": 3.273, + "step": 175900 }, { "epoch": 0.58, - "learning_rate": 2.0855003194705713e-05, - "loss": 3.1498, - "step": 163300 + "learning_rate": 2.0837268645092876e-05, + "loss": 3.2855, + "step": 176000 }, { "epoch": 0.58, - "learning_rate": 2.0837155676760034e-05, - "loss": 3.1402, - "step": 163400 + "learning_rate": 2.0820698911368494e-05, + "loss": 3.2834, + "step": 176100 }, { "epoch": 0.58, - "learning_rate": 2.0819308158814355e-05, - "loss": 3.1327, - "step": 163500 + "learning_rate": 2.0804129177644116e-05, + "loss": 3.2762, + "step": 176200 }, { "epoch": 0.58, - "learning_rate": 2.0801460640868677e-05, - "loss": 3.1435, - "step": 163600 + "learning_rate": 2.0787559443919737e-05, + "loss": 3.2869, + "step": 176300 }, { "epoch": 0.58, - "learning_rate": 2.0783613122922994e-05, - "loss": 3.1312, - "step": 163700 + "learning_rate": 2.0770989710195355e-05, + "loss": 3.277, + "step": 176400 }, { "epoch": 0.58, - "learning_rate": 2.0765765604977316e-05, - "loss": 3.1379, - "step": 163800 + "learning_rate": 2.075441997647098e-05, + "loss": 3.2718, + "step": 176500 }, { "epoch": 0.59, - "learning_rate": 2.0747918087031637e-05, - "loss": 3.1406, - "step": 163900 + "learning_rate": 2.0737850242746602e-05, + "loss": 3.2905, + "step": 176600 }, { "epoch": 0.59, - "learning_rate": 2.0730070569085958e-05, - "loss": 3.1293, - "step": 164000 + "learning_rate": 2.072128050902222e-05, + "loss": 3.2746, + "step": 176700 }, { "epoch": 0.59, - "learning_rate": 2.071222305114028e-05, - "loss": 3.1281, - "step": 164100 + "learning_rate": 2.070471077529784e-05, + "loss": 3.2803, + "step": 176800 }, { "epoch": 0.59, - "learning_rate": 2.06943755331946e-05, - "loss": 3.1433, - "step": 164200 + "learning_rate": 2.0688141041573463e-05, + "loss": 3.27, + "step": 176900 }, { "epoch": 0.59, - "learning_rate": 2.0676528015248918e-05, - "loss": 3.1484, - "step": 164300 + "learning_rate": 2.0671571307849084e-05, + "loss": 3.2631, + "step": 177000 }, { "epoch": 0.59, - "learning_rate": 2.065868049730324e-05, - "loss": 3.1397, - "step": 164400 + "learning_rate": 2.0655001574124706e-05, + "loss": 3.2897, + "step": 177100 }, { "epoch": 0.59, - "learning_rate": 2.064083297935756e-05, - "loss": 3.1332, - "step": 164500 + "learning_rate": 2.0638431840400327e-05, + "loss": 3.2775, + "step": 177200 }, { "epoch": 0.59, - "learning_rate": 2.0622985461411882e-05, - "loss": 3.1345, - "step": 164600 + "learning_rate": 2.0621862106675945e-05, + "loss": 3.2823, + "step": 177300 }, { "epoch": 0.59, - "learning_rate": 2.0605137943466203e-05, - "loss": 3.1234, - "step": 164700 + "learning_rate": 2.0605292372951567e-05, + "loss": 3.2917, + "step": 177400 }, { "epoch": 0.59, - "learning_rate": 2.0587290425520524e-05, - "loss": 3.1335, - "step": 164800 + "learning_rate": 2.0588722639227188e-05, + "loss": 3.274, + "step": 177500 }, { "epoch": 0.59, - "learning_rate": 2.0569442907574846e-05, - "loss": 3.1478, - "step": 164900 + "learning_rate": 2.057215290550281e-05, + "loss": 3.2779, + "step": 177600 }, { "epoch": 0.59, - "learning_rate": 2.0551595389629167e-05, - "loss": 3.1365, - "step": 165000 + "learning_rate": 2.055558317177843e-05, + "loss": 3.2712, + "step": 177700 }, { "epoch": 0.59, - "learning_rate": 2.0533747871683488e-05, - "loss": 3.1522, - "step": 165100 + "learning_rate": 2.0539013438054053e-05, + "loss": 3.2744, + "step": 177800 }, { "epoch": 0.59, - "learning_rate": 2.051590035373781e-05, - "loss": 3.1304, - "step": 165200 + "learning_rate": 2.052244370432967e-05, + "loss": 3.2781, + "step": 177900 }, { "epoch": 0.59, - "learning_rate": 2.0498052835792127e-05, - "loss": 3.1281, - "step": 165300 + "learning_rate": 2.0505873970605292e-05, + "loss": 3.2889, + "step": 178000 }, { "epoch": 0.59, - "learning_rate": 2.0480205317846448e-05, - "loss": 3.1412, - "step": 165400 + "learning_rate": 2.0489304236880914e-05, + "loss": 3.2706, + "step": 178100 }, { "epoch": 0.59, - "learning_rate": 2.046235779990077e-05, - "loss": 3.1369, - "step": 165500 + "learning_rate": 2.0472734503156535e-05, + "loss": 3.2853, + "step": 178200 }, { "epoch": 0.59, - "learning_rate": 2.044451028195509e-05, - "loss": 3.1367, - "step": 165600 + "learning_rate": 2.0456164769432157e-05, + "loss": 3.2737, + "step": 178300 }, { "epoch": 0.59, - "learning_rate": 2.0426662764009412e-05, - "loss": 3.1362, - "step": 165700 + "learning_rate": 2.0439595035707775e-05, + "loss": 3.2676, + "step": 178400 }, { "epoch": 0.59, - "learning_rate": 2.040881524606373e-05, - "loss": 3.1372, - "step": 165800 + "learning_rate": 2.04230253019834e-05, + "loss": 3.2788, + "step": 178500 }, { "epoch": 0.59, - "learning_rate": 2.039096772811805e-05, - "loss": 3.1438, - "step": 165900 + "learning_rate": 2.040645556825902e-05, + "loss": 3.2943, + "step": 178600 }, { "epoch": 0.59, - "learning_rate": 2.0373120210172372e-05, - "loss": 3.1397, - "step": 166000 + "learning_rate": 2.038988583453464e-05, + "loss": 3.269, + "step": 178700 }, { "epoch": 0.59, - "learning_rate": 2.0355272692226693e-05, - "loss": 3.1377, - "step": 166100 + "learning_rate": 2.037331610081026e-05, + "loss": 3.265, + "step": 178800 }, { "epoch": 0.59, - "learning_rate": 2.0337425174281015e-05, - "loss": 3.1493, - "step": 166200 + "learning_rate": 2.0356746367085882e-05, + "loss": 3.2816, + "step": 178900 }, { "epoch": 0.59, - "learning_rate": 2.0319577656335332e-05, - "loss": 3.1418, - "step": 166300 + "learning_rate": 2.0340176633361503e-05, + "loss": 3.2758, + "step": 179000 }, { "epoch": 0.59, - "learning_rate": 2.0301730138389654e-05, - "loss": 3.1415, - "step": 166400 + "learning_rate": 2.0323606899637125e-05, + "loss": 3.2659, + "step": 179100 }, { "epoch": 0.59, - "learning_rate": 2.0283882620443975e-05, - "loss": 3.1316, - "step": 166500 + "learning_rate": 2.0307037165912746e-05, + "loss": 3.2791, + "step": 179200 }, { "epoch": 0.59, - "learning_rate": 2.0266035102498296e-05, - "loss": 3.1367, - "step": 166600 + "learning_rate": 2.0290467432188364e-05, + "loss": 3.2586, + "step": 179300 + }, + { + "epoch": 0.59, + "learning_rate": 2.0273897698463986e-05, + "loss": 3.2832, + "step": 179400 + }, + { + "epoch": 0.59, + "learning_rate": 2.0257327964739607e-05, + "loss": 3.2727, + "step": 179500 }, { "epoch": 0.6, - "learning_rate": 2.0248187584552617e-05, - "loss": 3.1298, - "step": 166700 + "learning_rate": 2.024075823101523e-05, + "loss": 3.2878, + "step": 179600 }, { "epoch": 0.6, - "learning_rate": 2.023034006660694e-05, - "loss": 3.1356, - "step": 166800 + "learning_rate": 2.022418849729085e-05, + "loss": 3.2717, + "step": 179700 }, { "epoch": 0.6, - "learning_rate": 2.0212492548661256e-05, - "loss": 3.1434, - "step": 166900 + "learning_rate": 2.0207618763566472e-05, + "loss": 3.2736, + "step": 179800 }, { "epoch": 0.6, - "learning_rate": 2.0194645030715577e-05, - "loss": 3.1319, - "step": 167000 + "learning_rate": 2.019104902984209e-05, + "loss": 3.2894, + "step": 179900 }, { "epoch": 0.6, - "learning_rate": 2.01767975127699e-05, - "loss": 3.144, - "step": 167100 + "learning_rate": 2.017447929611771e-05, + "loss": 3.2825, + "step": 180000 }, { "epoch": 0.6, - "learning_rate": 2.015894999482422e-05, - "loss": 3.1421, - "step": 167200 + "learning_rate": 2.0157909562393336e-05, + "loss": 3.2744, + "step": 180100 }, { "epoch": 0.6, - "learning_rate": 2.014110247687854e-05, - "loss": 3.1383, - "step": 167300 + "learning_rate": 2.0141339828668954e-05, + "loss": 3.2714, + "step": 180200 }, { "epoch": 0.6, - "learning_rate": 2.0123254958932862e-05, - "loss": 3.1379, - "step": 167400 + "learning_rate": 2.0124770094944576e-05, + "loss": 3.2727, + "step": 180300 }, { "epoch": 0.6, - "learning_rate": 2.0105407440987184e-05, - "loss": 3.1342, - "step": 167500 + "learning_rate": 2.0108200361220197e-05, + "loss": 3.2714, + "step": 180400 }, { "epoch": 0.6, - "learning_rate": 2.0087559923041505e-05, - "loss": 3.1274, - "step": 167600 + "learning_rate": 2.0091630627495815e-05, + "loss": 3.2763, + "step": 180500 }, { "epoch": 0.6, - "learning_rate": 2.0069712405095826e-05, - "loss": 3.1366, - "step": 167700 + "learning_rate": 2.007506089377144e-05, + "loss": 3.2797, + "step": 180600 }, { "epoch": 0.6, - "learning_rate": 2.0051864887150147e-05, - "loss": 3.1358, - "step": 167800 + "learning_rate": 2.0058491160047058e-05, + "loss": 3.2749, + "step": 180700 }, { "epoch": 0.6, - "learning_rate": 2.0034017369204465e-05, - "loss": 3.1322, - "step": 167900 + "learning_rate": 2.004192142632268e-05, + "loss": 3.279, + "step": 180800 }, { "epoch": 0.6, - "learning_rate": 2.0016169851258786e-05, - "loss": 3.1361, - "step": 168000 + "learning_rate": 2.00253516925983e-05, + "loss": 3.2736, + "step": 180900 }, { "epoch": 0.6, - "learning_rate": 1.9998322333313107e-05, - "loss": 3.1289, - "step": 168100 + "learning_rate": 2.000878195887392e-05, + "loss": 3.2795, + "step": 181000 }, { "epoch": 0.6, - "learning_rate": 1.998047481536743e-05, - "loss": 3.1436, - "step": 168200 + "learning_rate": 1.9992212225149544e-05, + "loss": 3.2749, + "step": 181100 }, { "epoch": 0.6, - "learning_rate": 1.996262729742175e-05, - "loss": 3.1443, - "step": 168300 + "learning_rate": 1.9975642491425166e-05, + "loss": 3.2735, + "step": 181200 }, { "epoch": 0.6, - "learning_rate": 1.9944779779476068e-05, - "loss": 3.1409, - "step": 168400 + "learning_rate": 1.9959072757700784e-05, + "loss": 3.2742, + "step": 181300 }, { "epoch": 0.6, - "learning_rate": 1.992693226153039e-05, - "loss": 3.1498, - "step": 168500 + "learning_rate": 1.9942503023976405e-05, + "loss": 3.2768, + "step": 181400 }, { "epoch": 0.6, - "learning_rate": 1.990908474358471e-05, - "loss": 3.1394, - "step": 168600 + "learning_rate": 1.9925933290252027e-05, + "loss": 3.2842, + "step": 181500 }, { "epoch": 0.6, - "learning_rate": 1.989123722563903e-05, - "loss": 3.1409, - "step": 168700 + "learning_rate": 1.9909363556527648e-05, + "loss": 3.2691, + "step": 181600 }, { "epoch": 0.6, - "learning_rate": 1.9873389707693353e-05, - "loss": 3.1357, - "step": 168800 + "learning_rate": 1.989279382280327e-05, + "loss": 3.2688, + "step": 181700 }, { "epoch": 0.6, - "learning_rate": 1.9855542189747674e-05, - "loss": 3.1363, - "step": 168900 + "learning_rate": 1.987622408907889e-05, + "loss": 3.2819, + "step": 181800 }, { "epoch": 0.6, - "learning_rate": 1.983769467180199e-05, - "loss": 3.143, - "step": 169000 + "learning_rate": 1.985965435535451e-05, + "loss": 3.2958, + "step": 181900 }, { "epoch": 0.6, - "learning_rate": 1.9819847153856313e-05, - "loss": 3.1284, - "step": 169100 + "learning_rate": 1.984308462163013e-05, + "loss": 3.2733, + "step": 182000 }, { "epoch": 0.6, - "learning_rate": 1.9801999635910634e-05, - "loss": 3.1341, - "step": 169200 + "learning_rate": 1.9826514887905752e-05, + "loss": 3.284, + "step": 182100 }, { "epoch": 0.6, - "learning_rate": 1.9784152117964955e-05, - "loss": 3.1332, - "step": 169300 + "learning_rate": 1.9809945154181373e-05, + "loss": 3.2737, + "step": 182200 }, { "epoch": 0.6, - "learning_rate": 1.9766304600019276e-05, - "loss": 3.1366, - "step": 169400 + "learning_rate": 1.9793375420456995e-05, + "loss": 3.2678, + "step": 182300 + }, + { + "epoch": 0.6, + "learning_rate": 1.9776805686732616e-05, + "loss": 3.2785, + "step": 182400 + }, + { + "epoch": 0.6, + "learning_rate": 1.9760235953008234e-05, + "loss": 3.2794, + "step": 182500 + }, + { + "epoch": 0.61, + "learning_rate": 1.9743666219283856e-05, + "loss": 3.2725, + "step": 182600 + }, + { + "epoch": 0.61, + "learning_rate": 1.972709648555948e-05, + "loss": 3.2826, + "step": 182700 + }, + { + "epoch": 0.61, + "learning_rate": 1.97105267518351e-05, + "loss": 3.2711, + "step": 182800 + }, + { + "epoch": 0.61, + "learning_rate": 1.969395701811072e-05, + "loss": 3.28, + "step": 182900 }, { "epoch": 0.61, - "learning_rate": 1.9748457082073594e-05, - "loss": 3.1444, - "step": 169500 + "learning_rate": 1.9677387284386342e-05, + "loss": 3.2706, + "step": 183000 }, { "epoch": 0.61, - "learning_rate": 1.9730609564127916e-05, - "loss": 3.1241, - "step": 169600 + "learning_rate": 1.966081755066196e-05, + "loss": 3.2668, + "step": 183100 }, { "epoch": 0.61, - "learning_rate": 1.9712762046182237e-05, - "loss": 3.135, - "step": 169700 + "learning_rate": 1.9644247816937585e-05, + "loss": 3.2762, + "step": 183200 }, { "epoch": 0.61, - "learning_rate": 1.969491452823656e-05, - "loss": 3.14, - "step": 169800 + "learning_rate": 1.9627678083213203e-05, + "loss": 3.2763, + "step": 183300 }, { "epoch": 0.61, - "learning_rate": 1.9677067010290883e-05, - "loss": 3.1357, - "step": 169900 + "learning_rate": 1.9611108349488824e-05, + "loss": 3.2811, + "step": 183400 }, { "epoch": 0.61, - "learning_rate": 1.96592194923452e-05, - "loss": 3.1379, - "step": 170000 + "learning_rate": 1.9594538615764446e-05, + "loss": 3.2608, + "step": 183500 }, { "epoch": 0.61, - "learning_rate": 1.964137197439952e-05, - "loss": 3.1387, - "step": 170100 + "learning_rate": 1.9577968882040064e-05, + "loss": 3.2719, + "step": 183600 }, { "epoch": 0.61, - "learning_rate": 1.9623524456453843e-05, - "loss": 3.1424, - "step": 170200 + "learning_rate": 1.956139914831569e-05, + "loss": 3.2689, + "step": 183700 }, { "epoch": 0.61, - "learning_rate": 1.9605676938508164e-05, - "loss": 3.1363, - "step": 170300 + "learning_rate": 1.954482941459131e-05, + "loss": 3.272, + "step": 183800 }, { "epoch": 0.61, - "learning_rate": 1.9587829420562485e-05, - "loss": 3.1242, - "step": 170400 + "learning_rate": 1.9528259680866928e-05, + "loss": 3.2739, + "step": 183900 }, { "epoch": 0.61, - "learning_rate": 1.9569981902616803e-05, - "loss": 3.1384, - "step": 170500 + "learning_rate": 1.951168994714255e-05, + "loss": 3.2628, + "step": 184000 }, { "epoch": 0.61, - "learning_rate": 1.9552134384671124e-05, - "loss": 3.15, - "step": 170600 + "learning_rate": 1.949512021341817e-05, + "loss": 3.2716, + "step": 184100 }, { "epoch": 0.61, - "learning_rate": 1.9534286866725445e-05, - "loss": 3.133, - "step": 170700 + "learning_rate": 1.9478550479693793e-05, + "loss": 3.2695, + "step": 184200 }, { "epoch": 0.61, - "learning_rate": 1.9516439348779767e-05, - "loss": 3.1258, - "step": 170800 + "learning_rate": 1.9461980745969414e-05, + "loss": 3.2758, + "step": 184300 }, { "epoch": 0.61, - "learning_rate": 1.9498591830834088e-05, - "loss": 3.1426, - "step": 170900 + "learning_rate": 1.9445411012245036e-05, + "loss": 3.2661, + "step": 184400 }, { "epoch": 0.61, - "learning_rate": 1.948074431288841e-05, - "loss": 3.1283, - "step": 171000 + "learning_rate": 1.9428841278520654e-05, + "loss": 3.2644, + "step": 184500 }, { "epoch": 0.61, - "learning_rate": 1.9462896794942727e-05, - "loss": 3.1294, - "step": 171100 + "learning_rate": 1.9412271544796275e-05, + "loss": 3.2676, + "step": 184600 }, { "epoch": 0.61, - "learning_rate": 1.9445049276997048e-05, - "loss": 3.1516, - "step": 171200 + "learning_rate": 1.9395701811071897e-05, + "loss": 3.2685, + "step": 184700 }, { "epoch": 0.61, - "learning_rate": 1.942720175905137e-05, - "loss": 3.1317, - "step": 171300 + "learning_rate": 1.9379132077347518e-05, + "loss": 3.2738, + "step": 184800 }, { "epoch": 0.61, - "learning_rate": 1.940935424110569e-05, - "loss": 3.1227, - "step": 171400 + "learning_rate": 1.936256234362314e-05, + "loss": 3.2685, + "step": 184900 }, { "epoch": 0.61, - "learning_rate": 1.9391506723160012e-05, - "loss": 3.1374, - "step": 171500 + "learning_rate": 1.934599260989876e-05, + "loss": 3.2767, + "step": 185000 }, { "epoch": 0.61, - "learning_rate": 1.937365920521433e-05, - "loss": 3.1381, - "step": 171600 + "learning_rate": 1.932942287617438e-05, + "loss": 3.283, + "step": 185100 }, { "epoch": 0.61, - "learning_rate": 1.935581168726865e-05, - "loss": 3.1476, - "step": 171700 + "learning_rate": 1.931285314245e-05, + "loss": 3.2907, + "step": 185200 }, { "epoch": 0.61, - "learning_rate": 1.9337964169322972e-05, - "loss": 3.133, - "step": 171800 + "learning_rate": 1.9296283408725625e-05, + "loss": 3.2751, + "step": 185300 }, { "epoch": 0.61, - "learning_rate": 1.9320116651377293e-05, - "loss": 3.1404, - "step": 171900 + "learning_rate": 1.9279713675001243e-05, + "loss": 3.2794, + "step": 185400 }, { "epoch": 0.61, - "learning_rate": 1.9302269133431615e-05, - "loss": 3.1346, - "step": 172000 + "learning_rate": 1.9263143941276865e-05, + "loss": 3.2789, + "step": 185500 }, { - "epoch": 0.61, - "learning_rate": 1.9284421615485936e-05, - "loss": 3.1327, - "step": 172100 + "epoch": 0.62, + "learning_rate": 1.9246574207552486e-05, + "loss": 3.2792, + "step": 185600 }, { - "epoch": 0.61, - "learning_rate": 1.9266574097540254e-05, - "loss": 3.1314, - "step": 172200 + "epoch": 0.62, + "learning_rate": 1.9230004473828104e-05, + "loss": 3.2708, + "step": 185700 }, { "epoch": 0.62, - "learning_rate": 1.9248726579594575e-05, - "loss": 3.1326, - "step": 172300 + "learning_rate": 1.921343474010373e-05, + "loss": 3.2807, + "step": 185800 }, { "epoch": 0.62, - "learning_rate": 1.92308790616489e-05, - "loss": 3.1395, - "step": 172400 + "learning_rate": 1.9196865006379347e-05, + "loss": 3.2696, + "step": 185900 }, { "epoch": 0.62, - "learning_rate": 1.921303154370322e-05, - "loss": 3.1406, - "step": 172500 + "learning_rate": 1.918029527265497e-05, + "loss": 3.2728, + "step": 186000 }, { "epoch": 0.62, - "learning_rate": 1.919518402575754e-05, - "loss": 3.1211, - "step": 172600 + "learning_rate": 1.916372553893059e-05, + "loss": 3.2733, + "step": 186100 }, { "epoch": 0.62, - "learning_rate": 1.917733650781186e-05, - "loss": 3.1378, - "step": 172700 + "learning_rate": 1.914715580520621e-05, + "loss": 3.275, + "step": 186200 }, { "epoch": 0.62, - "learning_rate": 1.915948898986618e-05, - "loss": 3.1195, - "step": 172800 + "learning_rate": 1.9130586071481833e-05, + "loss": 3.2787, + "step": 186300 }, { "epoch": 0.62, - "learning_rate": 1.9141641471920502e-05, - "loss": 3.1298, - "step": 172900 + "learning_rate": 1.9114016337757455e-05, + "loss": 3.2734, + "step": 186400 }, { "epoch": 0.62, - "learning_rate": 1.9123793953974823e-05, - "loss": 3.1243, - "step": 173000 + "learning_rate": 1.9097446604033073e-05, + "loss": 3.2839, + "step": 186500 }, { "epoch": 0.62, - "learning_rate": 1.9105946436029144e-05, - "loss": 3.1442, - "step": 173100 + "learning_rate": 1.9080876870308694e-05, + "loss": 3.2824, + "step": 186600 }, { "epoch": 0.62, - "learning_rate": 1.9088098918083462e-05, - "loss": 3.1313, - "step": 173200 + "learning_rate": 1.9064307136584316e-05, + "loss": 3.2762, + "step": 186700 }, { "epoch": 0.62, - "learning_rate": 1.9070251400137784e-05, - "loss": 3.1386, - "step": 173300 + "learning_rate": 1.9047737402859937e-05, + "loss": 3.2758, + "step": 186800 }, { "epoch": 0.62, - "learning_rate": 1.9052403882192105e-05, - "loss": 3.1342, - "step": 173400 + "learning_rate": 1.903116766913556e-05, + "loss": 3.2933, + "step": 186900 }, { "epoch": 0.62, - "learning_rate": 1.9034556364246426e-05, - "loss": 3.1377, - "step": 173500 + "learning_rate": 1.901459793541118e-05, + "loss": 3.2803, + "step": 187000 }, { "epoch": 0.62, - "learning_rate": 1.9016708846300747e-05, - "loss": 3.1359, - "step": 173600 + "learning_rate": 1.8998028201686798e-05, + "loss": 3.2726, + "step": 187100 }, { "epoch": 0.62, - "learning_rate": 1.8998861328355065e-05, - "loss": 3.137, - "step": 173700 + "learning_rate": 1.898145846796242e-05, + "loss": 3.2732, + "step": 187200 }, { "epoch": 0.62, - "learning_rate": 1.8981013810409386e-05, - "loss": 3.1389, - "step": 173800 + "learning_rate": 1.896488873423804e-05, + "loss": 3.2787, + "step": 187300 }, { "epoch": 0.62, - "learning_rate": 1.8963166292463707e-05, - "loss": 3.1357, - "step": 173900 + "learning_rate": 1.8948319000513663e-05, + "loss": 3.2736, + "step": 187400 }, { "epoch": 0.62, - "learning_rate": 1.894531877451803e-05, - "loss": 3.1385, - "step": 174000 + "learning_rate": 1.8931749266789284e-05, + "loss": 3.2773, + "step": 187500 }, { "epoch": 0.62, - "learning_rate": 1.892747125657235e-05, - "loss": 3.1332, - "step": 174100 + "learning_rate": 1.8915179533064906e-05, + "loss": 3.2698, + "step": 187600 }, { "epoch": 0.62, - "learning_rate": 1.890962373862667e-05, - "loss": 3.1357, - "step": 174200 + "learning_rate": 1.8898609799340524e-05, + "loss": 3.2671, + "step": 187700 }, { "epoch": 0.62, - "learning_rate": 1.889177622068099e-05, - "loss": 3.1356, - "step": 174300 + "learning_rate": 1.8882040065616145e-05, + "loss": 3.281, + "step": 187800 }, { "epoch": 0.62, - "learning_rate": 1.887392870273531e-05, - "loss": 3.1322, - "step": 174400 + "learning_rate": 1.886547033189177e-05, + "loss": 3.2684, + "step": 187900 }, { "epoch": 0.62, - "learning_rate": 1.885608118478963e-05, - "loss": 3.1409, - "step": 174500 + "learning_rate": 1.8848900598167388e-05, + "loss": 3.2603, + "step": 188000 }, { "epoch": 0.62, - "learning_rate": 1.8838233666843953e-05, - "loss": 3.1269, - "step": 174600 + "learning_rate": 1.883233086444301e-05, + "loss": 3.2864, + "step": 188100 }, { "epoch": 0.62, - "learning_rate": 1.8820386148898274e-05, - "loss": 3.1241, - "step": 174700 + "learning_rate": 1.881576113071863e-05, + "loss": 3.2795, + "step": 188200 }, { "epoch": 0.62, - "learning_rate": 1.880253863095259e-05, - "loss": 3.1413, - "step": 174800 + "learning_rate": 1.879919139699425e-05, + "loss": 3.296, + "step": 188300 }, { "epoch": 0.62, - "learning_rate": 1.8784691113006913e-05, - "loss": 3.1396, - "step": 174900 + "learning_rate": 1.8782621663269874e-05, + "loss": 3.2697, + "step": 188400 }, { "epoch": 0.62, - "learning_rate": 1.8766843595061237e-05, - "loss": 3.132, - "step": 175000 + "learning_rate": 1.8766051929545492e-05, + "loss": 3.2742, + "step": 188500 }, { "epoch": 0.63, - "learning_rate": 1.874899607711556e-05, - "loss": 3.1323, - "step": 175100 + "learning_rate": 1.8749482195821113e-05, + "loss": 3.2781, + "step": 188600 }, { "epoch": 0.63, - "learning_rate": 1.873114855916988e-05, - "loss": 3.1353, - "step": 175200 + "learning_rate": 1.8732912462096735e-05, + "loss": 3.2788, + "step": 188700 }, { "epoch": 0.63, - "learning_rate": 1.8713301041224198e-05, - "loss": 3.1417, - "step": 175300 + "learning_rate": 1.8716342728372356e-05, + "loss": 3.2663, + "step": 188800 }, { "epoch": 0.63, - "learning_rate": 1.869545352327852e-05, - "loss": 3.1348, - "step": 175400 + "learning_rate": 1.8699772994647978e-05, + "loss": 3.2897, + "step": 188900 }, { "epoch": 0.63, - "learning_rate": 1.867760600533284e-05, - "loss": 3.1281, - "step": 175500 + "learning_rate": 1.86832032609236e-05, + "loss": 3.2654, + "step": 189000 }, { "epoch": 0.63, - "learning_rate": 1.865975848738716e-05, - "loss": 3.1386, - "step": 175600 + "learning_rate": 1.8666633527199217e-05, + "loss": 3.2786, + "step": 189100 }, { "epoch": 0.63, - "learning_rate": 1.8641910969441483e-05, - "loss": 3.1323, - "step": 175700 + "learning_rate": 1.865006379347484e-05, + "loss": 3.2806, + "step": 189200 }, { "epoch": 0.63, - "learning_rate": 1.86240634514958e-05, - "loss": 3.1227, - "step": 175800 + "learning_rate": 1.863349405975046e-05, + "loss": 3.2782, + "step": 189300 }, { "epoch": 0.63, - "learning_rate": 1.860621593355012e-05, - "loss": 3.138, - "step": 175900 + "learning_rate": 1.8616924326026082e-05, + "loss": 3.2772, + "step": 189400 }, { "epoch": 0.63, - "learning_rate": 1.8588368415604443e-05, - "loss": 3.1257, - "step": 176000 + "learning_rate": 1.8600354592301703e-05, + "loss": 3.2688, + "step": 189500 }, { "epoch": 0.63, - "learning_rate": 1.8570520897658764e-05, - "loss": 3.1299, - "step": 176100 + "learning_rate": 1.8583784858577325e-05, + "loss": 3.2742, + "step": 189600 }, { "epoch": 0.63, - "learning_rate": 1.8552673379713085e-05, - "loss": 3.1314, - "step": 176200 + "learning_rate": 1.8567215124852943e-05, + "loss": 3.2817, + "step": 189700 }, { "epoch": 0.63, - "learning_rate": 1.8534825861767406e-05, - "loss": 3.1355, - "step": 176300 + "learning_rate": 1.8550645391128564e-05, + "loss": 3.2615, + "step": 189800 }, { "epoch": 0.63, - "learning_rate": 1.8516978343821724e-05, - "loss": 3.126, - "step": 176400 + "learning_rate": 1.8534075657404186e-05, + "loss": 3.2737, + "step": 189900 }, { "epoch": 0.63, - "learning_rate": 1.8499130825876045e-05, - "loss": 3.1312, - "step": 176500 + "learning_rate": 1.8517505923679807e-05, + "loss": 3.2839, + "step": 190000 }, { "epoch": 0.63, - "learning_rate": 1.8481283307930367e-05, - "loss": 3.1197, - "step": 176600 + "learning_rate": 1.850093618995543e-05, + "loss": 3.2694, + "step": 190100 }, { "epoch": 0.63, - "learning_rate": 1.8463435789984688e-05, - "loss": 3.1342, - "step": 176700 + "learning_rate": 1.848436645623105e-05, + "loss": 3.2874, + "step": 190200 }, { "epoch": 0.63, - "learning_rate": 1.844558827203901e-05, - "loss": 3.1384, - "step": 176800 + "learning_rate": 1.8467796722506668e-05, + "loss": 3.2645, + "step": 190300 }, { "epoch": 0.63, - "learning_rate": 1.8427740754093327e-05, - "loss": 3.1426, - "step": 176900 + "learning_rate": 1.8451226988782293e-05, + "loss": 3.2906, + "step": 190400 }, { "epoch": 0.63, - "learning_rate": 1.8409893236147648e-05, - "loss": 3.1237, - "step": 177000 + "learning_rate": 1.8434657255057915e-05, + "loss": 3.2579, + "step": 190500 }, { "epoch": 0.63, - "learning_rate": 1.839204571820197e-05, - "loss": 3.1245, - "step": 177100 + "learning_rate": 1.8418087521333533e-05, + "loss": 3.2554, + "step": 190600 }, { "epoch": 0.63, - "learning_rate": 1.837419820025629e-05, - "loss": 3.1365, - "step": 177200 + "learning_rate": 1.8401517787609154e-05, + "loss": 3.2818, + "step": 190700 }, { "epoch": 0.63, - "learning_rate": 1.8356350682310612e-05, - "loss": 3.1307, - "step": 177300 + "learning_rate": 1.8384948053884776e-05, + "loss": 3.2676, + "step": 190800 }, { "epoch": 0.63, - "learning_rate": 1.833850316436493e-05, - "loss": 3.1447, - "step": 177400 + "learning_rate": 1.8368378320160397e-05, + "loss": 3.2777, + "step": 190900 }, { "epoch": 0.63, - "learning_rate": 1.8320655646419254e-05, - "loss": 3.123, - "step": 177500 + "learning_rate": 1.835180858643602e-05, + "loss": 3.2698, + "step": 191000 }, { "epoch": 0.63, - "learning_rate": 1.8302808128473575e-05, - "loss": 3.132, - "step": 177600 + "learning_rate": 1.8335238852711637e-05, + "loss": 3.2867, + "step": 191100 }, { "epoch": 0.63, - "learning_rate": 1.8284960610527897e-05, - "loss": 3.1343, - "step": 177700 + "learning_rate": 1.8318669118987258e-05, + "loss": 3.2775, + "step": 191200 }, { "epoch": 0.63, - "learning_rate": 1.8267113092582218e-05, - "loss": 3.1298, - "step": 177800 + "learning_rate": 1.830209938526288e-05, + "loss": 3.2695, + "step": 191300 + }, + { + "epoch": 0.63, + "learning_rate": 1.82855296515385e-05, + "loss": 3.2669, + "step": 191400 + }, + { + "epoch": 0.63, + "learning_rate": 1.8268959917814122e-05, + "loss": 3.2675, + "step": 191500 + }, + { + "epoch": 0.63, + "learning_rate": 1.8252390184089744e-05, + "loss": 3.2769, + "step": 191600 }, { "epoch": 0.64, - "learning_rate": 1.8249265574636536e-05, - "loss": 3.1341, - "step": 177900 + "learning_rate": 1.8235820450365362e-05, + "loss": 3.2674, + "step": 191700 }, { "epoch": 0.64, - "learning_rate": 1.8231418056690857e-05, - "loss": 3.1278, - "step": 178000 + "learning_rate": 1.8219250716640983e-05, + "loss": 3.2807, + "step": 191800 }, { "epoch": 0.64, - "learning_rate": 1.8213570538745178e-05, - "loss": 3.1278, - "step": 178100 + "learning_rate": 1.8202680982916605e-05, + "loss": 3.2706, + "step": 191900 }, { "epoch": 0.64, - "learning_rate": 1.81957230207995e-05, - "loss": 3.1317, - "step": 178200 + "learning_rate": 1.8186111249192226e-05, + "loss": 3.2708, + "step": 192000 }, { "epoch": 0.64, - "learning_rate": 1.817787550285382e-05, - "loss": 3.1383, - "step": 178300 + "learning_rate": 1.8169541515467848e-05, + "loss": 3.2712, + "step": 192100 }, { "epoch": 0.64, - "learning_rate": 1.816002798490814e-05, - "loss": 3.1406, - "step": 178400 + "learning_rate": 1.815297178174347e-05, + "loss": 3.2755, + "step": 192200 }, { "epoch": 0.64, - "learning_rate": 1.814218046696246e-05, - "loss": 3.1498, - "step": 178500 + "learning_rate": 1.8136402048019087e-05, + "loss": 3.289, + "step": 192300 }, { "epoch": 0.64, - "learning_rate": 1.812433294901678e-05, - "loss": 3.1261, - "step": 178600 + "learning_rate": 1.811983231429471e-05, + "loss": 3.2719, + "step": 192400 }, { "epoch": 0.64, - "learning_rate": 1.8106485431071102e-05, - "loss": 3.1343, - "step": 178700 + "learning_rate": 1.8103262580570334e-05, + "loss": 3.2822, + "step": 192500 + }, + { + "epoch": 0.64, + "learning_rate": 1.8086692846845952e-05, + "loss": 3.2781, + "step": 192600 + }, + { + "epoch": 0.64, + "learning_rate": 1.8070123113121573e-05, + "loss": 3.2812, + "step": 192700 + }, + { + "epoch": 0.64, + "learning_rate": 1.8053553379397195e-05, + "loss": 3.2678, + "step": 192800 + }, + { + "epoch": 0.64, + "learning_rate": 1.8036983645672813e-05, + "loss": 3.2609, + "step": 192900 }, { "epoch": 0.64, - "learning_rate": 1.8088637913125423e-05, - "loss": 3.12, - "step": 178800 + "learning_rate": 1.8020413911948438e-05, + "loss": 3.2811, + "step": 193000 }, { "epoch": 0.64, - "learning_rate": 1.8070790395179744e-05, - "loss": 3.1398, - "step": 178900 + "learning_rate": 1.800384417822406e-05, + "loss": 3.2712, + "step": 193100 }, { "epoch": 0.64, - "learning_rate": 1.8052942877234062e-05, - "loss": 3.1298, - "step": 179000 + "learning_rate": 1.7987274444499677e-05, + "loss": 3.2702, + "step": 193200 }, { "epoch": 0.64, - "learning_rate": 1.8035095359288384e-05, - "loss": 3.1282, - "step": 179100 + "learning_rate": 1.79707047107753e-05, + "loss": 3.2763, + "step": 193300 }, { "epoch": 0.64, - "learning_rate": 1.8017247841342705e-05, - "loss": 3.13, - "step": 179200 + "learning_rate": 1.795413497705092e-05, + "loss": 3.2628, + "step": 193400 }, { "epoch": 0.64, - "learning_rate": 1.7999400323397026e-05, - "loss": 3.1396, - "step": 179300 + "learning_rate": 1.793756524332654e-05, + "loss": 3.2723, + "step": 193500 }, { "epoch": 0.64, - "learning_rate": 1.7981552805451347e-05, - "loss": 3.1321, - "step": 179400 + "learning_rate": 1.7920995509602163e-05, + "loss": 3.2768, + "step": 193600 }, { "epoch": 0.64, - "learning_rate": 1.7963705287505665e-05, - "loss": 3.1234, - "step": 179500 + "learning_rate": 1.790442577587778e-05, + "loss": 3.2732, + "step": 193700 }, { "epoch": 0.64, - "learning_rate": 1.7945857769559986e-05, - "loss": 3.1173, - "step": 179600 + "learning_rate": 1.7887856042153403e-05, + "loss": 3.2828, + "step": 193800 }, { "epoch": 0.64, - "learning_rate": 1.7928010251614307e-05, - "loss": 3.1246, - "step": 179700 + "learning_rate": 1.7871286308429024e-05, + "loss": 3.2745, + "step": 193900 }, { "epoch": 0.64, - "learning_rate": 1.791016273366863e-05, - "loss": 3.1257, - "step": 179800 + "learning_rate": 1.7854716574704646e-05, + "loss": 3.2677, + "step": 194000 }, { "epoch": 0.64, - "learning_rate": 1.789231521572295e-05, - "loss": 3.1294, - "step": 179900 + "learning_rate": 1.7838146840980267e-05, + "loss": 3.2841, + "step": 194100 }, { "epoch": 0.64, - "learning_rate": 1.787446769777727e-05, - "loss": 3.1373, - "step": 180000 + "learning_rate": 1.782157710725589e-05, + "loss": 3.2735, + "step": 194200 }, { "epoch": 0.64, - "learning_rate": 1.7856620179831592e-05, - "loss": 3.1256, - "step": 180100 + "learning_rate": 1.7805007373531507e-05, + "loss": 3.2743, + "step": 194300 }, { "epoch": 0.64, - "learning_rate": 1.7838772661885913e-05, - "loss": 3.1224, - "step": 180200 + "learning_rate": 1.7788437639807128e-05, + "loss": 3.2792, + "step": 194400 }, { "epoch": 0.64, - "learning_rate": 1.7820925143940235e-05, - "loss": 3.1327, - "step": 180300 + "learning_rate": 1.777186790608275e-05, + "loss": 3.2849, + "step": 194500 }, { "epoch": 0.64, - "learning_rate": 1.7803077625994556e-05, - "loss": 3.1312, - "step": 180400 + "learning_rate": 1.775529817235837e-05, + "loss": 3.2608, + "step": 194600 }, { - "epoch": 0.64, - "learning_rate": 1.7785230108048874e-05, - "loss": 3.1212, - "step": 180500 + "epoch": 0.65, + "learning_rate": 1.7738728438633992e-05, + "loss": 3.2722, + "step": 194700 }, { - "epoch": 0.64, - "learning_rate": 1.7767382590103195e-05, - "loss": 3.1233, - "step": 180600 + "epoch": 0.65, + "learning_rate": 1.7722158704909614e-05, + "loss": 3.2696, + "step": 194800 }, { "epoch": 0.65, - "learning_rate": 1.7749535072157516e-05, - "loss": 3.1275, - "step": 180700 + "learning_rate": 1.7705588971185232e-05, + "loss": 3.2643, + "step": 194900 }, { "epoch": 0.65, - "learning_rate": 1.7731687554211837e-05, - "loss": 3.1319, - "step": 180800 + "learning_rate": 1.7689019237460853e-05, + "loss": 3.276, + "step": 195000 }, { "epoch": 0.65, - "learning_rate": 1.771384003626616e-05, - "loss": 3.1228, - "step": 180900 + "learning_rate": 1.7672449503736478e-05, + "loss": 3.2827, + "step": 195100 }, { "epoch": 0.65, - "learning_rate": 1.769599251832048e-05, - "loss": 3.132, - "step": 181000 + "learning_rate": 1.7655879770012096e-05, + "loss": 3.2694, + "step": 195200 }, { "epoch": 0.65, - "learning_rate": 1.7678145000374798e-05, - "loss": 3.1283, - "step": 181100 + "learning_rate": 1.7639310036287718e-05, + "loss": 3.2827, + "step": 195300 }, { "epoch": 0.65, - "learning_rate": 1.766029748242912e-05, - "loss": 3.1359, - "step": 181200 + "learning_rate": 1.762274030256334e-05, + "loss": 3.2794, + "step": 195400 }, { "epoch": 0.65, - "learning_rate": 1.764244996448344e-05, - "loss": 3.1307, - "step": 181300 + "learning_rate": 1.7606170568838957e-05, + "loss": 3.2792, + "step": 195500 }, { "epoch": 0.65, - "learning_rate": 1.762460244653776e-05, - "loss": 3.1285, - "step": 181400 + "learning_rate": 1.7589600835114582e-05, + "loss": 3.2782, + "step": 195600 }, { "epoch": 0.65, - "learning_rate": 1.7606754928592082e-05, - "loss": 3.1332, - "step": 181500 + "learning_rate": 1.7573031101390204e-05, + "loss": 3.2843, + "step": 195700 }, { "epoch": 0.65, - "learning_rate": 1.75889074106464e-05, - "loss": 3.1411, - "step": 181600 + "learning_rate": 1.7556461367665822e-05, + "loss": 3.269, + "step": 195800 }, { "epoch": 0.65, - "learning_rate": 1.757105989270072e-05, - "loss": 3.1293, - "step": 181700 + "learning_rate": 1.7539891633941443e-05, + "loss": 3.2571, + "step": 195900 }, { "epoch": 0.65, - "learning_rate": 1.7553212374755043e-05, - "loss": 3.1288, - "step": 181800 + "learning_rate": 1.7523321900217065e-05, + "loss": 3.2737, + "step": 196000 }, { "epoch": 0.65, - "learning_rate": 1.7535364856809364e-05, - "loss": 3.1277, - "step": 181900 + "learning_rate": 1.7506752166492686e-05, + "loss": 3.2767, + "step": 196100 }, { "epoch": 0.65, - "learning_rate": 1.7517517338863685e-05, - "loss": 3.1302, - "step": 182000 + "learning_rate": 1.7490182432768308e-05, + "loss": 3.284, + "step": 196200 }, { "epoch": 0.65, - "learning_rate": 1.7499669820918006e-05, - "loss": 3.1323, - "step": 182100 + "learning_rate": 1.7473612699043926e-05, + "loss": 3.2747, + "step": 196300 }, { "epoch": 0.65, - "learning_rate": 1.7481822302972324e-05, - "loss": 3.126, - "step": 182200 + "learning_rate": 1.7457042965319547e-05, + "loss": 3.2852, + "step": 196400 }, { "epoch": 0.65, - "learning_rate": 1.7463974785026645e-05, - "loss": 3.1355, - "step": 182300 + "learning_rate": 1.744047323159517e-05, + "loss": 3.2653, + "step": 196500 }, { "epoch": 0.65, - "learning_rate": 1.7446127267080967e-05, - "loss": 3.1203, - "step": 182400 + "learning_rate": 1.742390349787079e-05, + "loss": 3.2773, + "step": 196600 }, { "epoch": 0.65, - "learning_rate": 1.7428279749135288e-05, - "loss": 3.1344, - "step": 182500 + "learning_rate": 1.740733376414641e-05, + "loss": 3.2758, + "step": 196700 }, { "epoch": 0.65, - "learning_rate": 1.741043223118961e-05, - "loss": 3.1308, - "step": 182600 + "learning_rate": 1.7390764030422033e-05, + "loss": 3.2789, + "step": 196800 }, { "epoch": 0.65, - "learning_rate": 1.739258471324393e-05, - "loss": 3.1342, - "step": 182700 + "learning_rate": 1.737419429669765e-05, + "loss": 3.2661, + "step": 196900 }, { "epoch": 0.65, - "learning_rate": 1.737473719529825e-05, - "loss": 3.122, - "step": 182800 + "learning_rate": 1.7357624562973273e-05, + "loss": 3.2812, + "step": 197000 }, { "epoch": 0.65, - "learning_rate": 1.7356889677352573e-05, - "loss": 3.1351, - "step": 182900 + "learning_rate": 1.7341054829248894e-05, + "loss": 3.262, + "step": 197100 }, { "epoch": 0.65, - "learning_rate": 1.7339042159406894e-05, - "loss": 3.1266, - "step": 183000 + "learning_rate": 1.7324485095524516e-05, + "loss": 3.2723, + "step": 197200 }, { "epoch": 0.65, - "learning_rate": 1.7321194641461215e-05, - "loss": 3.1393, - "step": 183100 + "learning_rate": 1.7307915361800137e-05, + "loss": 3.2711, + "step": 197300 }, { "epoch": 0.65, - "learning_rate": 1.7303347123515533e-05, - "loss": 3.139, - "step": 183200 + "learning_rate": 1.729134562807576e-05, + "loss": 3.2912, + "step": 197400 }, { "epoch": 0.65, - "learning_rate": 1.7285499605569854e-05, - "loss": 3.1363, - "step": 183300 + "learning_rate": 1.7274775894351377e-05, + "loss": 3.2658, + "step": 197500 }, { "epoch": 0.65, - "learning_rate": 1.7267652087624175e-05, - "loss": 3.124, - "step": 183400 + "learning_rate": 1.7258206160626998e-05, + "loss": 3.2698, + "step": 197600 }, { "epoch": 0.66, - "learning_rate": 1.7249804569678497e-05, - "loss": 3.1286, - "step": 183500 + "learning_rate": 1.7241636426902623e-05, + "loss": 3.2782, + "step": 197700 }, { "epoch": 0.66, - "learning_rate": 1.7231957051732818e-05, - "loss": 3.1238, - "step": 183600 + "learning_rate": 1.722506669317824e-05, + "loss": 3.2734, + "step": 197800 }, { "epoch": 0.66, - "learning_rate": 1.7214109533787136e-05, - "loss": 3.1243, - "step": 183700 + "learning_rate": 1.7208496959453862e-05, + "loss": 3.2854, + "step": 197900 }, { "epoch": 0.66, - "learning_rate": 1.7196262015841457e-05, - "loss": 3.1202, - "step": 183800 + "learning_rate": 1.7191927225729484e-05, + "loss": 3.278, + "step": 198000 }, { "epoch": 0.66, - "learning_rate": 1.7178414497895778e-05, - "loss": 3.1328, - "step": 183900 + "learning_rate": 1.7175357492005102e-05, + "loss": 3.2804, + "step": 198100 }, { "epoch": 0.66, - "learning_rate": 1.71605669799501e-05, - "loss": 3.1232, - "step": 184000 + "learning_rate": 1.7158787758280727e-05, + "loss": 3.2614, + "step": 198200 }, { "epoch": 0.66, - "learning_rate": 1.714271946200442e-05, - "loss": 3.1449, - "step": 184100 + "learning_rate": 1.7142218024556348e-05, + "loss": 3.2862, + "step": 198300 }, { "epoch": 0.66, - "learning_rate": 1.7124871944058742e-05, - "loss": 3.1313, - "step": 184200 + "learning_rate": 1.7125648290831966e-05, + "loss": 3.2717, + "step": 198400 }, { "epoch": 0.66, - "learning_rate": 1.710702442611306e-05, - "loss": 3.1262, - "step": 184300 + "learning_rate": 1.7109078557107588e-05, + "loss": 3.2834, + "step": 198500 }, { "epoch": 0.66, - "learning_rate": 1.708917690816738e-05, - "loss": 3.1344, - "step": 184400 + "learning_rate": 1.709250882338321e-05, + "loss": 3.2916, + "step": 198600 }, { "epoch": 0.66, - "learning_rate": 1.7071329390221702e-05, - "loss": 3.1299, - "step": 184500 + "learning_rate": 1.707593908965883e-05, + "loss": 3.2828, + "step": 198700 }, { "epoch": 0.66, - "learning_rate": 1.7053481872276023e-05, - "loss": 3.1344, - "step": 184600 + "learning_rate": 1.7059369355934452e-05, + "loss": 3.282, + "step": 198800 }, { "epoch": 0.66, - "learning_rate": 1.7035634354330344e-05, - "loss": 3.1398, - "step": 184700 + "learning_rate": 1.704279962221007e-05, + "loss": 3.262, + "step": 198900 }, { "epoch": 0.66, - "learning_rate": 1.7017786836384662e-05, - "loss": 3.1356, - "step": 184800 + "learning_rate": 1.7026229888485692e-05, + "loss": 3.2708, + "step": 199000 }, { "epoch": 0.66, - "learning_rate": 1.6999939318438983e-05, - "loss": 3.1369, - "step": 184900 + "learning_rate": 1.7009660154761313e-05, + "loss": 3.2679, + "step": 199100 }, { "epoch": 0.66, - "learning_rate": 1.6982091800493305e-05, - "loss": 3.1232, - "step": 185000 + "learning_rate": 1.6993090421036935e-05, + "loss": 3.2758, + "step": 199200 }, { "epoch": 0.66, - "learning_rate": 1.6964244282547626e-05, - "loss": 3.1315, - "step": 185100 + "learning_rate": 1.6976520687312556e-05, + "loss": 3.2707, + "step": 199300 }, { "epoch": 0.66, - "learning_rate": 1.694639676460195e-05, - "loss": 3.1162, - "step": 185200 + "learning_rate": 1.6959950953588178e-05, + "loss": 3.2676, + "step": 199400 }, { "epoch": 0.66, - "learning_rate": 1.692854924665627e-05, - "loss": 3.1387, - "step": 185300 + "learning_rate": 1.6943381219863796e-05, + "loss": 3.2816, + "step": 199500 }, { "epoch": 0.66, - "learning_rate": 1.691070172871059e-05, - "loss": 3.1269, - "step": 185400 + "learning_rate": 1.6926811486139417e-05, + "loss": 3.2743, + "step": 199600 }, { "epoch": 0.66, - "learning_rate": 1.689285421076491e-05, - "loss": 3.125, - "step": 185500 + "learning_rate": 1.691024175241504e-05, + "loss": 3.2635, + "step": 199700 }, { "epoch": 0.66, - "learning_rate": 1.6875006692819232e-05, - "loss": 3.1371, - "step": 185600 + "learning_rate": 1.689367201869066e-05, + "loss": 3.2796, + "step": 199800 }, { "epoch": 0.66, - "learning_rate": 1.6857159174873553e-05, - "loss": 3.1338, - "step": 185700 + "learning_rate": 1.687710228496628e-05, + "loss": 3.272, + "step": 199900 }, { "epoch": 0.66, - "learning_rate": 1.683931165692787e-05, - "loss": 3.1286, - "step": 185800 + "learning_rate": 1.6860532551241903e-05, + "loss": 3.2711, + "step": 200000 }, { "epoch": 0.66, - "learning_rate": 1.6821464138982192e-05, - "loss": 3.124, - "step": 185900 + "learning_rate": 1.684396281751752e-05, + "loss": 3.2647, + "step": 200100 }, { "epoch": 0.66, - "learning_rate": 1.6803616621036513e-05, - "loss": 3.1215, - "step": 186000 + "learning_rate": 1.6827393083793143e-05, + "loss": 3.274, + "step": 200200 }, { "epoch": 0.66, - "learning_rate": 1.6785769103090835e-05, - "loss": 3.13, - "step": 186100 + "learning_rate": 1.6810823350068767e-05, + "loss": 3.2763, + "step": 200300 }, { "epoch": 0.66, - "learning_rate": 1.6767921585145156e-05, - "loss": 3.1392, - "step": 186200 + "learning_rate": 1.6794253616344386e-05, + "loss": 3.2745, + "step": 200400 }, { "epoch": 0.66, - "learning_rate": 1.6750074067199477e-05, - "loss": 3.1296, - "step": 186300 + "learning_rate": 1.6777683882620007e-05, + "loss": 3.2519, + "step": 200500 + }, + { + "epoch": 0.66, + "learning_rate": 1.676111414889563e-05, + "loss": 3.2775, + "step": 200600 }, { "epoch": 0.67, - "learning_rate": 1.6732226549253795e-05, - "loss": 3.1274, - "step": 186400 + "learning_rate": 1.674454441517125e-05, + "loss": 3.2831, + "step": 200700 }, { "epoch": 0.67, - "learning_rate": 1.6714379031308116e-05, - "loss": 3.1272, - "step": 186500 + "learning_rate": 1.672797468144687e-05, + "loss": 3.2673, + "step": 200800 }, { "epoch": 0.67, - "learning_rate": 1.6696531513362437e-05, - "loss": 3.1263, - "step": 186600 + "learning_rate": 1.6711404947722493e-05, + "loss": 3.2622, + "step": 200900 }, { "epoch": 0.67, - "learning_rate": 1.667868399541676e-05, - "loss": 3.1242, - "step": 186700 + "learning_rate": 1.669483521399811e-05, + "loss": 3.2647, + "step": 201000 }, { "epoch": 0.67, - "learning_rate": 1.666083647747108e-05, - "loss": 3.1294, - "step": 186800 + "learning_rate": 1.6678265480273732e-05, + "loss": 3.26, + "step": 201100 }, { "epoch": 0.67, - "learning_rate": 1.6642988959525398e-05, - "loss": 3.1363, - "step": 186900 + "learning_rate": 1.6661695746549354e-05, + "loss": 3.2538, + "step": 201200 }, { "epoch": 0.67, - "learning_rate": 1.662514144157972e-05, - "loss": 3.1321, - "step": 187000 + "learning_rate": 1.6645126012824975e-05, + "loss": 3.2711, + "step": 201300 }, { "epoch": 0.67, - "learning_rate": 1.660729392363404e-05, - "loss": 3.1286, - "step": 187100 + "learning_rate": 1.6628556279100597e-05, + "loss": 3.2769, + "step": 201400 }, { "epoch": 0.67, - "learning_rate": 1.658944640568836e-05, - "loss": 3.1261, - "step": 187200 + "learning_rate": 1.6611986545376215e-05, + "loss": 3.272, + "step": 201500 }, { "epoch": 0.67, - "learning_rate": 1.6571598887742682e-05, - "loss": 3.1291, - "step": 187300 + "learning_rate": 1.6595416811651836e-05, + "loss": 3.2759, + "step": 201600 }, { "epoch": 0.67, - "learning_rate": 1.6553751369797004e-05, - "loss": 3.1364, - "step": 187400 + "learning_rate": 1.6578847077927458e-05, + "loss": 3.2674, + "step": 201700 }, { "epoch": 0.67, - "learning_rate": 1.653590385185132e-05, - "loss": 3.1319, - "step": 187500 + "learning_rate": 1.656227734420308e-05, + "loss": 3.2609, + "step": 201800 }, { "epoch": 0.67, - "learning_rate": 1.6518056333905643e-05, - "loss": 3.1299, - "step": 187600 + "learning_rate": 1.65457076104787e-05, + "loss": 3.277, + "step": 201900 }, { "epoch": 0.67, - "learning_rate": 1.6500208815959967e-05, - "loss": 3.1234, - "step": 187700 + "learning_rate": 1.6529137876754322e-05, + "loss": 3.2703, + "step": 202000 }, { "epoch": 0.67, - "learning_rate": 1.648236129801429e-05, - "loss": 3.1269, - "step": 187800 + "learning_rate": 1.651256814302994e-05, + "loss": 3.2654, + "step": 202100 }, { "epoch": 0.67, - "learning_rate": 1.6464513780068606e-05, - "loss": 3.1363, - "step": 187900 + "learning_rate": 1.6495998409305562e-05, + "loss": 3.2692, + "step": 202200 }, { "epoch": 0.67, - "learning_rate": 1.6446666262122928e-05, - "loss": 3.1335, - "step": 188000 + "learning_rate": 1.6479428675581187e-05, + "loss": 3.2681, + "step": 202300 }, { "epoch": 0.67, - "learning_rate": 1.642881874417725e-05, - "loss": 3.1418, - "step": 188100 + "learning_rate": 1.6462858941856805e-05, + "loss": 3.2711, + "step": 202400 + }, + { + "epoch": 0.67, + "learning_rate": 1.6446289208132426e-05, + "loss": 3.2859, + "step": 202500 + }, + { + "epoch": 0.67, + "learning_rate": 1.6429719474408048e-05, + "loss": 3.2762, + "step": 202600 + }, + { + "epoch": 0.67, + "learning_rate": 1.6413149740683666e-05, + "loss": 3.2669, + "step": 202700 + }, + { + "epoch": 0.67, + "learning_rate": 1.639658000695929e-05, + "loss": 3.2609, + "step": 202800 + }, + { + "epoch": 0.67, + "learning_rate": 1.6380010273234912e-05, + "loss": 3.2642, + "step": 202900 }, { "epoch": 0.67, - "learning_rate": 1.641097122623157e-05, - "loss": 3.1346, - "step": 188200 + "learning_rate": 1.636344053951053e-05, + "loss": 3.2758, + "step": 203000 }, { "epoch": 0.67, - "learning_rate": 1.639312370828589e-05, - "loss": 3.1331, - "step": 188300 + "learning_rate": 1.634687080578615e-05, + "loss": 3.2725, + "step": 203100 }, { "epoch": 0.67, - "learning_rate": 1.6375276190340212e-05, - "loss": 3.1241, - "step": 188400 + "learning_rate": 1.6330301072061773e-05, + "loss": 3.255, + "step": 203200 }, { "epoch": 0.67, - "learning_rate": 1.635742867239453e-05, - "loss": 3.1376, - "step": 188500 + "learning_rate": 1.6313731338337395e-05, + "loss": 3.285, + "step": 203300 }, { "epoch": 0.67, - "learning_rate": 1.633958115444885e-05, - "loss": 3.1374, - "step": 188600 + "learning_rate": 1.6297161604613016e-05, + "loss": 3.2618, + "step": 203400 }, { "epoch": 0.67, - "learning_rate": 1.6321733636503173e-05, - "loss": 3.1248, - "step": 188700 + "learning_rate": 1.6280591870888637e-05, + "loss": 3.2692, + "step": 203500 }, { "epoch": 0.67, - "learning_rate": 1.6303886118557494e-05, - "loss": 3.1244, - "step": 188800 + "learning_rate": 1.6264022137164256e-05, + "loss": 3.2772, + "step": 203600 }, { - "epoch": 0.67, - "learning_rate": 1.6286038600611815e-05, - "loss": 3.1274, - "step": 188900 + "epoch": 0.68, + "learning_rate": 1.6247452403439877e-05, + "loss": 3.2657, + "step": 203700 }, { - "epoch": 0.67, - "learning_rate": 1.6268191082666133e-05, - "loss": 3.1286, - "step": 189000 + "epoch": 0.68, + "learning_rate": 1.62308826697155e-05, + "loss": 3.2651, + "step": 203800 }, { - "epoch": 0.67, - "learning_rate": 1.6250343564720454e-05, - "loss": 3.121, - "step": 189100 + "epoch": 0.68, + "learning_rate": 1.621431293599112e-05, + "loss": 3.2729, + "step": 203900 }, { "epoch": 0.68, - "learning_rate": 1.6232496046774775e-05, - "loss": 3.1287, - "step": 189200 + "learning_rate": 1.619774320226674e-05, + "loss": 3.2661, + "step": 204000 }, { "epoch": 0.68, - "learning_rate": 1.6214648528829097e-05, - "loss": 3.1245, - "step": 189300 + "learning_rate": 1.618117346854236e-05, + "loss": 3.2808, + "step": 204100 }, { "epoch": 0.68, - "learning_rate": 1.6196801010883418e-05, - "loss": 3.1183, - "step": 189400 + "learning_rate": 1.616460373481798e-05, + "loss": 3.2671, + "step": 204200 }, { "epoch": 0.68, - "learning_rate": 1.6178953492937736e-05, - "loss": 3.1179, - "step": 189500 + "learning_rate": 1.6148034001093602e-05, + "loss": 3.2564, + "step": 204300 }, { "epoch": 0.68, - "learning_rate": 1.6161105974992057e-05, - "loss": 3.1254, - "step": 189600 + "learning_rate": 1.6131464267369224e-05, + "loss": 3.2659, + "step": 204400 }, { "epoch": 0.68, - "learning_rate": 1.6143258457046378e-05, - "loss": 3.121, - "step": 189700 + "learning_rate": 1.6114894533644845e-05, + "loss": 3.2725, + "step": 204500 }, { "epoch": 0.68, - "learning_rate": 1.61254109391007e-05, - "loss": 3.124, - "step": 189800 + "learning_rate": 1.6098324799920467e-05, + "loss": 3.2711, + "step": 204600 }, { "epoch": 0.68, - "learning_rate": 1.610756342115502e-05, - "loss": 3.1131, - "step": 189900 + "learning_rate": 1.6081755066196085e-05, + "loss": 3.2673, + "step": 204700 }, { "epoch": 0.68, - "learning_rate": 1.6089715903209342e-05, - "loss": 3.1189, - "step": 190000 + "learning_rate": 1.6065185332471706e-05, + "loss": 3.2573, + "step": 204800 }, { "epoch": 0.68, - "learning_rate": 1.607186838526366e-05, - "loss": 3.1255, - "step": 190100 + "learning_rate": 1.604861559874733e-05, + "loss": 3.272, + "step": 204900 }, { "epoch": 0.68, - "learning_rate": 1.605402086731798e-05, - "loss": 3.1354, - "step": 190200 + "learning_rate": 1.603204586502295e-05, + "loss": 3.2781, + "step": 205000 }, { "epoch": 0.68, - "learning_rate": 1.6036173349372305e-05, - "loss": 3.1248, - "step": 190300 + "learning_rate": 1.601547613129857e-05, + "loss": 3.267, + "step": 205100 }, { "epoch": 0.68, - "learning_rate": 1.6018325831426627e-05, - "loss": 3.1227, - "step": 190400 + "learning_rate": 1.5998906397574192e-05, + "loss": 3.2583, + "step": 205200 }, { "epoch": 0.68, - "learning_rate": 1.6000478313480944e-05, - "loss": 3.1121, - "step": 190500 + "learning_rate": 1.598233666384981e-05, + "loss": 3.2733, + "step": 205300 }, { "epoch": 0.68, - "learning_rate": 1.5982630795535266e-05, - "loss": 3.1204, - "step": 190600 + "learning_rate": 1.5965766930125435e-05, + "loss": 3.2601, + "step": 205400 }, { "epoch": 0.68, - "learning_rate": 1.5964783277589587e-05, - "loss": 3.1311, - "step": 190700 + "learning_rate": 1.5949197196401057e-05, + "loss": 3.2657, + "step": 205500 }, { "epoch": 0.68, - "learning_rate": 1.5946935759643908e-05, - "loss": 3.1149, - "step": 190800 + "learning_rate": 1.5932627462676675e-05, + "loss": 3.2769, + "step": 205600 }, { "epoch": 0.68, - "learning_rate": 1.592908824169823e-05, - "loss": 3.1223, - "step": 190900 + "learning_rate": 1.5916057728952296e-05, + "loss": 3.265, + "step": 205700 }, { "epoch": 0.68, - "learning_rate": 1.591124072375255e-05, - "loss": 3.131, - "step": 191000 + "learning_rate": 1.5899487995227918e-05, + "loss": 3.272, + "step": 205800 }, { "epoch": 0.68, - "learning_rate": 1.589339320580687e-05, - "loss": 3.122, - "step": 191100 + "learning_rate": 1.588291826150354e-05, + "loss": 3.278, + "step": 205900 }, { "epoch": 0.68, - "learning_rate": 1.587554568786119e-05, - "loss": 3.1225, - "step": 191200 + "learning_rate": 1.586634852777916e-05, + "loss": 3.2666, + "step": 206000 }, { "epoch": 0.68, - "learning_rate": 1.585769816991551e-05, - "loss": 3.1244, - "step": 191300 + "learning_rate": 1.5849778794054782e-05, + "loss": 3.2741, + "step": 206100 }, { "epoch": 0.68, - "learning_rate": 1.5839850651969832e-05, - "loss": 3.1167, - "step": 191400 + "learning_rate": 1.58332090603304e-05, + "loss": 3.26, + "step": 206200 }, { "epoch": 0.68, - "learning_rate": 1.5822003134024153e-05, - "loss": 3.123, - "step": 191500 + "learning_rate": 1.581663932660602e-05, + "loss": 3.2676, + "step": 206300 }, { "epoch": 0.68, - "learning_rate": 1.580415561607847e-05, - "loss": 3.1389, - "step": 191600 + "learning_rate": 1.5800069592881643e-05, + "loss": 3.2819, + "step": 206400 }, { "epoch": 0.68, - "learning_rate": 1.5786308098132792e-05, - "loss": 3.1239, - "step": 191700 + "learning_rate": 1.5783499859157265e-05, + "loss": 3.2651, + "step": 206500 }, { "epoch": 0.68, - "learning_rate": 1.5768460580187113e-05, - "loss": 3.1185, - "step": 191800 + "learning_rate": 1.5766930125432886e-05, + "loss": 3.2679, + "step": 206600 }, { "epoch": 0.68, - "learning_rate": 1.5750613062241435e-05, - "loss": 3.125, - "step": 191900 + "learning_rate": 1.5750360391708504e-05, + "loss": 3.2687, + "step": 206700 }, { "epoch": 0.69, - "learning_rate": 1.5732765544295756e-05, - "loss": 3.1345, - "step": 192000 + "learning_rate": 1.5733790657984126e-05, + "loss": 3.2705, + "step": 206800 }, { "epoch": 0.69, - "learning_rate": 1.5714918026350077e-05, - "loss": 3.1145, - "step": 192100 + "learning_rate": 1.5717220924259747e-05, + "loss": 3.2602, + "step": 206900 }, { "epoch": 0.69, - "learning_rate": 1.5697070508404395e-05, - "loss": 3.12, - "step": 192200 + "learning_rate": 1.570065119053537e-05, + "loss": 3.28, + "step": 207000 }, { "epoch": 0.69, - "learning_rate": 1.5679222990458716e-05, - "loss": 3.1294, - "step": 192300 + "learning_rate": 1.568408145681099e-05, + "loss": 3.2859, + "step": 207100 }, { "epoch": 0.69, - "learning_rate": 1.5661375472513037e-05, - "loss": 3.1238, - "step": 192400 + "learning_rate": 1.566751172308661e-05, + "loss": 3.267, + "step": 207200 }, { "epoch": 0.69, - "learning_rate": 1.564352795456736e-05, - "loss": 3.1256, - "step": 192500 + "learning_rate": 1.565094198936223e-05, + "loss": 3.2582, + "step": 207300 }, { "epoch": 0.69, - "learning_rate": 1.562568043662168e-05, - "loss": 3.1356, - "step": 192600 + "learning_rate": 1.563437225563785e-05, + "loss": 3.2728, + "step": 207400 }, { "epoch": 0.69, - "learning_rate": 1.5607832918675998e-05, - "loss": 3.1153, - "step": 192700 + "learning_rate": 1.5617802521913476e-05, + "loss": 3.2592, + "step": 207500 }, { "epoch": 0.69, - "learning_rate": 1.5589985400730322e-05, - "loss": 3.1299, - "step": 192800 + "learning_rate": 1.5601232788189094e-05, + "loss": 3.2644, + "step": 207600 }, { "epoch": 0.69, - "learning_rate": 1.5572137882784643e-05, - "loss": 3.1328, - "step": 192900 + "learning_rate": 1.5584663054464715e-05, + "loss": 3.2588, + "step": 207700 }, { "epoch": 0.69, - "learning_rate": 1.5554290364838965e-05, - "loss": 3.1373, - "step": 193000 + "learning_rate": 1.5568093320740337e-05, + "loss": 3.2614, + "step": 207800 }, { "epoch": 0.69, - "learning_rate": 1.5536442846893286e-05, - "loss": 3.1266, - "step": 193100 + "learning_rate": 1.5551523587015955e-05, + "loss": 3.2743, + "step": 207900 }, { "epoch": 0.69, - "learning_rate": 1.5518595328947604e-05, - "loss": 3.1223, - "step": 193200 + "learning_rate": 1.553495385329158e-05, + "loss": 3.2708, + "step": 208000 }, { "epoch": 0.69, - "learning_rate": 1.5500747811001925e-05, - "loss": 3.1258, - "step": 193300 + "learning_rate": 1.55183841195672e-05, + "loss": 3.2642, + "step": 208100 }, { "epoch": 0.69, - "learning_rate": 1.5482900293056246e-05, - "loss": 3.1174, - "step": 193400 + "learning_rate": 1.550181438584282e-05, + "loss": 3.2638, + "step": 208200 }, { "epoch": 0.69, - "learning_rate": 1.5465052775110567e-05, - "loss": 3.1294, - "step": 193500 + "learning_rate": 1.548524465211844e-05, + "loss": 3.2632, + "step": 208300 }, { "epoch": 0.69, - "learning_rate": 1.544720525716489e-05, - "loss": 3.1213, - "step": 193600 + "learning_rate": 1.5468674918394062e-05, + "loss": 3.2665, + "step": 208400 }, { "epoch": 0.69, - "learning_rate": 1.5429357739219206e-05, - "loss": 3.1252, - "step": 193700 + "learning_rate": 1.5452105184669684e-05, + "loss": 3.2573, + "step": 208500 }, { "epoch": 0.69, - "learning_rate": 1.5411510221273528e-05, - "loss": 3.123, - "step": 193800 + "learning_rate": 1.5435535450945305e-05, + "loss": 3.2811, + "step": 208600 }, { "epoch": 0.69, - "learning_rate": 1.539366270332785e-05, - "loss": 3.1162, - "step": 193900 + "learning_rate": 1.5418965717220927e-05, + "loss": 3.2649, + "step": 208700 }, { "epoch": 0.69, - "learning_rate": 1.537581518538217e-05, - "loss": 3.1252, - "step": 194000 + "learning_rate": 1.5402395983496545e-05, + "loss": 3.2668, + "step": 208800 }, { "epoch": 0.69, - "learning_rate": 1.535796766743649e-05, - "loss": 3.1217, - "step": 194100 + "learning_rate": 1.5385826249772166e-05, + "loss": 3.2554, + "step": 208900 }, { "epoch": 0.69, - "learning_rate": 1.5340120149490812e-05, - "loss": 3.1238, - "step": 194200 + "learning_rate": 1.5369256516047788e-05, + "loss": 3.2817, + "step": 209000 }, { "epoch": 0.69, - "learning_rate": 1.532227263154513e-05, - "loss": 3.1294, - "step": 194300 + "learning_rate": 1.535268678232341e-05, + "loss": 3.2759, + "step": 209100 }, { "epoch": 0.69, - "learning_rate": 1.530442511359945e-05, - "loss": 3.124, - "step": 194400 + "learning_rate": 1.533611704859903e-05, + "loss": 3.2723, + "step": 209200 }, { "epoch": 0.69, - "learning_rate": 1.5286577595653773e-05, - "loss": 3.1274, - "step": 194500 + "learning_rate": 1.531954731487465e-05, + "loss": 3.2701, + "step": 209300 }, { "epoch": 0.69, - "learning_rate": 1.5268730077708094e-05, - "loss": 3.1375, - "step": 194600 + "learning_rate": 1.530297758115027e-05, + "loss": 3.2646, + "step": 209400 }, { "epoch": 0.69, - "learning_rate": 1.5250882559762413e-05, - "loss": 3.1158, - "step": 194700 + "learning_rate": 1.528640784742589e-05, + "loss": 3.2729, + "step": 209500 + }, + { + "epoch": 0.69, + "learning_rate": 1.5269838113701513e-05, + "loss": 3.2627, + "step": 209600 + }, + { + "epoch": 0.69, + "learning_rate": 1.5253268379977135e-05, + "loss": 3.2799, + "step": 209700 }, { "epoch": 0.7, - "learning_rate": 1.5233035041816735e-05, - "loss": 3.1363, - "step": 194800 + "learning_rate": 1.5236698646252756e-05, + "loss": 3.2756, + "step": 209800 }, { "epoch": 0.7, - "learning_rate": 1.5215187523871056e-05, - "loss": 3.1311, - "step": 194900 + "learning_rate": 1.5220128912528376e-05, + "loss": 3.276, + "step": 209900 }, { "epoch": 0.7, - "learning_rate": 1.5197340005925375e-05, - "loss": 3.1218, - "step": 195000 + "learning_rate": 1.5203559178803997e-05, + "loss": 3.2698, + "step": 210000 }, { "epoch": 0.7, - "learning_rate": 1.5179492487979697e-05, - "loss": 3.1282, - "step": 195100 + "learning_rate": 1.5186989445079619e-05, + "loss": 3.2557, + "step": 210100 }, { "epoch": 0.7, - "learning_rate": 1.5161644970034016e-05, - "loss": 3.1175, - "step": 195200 + "learning_rate": 1.5170419711355239e-05, + "loss": 3.2655, + "step": 210200 }, { "epoch": 0.7, - "learning_rate": 1.5143797452088337e-05, - "loss": 3.115, - "step": 195300 + "learning_rate": 1.515384997763086e-05, + "loss": 3.2645, + "step": 210300 }, { "epoch": 0.7, - "learning_rate": 1.512594993414266e-05, - "loss": 3.1264, - "step": 195400 + "learning_rate": 1.5137280243906481e-05, + "loss": 3.2626, + "step": 210400 }, { "epoch": 0.7, - "learning_rate": 1.5108102416196981e-05, - "loss": 3.1281, - "step": 195500 + "learning_rate": 1.5120710510182101e-05, + "loss": 3.2686, + "step": 210500 }, { "epoch": 0.7, - "learning_rate": 1.5090254898251303e-05, - "loss": 3.1347, - "step": 195600 + "learning_rate": 1.5104140776457723e-05, + "loss": 3.2641, + "step": 210600 }, { "epoch": 0.7, - "learning_rate": 1.5072407380305622e-05, - "loss": 3.1207, - "step": 195700 + "learning_rate": 1.5087571042733344e-05, + "loss": 3.2622, + "step": 210700 }, { "epoch": 0.7, - "learning_rate": 1.5054559862359943e-05, - "loss": 3.1319, - "step": 195800 + "learning_rate": 1.5071001309008964e-05, + "loss": 3.267, + "step": 210800 }, { "epoch": 0.7, - "learning_rate": 1.5036712344414265e-05, - "loss": 3.1195, - "step": 195900 + "learning_rate": 1.5054431575284585e-05, + "loss": 3.2524, + "step": 210900 }, { "epoch": 0.7, - "learning_rate": 1.5018864826468584e-05, - "loss": 3.1151, - "step": 196000 + "learning_rate": 1.5037861841560209e-05, + "loss": 3.2742, + "step": 211000 }, { "epoch": 0.7, - "learning_rate": 1.5001017308522905e-05, - "loss": 3.1169, - "step": 196100 + "learning_rate": 1.5021292107835827e-05, + "loss": 3.2675, + "step": 211100 }, { "epoch": 0.7, - "learning_rate": 1.4983169790577225e-05, - "loss": 3.1224, - "step": 196200 + "learning_rate": 1.500472237411145e-05, + "loss": 3.266, + "step": 211200 }, { "epoch": 0.7, - "learning_rate": 1.4965322272631546e-05, - "loss": 3.1324, - "step": 196300 + "learning_rate": 1.4988152640387071e-05, + "loss": 3.2709, + "step": 211300 }, { "epoch": 0.7, - "learning_rate": 1.4947474754685867e-05, - "loss": 3.1289, - "step": 196400 + "learning_rate": 1.497158290666269e-05, + "loss": 3.2726, + "step": 211400 }, { "epoch": 0.7, - "learning_rate": 1.4929627236740187e-05, - "loss": 3.1293, - "step": 196500 + "learning_rate": 1.4955013172938312e-05, + "loss": 3.2645, + "step": 211500 }, { "epoch": 0.7, - "learning_rate": 1.4911779718794508e-05, - "loss": 3.122, - "step": 196600 + "learning_rate": 1.4938443439213934e-05, + "loss": 3.2738, + "step": 211600 }, { "epoch": 0.7, - "learning_rate": 1.489393220084883e-05, - "loss": 3.1252, - "step": 196700 + "learning_rate": 1.4921873705489554e-05, + "loss": 3.2913, + "step": 211700 }, { "epoch": 0.7, - "learning_rate": 1.4876084682903149e-05, - "loss": 3.1235, - "step": 196800 + "learning_rate": 1.4905303971765175e-05, + "loss": 3.252, + "step": 211800 }, { "epoch": 0.7, - "learning_rate": 1.485823716495747e-05, - "loss": 3.122, - "step": 196900 + "learning_rate": 1.4888734238040793e-05, + "loss": 3.2723, + "step": 211900 }, { "epoch": 0.7, - "learning_rate": 1.4840389647011791e-05, - "loss": 3.1222, - "step": 197000 + "learning_rate": 1.4872164504316416e-05, + "loss": 3.2825, + "step": 212000 }, { "epoch": 0.7, - "learning_rate": 1.482254212906611e-05, - "loss": 3.1248, - "step": 197100 + "learning_rate": 1.4855594770592038e-05, + "loss": 3.2527, + "step": 212100 }, { "epoch": 0.7, - "learning_rate": 1.4804694611120432e-05, - "loss": 3.1217, - "step": 197200 + "learning_rate": 1.4839025036867658e-05, + "loss": 3.2679, + "step": 212200 }, { "epoch": 0.7, - "learning_rate": 1.4786847093174751e-05, - "loss": 3.1317, - "step": 197300 + "learning_rate": 1.4822455303143279e-05, + "loss": 3.2703, + "step": 212300 }, { "epoch": 0.7, - "learning_rate": 1.4768999575229073e-05, - "loss": 3.1219, - "step": 197400 + "learning_rate": 1.48058855694189e-05, + "loss": 3.2642, + "step": 212400 }, { "epoch": 0.7, - "learning_rate": 1.4751152057283394e-05, - "loss": 3.1173, - "step": 197500 + "learning_rate": 1.478931583569452e-05, + "loss": 3.2626, + "step": 212500 + }, + { + "epoch": 0.7, + "learning_rate": 1.4772746101970142e-05, + "loss": 3.2632, + "step": 212600 + }, + { + "epoch": 0.7, + "learning_rate": 1.4756176368245763e-05, + "loss": 3.2841, + "step": 212700 + }, + { + "epoch": 0.71, + "learning_rate": 1.4739606634521383e-05, + "loss": 3.2687, + "step": 212800 + }, + { + "epoch": 0.71, + "learning_rate": 1.4723036900797005e-05, + "loss": 3.2673, + "step": 212900 }, { "epoch": 0.71, - "learning_rate": 1.4733304539337713e-05, - "loss": 3.1181, - "step": 197600 + "learning_rate": 1.4706467167072626e-05, + "loss": 3.2596, + "step": 213000 }, { "epoch": 0.71, - "learning_rate": 1.4715457021392035e-05, - "loss": 3.1126, - "step": 197700 + "learning_rate": 1.4689897433348246e-05, + "loss": 3.2696, + "step": 213100 }, { "epoch": 0.71, - "learning_rate": 1.4697609503446356e-05, - "loss": 3.1318, - "step": 197800 + "learning_rate": 1.4673327699623867e-05, + "loss": 3.2732, + "step": 213200 }, { "epoch": 0.71, - "learning_rate": 1.4679761985500679e-05, - "loss": 3.123, - "step": 197900 + "learning_rate": 1.465675796589949e-05, + "loss": 3.2571, + "step": 213300 }, { "epoch": 0.71, - "learning_rate": 1.4661914467554998e-05, - "loss": 3.1261, - "step": 198000 + "learning_rate": 1.4640188232175109e-05, + "loss": 3.2726, + "step": 213400 }, { "epoch": 0.71, - "learning_rate": 1.464406694960932e-05, - "loss": 3.118, - "step": 198100 + "learning_rate": 1.462361849845073e-05, + "loss": 3.2675, + "step": 213500 }, { "epoch": 0.71, - "learning_rate": 1.462621943166364e-05, - "loss": 3.1183, - "step": 198200 + "learning_rate": 1.4607048764726353e-05, + "loss": 3.2576, + "step": 213600 }, { "epoch": 0.71, - "learning_rate": 1.460837191371796e-05, - "loss": 3.1239, - "step": 198300 + "learning_rate": 1.4590479031001971e-05, + "loss": 3.2547, + "step": 213700 }, { "epoch": 0.71, - "learning_rate": 1.4590524395772281e-05, - "loss": 3.1142, - "step": 198400 + "learning_rate": 1.4573909297277594e-05, + "loss": 3.282, + "step": 213800 }, { "epoch": 0.71, - "learning_rate": 1.4572676877826603e-05, - "loss": 3.1276, - "step": 198500 + "learning_rate": 1.4557339563553216e-05, + "loss": 3.2658, + "step": 213900 }, { "epoch": 0.71, - "learning_rate": 1.4554829359880922e-05, - "loss": 3.1186, - "step": 198600 + "learning_rate": 1.4540769829828834e-05, + "loss": 3.2729, + "step": 214000 }, { "epoch": 0.71, - "learning_rate": 1.4536981841935243e-05, - "loss": 3.1233, - "step": 198700 + "learning_rate": 1.4524200096104457e-05, + "loss": 3.2687, + "step": 214100 }, { "epoch": 0.71, - "learning_rate": 1.4519134323989565e-05, - "loss": 3.1223, - "step": 198800 + "learning_rate": 1.4507630362380079e-05, + "loss": 3.2659, + "step": 214200 }, { "epoch": 0.71, - "learning_rate": 1.4501286806043884e-05, - "loss": 3.119, - "step": 198900 + "learning_rate": 1.4491060628655698e-05, + "loss": 3.2719, + "step": 214300 }, { "epoch": 0.71, - "learning_rate": 1.4483439288098205e-05, - "loss": 3.1177, - "step": 199000 + "learning_rate": 1.447449089493132e-05, + "loss": 3.2633, + "step": 214400 }, { "epoch": 0.71, - "learning_rate": 1.4465591770152525e-05, - "loss": 3.126, - "step": 199100 + "learning_rate": 1.445792116120694e-05, + "loss": 3.2628, + "step": 214500 }, { "epoch": 0.71, - "learning_rate": 1.4447744252206846e-05, - "loss": 3.129, - "step": 199200 + "learning_rate": 1.4441351427482561e-05, + "loss": 3.2652, + "step": 214600 }, { "epoch": 0.71, - "learning_rate": 1.4429896734261167e-05, - "loss": 3.1285, - "step": 199300 + "learning_rate": 1.4424781693758182e-05, + "loss": 3.2631, + "step": 214700 }, { "epoch": 0.71, - "learning_rate": 1.4412049216315487e-05, - "loss": 3.1231, - "step": 199400 + "learning_rate": 1.4408211960033802e-05, + "loss": 3.2642, + "step": 214800 }, { "epoch": 0.71, - "learning_rate": 1.4394201698369808e-05, - "loss": 3.1198, - "step": 199500 + "learning_rate": 1.4391642226309424e-05, + "loss": 3.267, + "step": 214900 }, { "epoch": 0.71, - "learning_rate": 1.437635418042413e-05, - "loss": 3.1282, - "step": 199600 + "learning_rate": 1.4375072492585045e-05, + "loss": 3.2726, + "step": 215000 }, { "epoch": 0.71, - "learning_rate": 1.4358506662478449e-05, - "loss": 3.1317, - "step": 199700 + "learning_rate": 1.4358502758860665e-05, + "loss": 3.2743, + "step": 215100 }, { "epoch": 0.71, - "learning_rate": 1.434065914453277e-05, - "loss": 3.1208, - "step": 199800 + "learning_rate": 1.4341933025136286e-05, + "loss": 3.2726, + "step": 215200 }, { "epoch": 0.71, - "learning_rate": 1.4322811626587091e-05, - "loss": 3.1203, - "step": 199900 + "learning_rate": 1.4325363291411908e-05, + "loss": 3.2818, + "step": 215300 }, { "epoch": 0.71, - "learning_rate": 1.430496410864141e-05, - "loss": 3.1318, - "step": 200000 + "learning_rate": 1.4308793557687528e-05, + "loss": 3.2623, + "step": 215400 }, { "epoch": 0.71, - "learning_rate": 1.4287116590695732e-05, - "loss": 3.1188, - "step": 200100 + "learning_rate": 1.4292223823963149e-05, + "loss": 3.2673, + "step": 215500 }, { "epoch": 0.71, - "learning_rate": 1.4269269072750051e-05, - "loss": 3.1223, - "step": 200200 + "learning_rate": 1.427565409023877e-05, + "loss": 3.2711, + "step": 215600 }, { "epoch": 0.71, - "learning_rate": 1.4251421554804373e-05, - "loss": 3.1178, - "step": 200300 + "learning_rate": 1.425908435651439e-05, + "loss": 3.2587, + "step": 215700 }, { "epoch": 0.72, - "learning_rate": 1.4233574036858694e-05, - "loss": 3.1117, - "step": 200400 + "learning_rate": 1.4242514622790012e-05, + "loss": 3.2702, + "step": 215800 }, { "epoch": 0.72, - "learning_rate": 1.4215726518913017e-05, - "loss": 3.1254, - "step": 200500 + "learning_rate": 1.4225944889065635e-05, + "loss": 3.274, + "step": 215900 }, { "epoch": 0.72, - "learning_rate": 1.4197879000967338e-05, - "loss": 3.1241, - "step": 200600 + "learning_rate": 1.4209375155341253e-05, + "loss": 3.2676, + "step": 216000 }, { "epoch": 0.72, - "learning_rate": 1.4180031483021658e-05, - "loss": 3.1169, - "step": 200700 + "learning_rate": 1.4192805421616876e-05, + "loss": 3.2663, + "step": 216100 }, { "epoch": 0.72, - "learning_rate": 1.4162183965075979e-05, - "loss": 3.1193, - "step": 200800 + "learning_rate": 1.4176235687892498e-05, + "loss": 3.2568, + "step": 216200 }, { "epoch": 0.72, - "learning_rate": 1.41443364471303e-05, - "loss": 3.1267, - "step": 200900 + "learning_rate": 1.4159665954168116e-05, + "loss": 3.2576, + "step": 216300 }, { "epoch": 0.72, - "learning_rate": 1.412648892918462e-05, - "loss": 3.1263, - "step": 201000 + "learning_rate": 1.4143096220443739e-05, + "loss": 3.262, + "step": 216400 }, { "epoch": 0.72, - "learning_rate": 1.410864141123894e-05, - "loss": 3.1111, - "step": 201100 + "learning_rate": 1.412652648671936e-05, + "loss": 3.2699, + "step": 216500 }, { "epoch": 0.72, - "learning_rate": 1.409079389329326e-05, - "loss": 3.1135, - "step": 201200 + "learning_rate": 1.410995675299498e-05, + "loss": 3.2637, + "step": 216600 }, { "epoch": 0.72, - "learning_rate": 1.4072946375347581e-05, - "loss": 3.1293, - "step": 201300 + "learning_rate": 1.4093387019270602e-05, + "loss": 3.2598, + "step": 216700 }, { "epoch": 0.72, - "learning_rate": 1.4055098857401903e-05, - "loss": 3.1282, - "step": 201400 + "learning_rate": 1.4076817285546223e-05, + "loss": 3.2566, + "step": 216800 }, { "epoch": 0.72, - "learning_rate": 1.4037251339456222e-05, - "loss": 3.124, - "step": 201500 + "learning_rate": 1.4060247551821843e-05, + "loss": 3.2691, + "step": 216900 }, { "epoch": 0.72, - "learning_rate": 1.4019403821510543e-05, - "loss": 3.1283, - "step": 201600 + "learning_rate": 1.4043677818097464e-05, + "loss": 3.2843, + "step": 217000 }, { "epoch": 0.72, - "learning_rate": 1.4001556303564865e-05, - "loss": 3.1172, - "step": 201700 + "learning_rate": 1.4027108084373084e-05, + "loss": 3.2771, + "step": 217100 }, { "epoch": 0.72, - "learning_rate": 1.3983708785619184e-05, - "loss": 3.1233, - "step": 201800 + "learning_rate": 1.4010538350648706e-05, + "loss": 3.2689, + "step": 217200 }, { "epoch": 0.72, - "learning_rate": 1.3965861267673505e-05, - "loss": 3.1149, - "step": 201900 + "learning_rate": 1.3993968616924327e-05, + "loss": 3.2526, + "step": 217300 }, { "epoch": 0.72, - "learning_rate": 1.3948013749727827e-05, - "loss": 3.1192, - "step": 202000 + "learning_rate": 1.3977398883199947e-05, + "loss": 3.26, + "step": 217400 }, { "epoch": 0.72, - "learning_rate": 1.3930166231782146e-05, - "loss": 3.1165, - "step": 202100 + "learning_rate": 1.3960829149475568e-05, + "loss": 3.2756, + "step": 217500 }, { "epoch": 0.72, - "learning_rate": 1.3912318713836467e-05, - "loss": 3.1175, - "step": 202200 + "learning_rate": 1.394425941575119e-05, + "loss": 3.2708, + "step": 217600 }, { "epoch": 0.72, - "learning_rate": 1.3894471195890787e-05, - "loss": 3.111, - "step": 202300 + "learning_rate": 1.392768968202681e-05, + "loss": 3.2598, + "step": 217700 }, { "epoch": 0.72, - "learning_rate": 1.3876623677945108e-05, - "loss": 3.1181, - "step": 202400 + "learning_rate": 1.3911119948302431e-05, + "loss": 3.2672, + "step": 217800 }, { "epoch": 0.72, - "learning_rate": 1.385877615999943e-05, - "loss": 3.1273, - "step": 202500 + "learning_rate": 1.3894550214578053e-05, + "loss": 3.2649, + "step": 217900 }, { "epoch": 0.72, - "learning_rate": 1.3840928642053749e-05, - "loss": 3.1264, - "step": 202600 + "learning_rate": 1.3877980480853672e-05, + "loss": 3.268, + "step": 218000 }, { "epoch": 0.72, - "learning_rate": 1.382308112410807e-05, - "loss": 3.1242, - "step": 202700 + "learning_rate": 1.3861410747129294e-05, + "loss": 3.2598, + "step": 218100 }, { "epoch": 0.72, - "learning_rate": 1.3805233606162391e-05, - "loss": 3.1214, - "step": 202800 + "learning_rate": 1.3844841013404917e-05, + "loss": 3.258, + "step": 218200 }, { "epoch": 0.72, - "learning_rate": 1.378738608821671e-05, - "loss": 3.1176, - "step": 202900 + "learning_rate": 1.3828271279680535e-05, + "loss": 3.2624, + "step": 218300 }, { "epoch": 0.72, - "learning_rate": 1.3769538570271035e-05, - "loss": 3.1229, - "step": 203000 + "learning_rate": 1.3811701545956156e-05, + "loss": 3.2686, + "step": 218400 }, { "epoch": 0.72, - "learning_rate": 1.3751691052325355e-05, - "loss": 3.1005, - "step": 203100 + "learning_rate": 1.379513181223178e-05, + "loss": 3.2719, + "step": 218500 + }, + { + "epoch": 0.72, + "learning_rate": 1.3778562078507398e-05, + "loss": 3.2599, + "step": 218600 + }, + { + "epoch": 0.72, + "learning_rate": 1.3761992344783021e-05, + "loss": 3.2622, + "step": 218700 }, { "epoch": 0.73, - "learning_rate": 1.3733843534379676e-05, - "loss": 3.1198, - "step": 203200 + "learning_rate": 1.3745422611058642e-05, + "loss": 3.2629, + "step": 218800 }, { "epoch": 0.73, - "learning_rate": 1.3715996016433996e-05, - "loss": 3.1175, - "step": 203300 + "learning_rate": 1.372885287733426e-05, + "loss": 3.266, + "step": 218900 }, { "epoch": 0.73, - "learning_rate": 1.3698148498488317e-05, - "loss": 3.118, - "step": 203400 + "learning_rate": 1.3712283143609884e-05, + "loss": 3.2661, + "step": 219000 }, { "epoch": 0.73, - "learning_rate": 1.3680300980542638e-05, - "loss": 3.117, - "step": 203500 + "learning_rate": 1.3695713409885505e-05, + "loss": 3.2568, + "step": 219100 }, { "epoch": 0.73, - "learning_rate": 1.3662453462596957e-05, - "loss": 3.1157, - "step": 203600 + "learning_rate": 1.3679143676161125e-05, + "loss": 3.2693, + "step": 219200 }, { "epoch": 0.73, - "learning_rate": 1.3644605944651279e-05, - "loss": 3.1147, - "step": 203700 + "learning_rate": 1.3662573942436746e-05, + "loss": 3.2605, + "step": 219300 }, { "epoch": 0.73, - "learning_rate": 1.36267584267056e-05, - "loss": 3.1125, - "step": 203800 + "learning_rate": 1.3646004208712368e-05, + "loss": 3.2639, + "step": 219400 }, { "epoch": 0.73, - "learning_rate": 1.360891090875992e-05, - "loss": 3.1193, - "step": 203900 + "learning_rate": 1.3629434474987988e-05, + "loss": 3.2749, + "step": 219500 }, { "epoch": 0.73, - "learning_rate": 1.359106339081424e-05, - "loss": 3.1216, - "step": 204000 + "learning_rate": 1.3612864741263609e-05, + "loss": 3.2569, + "step": 219600 }, { "epoch": 0.73, - "learning_rate": 1.357321587286856e-05, - "loss": 3.1186, - "step": 204100 + "learning_rate": 1.3596295007539229e-05, + "loss": 3.2594, + "step": 219700 }, { "epoch": 0.73, - "learning_rate": 1.3555368354922881e-05, - "loss": 3.1212, - "step": 204200 + "learning_rate": 1.357972527381485e-05, + "loss": 3.2759, + "step": 219800 }, { "epoch": 0.73, - "learning_rate": 1.3537520836977203e-05, - "loss": 3.1184, - "step": 204300 + "learning_rate": 1.3563155540090472e-05, + "loss": 3.2674, + "step": 219900 }, { "epoch": 0.73, - "learning_rate": 1.3519673319031522e-05, - "loss": 3.1188, - "step": 204400 + "learning_rate": 1.3546585806366091e-05, + "loss": 3.2588, + "step": 220000 }, { "epoch": 0.73, - "learning_rate": 1.3501825801085843e-05, - "loss": 3.1249, - "step": 204500 + "learning_rate": 1.3530016072641713e-05, + "loss": 3.274, + "step": 220100 }, { "epoch": 0.73, - "learning_rate": 1.3483978283140165e-05, - "loss": 3.127, - "step": 204600 + "learning_rate": 1.3513446338917334e-05, + "loss": 3.2662, + "step": 220200 }, { "epoch": 0.73, - "learning_rate": 1.3466130765194484e-05, - "loss": 3.1259, - "step": 204700 + "learning_rate": 1.3496876605192954e-05, + "loss": 3.2666, + "step": 220300 }, { "epoch": 0.73, - "learning_rate": 1.3448283247248805e-05, - "loss": 3.1129, - "step": 204800 + "learning_rate": 1.3480306871468576e-05, + "loss": 3.2626, + "step": 220400 }, { "epoch": 0.73, - "learning_rate": 1.3430435729303127e-05, - "loss": 3.117, - "step": 204900 + "learning_rate": 1.3463737137744197e-05, + "loss": 3.2532, + "step": 220500 }, { "epoch": 0.73, - "learning_rate": 1.3412588211357446e-05, - "loss": 3.131, - "step": 205000 + "learning_rate": 1.3447167404019817e-05, + "loss": 3.262, + "step": 220600 }, { "epoch": 0.73, - "learning_rate": 1.3394740693411767e-05, - "loss": 3.1236, - "step": 205100 + "learning_rate": 1.3430597670295438e-05, + "loss": 3.2657, + "step": 220700 }, { "epoch": 0.73, - "learning_rate": 1.3376893175466087e-05, - "loss": 3.1292, - "step": 205200 + "learning_rate": 1.3414027936571061e-05, + "loss": 3.2636, + "step": 220800 }, { "epoch": 0.73, - "learning_rate": 1.3359045657520408e-05, - "loss": 3.1128, - "step": 205300 + "learning_rate": 1.339745820284668e-05, + "loss": 3.2704, + "step": 220900 }, { "epoch": 0.73, - "learning_rate": 1.334119813957473e-05, - "loss": 3.1096, - "step": 205400 + "learning_rate": 1.3380888469122301e-05, + "loss": 3.254, + "step": 221000 }, { "epoch": 0.73, - "learning_rate": 1.3323350621629049e-05, - "loss": 3.1223, - "step": 205500 + "learning_rate": 1.3364318735397924e-05, + "loss": 3.266, + "step": 221100 }, { "epoch": 0.73, - "learning_rate": 1.3305503103683373e-05, - "loss": 3.1319, - "step": 205600 + "learning_rate": 1.3347749001673542e-05, + "loss": 3.2574, + "step": 221200 }, { "epoch": 0.73, - "learning_rate": 1.3287655585737693e-05, - "loss": 3.115, - "step": 205700 + "learning_rate": 1.3331179267949165e-05, + "loss": 3.2608, + "step": 221300 }, { "epoch": 0.73, - "learning_rate": 1.3269808067792014e-05, - "loss": 3.1165, - "step": 205800 + "learning_rate": 1.3314609534224787e-05, + "loss": 3.2712, + "step": 221400 }, { "epoch": 0.73, - "learning_rate": 1.3251960549846335e-05, - "loss": 3.1099, - "step": 205900 + "learning_rate": 1.3298039800500407e-05, + "loss": 3.266, + "step": 221500 + }, + { + "epoch": 0.73, + "learning_rate": 1.3281470066776028e-05, + "loss": 3.267, + "step": 221600 + }, + { + "epoch": 0.73, + "learning_rate": 1.326490033305165e-05, + "loss": 3.262, + "step": 221700 }, { "epoch": 0.74, - "learning_rate": 1.3234113031900655e-05, - "loss": 3.1193, - "step": 206000 + "learning_rate": 1.324833059932727e-05, + "loss": 3.2646, + "step": 221800 }, { "epoch": 0.74, - "learning_rate": 1.3216265513954976e-05, - "loss": 3.1213, - "step": 206100 + "learning_rate": 1.3231760865602891e-05, + "loss": 3.2729, + "step": 221900 }, { "epoch": 0.74, - "learning_rate": 1.3198417996009296e-05, - "loss": 3.1179, - "step": 206200 + "learning_rate": 1.3215191131878512e-05, + "loss": 3.2749, + "step": 222000 }, { "epoch": 0.74, - "learning_rate": 1.3180570478063617e-05, - "loss": 3.1234, - "step": 206300 + "learning_rate": 1.3198621398154132e-05, + "loss": 3.2606, + "step": 222100 }, { "epoch": 0.74, - "learning_rate": 1.3162722960117938e-05, - "loss": 3.1193, - "step": 206400 + "learning_rate": 1.3182051664429754e-05, + "loss": 3.2684, + "step": 222200 }, { "epoch": 0.74, - "learning_rate": 1.3144875442172257e-05, - "loss": 3.1127, - "step": 206500 + "learning_rate": 1.3165481930705373e-05, + "loss": 3.2667, + "step": 222300 }, { "epoch": 0.74, - "learning_rate": 1.3127027924226579e-05, - "loss": 3.1233, - "step": 206600 + "learning_rate": 1.3148912196980995e-05, + "loss": 3.2734, + "step": 222400 }, { "epoch": 0.74, - "learning_rate": 1.31091804062809e-05, - "loss": 3.1319, - "step": 206700 + "learning_rate": 1.3132342463256616e-05, + "loss": 3.2592, + "step": 222500 + }, + { + "epoch": 0.74, + "learning_rate": 1.3115772729532236e-05, + "loss": 3.2665, + "step": 222600 + }, + { + "epoch": 0.74, + "learning_rate": 1.3099202995807858e-05, + "loss": 3.2707, + "step": 222700 + }, + { + "epoch": 0.74, + "learning_rate": 1.3082633262083479e-05, + "loss": 3.2675, + "step": 222800 + }, + { + "epoch": 0.74, + "learning_rate": 1.3066063528359099e-05, + "loss": 3.2628, + "step": 222900 + }, + { + "epoch": 0.74, + "learning_rate": 1.304949379463472e-05, + "loss": 3.2799, + "step": 223000 }, { "epoch": 0.74, - "learning_rate": 1.309133288833522e-05, - "loss": 3.116, - "step": 206800 + "learning_rate": 1.3032924060910343e-05, + "loss": 3.269, + "step": 223100 }, { "epoch": 0.74, - "learning_rate": 1.307348537038954e-05, - "loss": 3.1248, - "step": 206900 + "learning_rate": 1.3016354327185961e-05, + "loss": 3.2689, + "step": 223200 }, { "epoch": 0.74, - "learning_rate": 1.3055637852443862e-05, - "loss": 3.1201, - "step": 207000 + "learning_rate": 1.2999784593461583e-05, + "loss": 3.2529, + "step": 223300 }, { "epoch": 0.74, - "learning_rate": 1.3037790334498181e-05, - "loss": 3.1161, - "step": 207100 + "learning_rate": 1.2983214859737206e-05, + "loss": 3.2642, + "step": 223400 }, { "epoch": 0.74, - "learning_rate": 1.3019942816552503e-05, - "loss": 3.1159, - "step": 207200 + "learning_rate": 1.2966645126012824e-05, + "loss": 3.2623, + "step": 223500 }, { "epoch": 0.74, - "learning_rate": 1.3002095298606822e-05, - "loss": 3.1165, - "step": 207300 + "learning_rate": 1.2950075392288447e-05, + "loss": 3.279, + "step": 223600 }, { "epoch": 0.74, - "learning_rate": 1.2984247780661143e-05, - "loss": 3.1198, - "step": 207400 + "learning_rate": 1.2933505658564069e-05, + "loss": 3.2653, + "step": 223700 }, { "epoch": 0.74, - "learning_rate": 1.2966400262715465e-05, - "loss": 3.1218, - "step": 207500 + "learning_rate": 1.2916935924839687e-05, + "loss": 3.2653, + "step": 223800 }, { "epoch": 0.74, - "learning_rate": 1.2948552744769784e-05, - "loss": 3.1109, - "step": 207600 + "learning_rate": 1.290036619111531e-05, + "loss": 3.266, + "step": 223900 }, { "epoch": 0.74, - "learning_rate": 1.2930705226824105e-05, - "loss": 3.1129, - "step": 207700 + "learning_rate": 1.2883796457390931e-05, + "loss": 3.2617, + "step": 224000 }, { "epoch": 0.74, - "learning_rate": 1.2912857708878426e-05, - "loss": 3.1153, - "step": 207800 + "learning_rate": 1.2867226723666551e-05, + "loss": 3.2672, + "step": 224100 }, { "epoch": 0.74, - "learning_rate": 1.2895010190932746e-05, - "loss": 3.1086, - "step": 207900 + "learning_rate": 1.2850656989942173e-05, + "loss": 3.267, + "step": 224200 }, { "epoch": 0.74, - "learning_rate": 1.2877162672987067e-05, - "loss": 3.1138, - "step": 208000 + "learning_rate": 1.2834087256217794e-05, + "loss": 3.2694, + "step": 224300 }, { "epoch": 0.74, - "learning_rate": 1.285931515504139e-05, - "loss": 3.1197, - "step": 208100 + "learning_rate": 1.2817517522493414e-05, + "loss": 3.263, + "step": 224400 }, { "epoch": 0.74, - "learning_rate": 1.2841467637095711e-05, - "loss": 3.117, - "step": 208200 + "learning_rate": 1.2800947788769035e-05, + "loss": 3.2549, + "step": 224500 }, { "epoch": 0.74, - "learning_rate": 1.2823620119150031e-05, - "loss": 3.1098, - "step": 208300 + "learning_rate": 1.2784378055044657e-05, + "loss": 3.2633, + "step": 224600 }, { "epoch": 0.74, - "learning_rate": 1.2805772601204352e-05, - "loss": 3.1239, - "step": 208400 + "learning_rate": 1.2767808321320277e-05, + "loss": 3.2643, + "step": 224700 }, { "epoch": 0.74, - "learning_rate": 1.2787925083258673e-05, - "loss": 3.1184, - "step": 208500 + "learning_rate": 1.2751238587595898e-05, + "loss": 3.2598, + "step": 224800 }, { - "epoch": 0.74, - "learning_rate": 1.2770077565312993e-05, - "loss": 3.1145, - "step": 208600 + "epoch": 0.75, + "learning_rate": 1.2734668853871518e-05, + "loss": 3.2547, + "step": 224900 }, { - "epoch": 0.74, - "learning_rate": 1.2752230047367314e-05, - "loss": 3.1148, - "step": 208700 + "epoch": 0.75, + "learning_rate": 1.271809912014714e-05, + "loss": 3.2544, + "step": 225000 }, { "epoch": 0.75, - "learning_rate": 1.2734382529421635e-05, - "loss": 3.1275, - "step": 208800 + "learning_rate": 1.2701529386422761e-05, + "loss": 3.2636, + "step": 225100 }, { "epoch": 0.75, - "learning_rate": 1.2716535011475955e-05, - "loss": 3.1138, - "step": 208900 + "learning_rate": 1.268495965269838e-05, + "loss": 3.265, + "step": 225200 }, { "epoch": 0.75, - "learning_rate": 1.2698687493530276e-05, - "loss": 3.12, - "step": 209000 + "learning_rate": 1.2668389918974002e-05, + "loss": 3.2606, + "step": 225300 }, { "epoch": 0.75, - "learning_rate": 1.2680839975584596e-05, - "loss": 3.1208, - "step": 209100 + "learning_rate": 1.2651820185249624e-05, + "loss": 3.2538, + "step": 225400 }, { "epoch": 0.75, - "learning_rate": 1.2662992457638917e-05, - "loss": 3.1268, - "step": 209200 + "learning_rate": 1.2635250451525243e-05, + "loss": 3.2654, + "step": 225500 }, { "epoch": 0.75, - "learning_rate": 1.2645144939693238e-05, - "loss": 3.1138, - "step": 209300 + "learning_rate": 1.2618680717800865e-05, + "loss": 3.2661, + "step": 225600 }, { "epoch": 0.75, - "learning_rate": 1.2627297421747557e-05, - "loss": 3.1217, - "step": 209400 + "learning_rate": 1.2602110984076488e-05, + "loss": 3.2572, + "step": 225700 }, { "epoch": 0.75, - "learning_rate": 1.2609449903801879e-05, - "loss": 3.1225, - "step": 209500 + "learning_rate": 1.2585541250352106e-05, + "loss": 3.2721, + "step": 225800 }, { "epoch": 0.75, - "learning_rate": 1.25916023858562e-05, - "loss": 3.1144, - "step": 209600 + "learning_rate": 1.2568971516627728e-05, + "loss": 3.257, + "step": 225900 }, { "epoch": 0.75, - "learning_rate": 1.257375486791052e-05, - "loss": 3.1093, - "step": 209700 + "learning_rate": 1.255240178290335e-05, + "loss": 3.2626, + "step": 226000 }, { "epoch": 0.75, - "learning_rate": 1.255590734996484e-05, - "loss": 3.1145, - "step": 209800 + "learning_rate": 1.2535832049178969e-05, + "loss": 3.2656, + "step": 226100 }, { "epoch": 0.75, - "learning_rate": 1.2538059832019162e-05, - "loss": 3.1217, - "step": 209900 + "learning_rate": 1.2519262315454592e-05, + "loss": 3.2557, + "step": 226200 }, { "epoch": 0.75, - "learning_rate": 1.2520212314073481e-05, - "loss": 3.1045, - "step": 210000 + "learning_rate": 1.2502692581730213e-05, + "loss": 3.2552, + "step": 226300 }, { "epoch": 0.75, - "learning_rate": 1.2502364796127803e-05, - "loss": 3.1277, - "step": 210100 + "learning_rate": 1.2486122848005833e-05, + "loss": 3.2574, + "step": 226400 }, { "epoch": 0.75, - "learning_rate": 1.2484517278182124e-05, - "loss": 3.1177, - "step": 210200 + "learning_rate": 1.2469553114281455e-05, + "loss": 3.2704, + "step": 226500 }, { "epoch": 0.75, - "learning_rate": 1.2466669760236445e-05, - "loss": 3.1153, - "step": 210300 + "learning_rate": 1.2452983380557074e-05, + "loss": 3.2673, + "step": 226600 }, { "epoch": 0.75, - "learning_rate": 1.2448822242290766e-05, - "loss": 3.1173, - "step": 210400 + "learning_rate": 1.2436413646832696e-05, + "loss": 3.2593, + "step": 226700 }, { "epoch": 0.75, - "learning_rate": 1.2430974724345086e-05, - "loss": 3.1259, - "step": 210500 + "learning_rate": 1.2419843913108317e-05, + "loss": 3.2577, + "step": 226800 }, { "epoch": 0.75, - "learning_rate": 1.2413127206399407e-05, - "loss": 3.12, - "step": 210600 + "learning_rate": 1.2403274179383937e-05, + "loss": 3.2597, + "step": 226900 }, { "epoch": 0.75, - "learning_rate": 1.2395279688453726e-05, - "loss": 3.117, - "step": 210700 + "learning_rate": 1.2386704445659559e-05, + "loss": 3.2691, + "step": 227000 }, { "epoch": 0.75, - "learning_rate": 1.2377432170508048e-05, - "loss": 3.1198, - "step": 210800 + "learning_rate": 1.237013471193518e-05, + "loss": 3.2644, + "step": 227100 }, { "epoch": 0.75, - "learning_rate": 1.2359584652562369e-05, - "loss": 3.1179, - "step": 210900 + "learning_rate": 1.2353564978210802e-05, + "loss": 3.2677, + "step": 227200 }, { "epoch": 0.75, - "learning_rate": 1.2341737134616688e-05, - "loss": 3.1309, - "step": 211000 + "learning_rate": 1.2336995244486421e-05, + "loss": 3.2728, + "step": 227300 }, { "epoch": 0.75, - "learning_rate": 1.232388961667101e-05, - "loss": 3.1112, - "step": 211100 + "learning_rate": 1.2320425510762043e-05, + "loss": 3.2588, + "step": 227400 }, { "epoch": 0.75, - "learning_rate": 1.2306042098725331e-05, - "loss": 3.1028, - "step": 211200 + "learning_rate": 1.2303855777037664e-05, + "loss": 3.2624, + "step": 227500 }, { "epoch": 0.75, - "learning_rate": 1.2288194580779652e-05, - "loss": 3.1148, - "step": 211300 + "learning_rate": 1.2287286043313284e-05, + "loss": 3.2602, + "step": 227600 }, { "epoch": 0.75, - "learning_rate": 1.2270347062833973e-05, - "loss": 3.1161, - "step": 211400 + "learning_rate": 1.2270716309588905e-05, + "loss": 3.2576, + "step": 227700 }, { "epoch": 0.75, - "learning_rate": 1.2252499544888293e-05, - "loss": 3.1272, - "step": 211500 + "learning_rate": 1.2254146575864527e-05, + "loss": 3.2722, + "step": 227800 }, { "epoch": 0.76, - "learning_rate": 1.2234652026942614e-05, - "loss": 3.1159, - "step": 211600 + "learning_rate": 1.2237576842140147e-05, + "loss": 3.2601, + "step": 227900 }, { "epoch": 0.76, - "learning_rate": 1.2216804508996935e-05, - "loss": 3.1177, - "step": 211700 + "learning_rate": 1.222100710841577e-05, + "loss": 3.2778, + "step": 228000 }, { "epoch": 0.76, - "learning_rate": 1.2198956991051255e-05, - "loss": 3.1111, - "step": 211800 + "learning_rate": 1.220443737469139e-05, + "loss": 3.2706, + "step": 228100 }, { "epoch": 0.76, - "learning_rate": 1.2181109473105576e-05, - "loss": 3.1094, - "step": 211900 + "learning_rate": 1.218786764096701e-05, + "loss": 3.263, + "step": 228200 }, { "epoch": 0.76, - "learning_rate": 1.2163261955159897e-05, - "loss": 3.1161, - "step": 212000 + "learning_rate": 1.2171297907242631e-05, + "loss": 3.2633, + "step": 228300 }, { "epoch": 0.76, - "learning_rate": 1.2145414437214217e-05, - "loss": 3.1187, - "step": 212100 + "learning_rate": 1.2154728173518252e-05, + "loss": 3.2645, + "step": 228400 }, { "epoch": 0.76, - "learning_rate": 1.2127566919268538e-05, - "loss": 3.1143, - "step": 212200 + "learning_rate": 1.2138158439793874e-05, + "loss": 3.2625, + "step": 228500 }, { "epoch": 0.76, - "learning_rate": 1.2109719401322857e-05, - "loss": 3.1124, - "step": 212300 + "learning_rate": 1.2121588706069494e-05, + "loss": 3.2656, + "step": 228600 }, { "epoch": 0.76, - "learning_rate": 1.2091871883377179e-05, - "loss": 3.1208, - "step": 212400 + "learning_rate": 1.2105018972345115e-05, + "loss": 3.2531, + "step": 228700 }, { "epoch": 0.76, - "learning_rate": 1.20740243654315e-05, - "loss": 3.1134, - "step": 212500 + "learning_rate": 1.2088449238620737e-05, + "loss": 3.2526, + "step": 228800 }, { "epoch": 0.76, - "learning_rate": 1.2056176847485821e-05, - "loss": 3.1282, - "step": 212600 + "learning_rate": 1.2071879504896356e-05, + "loss": 3.2629, + "step": 228900 }, { "epoch": 0.76, - "learning_rate": 1.2038329329540142e-05, - "loss": 3.115, - "step": 212700 + "learning_rate": 1.2055309771171978e-05, + "loss": 3.2644, + "step": 229000 }, { "epoch": 0.76, - "learning_rate": 1.2020481811594462e-05, - "loss": 3.1127, - "step": 212800 + "learning_rate": 1.20387400374476e-05, + "loss": 3.2548, + "step": 229100 }, { "epoch": 0.76, - "learning_rate": 1.2002634293648783e-05, - "loss": 3.1195, - "step": 212900 + "learning_rate": 1.2022170303723219e-05, + "loss": 3.2718, + "step": 229200 }, { "epoch": 0.76, - "learning_rate": 1.1984786775703104e-05, - "loss": 3.1201, - "step": 213000 + "learning_rate": 1.2005600569998842e-05, + "loss": 3.2608, + "step": 229300 }, { "epoch": 0.76, - "learning_rate": 1.1966939257757424e-05, - "loss": 3.1262, - "step": 213100 + "learning_rate": 1.1989030836274462e-05, + "loss": 3.2688, + "step": 229400 }, { "epoch": 0.76, - "learning_rate": 1.1949091739811745e-05, - "loss": 3.1148, - "step": 213200 + "learning_rate": 1.1972461102550082e-05, + "loss": 3.2618, + "step": 229500 }, { "epoch": 0.76, - "learning_rate": 1.1931244221866066e-05, - "loss": 3.1202, - "step": 213300 + "learning_rate": 1.1955891368825703e-05, + "loss": 3.2599, + "step": 229600 }, { "epoch": 0.76, - "learning_rate": 1.1913396703920386e-05, - "loss": 3.1115, - "step": 213400 + "learning_rate": 1.1939321635101325e-05, + "loss": 3.2763, + "step": 229700 }, { "epoch": 0.76, - "learning_rate": 1.1895549185974707e-05, - "loss": 3.1173, - "step": 213500 + "learning_rate": 1.1922751901376946e-05, + "loss": 3.2567, + "step": 229800 }, { "epoch": 0.76, - "learning_rate": 1.1877701668029028e-05, - "loss": 3.1177, - "step": 213600 + "learning_rate": 1.1906182167652566e-05, + "loss": 3.2587, + "step": 229900 }, { "epoch": 0.76, - "learning_rate": 1.1859854150083348e-05, - "loss": 3.1215, - "step": 213700 + "learning_rate": 1.1889612433928187e-05, + "loss": 3.2432, + "step": 230000 }, { "epoch": 0.76, - "learning_rate": 1.1842006632137669e-05, - "loss": 3.1246, - "step": 213800 + "learning_rate": 1.1873042700203809e-05, + "loss": 3.2744, + "step": 230100 }, { "epoch": 0.76, - "learning_rate": 1.182415911419199e-05, - "loss": 3.1064, - "step": 213900 + "learning_rate": 1.1856472966479429e-05, + "loss": 3.2633, + "step": 230200 }, { "epoch": 0.76, - "learning_rate": 1.1806311596246311e-05, - "loss": 3.1118, - "step": 214000 + "learning_rate": 1.183990323275505e-05, + "loss": 3.2665, + "step": 230300 }, { "epoch": 0.76, - "learning_rate": 1.1788464078300633e-05, - "loss": 3.115, - "step": 214100 + "learning_rate": 1.1823333499030672e-05, + "loss": 3.2705, + "step": 230400 }, { "epoch": 0.76, - "learning_rate": 1.1770616560354952e-05, - "loss": 3.115, - "step": 214200 + "learning_rate": 1.1806763765306291e-05, + "loss": 3.2464, + "step": 230500 }, { "epoch": 0.76, - "learning_rate": 1.1752769042409273e-05, - "loss": 3.1187, - "step": 214300 + "learning_rate": 1.1790194031581914e-05, + "loss": 3.263, + "step": 230600 + }, + { + "epoch": 0.76, + "learning_rate": 1.1773624297857534e-05, + "loss": 3.2483, + "step": 230700 + }, + { + "epoch": 0.76, + "learning_rate": 1.1757054564133154e-05, + "loss": 3.2757, + "step": 230800 }, { "epoch": 0.77, - "learning_rate": 1.1734921524463593e-05, - "loss": 3.1202, - "step": 214400 + "learning_rate": 1.1740484830408775e-05, + "loss": 3.2705, + "step": 230900 }, { "epoch": 0.77, - "learning_rate": 1.1717074006517914e-05, - "loss": 3.1011, - "step": 214500 + "learning_rate": 1.1723915096684397e-05, + "loss": 3.2578, + "step": 231000 }, { "epoch": 0.77, - "learning_rate": 1.1699226488572235e-05, - "loss": 3.0945, - "step": 214600 + "learning_rate": 1.1707345362960018e-05, + "loss": 3.2782, + "step": 231100 }, { "epoch": 0.77, - "learning_rate": 1.1681378970626555e-05, - "loss": 3.1116, - "step": 214700 + "learning_rate": 1.1690775629235638e-05, + "loss": 3.2617, + "step": 231200 }, { "epoch": 0.77, - "learning_rate": 1.1663531452680876e-05, - "loss": 3.1173, - "step": 214800 + "learning_rate": 1.167420589551126e-05, + "loss": 3.2722, + "step": 231300 }, { "epoch": 0.77, - "learning_rate": 1.1645683934735197e-05, - "loss": 3.1125, - "step": 214900 + "learning_rate": 1.1657636161786881e-05, + "loss": 3.2749, + "step": 231400 }, { "epoch": 0.77, - "learning_rate": 1.1627836416789517e-05, - "loss": 3.1284, - "step": 215000 + "learning_rate": 1.1641066428062501e-05, + "loss": 3.2623, + "step": 231500 }, { "epoch": 0.77, - "learning_rate": 1.1609988898843838e-05, - "loss": 3.1196, - "step": 215100 + "learning_rate": 1.1624496694338122e-05, + "loss": 3.2635, + "step": 231600 }, { "epoch": 0.77, - "learning_rate": 1.1592141380898159e-05, - "loss": 3.1222, - "step": 215200 + "learning_rate": 1.1607926960613744e-05, + "loss": 3.2798, + "step": 231700 }, { "epoch": 0.77, - "learning_rate": 1.157429386295248e-05, - "loss": 3.1132, - "step": 215300 + "learning_rate": 1.1591357226889364e-05, + "loss": 3.26, + "step": 231800 }, { "epoch": 0.77, - "learning_rate": 1.1556446345006802e-05, - "loss": 3.0978, - "step": 215400 + "learning_rate": 1.1574787493164987e-05, + "loss": 3.2534, + "step": 231900 }, { "epoch": 0.77, - "learning_rate": 1.1538598827061121e-05, - "loss": 3.1204, - "step": 215500 + "learning_rate": 1.1558217759440607e-05, + "loss": 3.2755, + "step": 232000 }, { "epoch": 0.77, - "learning_rate": 1.1520751309115442e-05, - "loss": 3.1102, - "step": 215600 + "learning_rate": 1.1541648025716226e-05, + "loss": 3.2607, + "step": 232100 }, { "epoch": 0.77, - "learning_rate": 1.1502903791169762e-05, - "loss": 3.1149, - "step": 215700 + "learning_rate": 1.1525078291991848e-05, + "loss": 3.2682, + "step": 232200 }, { "epoch": 0.77, - "learning_rate": 1.1485056273224083e-05, - "loss": 3.1155, - "step": 215800 + "learning_rate": 1.150850855826747e-05, + "loss": 3.2503, + "step": 232300 }, { "epoch": 0.77, - "learning_rate": 1.1467208755278404e-05, - "loss": 3.1076, - "step": 215900 + "learning_rate": 1.149193882454309e-05, + "loss": 3.2657, + "step": 232400 }, { "epoch": 0.77, - "learning_rate": 1.1449361237332724e-05, - "loss": 3.1117, - "step": 216000 + "learning_rate": 1.147536909081871e-05, + "loss": 3.2631, + "step": 232500 }, { "epoch": 0.77, - "learning_rate": 1.1431513719387045e-05, - "loss": 3.1172, - "step": 216100 + "learning_rate": 1.1458799357094332e-05, + "loss": 3.2601, + "step": 232600 }, { "epoch": 0.77, - "learning_rate": 1.1413666201441366e-05, - "loss": 3.1145, - "step": 216200 + "learning_rate": 1.1442229623369953e-05, + "loss": 3.2585, + "step": 232700 + }, + { + "epoch": 0.77, + "learning_rate": 1.1425659889645573e-05, + "loss": 3.2559, + "step": 232800 + }, + { + "epoch": 0.77, + "learning_rate": 1.1409090155921195e-05, + "loss": 3.2561, + "step": 232900 + }, + { + "epoch": 0.77, + "learning_rate": 1.1392520422196816e-05, + "loss": 3.275, + "step": 233000 + }, + { + "epoch": 0.77, + "learning_rate": 1.1375950688472436e-05, + "loss": 3.2491, + "step": 233100 }, { "epoch": 0.77, - "learning_rate": 1.1395818683495686e-05, - "loss": 3.1208, - "step": 216300 + "learning_rate": 1.1359380954748059e-05, + "loss": 3.253, + "step": 233200 }, { "epoch": 0.77, - "learning_rate": 1.1377971165550009e-05, - "loss": 3.116, - "step": 216400 + "learning_rate": 1.1342811221023679e-05, + "loss": 3.2698, + "step": 233300 }, { "epoch": 0.77, - "learning_rate": 1.1360123647604328e-05, - "loss": 3.1224, - "step": 216500 + "learning_rate": 1.13262414872993e-05, + "loss": 3.2598, + "step": 233400 }, { "epoch": 0.77, - "learning_rate": 1.134227612965865e-05, - "loss": 3.1217, - "step": 216600 + "learning_rate": 1.130967175357492e-05, + "loss": 3.2548, + "step": 233500 }, { "epoch": 0.77, - "learning_rate": 1.132442861171297e-05, - "loss": 3.1218, - "step": 216700 + "learning_rate": 1.1293102019850542e-05, + "loss": 3.263, + "step": 233600 }, { "epoch": 0.77, - "learning_rate": 1.130658109376729e-05, - "loss": 3.1074, - "step": 216800 + "learning_rate": 1.1276532286126163e-05, + "loss": 3.2648, + "step": 233700 }, { "epoch": 0.77, - "learning_rate": 1.1288733575821611e-05, - "loss": 3.1181, - "step": 216900 + "learning_rate": 1.1259962552401783e-05, + "loss": 3.265, + "step": 233800 }, { - "epoch": 0.77, - "learning_rate": 1.1270886057875933e-05, - "loss": 3.113, - "step": 217000 + "epoch": 0.78, + "learning_rate": 1.1243392818677404e-05, + "loss": 3.2794, + "step": 233900 }, { - "epoch": 0.77, - "learning_rate": 1.1253038539930252e-05, - "loss": 3.1174, - "step": 217100 + "epoch": 0.78, + "learning_rate": 1.1226823084953026e-05, + "loss": 3.2626, + "step": 234000 }, { "epoch": 0.78, - "learning_rate": 1.1235191021984573e-05, - "loss": 3.102, - "step": 217200 + "learning_rate": 1.1210253351228645e-05, + "loss": 3.2679, + "step": 234100 }, { "epoch": 0.78, - "learning_rate": 1.1217343504038893e-05, - "loss": 3.1262, - "step": 217300 + "learning_rate": 1.1193683617504269e-05, + "loss": 3.2612, + "step": 234200 }, { "epoch": 0.78, - "learning_rate": 1.1199495986093214e-05, - "loss": 3.1067, - "step": 217400 + "learning_rate": 1.1177113883779888e-05, + "loss": 3.2558, + "step": 234300 }, { "epoch": 0.78, - "learning_rate": 1.1181648468147535e-05, - "loss": 3.1075, - "step": 217500 + "learning_rate": 1.1160544150055508e-05, + "loss": 3.264, + "step": 234400 }, { "epoch": 0.78, - "learning_rate": 1.1163800950201855e-05, - "loss": 3.1155, - "step": 217600 + "learning_rate": 1.1143974416331131e-05, + "loss": 3.2554, + "step": 234500 }, { "epoch": 0.78, - "learning_rate": 1.1145953432256178e-05, - "loss": 3.1221, - "step": 217700 + "learning_rate": 1.1127404682606751e-05, + "loss": 3.2616, + "step": 234600 }, { "epoch": 0.78, - "learning_rate": 1.1128105914310497e-05, - "loss": 3.1103, - "step": 217800 + "learning_rate": 1.1110834948882373e-05, + "loss": 3.2619, + "step": 234700 }, { "epoch": 0.78, - "learning_rate": 1.1110258396364818e-05, - "loss": 3.1137, - "step": 217900 + "learning_rate": 1.1094265215157992e-05, + "loss": 3.2507, + "step": 234800 }, { "epoch": 0.78, - "learning_rate": 1.109241087841914e-05, - "loss": 3.1073, - "step": 218000 + "learning_rate": 1.1077695481433614e-05, + "loss": 3.2593, + "step": 234900 }, { "epoch": 0.78, - "learning_rate": 1.1074563360473459e-05, - "loss": 3.1217, - "step": 218100 + "learning_rate": 1.1061125747709235e-05, + "loss": 3.2572, + "step": 235000 }, { "epoch": 0.78, - "learning_rate": 1.105671584252778e-05, - "loss": 3.1278, - "step": 218200 + "learning_rate": 1.1044556013984855e-05, + "loss": 3.2724, + "step": 235100 }, { "epoch": 0.78, - "learning_rate": 1.1038868324582102e-05, - "loss": 3.1124, - "step": 218300 + "learning_rate": 1.1027986280260477e-05, + "loss": 3.2596, + "step": 235200 }, { "epoch": 0.78, - "learning_rate": 1.1021020806636421e-05, - "loss": 3.1083, - "step": 218400 + "learning_rate": 1.1011416546536098e-05, + "loss": 3.258, + "step": 235300 }, { "epoch": 0.78, - "learning_rate": 1.1003173288690742e-05, - "loss": 3.1068, - "step": 218500 + "learning_rate": 1.0994846812811718e-05, + "loss": 3.2637, + "step": 235400 }, { "epoch": 0.78, - "learning_rate": 1.0985325770745063e-05, - "loss": 3.1166, - "step": 218600 + "learning_rate": 1.0978277079087341e-05, + "loss": 3.2707, + "step": 235500 }, { "epoch": 0.78, - "learning_rate": 1.0967478252799383e-05, - "loss": 3.1131, - "step": 218700 + "learning_rate": 1.096170734536296e-05, + "loss": 3.2546, + "step": 235600 }, { "epoch": 0.78, - "learning_rate": 1.0949630734853704e-05, - "loss": 3.1102, - "step": 218800 + "learning_rate": 1.094513761163858e-05, + "loss": 3.2528, + "step": 235700 }, { "epoch": 0.78, - "learning_rate": 1.0931783216908024e-05, - "loss": 3.1248, - "step": 218900 + "learning_rate": 1.0928567877914204e-05, + "loss": 3.2718, + "step": 235800 }, { "epoch": 0.78, - "learning_rate": 1.0913935698962347e-05, - "loss": 3.1065, - "step": 219000 + "learning_rate": 1.0911998144189823e-05, + "loss": 3.246, + "step": 235900 }, { "epoch": 0.78, - "learning_rate": 1.0896088181016668e-05, - "loss": 3.1201, - "step": 219100 + "learning_rate": 1.0895428410465445e-05, + "loss": 3.2584, + "step": 236000 }, { "epoch": 0.78, - "learning_rate": 1.0878240663070987e-05, - "loss": 3.119, - "step": 219200 + "learning_rate": 1.0878858676741065e-05, + "loss": 3.2703, + "step": 236100 }, { "epoch": 0.78, - "learning_rate": 1.0860393145125309e-05, - "loss": 3.1174, - "step": 219300 + "learning_rate": 1.0862288943016686e-05, + "loss": 3.2502, + "step": 236200 }, { "epoch": 0.78, - "learning_rate": 1.0842545627179628e-05, - "loss": 3.1165, - "step": 219400 + "learning_rate": 1.0845719209292308e-05, + "loss": 3.2637, + "step": 236300 }, { "epoch": 0.78, - "learning_rate": 1.082469810923395e-05, - "loss": 3.1275, - "step": 219500 + "learning_rate": 1.0829149475567927e-05, + "loss": 3.2497, + "step": 236400 }, { "epoch": 0.78, - "learning_rate": 1.080685059128827e-05, - "loss": 3.1232, - "step": 219600 + "learning_rate": 1.0812579741843549e-05, + "loss": 3.2672, + "step": 236500 }, { "epoch": 0.78, - "learning_rate": 1.078900307334259e-05, - "loss": 3.1182, - "step": 219700 + "learning_rate": 1.079601000811917e-05, + "loss": 3.2641, + "step": 236600 }, { "epoch": 0.78, - "learning_rate": 1.0771155555396911e-05, - "loss": 3.1098, - "step": 219800 + "learning_rate": 1.077944027439479e-05, + "loss": 3.2619, + "step": 236700 }, { "epoch": 0.78, - "learning_rate": 1.0753308037451233e-05, - "loss": 3.1092, - "step": 219900 + "learning_rate": 1.0762870540670413e-05, + "loss": 3.2614, + "step": 236800 }, { "epoch": 0.79, - "learning_rate": 1.0735460519505552e-05, - "loss": 3.1173, - "step": 220000 + "learning_rate": 1.0746300806946033e-05, + "loss": 3.2453, + "step": 236900 }, { "epoch": 0.79, - "learning_rate": 1.0717613001559873e-05, - "loss": 3.1168, - "step": 220100 + "learning_rate": 1.0729731073221653e-05, + "loss": 3.2767, + "step": 237000 }, { "epoch": 0.79, - "learning_rate": 1.0699765483614194e-05, - "loss": 3.111, - "step": 220200 + "learning_rate": 1.0713161339497276e-05, + "loss": 3.2725, + "step": 237100 }, { "epoch": 0.79, - "learning_rate": 1.0681917965668516e-05, - "loss": 3.1174, - "step": 220300 + "learning_rate": 1.0696591605772896e-05, + "loss": 3.2679, + "step": 237200 }, { "epoch": 0.79, - "learning_rate": 1.0664070447722837e-05, - "loss": 3.128, - "step": 220400 + "learning_rate": 1.0680021872048517e-05, + "loss": 3.2508, + "step": 237300 }, { "epoch": 0.79, - "learning_rate": 1.0646222929777156e-05, - "loss": 3.1131, - "step": 220500 + "learning_rate": 1.0663452138324137e-05, + "loss": 3.2544, + "step": 237400 }, { "epoch": 0.79, - "learning_rate": 1.0628375411831478e-05, - "loss": 3.1186, - "step": 220600 + "learning_rate": 1.0646882404599758e-05, + "loss": 3.2497, + "step": 237500 }, { "epoch": 0.79, - "learning_rate": 1.0610527893885797e-05, - "loss": 3.1057, - "step": 220700 + "learning_rate": 1.063031267087538e-05, + "loss": 3.2581, + "step": 237600 }, { "epoch": 0.79, - "learning_rate": 1.0592680375940118e-05, - "loss": 3.1177, - "step": 220800 + "learning_rate": 1.0613742937151e-05, + "loss": 3.2723, + "step": 237700 }, { "epoch": 0.79, - "learning_rate": 1.057483285799444e-05, - "loss": 3.1139, - "step": 220900 + "learning_rate": 1.0597173203426621e-05, + "loss": 3.2564, + "step": 237800 }, { "epoch": 0.79, - "learning_rate": 1.0556985340048759e-05, - "loss": 3.1133, - "step": 221000 + "learning_rate": 1.0580603469702243e-05, + "loss": 3.2642, + "step": 237900 }, { "epoch": 0.79, - "learning_rate": 1.053913782210308e-05, - "loss": 3.1114, - "step": 221100 + "learning_rate": 1.0564033735977862e-05, + "loss": 3.2776, + "step": 238000 }, { "epoch": 0.79, - "learning_rate": 1.0521290304157402e-05, - "loss": 3.1237, - "step": 221200 + "learning_rate": 1.0547464002253486e-05, + "loss": 3.264, + "step": 238100 }, { "epoch": 0.79, - "learning_rate": 1.0503442786211721e-05, - "loss": 3.117, - "step": 221300 + "learning_rate": 1.0530894268529105e-05, + "loss": 3.2597, + "step": 238200 }, { "epoch": 0.79, - "learning_rate": 1.0485595268266042e-05, - "loss": 3.1076, - "step": 221400 + "learning_rate": 1.0514324534804727e-05, + "loss": 3.2609, + "step": 238300 }, { "epoch": 0.79, - "learning_rate": 1.0467747750320363e-05, - "loss": 3.1113, - "step": 221500 + "learning_rate": 1.0497754801080348e-05, + "loss": 3.2654, + "step": 238400 }, { "epoch": 0.79, - "learning_rate": 1.0449900232374685e-05, - "loss": 3.1191, - "step": 221600 + "learning_rate": 1.0481185067355968e-05, + "loss": 3.2496, + "step": 238500 }, { "epoch": 0.79, - "learning_rate": 1.0432052714429006e-05, - "loss": 3.1005, - "step": 221700 + "learning_rate": 1.046461533363159e-05, + "loss": 3.2799, + "step": 238600 }, { "epoch": 0.79, - "learning_rate": 1.0414205196483325e-05, - "loss": 3.1046, - "step": 221800 + "learning_rate": 1.044804559990721e-05, + "loss": 3.2657, + "step": 238700 }, { "epoch": 0.79, - "learning_rate": 1.0396357678537647e-05, - "loss": 3.1229, - "step": 221900 + "learning_rate": 1.043147586618283e-05, + "loss": 3.2495, + "step": 238800 }, { "epoch": 0.79, - "learning_rate": 1.0378510160591968e-05, - "loss": 3.1088, - "step": 222000 + "learning_rate": 1.0414906132458452e-05, + "loss": 3.2575, + "step": 238900 }, { "epoch": 0.79, - "learning_rate": 1.0360662642646287e-05, - "loss": 3.106, - "step": 222100 + "learning_rate": 1.0398336398734072e-05, + "loss": 3.2421, + "step": 239000 }, { "epoch": 0.79, - "learning_rate": 1.0342815124700609e-05, - "loss": 3.1018, - "step": 222200 + "learning_rate": 1.0381766665009695e-05, + "loss": 3.2636, + "step": 239100 }, { "epoch": 0.79, - "learning_rate": 1.0324967606754928e-05, - "loss": 3.1081, - "step": 222300 + "learning_rate": 1.0365196931285315e-05, + "loss": 3.2623, + "step": 239200 }, { "epoch": 0.79, - "learning_rate": 1.030712008880925e-05, - "loss": 3.1142, - "step": 222400 + "learning_rate": 1.0348627197560935e-05, + "loss": 3.2671, + "step": 239300 }, { "epoch": 0.79, - "learning_rate": 1.028927257086357e-05, - "loss": 3.1036, - "step": 222500 + "learning_rate": 1.0332057463836558e-05, + "loss": 3.247, + "step": 239400 }, { "epoch": 0.79, - "learning_rate": 1.027142505291789e-05, - "loss": 3.1141, - "step": 222600 + "learning_rate": 1.0315487730112178e-05, + "loss": 3.2798, + "step": 239500 }, { "epoch": 0.79, - "learning_rate": 1.0253577534972211e-05, - "loss": 3.1142, - "step": 222700 + "learning_rate": 1.0298917996387799e-05, + "loss": 3.2811, + "step": 239600 + }, + { + "epoch": 0.79, + "learning_rate": 1.028234826266342e-05, + "loss": 3.2641, + "step": 239700 + }, + { + "epoch": 0.79, + "learning_rate": 1.026577852893904e-05, + "loss": 3.2678, + "step": 239800 }, { "epoch": 0.8, - "learning_rate": 1.0235730017026532e-05, - "loss": 3.1188, - "step": 222800 + "learning_rate": 1.0249208795214662e-05, + "loss": 3.2535, + "step": 239900 }, { "epoch": 0.8, - "learning_rate": 1.0217882499080854e-05, - "loss": 3.1135, - "step": 222900 + "learning_rate": 1.0232639061490282e-05, + "loss": 3.2556, + "step": 240000 }, { "epoch": 0.8, - "learning_rate": 1.0200034981135175e-05, - "loss": 3.1039, - "step": 223000 + "learning_rate": 1.0216069327765903e-05, + "loss": 3.2472, + "step": 240100 }, { "epoch": 0.8, - "learning_rate": 1.0182187463189494e-05, - "loss": 3.1052, - "step": 223100 + "learning_rate": 1.0199499594041524e-05, + "loss": 3.2581, + "step": 240200 }, { "epoch": 0.8, - "learning_rate": 1.0164339945243816e-05, - "loss": 3.1058, - "step": 223200 + "learning_rate": 1.0182929860317144e-05, + "loss": 3.2605, + "step": 240300 }, { "epoch": 0.8, - "learning_rate": 1.0146492427298137e-05, - "loss": 3.1023, - "step": 223300 + "learning_rate": 1.0166360126592767e-05, + "loss": 3.2525, + "step": 240400 }, { "epoch": 0.8, - "learning_rate": 1.0128644909352456e-05, - "loss": 3.1168, - "step": 223400 + "learning_rate": 1.0149790392868387e-05, + "loss": 3.2509, + "step": 240500 }, { "epoch": 0.8, - "learning_rate": 1.0110797391406778e-05, - "loss": 3.1073, - "step": 223500 + "learning_rate": 1.0133220659144007e-05, + "loss": 3.2673, + "step": 240600 }, { "epoch": 0.8, - "learning_rate": 1.0092949873461099e-05, - "loss": 3.1227, - "step": 223600 + "learning_rate": 1.011665092541963e-05, + "loss": 3.2623, + "step": 240700 }, { "epoch": 0.8, - "learning_rate": 1.0075102355515418e-05, - "loss": 3.1163, - "step": 223700 + "learning_rate": 1.010008119169525e-05, + "loss": 3.2658, + "step": 240800 }, { "epoch": 0.8, - "learning_rate": 1.005725483756974e-05, - "loss": 3.1233, - "step": 223800 + "learning_rate": 1.0083511457970871e-05, + "loss": 3.2704, + "step": 240900 }, { "epoch": 0.8, - "learning_rate": 1.0039407319624059e-05, - "loss": 3.1082, - "step": 223900 + "learning_rate": 1.0066941724246493e-05, + "loss": 3.2569, + "step": 241000 }, { "epoch": 0.8, - "learning_rate": 1.002155980167838e-05, - "loss": 3.114, - "step": 224000 + "learning_rate": 1.0050371990522113e-05, + "loss": 3.2645, + "step": 241100 }, { "epoch": 0.8, - "learning_rate": 1.0003712283732703e-05, - "loss": 3.1148, - "step": 224100 + "learning_rate": 1.0033802256797734e-05, + "loss": 3.2605, + "step": 241200 }, { "epoch": 0.8, - "learning_rate": 9.985864765787023e-06, - "loss": 3.1089, - "step": 224200 + "learning_rate": 1.0017232523073354e-05, + "loss": 3.2629, + "step": 241300 }, { "epoch": 0.8, - "learning_rate": 9.968017247841344e-06, - "loss": 3.1101, - "step": 224300 + "learning_rate": 1.0000662789348975e-05, + "loss": 3.2647, + "step": 241400 }, { "epoch": 0.8, - "learning_rate": 9.950169729895663e-06, - "loss": 3.1099, - "step": 224400 + "learning_rate": 9.984093055624597e-06, + "loss": 3.2554, + "step": 241500 }, { "epoch": 0.8, - "learning_rate": 9.932322211949985e-06, - "loss": 3.1104, - "step": 224500 + "learning_rate": 9.967523321900217e-06, + "loss": 3.2658, + "step": 241600 }, { "epoch": 0.8, - "learning_rate": 9.914474694004306e-06, - "loss": 3.1166, - "step": 224600 + "learning_rate": 9.95095358817584e-06, + "loss": 3.256, + "step": 241700 }, { "epoch": 0.8, - "learning_rate": 9.896627176058625e-06, - "loss": 3.1132, - "step": 224700 + "learning_rate": 9.93438385445146e-06, + "loss": 3.2568, + "step": 241800 }, { "epoch": 0.8, - "learning_rate": 9.878779658112947e-06, - "loss": 3.1171, - "step": 224800 + "learning_rate": 9.91781412072708e-06, + "loss": 3.2656, + "step": 241900 }, { "epoch": 0.8, - "learning_rate": 9.860932140167268e-06, - "loss": 3.1173, - "step": 224900 + "learning_rate": 9.901244387002702e-06, + "loss": 3.2557, + "step": 242000 }, { "epoch": 0.8, - "learning_rate": 9.843084622221587e-06, - "loss": 3.107, - "step": 225000 + "learning_rate": 9.884674653278322e-06, + "loss": 3.2377, + "step": 242100 }, { "epoch": 0.8, - "learning_rate": 9.825237104275909e-06, - "loss": 3.1022, - "step": 225100 + "learning_rate": 9.868104919553944e-06, + "loss": 3.2719, + "step": 242200 }, { "epoch": 0.8, - "learning_rate": 9.80738958633023e-06, - "loss": 3.1145, - "step": 225200 + "learning_rate": 9.851535185829565e-06, + "loss": 3.2636, + "step": 242300 }, { "epoch": 0.8, - "learning_rate": 9.78954206838455e-06, - "loss": 3.1061, - "step": 225300 + "learning_rate": 9.834965452105185e-06, + "loss": 3.2632, + "step": 242400 }, { "epoch": 0.8, - "learning_rate": 9.771694550438872e-06, - "loss": 3.1113, - "step": 225400 + "learning_rate": 9.818395718380806e-06, + "loss": 3.2589, + "step": 242500 }, { "epoch": 0.8, - "learning_rate": 9.753847032493192e-06, - "loss": 3.1118, - "step": 225500 + "learning_rate": 9.801825984656426e-06, + "loss": 3.2642, + "step": 242600 + }, + { + "epoch": 0.8, + "learning_rate": 9.785256250932048e-06, + "loss": 3.2494, + "step": 242700 + }, + { + "epoch": 0.8, + "learning_rate": 9.768686517207669e-06, + "loss": 3.2668, + "step": 242800 + }, + { + "epoch": 0.8, + "learning_rate": 9.752116783483289e-06, + "loss": 3.2728, + "step": 242900 }, { "epoch": 0.81, - "learning_rate": 9.735999514547513e-06, - "loss": 3.1156, - "step": 225600 + "learning_rate": 9.735547049758912e-06, + "loss": 3.2542, + "step": 243000 }, { "epoch": 0.81, - "learning_rate": 9.718151996601834e-06, - "loss": 3.1138, - "step": 225700 + "learning_rate": 9.718977316034532e-06, + "loss": 3.2544, + "step": 243100 + }, + { + "epoch": 0.81, + "learning_rate": 9.702407582310152e-06, + "loss": 3.2593, + "step": 243200 + }, + { + "epoch": 0.81, + "learning_rate": 9.685837848585775e-06, + "loss": 3.26, + "step": 243300 + }, + { + "epoch": 0.81, + "learning_rate": 9.669268114861394e-06, + "loss": 3.2395, + "step": 243400 + }, + { + "epoch": 0.81, + "learning_rate": 9.652698381137016e-06, + "loss": 3.2452, + "step": 243500 }, { "epoch": 0.81, - "learning_rate": 9.700304478656154e-06, - "loss": 3.1071, - "step": 225800 + "learning_rate": 9.636128647412637e-06, + "loss": 3.2545, + "step": 243600 }, { "epoch": 0.81, - "learning_rate": 9.682456960710475e-06, - "loss": 3.121, - "step": 225900 + "learning_rate": 9.619558913688257e-06, + "loss": 3.2534, + "step": 243700 }, { "epoch": 0.81, - "learning_rate": 9.664609442764794e-06, - "loss": 3.1102, - "step": 226000 + "learning_rate": 9.602989179963879e-06, + "loss": 3.2474, + "step": 243800 }, { "epoch": 0.81, - "learning_rate": 9.646761924819116e-06, - "loss": 3.1101, - "step": 226100 + "learning_rate": 9.586419446239498e-06, + "loss": 3.2655, + "step": 243900 }, { "epoch": 0.81, - "learning_rate": 9.628914406873437e-06, - "loss": 3.1073, - "step": 226200 + "learning_rate": 9.56984971251512e-06, + "loss": 3.2599, + "step": 244000 }, { "epoch": 0.81, - "learning_rate": 9.611066888927756e-06, - "loss": 3.1117, - "step": 226300 + "learning_rate": 9.553279978790741e-06, + "loss": 3.2589, + "step": 244100 }, { "epoch": 0.81, - "learning_rate": 9.593219370982078e-06, - "loss": 3.1092, - "step": 226400 + "learning_rate": 9.536710245066361e-06, + "loss": 3.2568, + "step": 244200 }, { "epoch": 0.81, - "learning_rate": 9.575371853036399e-06, - "loss": 3.1096, - "step": 226500 + "learning_rate": 9.520140511341984e-06, + "loss": 3.2597, + "step": 244300 }, { "epoch": 0.81, - "learning_rate": 9.557524335090718e-06, - "loss": 3.1096, - "step": 226600 + "learning_rate": 9.503570777617604e-06, + "loss": 3.2552, + "step": 244400 }, { "epoch": 0.81, - "learning_rate": 9.539676817145041e-06, - "loss": 3.1076, - "step": 226700 + "learning_rate": 9.487001043893226e-06, + "loss": 3.2448, + "step": 244500 }, { "epoch": 0.81, - "learning_rate": 9.52182929919936e-06, - "loss": 3.1082, - "step": 226800 + "learning_rate": 9.470431310168847e-06, + "loss": 3.2578, + "step": 244600 }, { "epoch": 0.81, - "learning_rate": 9.503981781253682e-06, - "loss": 3.1176, - "step": 226900 + "learning_rate": 9.453861576444467e-06, + "loss": 3.2493, + "step": 244700 }, { "epoch": 0.81, - "learning_rate": 9.486134263308003e-06, - "loss": 3.1133, - "step": 227000 + "learning_rate": 9.437291842720088e-06, + "loss": 3.2493, + "step": 244800 }, { "epoch": 0.81, - "learning_rate": 9.468286745362323e-06, - "loss": 3.1132, - "step": 227100 + "learning_rate": 9.42072210899571e-06, + "loss": 3.2673, + "step": 244900 }, { "epoch": 0.81, - "learning_rate": 9.450439227416644e-06, - "loss": 3.1136, - "step": 227200 + "learning_rate": 9.40415237527133e-06, + "loss": 3.2691, + "step": 245000 }, { "epoch": 0.81, - "learning_rate": 9.432591709470963e-06, - "loss": 3.1199, - "step": 227300 + "learning_rate": 9.387582641546951e-06, + "loss": 3.2496, + "step": 245100 }, { "epoch": 0.81, - "learning_rate": 9.414744191525285e-06, - "loss": 3.1173, - "step": 227400 + "learning_rate": 9.37101290782257e-06, + "loss": 3.2671, + "step": 245200 }, { "epoch": 0.81, - "learning_rate": 9.396896673579606e-06, - "loss": 3.1019, - "step": 227500 + "learning_rate": 9.354443174098194e-06, + "loss": 3.2581, + "step": 245300 }, { "epoch": 0.81, - "learning_rate": 9.379049155633925e-06, - "loss": 3.1111, - "step": 227600 + "learning_rate": 9.337873440373814e-06, + "loss": 3.255, + "step": 245400 }, { "epoch": 0.81, - "learning_rate": 9.361201637688247e-06, - "loss": 3.1148, - "step": 227700 + "learning_rate": 9.321303706649433e-06, + "loss": 3.2606, + "step": 245500 }, { "epoch": 0.81, - "learning_rate": 9.343354119742568e-06, - "loss": 3.1214, - "step": 227800 + "learning_rate": 9.304733972925057e-06, + "loss": 3.27, + "step": 245600 }, { "epoch": 0.81, - "learning_rate": 9.325506601796889e-06, - "loss": 3.1209, - "step": 227900 + "learning_rate": 9.288164239200676e-06, + "loss": 3.2683, + "step": 245700 }, { "epoch": 0.81, - "learning_rate": 9.30765908385121e-06, - "loss": 3.1108, - "step": 228000 + "learning_rate": 9.271594505476298e-06, + "loss": 3.2596, + "step": 245800 }, { "epoch": 0.81, - "learning_rate": 9.28981156590553e-06, - "loss": 3.1097, - "step": 228100 + "learning_rate": 9.25502477175192e-06, + "loss": 3.2673, + "step": 245900 }, { - "epoch": 0.81, - "learning_rate": 9.271964047959851e-06, - "loss": 3.1255, - "step": 228200 + "epoch": 0.82, + "learning_rate": 9.238455038027539e-06, + "loss": 3.2601, + "step": 246000 }, { - "epoch": 0.81, - "learning_rate": 9.254116530014172e-06, - "loss": 3.1081, - "step": 228300 + "epoch": 0.82, + "learning_rate": 9.22188530430316e-06, + "loss": 3.2592, + "step": 246100 }, { "epoch": 0.82, - "learning_rate": 9.236269012068492e-06, - "loss": 3.1152, - "step": 228400 + "learning_rate": 9.205315570578782e-06, + "loss": 3.2513, + "step": 246200 }, { "epoch": 0.82, - "learning_rate": 9.218421494122813e-06, - "loss": 3.1246, - "step": 228500 + "learning_rate": 9.188745836854402e-06, + "loss": 3.2455, + "step": 246300 }, { "epoch": 0.82, - "learning_rate": 9.200573976177134e-06, - "loss": 3.119, - "step": 228600 + "learning_rate": 9.172176103130023e-06, + "loss": 3.2609, + "step": 246400 }, { "epoch": 0.82, - "learning_rate": 9.182726458231454e-06, - "loss": 3.1112, - "step": 228700 + "learning_rate": 9.155606369405643e-06, + "loss": 3.2354, + "step": 246500 }, { "epoch": 0.82, - "learning_rate": 9.164878940285775e-06, - "loss": 3.1197, - "step": 228800 + "learning_rate": 9.139036635681266e-06, + "loss": 3.2476, + "step": 246600 }, { "epoch": 0.82, - "learning_rate": 9.147031422340094e-06, - "loss": 3.1128, - "step": 228900 + "learning_rate": 9.122466901956886e-06, + "loss": 3.2546, + "step": 246700 }, { "epoch": 0.82, - "learning_rate": 9.129183904394416e-06, - "loss": 3.1163, - "step": 229000 + "learning_rate": 9.105897168232506e-06, + "loss": 3.2549, + "step": 246800 }, { "epoch": 0.82, - "learning_rate": 9.111336386448737e-06, - "loss": 3.1116, - "step": 229100 + "learning_rate": 9.089327434508129e-06, + "loss": 3.2424, + "step": 246900 }, { "epoch": 0.82, - "learning_rate": 9.093488868503058e-06, - "loss": 3.111, - "step": 229200 + "learning_rate": 9.072757700783749e-06, + "loss": 3.2676, + "step": 247000 }, { "epoch": 0.82, - "learning_rate": 9.07564135055738e-06, - "loss": 3.1093, - "step": 229300 + "learning_rate": 9.05618796705937e-06, + "loss": 3.2484, + "step": 247100 }, { "epoch": 0.82, - "learning_rate": 9.057793832611699e-06, - "loss": 3.1003, - "step": 229400 + "learning_rate": 9.039618233334992e-06, + "loss": 3.2649, + "step": 247200 }, { "epoch": 0.82, - "learning_rate": 9.03994631466602e-06, - "loss": 3.1092, - "step": 229500 + "learning_rate": 9.023048499610611e-06, + "loss": 3.2618, + "step": 247300 }, { "epoch": 0.82, - "learning_rate": 9.022098796720341e-06, - "loss": 3.1157, - "step": 229600 + "learning_rate": 9.006478765886233e-06, + "loss": 3.2714, + "step": 247400 }, { "epoch": 0.82, - "learning_rate": 9.00425127877466e-06, - "loss": 3.1178, - "step": 229700 + "learning_rate": 8.989909032161854e-06, + "loss": 3.2691, + "step": 247500 }, { "epoch": 0.82, - "learning_rate": 8.986403760828982e-06, - "loss": 3.12, - "step": 229800 + "learning_rate": 8.973339298437474e-06, + "loss": 3.2655, + "step": 247600 }, { "epoch": 0.82, - "learning_rate": 8.968556242883303e-06, - "loss": 3.1015, - "step": 229900 + "learning_rate": 8.956769564713096e-06, + "loss": 3.2716, + "step": 247700 }, { "epoch": 0.82, - "learning_rate": 8.950708724937623e-06, - "loss": 3.1024, - "step": 230000 + "learning_rate": 8.940199830988715e-06, + "loss": 3.2435, + "step": 247800 }, { "epoch": 0.82, - "learning_rate": 8.932861206991944e-06, - "loss": 3.1115, - "step": 230100 + "learning_rate": 8.923630097264338e-06, + "loss": 3.2454, + "step": 247900 }, { "epoch": 0.82, - "learning_rate": 8.915013689046265e-06, - "loss": 3.1154, - "step": 230200 + "learning_rate": 8.907060363539958e-06, + "loss": 3.2509, + "step": 248000 }, { "epoch": 0.82, - "learning_rate": 8.897166171100585e-06, - "loss": 3.1188, - "step": 230300 + "learning_rate": 8.890490629815578e-06, + "loss": 3.2453, + "step": 248100 }, { "epoch": 0.82, - "learning_rate": 8.879318653154906e-06, - "loss": 3.1094, - "step": 230400 + "learning_rate": 8.873920896091201e-06, + "loss": 3.266, + "step": 248200 }, { "epoch": 0.82, - "learning_rate": 8.861471135209227e-06, - "loss": 3.1042, - "step": 230500 + "learning_rate": 8.857351162366821e-06, + "loss": 3.2502, + "step": 248300 }, { "epoch": 0.82, - "learning_rate": 8.843623617263548e-06, - "loss": 3.1155, - "step": 230600 + "learning_rate": 8.840781428642442e-06, + "loss": 3.262, + "step": 248400 }, { "epoch": 0.82, - "learning_rate": 8.82577609931787e-06, - "loss": 3.1089, - "step": 230700 + "learning_rate": 8.824211694918064e-06, + "loss": 3.2582, + "step": 248500 }, { "epoch": 0.82, - "learning_rate": 8.807928581372189e-06, - "loss": 3.1121, - "step": 230800 + "learning_rate": 8.807641961193684e-06, + "loss": 3.2581, + "step": 248600 }, { "epoch": 0.82, - "learning_rate": 8.79008106342651e-06, - "loss": 3.1068, - "step": 230900 + "learning_rate": 8.791072227469305e-06, + "loss": 3.2618, + "step": 248700 }, { "epoch": 0.82, - "learning_rate": 8.77223354548083e-06, - "loss": 3.1104, - "step": 231000 + "learning_rate": 8.774502493744927e-06, + "loss": 3.2507, + "step": 248800 }, { "epoch": 0.82, - "learning_rate": 8.754386027535151e-06, - "loss": 3.1157, - "step": 231100 + "learning_rate": 8.757932760020546e-06, + "loss": 3.2429, + "step": 248900 }, { "epoch": 0.83, - "learning_rate": 8.736538509589472e-06, - "loss": 3.1072, - "step": 231200 + "learning_rate": 8.741363026296168e-06, + "loss": 3.2569, + "step": 249000 }, { "epoch": 0.83, - "learning_rate": 8.718690991643792e-06, - "loss": 3.1142, - "step": 231300 + "learning_rate": 8.724793292571788e-06, + "loss": 3.245, + "step": 249100 }, { "epoch": 0.83, - "learning_rate": 8.700843473698113e-06, - "loss": 3.1002, - "step": 231400 + "learning_rate": 8.70822355884741e-06, + "loss": 3.2469, + "step": 249200 }, { "epoch": 0.83, - "learning_rate": 8.682995955752434e-06, - "loss": 3.1065, - "step": 231500 + "learning_rate": 8.69165382512303e-06, + "loss": 3.2576, + "step": 249300 }, { "epoch": 0.83, - "learning_rate": 8.665148437806754e-06, - "loss": 3.1119, - "step": 231600 + "learning_rate": 8.67508409139865e-06, + "loss": 3.2481, + "step": 249400 }, { "epoch": 0.83, - "learning_rate": 8.647300919861075e-06, - "loss": 3.1145, - "step": 231700 + "learning_rate": 8.658514357674273e-06, + "loss": 3.2513, + "step": 249500 }, { "epoch": 0.83, - "learning_rate": 8.629453401915396e-06, - "loss": 3.1129, - "step": 231800 + "learning_rate": 8.641944623949893e-06, + "loss": 3.2557, + "step": 249600 }, { "epoch": 0.83, - "learning_rate": 8.611605883969717e-06, - "loss": 3.1116, - "step": 231900 + "learning_rate": 8.625374890225515e-06, + "loss": 3.2621, + "step": 249700 }, { "epoch": 0.83, - "learning_rate": 8.593758366024039e-06, - "loss": 3.1112, - "step": 232000 + "learning_rate": 8.608805156501136e-06, + "loss": 3.2489, + "step": 249800 }, { "epoch": 0.83, - "learning_rate": 8.575910848078358e-06, - "loss": 3.1145, - "step": 232100 + "learning_rate": 8.592235422776756e-06, + "loss": 3.247, + "step": 249900 }, { "epoch": 0.83, - "learning_rate": 8.55806333013268e-06, - "loss": 3.1049, - "step": 232200 + "learning_rate": 8.575665689052377e-06, + "loss": 3.2597, + "step": 250000 }, { "epoch": 0.83, - "learning_rate": 8.540215812186999e-06, - "loss": 3.1013, - "step": 232300 + "learning_rate": 8.559095955327999e-06, + "loss": 3.244, + "step": 250100 }, { "epoch": 0.83, - "learning_rate": 8.52236829424132e-06, - "loss": 3.1072, - "step": 232400 + "learning_rate": 8.542526221603619e-06, + "loss": 3.2742, + "step": 250200 }, { "epoch": 0.83, - "learning_rate": 8.504520776295641e-06, - "loss": 3.1063, - "step": 232500 + "learning_rate": 8.52595648787924e-06, + "loss": 3.2509, + "step": 250300 }, { "epoch": 0.83, - "learning_rate": 8.48667325834996e-06, - "loss": 3.1109, - "step": 232600 + "learning_rate": 8.50938675415486e-06, + "loss": 3.2494, + "step": 250400 }, { "epoch": 0.83, - "learning_rate": 8.468825740404282e-06, - "loss": 3.1093, - "step": 232700 + "learning_rate": 8.492817020430483e-06, + "loss": 3.2521, + "step": 250500 }, { "epoch": 0.83, - "learning_rate": 8.450978222458603e-06, - "loss": 3.1143, - "step": 232800 + "learning_rate": 8.476247286706103e-06, + "loss": 3.2508, + "step": 250600 }, { "epoch": 0.83, - "learning_rate": 8.433130704512923e-06, - "loss": 3.1031, - "step": 232900 + "learning_rate": 8.459677552981724e-06, + "loss": 3.263, + "step": 250700 }, { "epoch": 0.83, - "learning_rate": 8.415283186567246e-06, - "loss": 3.1126, - "step": 233000 + "learning_rate": 8.443107819257346e-06, + "loss": 3.2574, + "step": 250800 }, { "epoch": 0.83, - "learning_rate": 8.397435668621565e-06, - "loss": 3.1134, - "step": 233100 + "learning_rate": 8.426538085532966e-06, + "loss": 3.2547, + "step": 250900 }, { "epoch": 0.83, - "learning_rate": 8.379588150675886e-06, - "loss": 3.1066, - "step": 233200 + "learning_rate": 8.409968351808587e-06, + "loss": 3.2543, + "step": 251000 }, { "epoch": 0.83, - "learning_rate": 8.361740632730208e-06, - "loss": 3.1172, - "step": 233300 + "learning_rate": 8.393398618084208e-06, + "loss": 3.2522, + "step": 251100 }, { "epoch": 0.83, - "learning_rate": 8.343893114784527e-06, - "loss": 3.0946, - "step": 233400 + "learning_rate": 8.376828884359828e-06, + "loss": 3.2499, + "step": 251200 }, { "epoch": 0.83, - "learning_rate": 8.326045596838848e-06, - "loss": 3.1051, - "step": 233500 + "learning_rate": 8.36025915063545e-06, + "loss": 3.2579, + "step": 251300 }, { "epoch": 0.83, - "learning_rate": 8.30819807889317e-06, - "loss": 3.1152, - "step": 233600 + "learning_rate": 8.343689416911071e-06, + "loss": 3.2581, + "step": 251400 }, { "epoch": 0.83, - "learning_rate": 8.290350560947489e-06, - "loss": 3.1044, - "step": 233700 + "learning_rate": 8.327119683186693e-06, + "loss": 3.256, + "step": 251500 }, { "epoch": 0.83, - "learning_rate": 8.27250304300181e-06, - "loss": 3.1092, - "step": 233800 + "learning_rate": 8.310549949462312e-06, + "loss": 3.2564, + "step": 251600 }, { "epoch": 0.83, - "learning_rate": 8.25465552505613e-06, - "loss": 3.1119, - "step": 233900 + "learning_rate": 8.293980215737932e-06, + "loss": 3.2578, + "step": 251700 + }, + { + "epoch": 0.83, + "learning_rate": 8.277410482013555e-06, + "loss": 3.2483, + "step": 251800 + }, + { + "epoch": 0.83, + "learning_rate": 8.260840748289175e-06, + "loss": 3.2581, + "step": 251900 }, { "epoch": 0.84, - "learning_rate": 8.236808007110451e-06, - "loss": 3.1014, - "step": 234000 + "learning_rate": 8.244271014564797e-06, + "loss": 3.2656, + "step": 252000 }, { "epoch": 0.84, - "learning_rate": 8.218960489164772e-06, - "loss": 3.1139, - "step": 234100 + "learning_rate": 8.227701280840418e-06, + "loss": 3.2674, + "step": 252100 }, { "epoch": 0.84, - "learning_rate": 8.201112971219092e-06, - "loss": 3.1081, - "step": 234200 + "learning_rate": 8.211131547116038e-06, + "loss": 3.2455, + "step": 252200 }, { "epoch": 0.84, - "learning_rate": 8.183265453273415e-06, - "loss": 3.1095, - "step": 234300 + "learning_rate": 8.19456181339166e-06, + "loss": 3.2503, + "step": 252300 }, { "epoch": 0.84, - "learning_rate": 8.165417935327734e-06, - "loss": 3.1172, - "step": 234400 + "learning_rate": 8.17799207966728e-06, + "loss": 3.2462, + "step": 252400 }, { "epoch": 0.84, - "learning_rate": 8.147570417382055e-06, - "loss": 3.1054, - "step": 234500 + "learning_rate": 8.1614223459429e-06, + "loss": 3.2531, + "step": 252500 }, { "epoch": 0.84, - "learning_rate": 8.129722899436377e-06, - "loss": 3.1186, - "step": 234600 + "learning_rate": 8.144852612218522e-06, + "loss": 3.2386, + "step": 252600 }, { "epoch": 0.84, - "learning_rate": 8.111875381490696e-06, - "loss": 3.1086, - "step": 234700 + "learning_rate": 8.128282878494143e-06, + "loss": 3.2602, + "step": 252700 }, { "epoch": 0.84, - "learning_rate": 8.094027863545017e-06, - "loss": 3.1144, - "step": 234800 + "learning_rate": 8.111713144769765e-06, + "loss": 3.2487, + "step": 252800 + }, + { + "epoch": 0.84, + "learning_rate": 8.095143411045385e-06, + "loss": 3.2579, + "step": 252900 + }, + { + "epoch": 0.84, + "learning_rate": 8.078573677321004e-06, + "loss": 3.2419, + "step": 253000 + }, + { + "epoch": 0.84, + "learning_rate": 8.062003943596628e-06, + "loss": 3.2558, + "step": 253100 + }, + { + "epoch": 0.84, + "learning_rate": 8.045434209872247e-06, + "loss": 3.2537, + "step": 253200 + }, + { + "epoch": 0.84, + "learning_rate": 8.028864476147869e-06, + "loss": 3.2619, + "step": 253300 }, { "epoch": 0.84, - "learning_rate": 8.076180345599339e-06, - "loss": 3.1034, - "step": 234900 + "learning_rate": 8.01229474242349e-06, + "loss": 3.2587, + "step": 253400 }, { "epoch": 0.84, - "learning_rate": 8.058332827653658e-06, - "loss": 3.1071, - "step": 235000 + "learning_rate": 7.99572500869911e-06, + "loss": 3.2565, + "step": 253500 }, { "epoch": 0.84, - "learning_rate": 8.04048530970798e-06, - "loss": 3.1161, - "step": 235100 + "learning_rate": 7.979155274974732e-06, + "loss": 3.26, + "step": 253600 }, { "epoch": 0.84, - "learning_rate": 8.0226377917623e-06, - "loss": 3.1054, - "step": 235200 + "learning_rate": 7.962585541250353e-06, + "loss": 3.2609, + "step": 253700 }, { "epoch": 0.84, - "learning_rate": 8.00479027381662e-06, - "loss": 3.1002, - "step": 235300 + "learning_rate": 7.946015807525973e-06, + "loss": 3.2486, + "step": 253800 }, { "epoch": 0.84, - "learning_rate": 7.986942755870941e-06, - "loss": 3.1097, - "step": 235400 + "learning_rate": 7.929446073801594e-06, + "loss": 3.2567, + "step": 253900 }, { "epoch": 0.84, - "learning_rate": 7.96909523792526e-06, - "loss": 3.1105, - "step": 235500 + "learning_rate": 7.912876340077216e-06, + "loss": 3.2568, + "step": 254000 }, { "epoch": 0.84, - "learning_rate": 7.951247719979584e-06, - "loss": 3.1119, - "step": 235600 + "learning_rate": 7.896306606352837e-06, + "loss": 3.2586, + "step": 254100 }, { "epoch": 0.84, - "learning_rate": 7.933400202033905e-06, - "loss": 3.1035, - "step": 235700 + "learning_rate": 7.879736872628457e-06, + "loss": 3.2645, + "step": 254200 }, { "epoch": 0.84, - "learning_rate": 7.915552684088224e-06, - "loss": 3.1121, - "step": 235800 + "learning_rate": 7.863167138904077e-06, + "loss": 3.2574, + "step": 254300 }, { "epoch": 0.84, - "learning_rate": 7.897705166142546e-06, - "loss": 3.1041, - "step": 235900 + "learning_rate": 7.8465974051797e-06, + "loss": 3.2594, + "step": 254400 }, { "epoch": 0.84, - "learning_rate": 7.879857648196865e-06, - "loss": 3.0987, - "step": 236000 + "learning_rate": 7.83002767145532e-06, + "loss": 3.2492, + "step": 254500 }, { "epoch": 0.84, - "learning_rate": 7.862010130251186e-06, - "loss": 3.1035, - "step": 236100 + "learning_rate": 7.813457937730941e-06, + "loss": 3.2527, + "step": 254600 }, { "epoch": 0.84, - "learning_rate": 7.844162612305508e-06, - "loss": 3.117, - "step": 236200 + "learning_rate": 7.796888204006563e-06, + "loss": 3.2576, + "step": 254700 }, { "epoch": 0.84, - "learning_rate": 7.826315094359827e-06, - "loss": 3.1166, - "step": 236300 + "learning_rate": 7.780318470282182e-06, + "loss": 3.2318, + "step": 254800 }, { "epoch": 0.84, - "learning_rate": 7.808467576414148e-06, - "loss": 3.1064, - "step": 236400 + "learning_rate": 7.763748736557804e-06, + "loss": 3.261, + "step": 254900 }, { - "epoch": 0.84, - "learning_rate": 7.79062005846847e-06, - "loss": 3.1009, - "step": 236500 + "epoch": 0.85, + "learning_rate": 7.747179002833425e-06, + "loss": 3.2483, + "step": 255000 }, { - "epoch": 0.84, - "learning_rate": 7.772772540522789e-06, - "loss": 3.1101, - "step": 236600 + "epoch": 0.85, + "learning_rate": 7.730609269109045e-06, + "loss": 3.2741, + "step": 255100 }, { - "epoch": 0.84, - "learning_rate": 7.75492502257711e-06, - "loss": 3.1102, - "step": 236700 + "epoch": 0.85, + "learning_rate": 7.714039535384667e-06, + "loss": 3.252, + "step": 255200 }, { "epoch": 0.85, - "learning_rate": 7.737077504631431e-06, - "loss": 3.1213, - "step": 236800 + "learning_rate": 7.697469801660288e-06, + "loss": 3.2647, + "step": 255300 }, { "epoch": 0.85, - "learning_rate": 7.719229986685753e-06, - "loss": 3.1051, - "step": 236900 + "learning_rate": 7.68090006793591e-06, + "loss": 3.2475, + "step": 255400 }, { "epoch": 0.85, - "learning_rate": 7.701382468740074e-06, - "loss": 3.1171, - "step": 237000 + "learning_rate": 7.66433033421153e-06, + "loss": 3.2631, + "step": 255500 }, { "epoch": 0.85, - "learning_rate": 7.683534950794393e-06, - "loss": 3.1063, - "step": 237100 + "learning_rate": 7.64776060048715e-06, + "loss": 3.2574, + "step": 255600 }, { "epoch": 0.85, - "learning_rate": 7.665687432848715e-06, - "loss": 3.1167, - "step": 237200 + "learning_rate": 7.631190866762772e-06, + "loss": 3.2533, + "step": 255700 }, { "epoch": 0.85, - "learning_rate": 7.647839914903036e-06, - "loss": 3.1081, - "step": 237300 + "learning_rate": 7.614621133038392e-06, + "loss": 3.2632, + "step": 255800 }, { "epoch": 0.85, - "learning_rate": 7.629992396957355e-06, - "loss": 3.102, - "step": 237400 + "learning_rate": 7.598051399314013e-06, + "loss": 3.2413, + "step": 255900 }, { "epoch": 0.85, - "learning_rate": 7.6121448790116766e-06, - "loss": 3.0976, - "step": 237500 + "learning_rate": 7.581481665589635e-06, + "loss": 3.2713, + "step": 256000 }, { "epoch": 0.85, - "learning_rate": 7.594297361065997e-06, - "loss": 3.0966, - "step": 237600 + "learning_rate": 7.5649119318652555e-06, + "loss": 3.2554, + "step": 256100 }, { "epoch": 0.85, - "learning_rate": 7.576449843120317e-06, - "loss": 3.0995, - "step": 237700 + "learning_rate": 7.548342198140876e-06, + "loss": 3.2495, + "step": 256200 }, { "epoch": 0.85, - "learning_rate": 7.558602325174638e-06, - "loss": 3.0967, - "step": 237800 + "learning_rate": 7.531772464416498e-06, + "loss": 3.2518, + "step": 256300 }, { "epoch": 0.85, - "learning_rate": 7.540754807228959e-06, - "loss": 3.1156, - "step": 237900 + "learning_rate": 7.515202730692118e-06, + "loss": 3.2425, + "step": 256400 }, { "epoch": 0.85, - "learning_rate": 7.522907289283279e-06, - "loss": 3.1018, - "step": 238000 + "learning_rate": 7.498632996967739e-06, + "loss": 3.2487, + "step": 256500 }, { "epoch": 0.85, - "learning_rate": 7.505059771337601e-06, - "loss": 3.1002, - "step": 238100 + "learning_rate": 7.48206326324336e-06, + "loss": 3.2548, + "step": 256600 }, { "epoch": 0.85, - "learning_rate": 7.487212253391922e-06, - "loss": 3.1077, - "step": 238200 + "learning_rate": 7.465493529518981e-06, + "loss": 3.263, + "step": 256700 }, { "epoch": 0.85, - "learning_rate": 7.469364735446242e-06, - "loss": 3.1126, - "step": 238300 + "learning_rate": 7.448923795794602e-06, + "loss": 3.2506, + "step": 256800 }, { "epoch": 0.85, - "learning_rate": 7.451517217500563e-06, - "loss": 3.1007, - "step": 238400 + "learning_rate": 7.432354062070222e-06, + "loss": 3.2519, + "step": 256900 }, { "epoch": 0.85, - "learning_rate": 7.433669699554884e-06, - "loss": 3.1105, - "step": 238500 + "learning_rate": 7.4157843283458445e-06, + "loss": 3.2595, + "step": 257000 }, { "epoch": 0.85, - "learning_rate": 7.415822181609204e-06, - "loss": 3.1182, - "step": 238600 + "learning_rate": 7.399214594621464e-06, + "loss": 3.2773, + "step": 257100 }, { "epoch": 0.85, - "learning_rate": 7.397974663663524e-06, - "loss": 3.111, - "step": 238700 + "learning_rate": 7.382644860897085e-06, + "loss": 3.2458, + "step": 257200 }, { "epoch": 0.85, - "learning_rate": 7.3801271457178456e-06, - "loss": 3.1045, - "step": 238800 + "learning_rate": 7.366075127172707e-06, + "loss": 3.2609, + "step": 257300 }, { "epoch": 0.85, - "learning_rate": 7.362279627772166e-06, - "loss": 3.1078, - "step": 238900 + "learning_rate": 7.349505393448328e-06, + "loss": 3.2643, + "step": 257400 }, { "epoch": 0.85, - "learning_rate": 7.344432109826486e-06, - "loss": 3.105, - "step": 239000 + "learning_rate": 7.3329356597239485e-06, + "loss": 3.2548, + "step": 257500 }, { "epoch": 0.85, - "learning_rate": 7.326584591880807e-06, - "loss": 3.115, - "step": 239100 + "learning_rate": 7.31636592599957e-06, + "loss": 3.2508, + "step": 257600 }, { "epoch": 0.85, - "learning_rate": 7.308737073935128e-06, - "loss": 3.1198, - "step": 239200 + "learning_rate": 7.2997961922751906e-06, + "loss": 3.2571, + "step": 257700 }, { "epoch": 0.85, - "learning_rate": 7.290889555989448e-06, - "loss": 3.1087, - "step": 239300 + "learning_rate": 7.283226458550811e-06, + "loss": 3.2534, + "step": 257800 }, { "epoch": 0.85, - "learning_rate": 7.27304203804377e-06, - "loss": 3.1129, - "step": 239400 + "learning_rate": 7.266656724826433e-06, + "loss": 3.2628, + "step": 257900 }, { "epoch": 0.85, - "learning_rate": 7.255194520098091e-06, - "loss": 3.1096, - "step": 239500 + "learning_rate": 7.250086991102053e-06, + "loss": 3.2537, + "step": 258000 }, { "epoch": 0.86, - "learning_rate": 7.237347002152411e-06, - "loss": 3.0973, - "step": 239600 + "learning_rate": 7.233517257377674e-06, + "loss": 3.2551, + "step": 258100 }, { "epoch": 0.86, - "learning_rate": 7.219499484206732e-06, - "loss": 3.109, - "step": 239700 + "learning_rate": 7.2169475236532945e-06, + "loss": 3.2408, + "step": 258200 }, { "epoch": 0.86, - "learning_rate": 7.201651966261053e-06, - "loss": 3.109, - "step": 239800 + "learning_rate": 7.200377789928917e-06, + "loss": 3.2502, + "step": 258300 }, { "epoch": 0.86, - "learning_rate": 7.183804448315373e-06, - "loss": 3.1081, - "step": 239900 + "learning_rate": 7.1838080562045374e-06, + "loss": 3.2546, + "step": 258400 }, { "epoch": 0.86, - "learning_rate": 7.165956930369694e-06, - "loss": 3.1018, - "step": 240000 + "learning_rate": 7.167238322480157e-06, + "loss": 3.2692, + "step": 258500 }, { "epoch": 0.86, - "learning_rate": 7.148109412424015e-06, - "loss": 3.1155, - "step": 240100 + "learning_rate": 7.1506685887557795e-06, + "loss": 3.2444, + "step": 258600 }, { "epoch": 0.86, - "learning_rate": 7.130261894478335e-06, - "loss": 3.1031, - "step": 240200 + "learning_rate": 7.1340988550314e-06, + "loss": 3.2558, + "step": 258700 }, { "epoch": 0.86, - "learning_rate": 7.112414376532655e-06, - "loss": 3.1074, - "step": 240300 + "learning_rate": 7.117529121307021e-06, + "loss": 3.2513, + "step": 258800 }, { "epoch": 0.86, - "learning_rate": 7.0945668585869765e-06, - "loss": 3.1083, - "step": 240400 + "learning_rate": 7.100959387582642e-06, + "loss": 3.2618, + "step": 258900 }, { "epoch": 0.86, - "learning_rate": 7.076719340641297e-06, - "loss": 3.1161, - "step": 240500 + "learning_rate": 7.084389653858263e-06, + "loss": 3.2684, + "step": 259000 }, { "epoch": 0.86, - "learning_rate": 7.058871822695617e-06, - "loss": 3.1106, - "step": 240600 + "learning_rate": 7.0678199201338835e-06, + "loss": 3.2547, + "step": 259100 }, { "epoch": 0.86, - "learning_rate": 7.041024304749939e-06, - "loss": 3.0993, - "step": 240700 + "learning_rate": 7.051250186409506e-06, + "loss": 3.2509, + "step": 259200 }, { "epoch": 0.86, - "learning_rate": 7.02317678680426e-06, - "loss": 3.1103, - "step": 240800 + "learning_rate": 7.0346804526851256e-06, + "loss": 3.2637, + "step": 259300 }, { "epoch": 0.86, - "learning_rate": 7.005329268858581e-06, - "loss": 3.1123, - "step": 240900 + "learning_rate": 7.018110718960746e-06, + "loss": 3.2464, + "step": 259400 }, { "epoch": 0.86, - "learning_rate": 6.987481750912901e-06, - "loss": 3.107, - "step": 241000 + "learning_rate": 7.001540985236367e-06, + "loss": 3.2607, + "step": 259500 }, { "epoch": 0.86, - "learning_rate": 6.969634232967222e-06, - "loss": 3.098, - "step": 241100 + "learning_rate": 6.984971251511989e-06, + "loss": 3.2488, + "step": 259600 }, { "epoch": 0.86, - "learning_rate": 6.951786715021542e-06, - "loss": 3.1092, - "step": 241200 + "learning_rate": 6.96840151778761e-06, + "loss": 3.2616, + "step": 259700 }, { "epoch": 0.86, - "learning_rate": 6.933939197075863e-06, - "loss": 3.0975, - "step": 241300 + "learning_rate": 6.95183178406323e-06, + "loss": 3.2526, + "step": 259800 }, { "epoch": 0.86, - "learning_rate": 6.916091679130184e-06, - "loss": 3.099, - "step": 241400 + "learning_rate": 6.935262050338852e-06, + "loss": 3.2454, + "step": 259900 }, { "epoch": 0.86, - "learning_rate": 6.898244161184504e-06, - "loss": 3.1047, - "step": 241500 + "learning_rate": 6.9186923166144724e-06, + "loss": 3.2558, + "step": 260000 }, { "epoch": 0.86, - "learning_rate": 6.880396643238825e-06, - "loss": 3.1048, - "step": 241600 + "learning_rate": 6.902122582890093e-06, + "loss": 3.2624, + "step": 260100 }, { "epoch": 0.86, - "learning_rate": 6.8625491252931456e-06, - "loss": 3.1102, - "step": 241700 + "learning_rate": 6.8855528491657145e-06, + "loss": 3.2744, + "step": 260200 }, { "epoch": 0.86, - "learning_rate": 6.844701607347466e-06, - "loss": 3.1137, - "step": 241800 + "learning_rate": 6.868983115441335e-06, + "loss": 3.2541, + "step": 260300 }, { "epoch": 0.86, - "learning_rate": 6.826854089401786e-06, - "loss": 3.1049, - "step": 241900 + "learning_rate": 6.852413381716956e-06, + "loss": 3.244, + "step": 260400 }, { "epoch": 0.86, - "learning_rate": 6.809006571456108e-06, - "loss": 3.1038, - "step": 242000 + "learning_rate": 6.835843647992578e-06, + "loss": 3.2503, + "step": 260500 }, { "epoch": 0.86, - "learning_rate": 6.791159053510429e-06, - "loss": 3.115, - "step": 242100 + "learning_rate": 6.819273914268199e-06, + "loss": 3.2638, + "step": 260600 }, { "epoch": 0.86, - "learning_rate": 6.77331153556475e-06, - "loss": 3.106, - "step": 242200 + "learning_rate": 6.8027041805438185e-06, + "loss": 3.254, + "step": 260700 }, { "epoch": 0.86, - "learning_rate": 6.75546401761907e-06, - "loss": 3.098, - "step": 242300 + "learning_rate": 6.786134446819439e-06, + "loss": 3.2487, + "step": 260800 + }, + { + "epoch": 0.86, + "learning_rate": 6.769564713095061e-06, + "loss": 3.2601, + "step": 260900 + }, + { + "epoch": 0.86, + "learning_rate": 6.752994979370682e-06, + "loss": 3.2533, + "step": 261000 }, { "epoch": 0.87, - "learning_rate": 6.737616499673391e-06, - "loss": 3.1125, - "step": 242400 + "learning_rate": 6.736425245646303e-06, + "loss": 3.249, + "step": 261100 }, { "epoch": 0.87, - "learning_rate": 6.719768981727712e-06, - "loss": 3.1109, - "step": 242500 + "learning_rate": 6.719855511921924e-06, + "loss": 3.2583, + "step": 261200 }, { "epoch": 0.87, - "learning_rate": 6.701921463782032e-06, - "loss": 3.1081, - "step": 242600 + "learning_rate": 6.703285778197545e-06, + "loss": 3.2441, + "step": 261300 }, { "epoch": 0.87, - "learning_rate": 6.684073945836353e-06, - "loss": 3.1111, - "step": 242700 + "learning_rate": 6.686716044473165e-06, + "loss": 3.2649, + "step": 261400 }, { "epoch": 0.87, - "learning_rate": 6.666226427890673e-06, - "loss": 3.1075, - "step": 242800 + "learning_rate": 6.670146310748787e-06, + "loss": 3.2538, + "step": 261500 }, { "epoch": 0.87, - "learning_rate": 6.648378909944994e-06, - "loss": 3.1038, - "step": 242900 + "learning_rate": 6.6535765770244074e-06, + "loss": 3.2581, + "step": 261600 }, { "epoch": 0.87, - "learning_rate": 6.6305313919993146e-06, - "loss": 3.1086, - "step": 243000 + "learning_rate": 6.637006843300028e-06, + "loss": 3.2575, + "step": 261700 }, { "epoch": 0.87, - "learning_rate": 6.612683874053635e-06, - "loss": 3.1017, - "step": 243100 + "learning_rate": 6.62043710957565e-06, + "loss": 3.256, + "step": 261800 }, { "epoch": 0.87, - "learning_rate": 6.594836356107955e-06, - "loss": 3.1, - "step": 243200 + "learning_rate": 6.603867375851271e-06, + "loss": 3.2603, + "step": 261900 }, { "epoch": 0.87, - "learning_rate": 6.576988838162277e-06, - "loss": 3.1061, - "step": 243300 + "learning_rate": 6.587297642126891e-06, + "loss": 3.2464, + "step": 262000 }, { "epoch": 0.87, - "learning_rate": 6.559141320216599e-06, - "loss": 3.1011, - "step": 243400 + "learning_rate": 6.570727908402511e-06, + "loss": 3.2558, + "step": 262100 }, { "epoch": 0.87, - "learning_rate": 6.541293802270919e-06, - "loss": 3.1099, - "step": 243500 + "learning_rate": 6.554158174678134e-06, + "loss": 3.2585, + "step": 262200 }, { "epoch": 0.87, - "learning_rate": 6.523446284325239e-06, - "loss": 3.1032, - "step": 243600 + "learning_rate": 6.537588440953754e-06, + "loss": 3.2559, + "step": 262300 }, { "epoch": 0.87, - "learning_rate": 6.50559876637956e-06, - "loss": 3.1094, - "step": 243700 + "learning_rate": 6.521018707229375e-06, + "loss": 3.2551, + "step": 262400 }, { "epoch": 0.87, - "learning_rate": 6.487751248433881e-06, - "loss": 3.1114, - "step": 243800 + "learning_rate": 6.504448973504996e-06, + "loss": 3.2528, + "step": 262500 }, { "epoch": 0.87, - "learning_rate": 6.469903730488201e-06, - "loss": 3.1041, - "step": 243900 + "learning_rate": 6.487879239780617e-06, + "loss": 3.2655, + "step": 262600 }, { "epoch": 0.87, - "learning_rate": 6.452056212542522e-06, - "loss": 3.0987, - "step": 244000 + "learning_rate": 6.471309506056238e-06, + "loss": 3.2426, + "step": 262700 }, { "epoch": 0.87, - "learning_rate": 6.434208694596843e-06, - "loss": 3.1054, - "step": 244100 + "learning_rate": 6.454739772331859e-06, + "loss": 3.2412, + "step": 262800 }, { "epoch": 0.87, - "learning_rate": 6.416361176651163e-06, - "loss": 3.1045, - "step": 244200 + "learning_rate": 6.43817003860748e-06, + "loss": 3.2536, + "step": 262900 }, { "epoch": 0.87, - "learning_rate": 6.398513658705484e-06, - "loss": 3.1014, - "step": 244300 + "learning_rate": 6.4216003048831e-06, + "loss": 3.2496, + "step": 263000 }, { "epoch": 0.87, - "learning_rate": 6.380666140759804e-06, - "loss": 3.1006, - "step": 244400 + "learning_rate": 6.405030571158723e-06, + "loss": 3.2526, + "step": 263100 + }, + { + "epoch": 0.87, + "learning_rate": 6.388460837434343e-06, + "loss": 3.242, + "step": 263200 + }, + { + "epoch": 0.87, + "learning_rate": 6.371891103709964e-06, + "loss": 3.2421, + "step": 263300 + }, + { + "epoch": 0.87, + "learning_rate": 6.355321369985584e-06, + "loss": 3.2572, + "step": 263400 + }, + { + "epoch": 0.87, + "learning_rate": 6.338751636261206e-06, + "loss": 3.2512, + "step": 263500 }, { "epoch": 0.87, - "learning_rate": 6.362818622814126e-06, - "loss": 3.1064, - "step": 244500 + "learning_rate": 6.322181902536827e-06, + "loss": 3.249, + "step": 263600 }, { "epoch": 0.87, - "learning_rate": 6.344971104868447e-06, - "loss": 3.1124, - "step": 244600 + "learning_rate": 6.305612168812447e-06, + "loss": 3.2579, + "step": 263700 }, { "epoch": 0.87, - "learning_rate": 6.327123586922768e-06, - "loss": 3.108, - "step": 244700 + "learning_rate": 6.289042435088069e-06, + "loss": 3.2446, + "step": 263800 }, { "epoch": 0.87, - "learning_rate": 6.309276068977088e-06, - "loss": 3.1034, - "step": 244800 + "learning_rate": 6.272472701363689e-06, + "loss": 3.2631, + "step": 263900 }, { "epoch": 0.87, - "learning_rate": 6.291428551031408e-06, - "loss": 3.1064, - "step": 244900 + "learning_rate": 6.25590296763931e-06, + "loss": 3.253, + "step": 264000 }, { - "epoch": 0.87, - "learning_rate": 6.2735810330857296e-06, - "loss": 3.1076, - "step": 245000 + "epoch": 0.88, + "learning_rate": 6.239333233914931e-06, + "loss": 3.25, + "step": 264100 }, { - "epoch": 0.87, - "learning_rate": 6.25573351514005e-06, - "loss": 3.1084, - "step": 245100 + "epoch": 0.88, + "learning_rate": 6.222763500190552e-06, + "loss": 3.2476, + "step": 264200 }, { "epoch": 0.88, - "learning_rate": 6.23788599719437e-06, - "loss": 3.0986, - "step": 245200 + "learning_rate": 6.206193766466173e-06, + "loss": 3.2657, + "step": 264300 }, { "epoch": 0.88, - "learning_rate": 6.220038479248691e-06, - "loss": 3.0932, - "step": 245300 + "learning_rate": 6.189624032741794e-06, + "loss": 3.2558, + "step": 264400 }, { "epoch": 0.88, - "learning_rate": 6.202190961303012e-06, - "loss": 3.105, - "step": 245400 + "learning_rate": 6.173054299017416e-06, + "loss": 3.2506, + "step": 264500 }, { "epoch": 0.88, - "learning_rate": 6.184343443357333e-06, - "loss": 3.1116, - "step": 245500 + "learning_rate": 6.156484565293036e-06, + "loss": 3.2467, + "step": 264600 }, { "epoch": 0.88, - "learning_rate": 6.1664959254116535e-06, - "loss": 3.1009, - "step": 245600 + "learning_rate": 6.139914831568657e-06, + "loss": 3.25, + "step": 264700 }, { "epoch": 0.88, - "learning_rate": 6.148648407465974e-06, - "loss": 3.113, - "step": 245700 + "learning_rate": 6.1233450978442774e-06, + "loss": 3.2539, + "step": 264800 }, { "epoch": 0.88, - "learning_rate": 6.130800889520295e-06, - "loss": 3.1073, - "step": 245800 + "learning_rate": 6.106775364119899e-06, + "loss": 3.2447, + "step": 264900 }, { "epoch": 0.88, - "learning_rate": 6.112953371574615e-06, - "loss": 3.1073, - "step": 245900 + "learning_rate": 6.09020563039552e-06, + "loss": 3.2487, + "step": 265000 }, { "epoch": 0.88, - "learning_rate": 6.095105853628936e-06, - "loss": 3.107, - "step": 246000 + "learning_rate": 6.07363589667114e-06, + "loss": 3.2412, + "step": 265100 }, { "epoch": 0.88, - "learning_rate": 6.077258335683257e-06, - "loss": 3.1154, - "step": 246100 + "learning_rate": 6.057066162946762e-06, + "loss": 3.2428, + "step": 265200 }, { "epoch": 0.88, - "learning_rate": 6.059410817737577e-06, - "loss": 3.1188, - "step": 246200 + "learning_rate": 6.040496429222383e-06, + "loss": 3.2591, + "step": 265300 }, { "epoch": 0.88, - "learning_rate": 6.0415632997918986e-06, - "loss": 3.101, - "step": 246300 + "learning_rate": 6.023926695498004e-06, + "loss": 3.2555, + "step": 265400 }, { "epoch": 0.88, - "learning_rate": 6.023715781846219e-06, - "loss": 3.1166, - "step": 246400 + "learning_rate": 6.007356961773624e-06, + "loss": 3.244, + "step": 265500 }, { "epoch": 0.88, - "learning_rate": 6.005868263900539e-06, - "loss": 3.1149, - "step": 246500 + "learning_rate": 5.990787228049245e-06, + "loss": 3.2523, + "step": 265600 }, { "epoch": 0.88, - "learning_rate": 5.9880207459548605e-06, - "loss": 3.1046, - "step": 246600 + "learning_rate": 5.974217494324866e-06, + "loss": 3.2583, + "step": 265700 }, { "epoch": 0.88, - "learning_rate": 5.970173228009181e-06, - "loss": 3.1016, - "step": 246700 + "learning_rate": 5.957647760600488e-06, + "loss": 3.2514, + "step": 265800 }, { "epoch": 0.88, - "learning_rate": 5.952325710063502e-06, - "loss": 3.0996, - "step": 246800 + "learning_rate": 5.9410780268761085e-06, + "loss": 3.257, + "step": 265900 }, { "epoch": 0.88, - "learning_rate": 5.9344781921178225e-06, - "loss": 3.1002, - "step": 246900 + "learning_rate": 5.924508293151729e-06, + "loss": 3.2544, + "step": 266000 }, { "epoch": 0.88, - "learning_rate": 5.916630674172143e-06, - "loss": 3.1098, - "step": 247000 + "learning_rate": 5.90793855942735e-06, + "loss": 3.2597, + "step": 266100 }, { "epoch": 0.88, - "learning_rate": 5.898783156226464e-06, - "loss": 3.1044, - "step": 247100 + "learning_rate": 5.891368825702971e-06, + "loss": 3.2477, + "step": 266200 }, { "epoch": 0.88, - "learning_rate": 5.8809356382807844e-06, - "loss": 3.1009, - "step": 247200 + "learning_rate": 5.874799091978593e-06, + "loss": 3.2501, + "step": 266300 }, { "epoch": 0.88, - "learning_rate": 5.863088120335105e-06, - "loss": 3.1044, - "step": 247300 + "learning_rate": 5.858229358254213e-06, + "loss": 3.2673, + "step": 266400 }, { "epoch": 0.88, - "learning_rate": 5.845240602389426e-06, - "loss": 3.1076, - "step": 247400 + "learning_rate": 5.841659624529834e-06, + "loss": 3.2465, + "step": 266500 }, { "epoch": 0.88, - "learning_rate": 5.827393084443747e-06, - "loss": 3.1078, - "step": 247500 + "learning_rate": 5.825089890805455e-06, + "loss": 3.2702, + "step": 266600 }, { "epoch": 0.88, - "learning_rate": 5.809545566498068e-06, - "loss": 3.1014, - "step": 247600 + "learning_rate": 5.808520157081076e-06, + "loss": 3.258, + "step": 266700 }, { "epoch": 0.88, - "learning_rate": 5.791698048552388e-06, - "loss": 3.1087, - "step": 247700 + "learning_rate": 5.7919504233566975e-06, + "loss": 3.2592, + "step": 266800 }, { "epoch": 0.88, - "learning_rate": 5.773850530606708e-06, - "loss": 3.1007, - "step": 247800 + "learning_rate": 5.775380689632317e-06, + "loss": 3.2501, + "step": 266900 }, { "epoch": 0.88, - "learning_rate": 5.7560030126610295e-06, - "loss": 3.1028, - "step": 247900 + "learning_rate": 5.758810955907939e-06, + "loss": 3.2459, + "step": 267000 }, { "epoch": 0.89, - "learning_rate": 5.738155494715351e-06, - "loss": 3.0979, - "step": 248000 + "learning_rate": 5.74224122218356e-06, + "loss": 3.2495, + "step": 267100 }, { "epoch": 0.89, - "learning_rate": 5.720307976769671e-06, - "loss": 3.1032, - "step": 248100 + "learning_rate": 5.725671488459181e-06, + "loss": 3.2561, + "step": 267200 }, { "epoch": 0.89, - "learning_rate": 5.7024604588239915e-06, - "loss": 3.1104, - "step": 248200 + "learning_rate": 5.709101754734801e-06, + "loss": 3.2444, + "step": 267300 }, { "epoch": 0.89, - "learning_rate": 5.684612940878313e-06, - "loss": 3.1125, - "step": 248300 + "learning_rate": 5.692532021010422e-06, + "loss": 3.2715, + "step": 267400 }, { "epoch": 0.89, - "learning_rate": 5.666765422932633e-06, - "loss": 3.1088, - "step": 248400 + "learning_rate": 5.6759622872860435e-06, + "loss": 3.2521, + "step": 267500 }, { "epoch": 0.89, - "learning_rate": 5.6489179049869534e-06, - "loss": 3.1036, - "step": 248500 + "learning_rate": 5.659392553561665e-06, + "loss": 3.2609, + "step": 267600 }, { "epoch": 0.89, - "learning_rate": 5.631070387041274e-06, - "loss": 3.0997, - "step": 248600 + "learning_rate": 5.642822819837286e-06, + "loss": 3.2641, + "step": 267700 }, { "epoch": 0.89, - "learning_rate": 5.613222869095595e-06, - "loss": 3.1134, - "step": 248700 + "learning_rate": 5.626253086112906e-06, + "loss": 3.2566, + "step": 267800 }, { "epoch": 0.89, - "learning_rate": 5.595375351149916e-06, - "loss": 3.1048, - "step": 248800 + "learning_rate": 5.609683352388528e-06, + "loss": 3.2538, + "step": 267900 }, { "epoch": 0.89, - "learning_rate": 5.577527833204237e-06, - "loss": 3.1057, - "step": 248900 + "learning_rate": 5.593113618664148e-06, + "loss": 3.2493, + "step": 268000 }, { "epoch": 0.89, - "learning_rate": 5.559680315258557e-06, - "loss": 3.1128, - "step": 249000 + "learning_rate": 5.57654388493977e-06, + "loss": 3.2716, + "step": 268100 }, { "epoch": 0.89, - "learning_rate": 5.541832797312878e-06, - "loss": 3.1058, - "step": 249100 + "learning_rate": 5.5599741512153895e-06, + "loss": 3.2475, + "step": 268200 }, { "epoch": 0.89, - "learning_rate": 5.5239852793671986e-06, - "loss": 3.1052, - "step": 249200 + "learning_rate": 5.543404417491011e-06, + "loss": 3.247, + "step": 268300 }, { "epoch": 0.89, - "learning_rate": 5.50613776142152e-06, - "loss": 3.1029, - "step": 249300 + "learning_rate": 5.5268346837666325e-06, + "loss": 3.2506, + "step": 268400 }, { "epoch": 0.89, - "learning_rate": 5.48829024347584e-06, - "loss": 3.0938, - "step": 249400 + "learning_rate": 5.510264950042253e-06, + "loss": 3.2475, + "step": 268500 }, { "epoch": 0.89, - "learning_rate": 5.4704427255301605e-06, - "loss": 3.0966, - "step": 249500 + "learning_rate": 5.493695216317874e-06, + "loss": 3.2534, + "step": 268600 }, { "epoch": 0.89, - "learning_rate": 5.452595207584482e-06, - "loss": 3.1021, - "step": 249600 + "learning_rate": 5.477125482593494e-06, + "loss": 3.2625, + "step": 268700 }, { "epoch": 0.89, - "learning_rate": 5.434747689638802e-06, - "loss": 3.0987, - "step": 249700 + "learning_rate": 5.460555748869116e-06, + "loss": 3.2509, + "step": 268800 }, { "epoch": 0.89, - "learning_rate": 5.4169001716931225e-06, - "loss": 3.0943, - "step": 249800 + "learning_rate": 5.443986015144737e-06, + "loss": 3.2337, + "step": 268900 }, { "epoch": 0.89, - "learning_rate": 5.399052653747444e-06, - "loss": 3.1009, - "step": 249900 + "learning_rate": 5.427416281420358e-06, + "loss": 3.2574, + "step": 269000 }, { "epoch": 0.89, - "learning_rate": 5.381205135801765e-06, - "loss": 3.1115, - "step": 250000 + "learning_rate": 5.4108465476959785e-06, + "loss": 3.2448, + "step": 269100 }, { "epoch": 0.89, - "learning_rate": 5.363357617856085e-06, - "loss": 3.1097, - "step": 250100 + "learning_rate": 5.3942768139716e-06, + "loss": 3.2639, + "step": 269200 }, { "epoch": 0.89, - "learning_rate": 5.345510099910406e-06, - "loss": 3.1092, - "step": 250200 + "learning_rate": 5.377707080247221e-06, + "loss": 3.2423, + "step": 269300 }, { "epoch": 0.89, - "learning_rate": 5.327662581964726e-06, - "loss": 3.1112, - "step": 250300 + "learning_rate": 5.361137346522842e-06, + "loss": 3.2499, + "step": 269400 }, { "epoch": 0.89, - "learning_rate": 5.309815064019047e-06, - "loss": 3.1095, - "step": 250400 + "learning_rate": 5.344567612798463e-06, + "loss": 3.2569, + "step": 269500 }, { "epoch": 0.89, - "learning_rate": 5.2919675460733676e-06, - "loss": 3.1035, - "step": 250500 + "learning_rate": 5.327997879074083e-06, + "loss": 3.247, + "step": 269600 }, { "epoch": 0.89, - "learning_rate": 5.274120028127689e-06, - "loss": 3.0944, - "step": 250600 + "learning_rate": 5.311428145349705e-06, + "loss": 3.2541, + "step": 269700 }, { "epoch": 0.89, - "learning_rate": 5.256272510182009e-06, - "loss": 3.1062, - "step": 250700 + "learning_rate": 5.294858411625325e-06, + "loss": 3.2668, + "step": 269800 + }, + { + "epoch": 0.89, + "learning_rate": 5.278288677900947e-06, + "loss": 3.2492, + "step": 269900 + }, + { + "epoch": 0.89, + "learning_rate": 5.261718944176567e-06, + "loss": 3.2529, + "step": 270000 }, { "epoch": 0.9, - "learning_rate": 5.23842499223633e-06, - "loss": 3.1118, - "step": 250800 + "learning_rate": 5.245149210452188e-06, + "loss": 3.2539, + "step": 270100 }, { "epoch": 0.9, - "learning_rate": 5.220577474290651e-06, - "loss": 3.1035, - "step": 250900 + "learning_rate": 5.2285794767278096e-06, + "loss": 3.263, + "step": 270200 }, { "epoch": 0.9, - "learning_rate": 5.202729956344971e-06, - "loss": 3.1055, - "step": 251000 + "learning_rate": 5.21200974300343e-06, + "loss": 3.2425, + "step": 270300 }, { "epoch": 0.9, - "learning_rate": 5.1848824383992915e-06, - "loss": 3.0962, - "step": 251100 + "learning_rate": 5.195440009279051e-06, + "loss": 3.2496, + "step": 270400 }, { "epoch": 0.9, - "learning_rate": 5.167034920453613e-06, - "loss": 3.1116, - "step": 251200 + "learning_rate": 5.178870275554672e-06, + "loss": 3.2654, + "step": 270500 }, { "epoch": 0.9, - "learning_rate": 5.149187402507934e-06, - "loss": 3.1053, - "step": 251300 + "learning_rate": 5.162300541830293e-06, + "loss": 3.2359, + "step": 270600 }, { "epoch": 0.9, - "learning_rate": 5.131339884562254e-06, - "loss": 3.1036, - "step": 251400 + "learning_rate": 5.145730808105914e-06, + "loss": 3.2727, + "step": 270700 }, { "epoch": 0.9, - "learning_rate": 5.113492366616575e-06, - "loss": 3.1072, - "step": 251500 + "learning_rate": 5.129161074381535e-06, + "loss": 3.256, + "step": 270800 }, { "epoch": 0.9, - "learning_rate": 5.095644848670896e-06, - "loss": 3.1029, - "step": 251600 + "learning_rate": 5.112591340657156e-06, + "loss": 3.2564, + "step": 270900 }, { "epoch": 0.9, - "learning_rate": 5.077797330725216e-06, - "loss": 3.0967, - "step": 251700 + "learning_rate": 5.096021606932777e-06, + "loss": 3.2623, + "step": 271000 }, { "epoch": 0.9, - "learning_rate": 5.059949812779537e-06, - "loss": 3.0967, - "step": 251800 + "learning_rate": 5.079451873208398e-06, + "loss": 3.2435, + "step": 271100 }, { "epoch": 0.9, - "learning_rate": 5.042102294833858e-06, - "loss": 3.1091, - "step": 251900 + "learning_rate": 5.062882139484019e-06, + "loss": 3.2518, + "step": 271200 }, { "epoch": 0.9, - "learning_rate": 5.024254776888178e-06, - "loss": 3.1095, - "step": 252000 + "learning_rate": 5.04631240575964e-06, + "loss": 3.2454, + "step": 271300 }, { "epoch": 0.9, - "learning_rate": 5.006407258942499e-06, - "loss": 3.1111, - "step": 252100 + "learning_rate": 5.02974267203526e-06, + "loss": 3.2657, + "step": 271400 }, { "epoch": 0.9, - "learning_rate": 4.98855974099682e-06, - "loss": 3.1164, - "step": 252200 + "learning_rate": 5.013172938310882e-06, + "loss": 3.2521, + "step": 271500 }, { "epoch": 0.9, - "learning_rate": 4.97071222305114e-06, - "loss": 3.0984, - "step": 252300 + "learning_rate": 4.9966032045865025e-06, + "loss": 3.2494, + "step": 271600 }, { "epoch": 0.9, - "learning_rate": 4.952864705105461e-06, - "loss": 3.0967, - "step": 252400 + "learning_rate": 4.980033470862124e-06, + "loss": 3.2496, + "step": 271700 }, { "epoch": 0.9, - "learning_rate": 4.9350171871597826e-06, - "loss": 3.1089, - "step": 252500 + "learning_rate": 4.9634637371377446e-06, + "loss": 3.2596, + "step": 271800 }, { "epoch": 0.9, - "learning_rate": 4.917169669214103e-06, - "loss": 3.1003, - "step": 252600 + "learning_rate": 4.946894003413365e-06, + "loss": 3.2414, + "step": 271900 }, { "epoch": 0.9, - "learning_rate": 4.899322151268423e-06, - "loss": 3.0914, - "step": 252700 + "learning_rate": 4.930324269688987e-06, + "loss": 3.2573, + "step": 272000 }, { "epoch": 0.9, - "learning_rate": 4.881474633322744e-06, - "loss": 3.0976, - "step": 252800 + "learning_rate": 4.913754535964607e-06, + "loss": 3.2522, + "step": 272100 }, { "epoch": 0.9, - "learning_rate": 4.863627115377065e-06, - "loss": 3.0879, - "step": 252900 + "learning_rate": 4.897184802240228e-06, + "loss": 3.2581, + "step": 272200 }, { "epoch": 0.9, - "learning_rate": 4.845779597431385e-06, - "loss": 3.097, - "step": 253000 + "learning_rate": 4.880615068515849e-06, + "loss": 3.2549, + "step": 272300 }, { "epoch": 0.9, - "learning_rate": 4.8279320794857065e-06, - "loss": 3.09, - "step": 253100 + "learning_rate": 4.86404533479147e-06, + "loss": 3.2502, + "step": 272400 }, { "epoch": 0.9, - "learning_rate": 4.810084561540027e-06, - "loss": 3.1011, - "step": 253200 + "learning_rate": 4.8474756010670914e-06, + "loss": 3.2504, + "step": 272500 }, { "epoch": 0.9, - "learning_rate": 4.792237043594348e-06, - "loss": 3.1092, - "step": 253300 + "learning_rate": 4.830905867342712e-06, + "loss": 3.2536, + "step": 272600 }, { "epoch": 0.9, - "learning_rate": 4.774389525648668e-06, - "loss": 3.1055, - "step": 253400 + "learning_rate": 4.814336133618333e-06, + "loss": 3.2529, + "step": 272700 }, { "epoch": 0.9, - "learning_rate": 4.756542007702989e-06, - "loss": 3.0985, - "step": 253500 + "learning_rate": 4.797766399893954e-06, + "loss": 3.2578, + "step": 272800 + }, + { + "epoch": 0.9, + "learning_rate": 4.781196666169575e-06, + "loss": 3.2505, + "step": 272900 + }, + { + "epoch": 0.9, + "learning_rate": 4.764626932445196e-06, + "loss": 3.2568, + "step": 273000 + }, + { + "epoch": 0.91, + "learning_rate": 4.748057198720817e-06, + "loss": 3.265, + "step": 273100 + }, + { + "epoch": 0.91, + "learning_rate": 4.7314874649964375e-06, + "loss": 3.2586, + "step": 273200 + }, + { + "epoch": 0.91, + "learning_rate": 4.714917731272059e-06, + "loss": 3.2575, + "step": 273300 + }, + { + "epoch": 0.91, + "learning_rate": 4.6983479975476796e-06, + "loss": 3.2483, + "step": 273400 + }, + { + "epoch": 0.91, + "learning_rate": 4.6817782638233e-06, + "loss": 3.2363, + "step": 273500 }, { "epoch": 0.91, - "learning_rate": 4.738694489757309e-06, - "loss": 3.0891, - "step": 253600 + "learning_rate": 4.665208530098922e-06, + "loss": 3.2531, + "step": 273600 }, { "epoch": 0.91, - "learning_rate": 4.72084697181163e-06, - "loss": 3.0965, - "step": 253700 + "learning_rate": 4.648638796374542e-06, + "loss": 3.2443, + "step": 273700 }, { "epoch": 0.91, - "learning_rate": 4.7029994538659516e-06, - "loss": 3.1146, - "step": 253800 + "learning_rate": 4.632069062650164e-06, + "loss": 3.2613, + "step": 273800 }, { "epoch": 0.91, - "learning_rate": 4.685151935920272e-06, - "loss": 3.0973, - "step": 253900 + "learning_rate": 4.615499328925784e-06, + "loss": 3.2519, + "step": 273900 }, { "epoch": 0.91, - "learning_rate": 4.667304417974592e-06, - "loss": 3.0969, - "step": 254000 + "learning_rate": 4.598929595201405e-06, + "loss": 3.2395, + "step": 274000 }, { "epoch": 0.91, - "learning_rate": 4.6494569000289135e-06, - "loss": 3.1059, - "step": 254100 + "learning_rate": 4.5823598614770264e-06, + "loss": 3.2567, + "step": 274100 }, { "epoch": 0.91, - "learning_rate": 4.631609382083234e-06, - "loss": 3.1029, - "step": 254200 + "learning_rate": 4.565790127752647e-06, + "loss": 3.244, + "step": 274200 }, { "epoch": 0.91, - "learning_rate": 4.613761864137554e-06, - "loss": 3.1066, - "step": 254300 + "learning_rate": 4.5492203940282685e-06, + "loss": 3.2568, + "step": 274300 }, { "epoch": 0.91, - "learning_rate": 4.5959143461918755e-06, - "loss": 3.1087, - "step": 254400 + "learning_rate": 4.532650660303889e-06, + "loss": 3.2599, + "step": 274400 }, { "epoch": 0.91, - "learning_rate": 4.578066828246196e-06, - "loss": 3.0989, - "step": 254500 + "learning_rate": 4.51608092657951e-06, + "loss": 3.2632, + "step": 274500 }, { "epoch": 0.91, - "learning_rate": 4.560219310300517e-06, - "loss": 3.1001, - "step": 254600 + "learning_rate": 4.499511192855131e-06, + "loss": 3.2513, + "step": 274600 }, { "epoch": 0.91, - "learning_rate": 4.5423717923548374e-06, - "loss": 3.1032, - "step": 254700 + "learning_rate": 4.482941459130752e-06, + "loss": 3.2539, + "step": 274700 }, { "epoch": 0.91, - "learning_rate": 4.524524274409158e-06, - "loss": 3.1114, - "step": 254800 + "learning_rate": 4.466371725406373e-06, + "loss": 3.2443, + "step": 274800 }, { "epoch": 0.91, - "learning_rate": 4.506676756463479e-06, - "loss": 3.092, - "step": 254900 + "learning_rate": 4.449801991681994e-06, + "loss": 3.2453, + "step": 274900 }, { "epoch": 0.91, - "learning_rate": 4.488829238517799e-06, - "loss": 3.1003, - "step": 255000 + "learning_rate": 4.4332322579576146e-06, + "loss": 3.2433, + "step": 275000 }, { "epoch": 0.91, - "learning_rate": 4.470981720572121e-06, - "loss": 3.0936, - "step": 255100 + "learning_rate": 4.416662524233236e-06, + "loss": 3.2525, + "step": 275100 }, { "epoch": 0.91, - "learning_rate": 4.453134202626441e-06, - "loss": 3.1045, - "step": 255200 + "learning_rate": 4.400092790508857e-06, + "loss": 3.2611, + "step": 275200 }, { "epoch": 0.91, - "learning_rate": 4.435286684680761e-06, - "loss": 3.0991, - "step": 255300 + "learning_rate": 4.383523056784477e-06, + "loss": 3.2567, + "step": 275300 }, { "epoch": 0.91, - "learning_rate": 4.4174391667350825e-06, - "loss": 3.1063, - "step": 255400 + "learning_rate": 4.366953323060099e-06, + "loss": 3.2598, + "step": 275400 }, { "epoch": 0.91, - "learning_rate": 4.399591648789403e-06, - "loss": 3.1097, - "step": 255500 + "learning_rate": 4.350383589335719e-06, + "loss": 3.2616, + "step": 275500 }, { "epoch": 0.91, - "learning_rate": 4.381744130843723e-06, - "loss": 3.1077, - "step": 255600 + "learning_rate": 4.333813855611341e-06, + "loss": 3.2537, + "step": 275600 }, { "epoch": 0.91, - "learning_rate": 4.3638966128980445e-06, - "loss": 3.1014, - "step": 255700 + "learning_rate": 4.3172441218869614e-06, + "loss": 3.2519, + "step": 275700 }, { "epoch": 0.91, - "learning_rate": 4.346049094952366e-06, - "loss": 3.1013, - "step": 255800 + "learning_rate": 4.300674388162582e-06, + "loss": 3.2588, + "step": 275800 }, { "epoch": 0.91, - "learning_rate": 4.328201577006686e-06, - "loss": 3.1017, - "step": 255900 + "learning_rate": 4.2841046544382035e-06, + "loss": 3.2512, + "step": 275900 }, { "epoch": 0.91, - "learning_rate": 4.3103540590610064e-06, - "loss": 3.0963, - "step": 256000 + "learning_rate": 4.267534920713824e-06, + "loss": 3.2612, + "step": 276000 }, { "epoch": 0.91, - "learning_rate": 4.292506541115327e-06, - "loss": 3.1089, - "step": 256100 + "learning_rate": 4.250965186989446e-06, + "loss": 3.2596, + "step": 276100 }, { - "epoch": 0.91, - "learning_rate": 4.274659023169648e-06, - "loss": 3.1068, - "step": 256200 + "epoch": 0.92, + "learning_rate": 4.234395453265066e-06, + "loss": 3.2445, + "step": 276200 }, { - "epoch": 0.91, - "learning_rate": 4.256811505223969e-06, - "loss": 3.0942, - "step": 256300 + "epoch": 0.92, + "learning_rate": 4.217825719540687e-06, + "loss": 3.2519, + "step": 276300 }, { "epoch": 0.92, - "learning_rate": 4.23896398727829e-06, - "loss": 3.1015, - "step": 256400 + "learning_rate": 4.201255985816308e-06, + "loss": 3.2559, + "step": 276400 }, { "epoch": 0.92, - "learning_rate": 4.22111646933261e-06, - "loss": 3.1068, - "step": 256500 + "learning_rate": 4.184686252091929e-06, + "loss": 3.2577, + "step": 276500 }, { "epoch": 0.92, - "learning_rate": 4.203268951386931e-06, - "loss": 3.1053, - "step": 256600 + "learning_rate": 4.1681165183675496e-06, + "loss": 3.2445, + "step": 276600 }, { "epoch": 0.92, - "learning_rate": 4.1854214334412516e-06, - "loss": 3.0987, - "step": 256700 + "learning_rate": 4.151546784643171e-06, + "loss": 3.2335, + "step": 276700 }, { "epoch": 0.92, - "learning_rate": 4.167573915495572e-06, - "loss": 3.1102, - "step": 256800 + "learning_rate": 4.134977050918792e-06, + "loss": 3.2363, + "step": 276800 }, { "epoch": 0.92, - "learning_rate": 4.149726397549892e-06, - "loss": 3.1008, - "step": 256900 + "learning_rate": 4.118407317194413e-06, + "loss": 3.2511, + "step": 276900 }, { "epoch": 0.92, - "learning_rate": 4.1318788796042135e-06, - "loss": 3.0988, - "step": 257000 + "learning_rate": 4.101837583470034e-06, + "loss": 3.2516, + "step": 277000 }, { "epoch": 0.92, - "learning_rate": 4.114031361658535e-06, - "loss": 3.109, - "step": 257100 + "learning_rate": 4.085267849745654e-06, + "loss": 3.2581, + "step": 277100 }, { "epoch": 0.92, - "learning_rate": 4.096183843712855e-06, - "loss": 3.099, - "step": 257200 + "learning_rate": 4.068698116021276e-06, + "loss": 3.2456, + "step": 277200 }, { "epoch": 0.92, - "learning_rate": 4.0783363257671755e-06, - "loss": 3.1061, - "step": 257300 + "learning_rate": 4.0521283822968964e-06, + "loss": 3.2417, + "step": 277300 }, { "epoch": 0.92, - "learning_rate": 4.060488807821497e-06, - "loss": 3.1048, - "step": 257400 + "learning_rate": 4.035558648572518e-06, + "loss": 3.251, + "step": 277400 }, { "epoch": 0.92, - "learning_rate": 4.042641289875817e-06, - "loss": 3.1054, - "step": 257500 + "learning_rate": 4.0189889148481385e-06, + "loss": 3.2562, + "step": 277500 }, { "epoch": 0.92, - "learning_rate": 4.024793771930138e-06, - "loss": 3.0864, - "step": 257600 + "learning_rate": 4.002419181123759e-06, + "loss": 3.2414, + "step": 277600 }, { "epoch": 0.92, - "learning_rate": 4.006946253984459e-06, - "loss": 3.0902, - "step": 257700 + "learning_rate": 3.985849447399381e-06, + "loss": 3.2486, + "step": 277700 }, { "epoch": 0.92, - "learning_rate": 3.989098736038779e-06, - "loss": 3.0924, - "step": 257800 + "learning_rate": 3.969279713675001e-06, + "loss": 3.2617, + "step": 277800 }, { "epoch": 0.92, - "learning_rate": 3.9712512180931e-06, - "loss": 3.0962, - "step": 257900 + "learning_rate": 3.952709979950623e-06, + "loss": 3.2569, + "step": 277900 }, { "epoch": 0.92, - "learning_rate": 3.953403700147421e-06, - "loss": 3.1044, - "step": 258000 + "learning_rate": 3.936140246226243e-06, + "loss": 3.2565, + "step": 278000 }, { "epoch": 0.92, - "learning_rate": 3.935556182201741e-06, - "loss": 3.1063, - "step": 258100 + "learning_rate": 3.919570512501864e-06, + "loss": 3.2482, + "step": 278100 }, { "epoch": 0.92, - "learning_rate": 3.917708664256062e-06, - "loss": 3.1056, - "step": 258200 + "learning_rate": 3.903000778777485e-06, + "loss": 3.2436, + "step": 278200 }, { "epoch": 0.92, - "learning_rate": 3.899861146310383e-06, - "loss": 3.1084, - "step": 258300 + "learning_rate": 3.886431045053107e-06, + "loss": 3.2534, + "step": 278300 }, { "epoch": 0.92, - "learning_rate": 3.882013628364704e-06, - "loss": 3.1072, - "step": 258400 + "learning_rate": 3.869861311328727e-06, + "loss": 3.2516, + "step": 278400 }, { "epoch": 0.92, - "learning_rate": 3.864166110419024e-06, - "loss": 3.0959, - "step": 258500 + "learning_rate": 3.853291577604348e-06, + "loss": 3.263, + "step": 278500 }, { "epoch": 0.92, - "learning_rate": 3.8463185924733445e-06, - "loss": 3.0922, - "step": 258600 + "learning_rate": 3.836721843879969e-06, + "loss": 3.2548, + "step": 278600 }, { "epoch": 0.92, - "learning_rate": 3.828471074527666e-06, - "loss": 3.0972, - "step": 258700 + "learning_rate": 3.82015211015559e-06, + "loss": 3.2499, + "step": 278700 }, { "epoch": 0.92, - "learning_rate": 3.810623556581986e-06, - "loss": 3.098, - "step": 258800 + "learning_rate": 3.8035823764312113e-06, + "loss": 3.2487, + "step": 278800 }, { "epoch": 0.92, - "learning_rate": 3.7927760386363073e-06, - "loss": 3.0993, - "step": 258900 + "learning_rate": 3.787012642706832e-06, + "loss": 3.2629, + "step": 278900 }, { "epoch": 0.92, - "learning_rate": 3.774928520690628e-06, - "loss": 3.1033, - "step": 259000 + "learning_rate": 3.770442908982453e-06, + "loss": 3.2599, + "step": 279000 }, { "epoch": 0.92, - "learning_rate": 3.7570810027449484e-06, - "loss": 3.0959, - "step": 259100 + "learning_rate": 3.7538731752580735e-06, + "loss": 3.2592, + "step": 279100 }, { "epoch": 0.93, - "learning_rate": 3.7392334847992692e-06, - "loss": 3.0972, - "step": 259200 + "learning_rate": 3.7373034415336946e-06, + "loss": 3.2429, + "step": 279200 }, { "epoch": 0.93, - "learning_rate": 3.7213859668535896e-06, - "loss": 3.0985, - "step": 259300 + "learning_rate": 3.720733707809316e-06, + "loss": 3.2559, + "step": 279300 }, { "epoch": 0.93, - "learning_rate": 3.7035384489079104e-06, - "loss": 3.0993, - "step": 259400 + "learning_rate": 3.7041639740849362e-06, + "loss": 3.247, + "step": 279400 }, { "epoch": 0.93, - "learning_rate": 3.6856909309622316e-06, - "loss": 3.0949, - "step": 259500 + "learning_rate": 3.6875942403605577e-06, + "loss": 3.2498, + "step": 279500 }, { "epoch": 0.93, - "learning_rate": 3.6678434130165524e-06, - "loss": 3.0955, - "step": 259600 + "learning_rate": 3.6710245066361788e-06, + "loss": 3.2522, + "step": 279600 }, { "epoch": 0.93, - "learning_rate": 3.6499958950708728e-06, - "loss": 3.0982, - "step": 259700 + "learning_rate": 3.6544547729117994e-06, + "loss": 3.2548, + "step": 279700 }, { "epoch": 0.93, - "learning_rate": 3.6321483771251936e-06, - "loss": 3.0974, - "step": 259800 + "learning_rate": 3.6378850391874204e-06, + "loss": 3.2458, + "step": 279800 }, { "epoch": 0.93, - "learning_rate": 3.614300859179514e-06, - "loss": 3.0998, - "step": 259900 + "learning_rate": 3.621315305463041e-06, + "loss": 3.2569, + "step": 279900 }, { "epoch": 0.93, - "learning_rate": 3.5964533412338347e-06, - "loss": 3.0948, - "step": 260000 + "learning_rate": 3.6047455717386625e-06, + "loss": 3.2535, + "step": 280000 }, { "epoch": 0.93, - "learning_rate": 3.578605823288155e-06, - "loss": 3.0904, - "step": 260100 + "learning_rate": 3.5881758380142835e-06, + "loss": 3.2559, + "step": 280100 }, { "epoch": 0.93, - "learning_rate": 3.5607583053424763e-06, - "loss": 3.0838, - "step": 260200 + "learning_rate": 3.571606104289904e-06, + "loss": 3.2481, + "step": 280200 }, { "epoch": 0.93, - "learning_rate": 3.542910787396797e-06, - "loss": 3.104, - "step": 260300 + "learning_rate": 3.555036370565525e-06, + "loss": 3.2313, + "step": 280300 }, { "epoch": 0.93, - "learning_rate": 3.5250632694511175e-06, - "loss": 3.1062, - "step": 260400 + "learning_rate": 3.538466636841146e-06, + "loss": 3.2657, + "step": 280400 }, { "epoch": 0.93, - "learning_rate": 3.5072157515054382e-06, - "loss": 3.1, - "step": 260500 + "learning_rate": 3.521896903116767e-06, + "loss": 3.2597, + "step": 280500 }, { "epoch": 0.93, - "learning_rate": 3.489368233559759e-06, - "loss": 3.0983, - "step": 260600 + "learning_rate": 3.5053271693923883e-06, + "loss": 3.2486, + "step": 280600 }, { "epoch": 0.93, - "learning_rate": 3.4715207156140794e-06, - "loss": 3.1059, - "step": 260700 + "learning_rate": 3.488757435668009e-06, + "loss": 3.2732, + "step": 280700 }, { "epoch": 0.93, - "learning_rate": 3.4536731976684006e-06, - "loss": 3.1043, - "step": 260800 + "learning_rate": 3.47218770194363e-06, + "loss": 3.2479, + "step": 280800 }, { "epoch": 0.93, - "learning_rate": 3.4358256797227214e-06, - "loss": 3.0943, - "step": 260900 + "learning_rate": 3.455617968219251e-06, + "loss": 3.2473, + "step": 280900 }, { "epoch": 0.93, - "learning_rate": 3.4179781617770418e-06, - "loss": 3.0936, - "step": 261000 + "learning_rate": 3.4390482344948717e-06, + "loss": 3.2428, + "step": 281000 }, { "epoch": 0.93, - "learning_rate": 3.4001306438313626e-06, - "loss": 3.1083, - "step": 261100 + "learning_rate": 3.422478500770493e-06, + "loss": 3.2411, + "step": 281100 }, { "epoch": 0.93, - "learning_rate": 3.382283125885683e-06, - "loss": 3.1002, - "step": 261200 + "learning_rate": 3.4059087670461133e-06, + "loss": 3.2496, + "step": 281200 }, { "epoch": 0.93, - "learning_rate": 3.3644356079400037e-06, - "loss": 3.1005, - "step": 261300 + "learning_rate": 3.389339033321735e-06, + "loss": 3.2425, + "step": 281300 }, { "epoch": 0.93, - "learning_rate": 3.346588089994325e-06, - "loss": 3.1036, - "step": 261400 + "learning_rate": 3.372769299597356e-06, + "loss": 3.2326, + "step": 281400 }, { "epoch": 0.93, - "learning_rate": 3.3287405720486457e-06, - "loss": 3.1037, - "step": 261500 + "learning_rate": 3.3561995658729765e-06, + "loss": 3.2615, + "step": 281500 }, { "epoch": 0.93, - "learning_rate": 3.310893054102966e-06, - "loss": 3.1036, - "step": 261600 + "learning_rate": 3.3396298321485975e-06, + "loss": 3.2454, + "step": 281600 }, { "epoch": 0.93, - "learning_rate": 3.293045536157287e-06, - "loss": 3.0978, - "step": 261700 + "learning_rate": 3.323060098424218e-06, + "loss": 3.2517, + "step": 281700 }, { "epoch": 0.93, - "learning_rate": 3.2751980182116073e-06, - "loss": 3.0993, - "step": 261800 + "learning_rate": 3.306490364699839e-06, + "loss": 3.2438, + "step": 281800 }, { "epoch": 0.93, - "learning_rate": 3.257350500265928e-06, - "loss": 3.1144, - "step": 261900 + "learning_rate": 3.2899206309754606e-06, + "loss": 3.2532, + "step": 281900 + }, + { + "epoch": 0.93, + "learning_rate": 3.2733508972510813e-06, + "loss": 3.2498, + "step": 282000 + }, + { + "epoch": 0.93, + "learning_rate": 3.2567811635267023e-06, + "loss": 3.2473, + "step": 282100 }, { "epoch": 0.94, - "learning_rate": 3.2395029823202484e-06, - "loss": 3.103, - "step": 262000 + "learning_rate": 3.2402114298023233e-06, + "loss": 3.2422, + "step": 282200 }, { "epoch": 0.94, - "learning_rate": 3.22165546437457e-06, - "loss": 3.1045, - "step": 262100 + "learning_rate": 3.223641696077944e-06, + "loss": 3.2507, + "step": 282300 }, { "epoch": 0.94, - "learning_rate": 3.2038079464288904e-06, - "loss": 3.0942, - "step": 262200 + "learning_rate": 3.2070719623535654e-06, + "loss": 3.251, + "step": 282400 }, { "epoch": 0.94, - "learning_rate": 3.1859604284832112e-06, - "loss": 3.1026, - "step": 262300 + "learning_rate": 3.1905022286291856e-06, + "loss": 3.2553, + "step": 282500 }, { "epoch": 0.94, - "learning_rate": 3.1681129105375316e-06, - "loss": 3.0993, - "step": 262400 + "learning_rate": 3.173932494904807e-06, + "loss": 3.2451, + "step": 282600 }, { "epoch": 0.94, - "learning_rate": 3.1502653925918524e-06, - "loss": 3.1082, - "step": 262500 + "learning_rate": 3.157362761180428e-06, + "loss": 3.2596, + "step": 282700 }, { "epoch": 0.94, - "learning_rate": 3.1324178746461727e-06, - "loss": 3.0868, - "step": 262600 + "learning_rate": 3.1407930274560488e-06, + "loss": 3.2536, + "step": 282800 }, { "epoch": 0.94, - "learning_rate": 3.114570356700494e-06, - "loss": 3.1001, - "step": 262700 + "learning_rate": 3.12422329373167e-06, + "loss": 3.2478, + "step": 282900 }, { "epoch": 0.94, - "learning_rate": 3.0967228387548143e-06, - "loss": 3.0998, - "step": 262800 + "learning_rate": 3.107653560007291e-06, + "loss": 3.2625, + "step": 283000 }, { "epoch": 0.94, - "learning_rate": 3.078875320809135e-06, - "loss": 3.1123, - "step": 262900 + "learning_rate": 3.091083826282912e-06, + "loss": 3.2486, + "step": 283100 }, { "epoch": 0.94, - "learning_rate": 3.061027802863456e-06, - "loss": 3.1034, - "step": 263000 + "learning_rate": 3.0745140925585325e-06, + "loss": 3.2496, + "step": 283200 }, { "epoch": 0.94, - "learning_rate": 3.0431802849177767e-06, - "loss": 3.0894, - "step": 263100 + "learning_rate": 3.057944358834154e-06, + "loss": 3.2507, + "step": 283300 }, { "epoch": 0.94, - "learning_rate": 3.0253327669720975e-06, - "loss": 3.0998, - "step": 263200 + "learning_rate": 3.0413746251097746e-06, + "loss": 3.2544, + "step": 283400 }, { "epoch": 0.94, - "learning_rate": 3.007485249026418e-06, - "loss": 3.1085, - "step": 263300 + "learning_rate": 3.0248048913853956e-06, + "loss": 3.2437, + "step": 283500 }, { "epoch": 0.94, - "learning_rate": 2.9896377310807387e-06, - "loss": 3.1034, - "step": 263400 + "learning_rate": 3.0082351576610163e-06, + "loss": 3.2602, + "step": 283600 }, { "epoch": 0.94, - "learning_rate": 2.9717902131350594e-06, - "loss": 3.103, - "step": 263500 + "learning_rate": 2.9916654239366377e-06, + "loss": 3.2509, + "step": 283700 }, { "epoch": 0.94, - "learning_rate": 2.9539426951893802e-06, - "loss": 3.0973, - "step": 263600 + "learning_rate": 2.9750956902122583e-06, + "loss": 3.2376, + "step": 283800 }, { "epoch": 0.94, - "learning_rate": 2.9360951772437006e-06, - "loss": 3.1094, - "step": 263700 + "learning_rate": 2.9585259564878794e-06, + "loss": 3.2576, + "step": 283900 }, { "epoch": 0.94, - "learning_rate": 2.918247659298022e-06, - "loss": 3.1032, - "step": 263800 + "learning_rate": 2.9419562227635004e-06, + "loss": 3.252, + "step": 284000 }, { "epoch": 0.94, - "learning_rate": 2.900400141352342e-06, - "loss": 3.0908, - "step": 263900 + "learning_rate": 2.9253864890391215e-06, + "loss": 3.2466, + "step": 284100 }, { "epoch": 0.94, - "learning_rate": 2.882552623406663e-06, - "loss": 3.1135, - "step": 264000 + "learning_rate": 2.9088167553147425e-06, + "loss": 3.2527, + "step": 284200 }, { "epoch": 0.94, - "learning_rate": 2.8647051054609833e-06, - "loss": 3.0953, - "step": 264100 + "learning_rate": 2.892247021590363e-06, + "loss": 3.2576, + "step": 284300 }, { "epoch": 0.94, - "learning_rate": 2.8468575875153046e-06, - "loss": 3.1057, - "step": 264200 + "learning_rate": 2.875677287865984e-06, + "loss": 3.2492, + "step": 284400 }, { "epoch": 0.94, - "learning_rate": 2.829010069569625e-06, - "loss": 3.085, - "step": 264300 + "learning_rate": 2.859107554141605e-06, + "loss": 3.2415, + "step": 284500 }, { "epoch": 0.94, - "learning_rate": 2.8111625516239457e-06, - "loss": 3.1071, - "step": 264400 + "learning_rate": 2.8425378204172263e-06, + "loss": 3.2399, + "step": 284600 }, { "epoch": 0.94, - "learning_rate": 2.7933150336782665e-06, - "loss": 3.1122, - "step": 264500 + "learning_rate": 2.825968086692847e-06, + "loss": 3.2563, + "step": 284700 }, { "epoch": 0.94, - "learning_rate": 2.7754675157325873e-06, - "loss": 3.0926, - "step": 264600 + "learning_rate": 2.809398352968468e-06, + "loss": 3.2542, + "step": 284800 + }, + { + "epoch": 0.94, + "learning_rate": 2.7928286192440886e-06, + "loss": 3.2552, + "step": 284900 + }, + { + "epoch": 0.94, + "learning_rate": 2.77625888551971e-06, + "loss": 3.2447, + "step": 285000 + }, + { + "epoch": 0.94, + "learning_rate": 2.7596891517953306e-06, + "loss": 3.2464, + "step": 285100 + }, + { + "epoch": 0.95, + "learning_rate": 2.7431194180709517e-06, + "loss": 3.2474, + "step": 285200 + }, + { + "epoch": 0.95, + "learning_rate": 2.7265496843465727e-06, + "loss": 3.2489, + "step": 285300 }, { - "epoch": 0.94, - "learning_rate": 2.7576199977869077e-06, - "loss": 3.1015, - "step": 264700 + "epoch": 0.95, + "learning_rate": 2.7099799506221938e-06, + "loss": 3.2457, + "step": 285400 }, { "epoch": 0.95, - "learning_rate": 2.739772479841229e-06, - "loss": 3.1071, - "step": 264800 + "learning_rate": 2.693410216897815e-06, + "loss": 3.248, + "step": 285500 }, { "epoch": 0.95, - "learning_rate": 2.7219249618955493e-06, - "loss": 3.106, - "step": 264900 + "learning_rate": 2.6768404831734354e-06, + "loss": 3.2506, + "step": 285600 }, { "epoch": 0.95, - "learning_rate": 2.70407744394987e-06, - "loss": 3.0988, - "step": 265000 + "learning_rate": 2.6602707494490565e-06, + "loss": 3.2474, + "step": 285700 }, { "epoch": 0.95, - "learning_rate": 2.686229926004191e-06, - "loss": 3.0904, - "step": 265100 + "learning_rate": 2.643701015724677e-06, + "loss": 3.2457, + "step": 285800 }, { "epoch": 0.95, - "learning_rate": 2.6683824080585116e-06, - "loss": 3.0983, - "step": 265200 + "learning_rate": 2.6271312820002986e-06, + "loss": 3.2339, + "step": 285900 }, { "epoch": 0.95, - "learning_rate": 2.650534890112832e-06, - "loss": 3.0981, - "step": 265300 + "learning_rate": 2.610561548275919e-06, + "loss": 3.2555, + "step": 286000 }, { "epoch": 0.95, - "learning_rate": 2.6326873721671528e-06, - "loss": 3.1014, - "step": 265400 + "learning_rate": 2.5939918145515402e-06, + "loss": 3.2489, + "step": 286100 }, { "epoch": 0.95, - "learning_rate": 2.6148398542214736e-06, - "loss": 3.1077, - "step": 265500 + "learning_rate": 2.5774220808271613e-06, + "loss": 3.2534, + "step": 286200 }, { "epoch": 0.95, - "learning_rate": 2.5969923362757944e-06, - "loss": 3.0979, - "step": 265600 + "learning_rate": 2.5608523471027823e-06, + "loss": 3.2453, + "step": 286300 }, { "epoch": 0.95, - "learning_rate": 2.5791448183301147e-06, - "loss": 3.1003, - "step": 265700 + "learning_rate": 2.5442826133784034e-06, + "loss": 3.2474, + "step": 286400 }, { "epoch": 0.95, - "learning_rate": 2.5612973003844355e-06, - "loss": 3.0898, - "step": 265800 + "learning_rate": 2.527712879654024e-06, + "loss": 3.2515, + "step": 286500 }, { "epoch": 0.95, - "learning_rate": 2.5434497824387563e-06, - "loss": 3.102, - "step": 265900 + "learning_rate": 2.511143145929645e-06, + "loss": 3.2505, + "step": 286600 }, { "epoch": 0.95, - "learning_rate": 2.525602264493077e-06, - "loss": 3.1032, - "step": 266000 + "learning_rate": 2.494573412205266e-06, + "loss": 3.2454, + "step": 286700 }, { "epoch": 0.95, - "learning_rate": 2.507754746547398e-06, - "loss": 3.1042, - "step": 266100 + "learning_rate": 2.478003678480887e-06, + "loss": 3.2544, + "step": 286800 }, { "epoch": 0.95, - "learning_rate": 2.4899072286017183e-06, - "loss": 3.1097, - "step": 266200 + "learning_rate": 2.4614339447565077e-06, + "loss": 3.2502, + "step": 286900 }, { "epoch": 0.95, - "learning_rate": 2.472059710656039e-06, - "loss": 3.0939, - "step": 266300 + "learning_rate": 2.4448642110321288e-06, + "loss": 3.2385, + "step": 287000 }, { "epoch": 0.95, - "learning_rate": 2.45421219271036e-06, - "loss": 3.1096, - "step": 266400 + "learning_rate": 2.42829447730775e-06, + "loss": 3.2442, + "step": 287100 }, { "epoch": 0.95, - "learning_rate": 2.4363646747646806e-06, - "loss": 3.0964, - "step": 266500 + "learning_rate": 2.411724743583371e-06, + "loss": 3.2561, + "step": 287200 }, { "epoch": 0.95, - "learning_rate": 2.418517156819001e-06, - "loss": 3.1002, - "step": 266600 + "learning_rate": 2.395155009858992e-06, + "loss": 3.2454, + "step": 287300 }, { "epoch": 0.95, - "learning_rate": 2.4006696388733222e-06, - "loss": 3.0957, - "step": 266700 + "learning_rate": 2.3785852761346125e-06, + "loss": 3.2519, + "step": 287400 }, { "epoch": 0.95, - "learning_rate": 2.3828221209276426e-06, - "loss": 3.1137, - "step": 266800 + "learning_rate": 2.3620155424102336e-06, + "loss": 3.2516, + "step": 287500 }, { "epoch": 0.95, - "learning_rate": 2.3649746029819634e-06, - "loss": 3.093, - "step": 266900 + "learning_rate": 2.3454458086858546e-06, + "loss": 3.2579, + "step": 287600 }, { "epoch": 0.95, - "learning_rate": 2.347127085036284e-06, - "loss": 3.106, - "step": 267000 + "learning_rate": 2.3288760749614757e-06, + "loss": 3.2401, + "step": 287700 }, { "epoch": 0.95, - "learning_rate": 2.329279567090605e-06, - "loss": 3.0971, - "step": 267100 + "learning_rate": 2.3123063412370963e-06, + "loss": 3.255, + "step": 287800 }, { "epoch": 0.95, - "learning_rate": 2.3114320491449253e-06, - "loss": 3.1027, - "step": 267200 + "learning_rate": 2.2957366075127173e-06, + "loss": 3.2459, + "step": 287900 }, { "epoch": 0.95, - "learning_rate": 2.293584531199246e-06, - "loss": 3.0993, - "step": 267300 + "learning_rate": 2.2791668737883384e-06, + "loss": 3.2576, + "step": 288000 }, { "epoch": 0.95, - "learning_rate": 2.275737013253567e-06, - "loss": 3.0847, - "step": 267400 + "learning_rate": 2.2625971400639594e-06, + "loss": 3.2478, + "step": 288100 }, { - "epoch": 0.95, - "learning_rate": 2.2578894953078877e-06, - "loss": 3.0989, - "step": 267500 + "epoch": 0.96, + "learning_rate": 2.2460274063395804e-06, + "loss": 3.2433, + "step": 288200 }, { "epoch": 0.96, - "learning_rate": 2.240041977362208e-06, - "loss": 3.1027, - "step": 267600 + "learning_rate": 2.229457672615201e-06, + "loss": 3.2443, + "step": 288300 }, { "epoch": 0.96, - "learning_rate": 2.2221944594165293e-06, - "loss": 3.1041, - "step": 267700 + "learning_rate": 2.212887938890822e-06, + "loss": 3.2512, + "step": 288400 }, { "epoch": 0.96, - "learning_rate": 2.2043469414708497e-06, - "loss": 3.1089, - "step": 267800 + "learning_rate": 2.196318205166443e-06, + "loss": 3.2514, + "step": 288500 }, { "epoch": 0.96, - "learning_rate": 2.1864994235251705e-06, - "loss": 3.103, - "step": 267900 + "learning_rate": 2.179748471442064e-06, + "loss": 3.2551, + "step": 288600 }, { "epoch": 0.96, - "learning_rate": 2.1686519055794912e-06, - "loss": 3.1051, - "step": 268000 + "learning_rate": 2.163178737717685e-06, + "loss": 3.2427, + "step": 288700 }, { "epoch": 0.96, - "learning_rate": 2.150804387633812e-06, - "loss": 3.0911, - "step": 268100 + "learning_rate": 2.146609003993306e-06, + "loss": 3.2456, + "step": 288800 }, { "epoch": 0.96, - "learning_rate": 2.1329568696881324e-06, - "loss": 3.1115, - "step": 268200 + "learning_rate": 2.130039270268927e-06, + "loss": 3.229, + "step": 288900 }, { "epoch": 0.96, - "learning_rate": 2.115109351742453e-06, - "loss": 3.0927, - "step": 268300 + "learning_rate": 2.113469536544548e-06, + "loss": 3.2413, + "step": 289000 }, { "epoch": 0.96, - "learning_rate": 2.097261833796774e-06, - "loss": 3.1047, - "step": 268400 + "learning_rate": 2.0968998028201686e-06, + "loss": 3.244, + "step": 289100 }, { "epoch": 0.96, - "learning_rate": 2.0794143158510948e-06, - "loss": 3.1049, - "step": 268500 + "learning_rate": 2.0803300690957896e-06, + "loss": 3.2637, + "step": 289200 }, { "epoch": 0.96, - "learning_rate": 2.0615667979054156e-06, - "loss": 3.1014, - "step": 268600 + "learning_rate": 2.0637603353714107e-06, + "loss": 3.2523, + "step": 289300 }, { "epoch": 0.96, - "learning_rate": 2.043719279959736e-06, - "loss": 3.0993, - "step": 268700 + "learning_rate": 2.0471906016470317e-06, + "loss": 3.2443, + "step": 289400 }, { "epoch": 0.96, - "learning_rate": 2.0258717620140567e-06, - "loss": 3.0981, - "step": 268800 + "learning_rate": 2.0306208679226527e-06, + "loss": 3.2409, + "step": 289500 }, { "epoch": 0.96, - "learning_rate": 2.0080242440683775e-06, - "loss": 3.0993, - "step": 268900 + "learning_rate": 2.0140511341982734e-06, + "loss": 3.2374, + "step": 289600 }, { "epoch": 0.96, - "learning_rate": 1.9901767261226983e-06, - "loss": 3.1024, - "step": 269000 + "learning_rate": 1.9974814004738944e-06, + "loss": 3.255, + "step": 289700 }, { "epoch": 0.96, - "learning_rate": 1.9723292081770187e-06, - "loss": 3.1043, - "step": 269100 + "learning_rate": 1.9809116667495154e-06, + "loss": 3.2492, + "step": 289800 }, { "epoch": 0.96, - "learning_rate": 1.9544816902313395e-06, - "loss": 3.1003, - "step": 269200 + "learning_rate": 1.9643419330251365e-06, + "loss": 3.245, + "step": 289900 }, { "epoch": 0.96, - "learning_rate": 1.9366341722856603e-06, - "loss": 3.1079, - "step": 269300 + "learning_rate": 1.947772199300757e-06, + "loss": 3.2437, + "step": 290000 }, { "epoch": 0.96, - "learning_rate": 1.918786654339981e-06, - "loss": 3.0969, - "step": 269400 + "learning_rate": 1.931202465576378e-06, + "loss": 3.2524, + "step": 290100 }, { "epoch": 0.96, - "learning_rate": 1.9009391363943016e-06, - "loss": 3.1093, - "step": 269500 + "learning_rate": 1.914632731851999e-06, + "loss": 3.237, + "step": 290200 }, { "epoch": 0.96, - "learning_rate": 1.8830916184486226e-06, - "loss": 3.1003, - "step": 269600 + "learning_rate": 1.8980629981276202e-06, + "loss": 3.2353, + "step": 290300 }, { "epoch": 0.96, - "learning_rate": 1.8652441005029432e-06, - "loss": 3.1105, - "step": 269700 + "learning_rate": 1.881493264403241e-06, + "loss": 3.24, + "step": 290400 }, { "epoch": 0.96, - "learning_rate": 1.8473965825572638e-06, - "loss": 3.104, - "step": 269800 + "learning_rate": 1.864923530678862e-06, + "loss": 3.2448, + "step": 290500 }, { "epoch": 0.96, - "learning_rate": 1.8295490646115846e-06, - "loss": 3.0966, - "step": 269900 + "learning_rate": 1.8483537969544832e-06, + "loss": 3.2502, + "step": 290600 }, { "epoch": 0.96, - "learning_rate": 1.8117015466659054e-06, - "loss": 3.0993, - "step": 270000 + "learning_rate": 1.831784063230104e-06, + "loss": 3.2392, + "step": 290700 }, { "epoch": 0.96, - "learning_rate": 1.793854028720226e-06, - "loss": 3.0981, - "step": 270100 + "learning_rate": 1.815214329505725e-06, + "loss": 3.2376, + "step": 290800 }, { "epoch": 0.96, - "learning_rate": 1.7760065107745468e-06, - "loss": 3.1024, - "step": 270200 + "learning_rate": 1.7986445957813459e-06, + "loss": 3.2425, + "step": 290900 }, { "epoch": 0.96, - "learning_rate": 1.7581589928288673e-06, - "loss": 3.11, - "step": 270300 + "learning_rate": 1.7820748620569667e-06, + "loss": 3.2426, + "step": 291000 + }, + { + "epoch": 0.96, + "learning_rate": 1.765505128332588e-06, + "loss": 3.2412, + "step": 291100 }, { "epoch": 0.97, - "learning_rate": 1.740311474883188e-06, - "loss": 3.0886, - "step": 270400 + "learning_rate": 1.7489353946082088e-06, + "loss": 3.2503, + "step": 291200 }, { "epoch": 0.97, - "learning_rate": 1.722463956937509e-06, - "loss": 3.0924, - "step": 270500 + "learning_rate": 1.7323656608838296e-06, + "loss": 3.2537, + "step": 291300 }, { "epoch": 0.97, - "learning_rate": 1.7046164389918295e-06, - "loss": 3.1038, - "step": 270600 + "learning_rate": 1.7157959271594505e-06, + "loss": 3.2248, + "step": 291400 }, { "epoch": 0.97, - "learning_rate": 1.68676892104615e-06, - "loss": 3.0997, - "step": 270700 + "learning_rate": 1.6992261934350717e-06, + "loss": 3.241, + "step": 291500 }, { "epoch": 0.97, - "learning_rate": 1.6689214031004707e-06, - "loss": 3.0954, - "step": 270800 + "learning_rate": 1.6826564597106925e-06, + "loss": 3.2459, + "step": 291600 }, { "epoch": 0.97, - "learning_rate": 1.6510738851547917e-06, - "loss": 3.1086, - "step": 270900 + "learning_rate": 1.6660867259863134e-06, + "loss": 3.2414, + "step": 291700 }, { "epoch": 0.97, - "learning_rate": 1.6332263672091122e-06, - "loss": 3.106, - "step": 271000 + "learning_rate": 1.6495169922619344e-06, + "loss": 3.2381, + "step": 291800 }, { "epoch": 0.97, - "learning_rate": 1.6153788492634328e-06, - "loss": 3.0972, - "step": 271100 + "learning_rate": 1.6329472585375555e-06, + "loss": 3.2293, + "step": 291900 }, { "epoch": 0.97, - "learning_rate": 1.5975313313177538e-06, - "loss": 3.1045, - "step": 271200 + "learning_rate": 1.6163775248131765e-06, + "loss": 3.2505, + "step": 292000 }, { "epoch": 0.97, - "learning_rate": 1.5796838133720744e-06, - "loss": 3.0973, - "step": 271300 + "learning_rate": 1.5998077910887973e-06, + "loss": 3.2451, + "step": 292100 }, { "epoch": 0.97, - "learning_rate": 1.5618362954263952e-06, - "loss": 3.0925, - "step": 271400 + "learning_rate": 1.5832380573644182e-06, + "loss": 3.2446, + "step": 292200 }, { "epoch": 0.97, - "learning_rate": 1.5439887774807158e-06, - "loss": 3.0984, - "step": 271500 + "learning_rate": 1.566668323640039e-06, + "loss": 3.2557, + "step": 292300 }, { "epoch": 0.97, - "learning_rate": 1.5261412595350366e-06, - "loss": 3.1018, - "step": 271600 + "learning_rate": 1.55009858991566e-06, + "loss": 3.2457, + "step": 292400 }, { "epoch": 0.97, - "learning_rate": 1.5082937415893574e-06, - "loss": 3.1086, - "step": 271700 + "learning_rate": 1.533528856191281e-06, + "loss": 3.2484, + "step": 292500 }, { "epoch": 0.97, - "learning_rate": 1.490446223643678e-06, - "loss": 3.1012, - "step": 271800 + "learning_rate": 1.516959122466902e-06, + "loss": 3.2435, + "step": 292600 }, { "epoch": 0.97, - "learning_rate": 1.4725987056979987e-06, - "loss": 3.1042, - "step": 271900 + "learning_rate": 1.500389388742523e-06, + "loss": 3.2548, + "step": 292700 }, { "epoch": 0.97, - "learning_rate": 1.4547511877523193e-06, - "loss": 3.0976, - "step": 272000 + "learning_rate": 1.483819655018144e-06, + "loss": 3.2529, + "step": 292800 }, { "epoch": 0.97, - "learning_rate": 1.43690366980664e-06, - "loss": 3.0966, - "step": 272100 + "learning_rate": 1.467249921293765e-06, + "loss": 3.2526, + "step": 292900 }, { "epoch": 0.97, - "learning_rate": 1.4190561518609609e-06, - "loss": 3.1005, - "step": 272200 + "learning_rate": 1.4506801875693859e-06, + "loss": 3.2568, + "step": 293000 }, { "epoch": 0.97, - "learning_rate": 1.4012086339152815e-06, - "loss": 3.1006, - "step": 272300 + "learning_rate": 1.434110453845007e-06, + "loss": 3.2403, + "step": 293100 }, { "epoch": 0.97, - "learning_rate": 1.3833611159696023e-06, - "loss": 3.0919, - "step": 272400 + "learning_rate": 1.4175407201206278e-06, + "loss": 3.2485, + "step": 293200 }, { "epoch": 0.97, - "learning_rate": 1.365513598023923e-06, - "loss": 3.1069, - "step": 272500 + "learning_rate": 1.4009709863962486e-06, + "loss": 3.2338, + "step": 293300 }, { "epoch": 0.97, - "learning_rate": 1.3476660800782436e-06, - "loss": 3.0896, - "step": 272600 + "learning_rate": 1.3844012526718696e-06, + "loss": 3.2501, + "step": 293400 }, { "epoch": 0.97, - "learning_rate": 1.3298185621325644e-06, - "loss": 3.1053, - "step": 272700 + "learning_rate": 1.3678315189474905e-06, + "loss": 3.237, + "step": 293500 }, { "epoch": 0.97, - "learning_rate": 1.311971044186885e-06, - "loss": 3.1088, - "step": 272800 + "learning_rate": 1.3512617852231115e-06, + "loss": 3.2555, + "step": 293600 }, { "epoch": 0.97, - "learning_rate": 1.2941235262412056e-06, - "loss": 3.0929, - "step": 272900 + "learning_rate": 1.3346920514987323e-06, + "loss": 3.2482, + "step": 293700 }, { "epoch": 0.97, - "learning_rate": 1.2762760082955264e-06, - "loss": 3.0994, - "step": 273000 + "learning_rate": 1.3181223177743534e-06, + "loss": 3.2429, + "step": 293800 }, { "epoch": 0.97, - "learning_rate": 1.258428490349847e-06, - "loss": 3.0917, - "step": 273100 + "learning_rate": 1.3015525840499744e-06, + "loss": 3.2479, + "step": 293900 + }, + { + "epoch": 0.97, + "learning_rate": 1.2849828503255955e-06, + "loss": 3.2473, + "step": 294000 + }, + { + "epoch": 0.97, + "learning_rate": 1.2684131166012163e-06, + "loss": 3.2655, + "step": 294100 + }, + { + "epoch": 0.97, + "learning_rate": 1.2518433828768373e-06, + "loss": 3.235, + "step": 294200 }, { "epoch": 0.98, - "learning_rate": 1.2405809724041677e-06, - "loss": 3.1016, - "step": 273200 + "learning_rate": 1.2352736491524582e-06, + "loss": 3.2538, + "step": 294300 }, { "epoch": 0.98, - "learning_rate": 1.2227334544584885e-06, - "loss": 3.1068, - "step": 273300 + "learning_rate": 1.2187039154280792e-06, + "loss": 3.2426, + "step": 294400 }, { "epoch": 0.98, - "learning_rate": 1.2048859365128091e-06, - "loss": 3.0914, - "step": 273400 + "learning_rate": 1.2021341817037e-06, + "loss": 3.243, + "step": 294500 }, { "epoch": 0.98, - "learning_rate": 1.18703841856713e-06, - "loss": 3.1014, - "step": 273500 + "learning_rate": 1.1855644479793209e-06, + "loss": 3.2503, + "step": 294600 }, { "epoch": 0.98, - "learning_rate": 1.1691909006214505e-06, - "loss": 3.0983, - "step": 273600 + "learning_rate": 1.168994714254942e-06, + "loss": 3.2571, + "step": 294700 }, { "epoch": 0.98, - "learning_rate": 1.1513433826757713e-06, - "loss": 3.0964, - "step": 273700 + "learning_rate": 1.1524249805305628e-06, + "loss": 3.2534, + "step": 294800 }, { "epoch": 0.98, - "learning_rate": 1.133495864730092e-06, - "loss": 3.0984, - "step": 273800 + "learning_rate": 1.1358552468061838e-06, + "loss": 3.2477, + "step": 294900 }, { "epoch": 0.98, - "learning_rate": 1.1156483467844126e-06, - "loss": 3.0974, - "step": 273900 + "learning_rate": 1.1192855130818048e-06, + "loss": 3.2456, + "step": 295000 }, { "epoch": 0.98, - "learning_rate": 1.0978008288387334e-06, - "loss": 3.1021, - "step": 274000 + "learning_rate": 1.1027157793574259e-06, + "loss": 3.2562, + "step": 295100 }, { "epoch": 0.98, - "learning_rate": 1.0799533108930542e-06, - "loss": 3.0897, - "step": 274100 + "learning_rate": 1.0861460456330467e-06, + "loss": 3.2389, + "step": 295200 }, { "epoch": 0.98, - "learning_rate": 1.0621057929473748e-06, - "loss": 3.107, - "step": 274200 + "learning_rate": 1.0695763119086678e-06, + "loss": 3.2564, + "step": 295300 }, { "epoch": 0.98, - "learning_rate": 1.0442582750016956e-06, - "loss": 3.1011, - "step": 274300 + "learning_rate": 1.0530065781842886e-06, + "loss": 3.2599, + "step": 295400 }, { "epoch": 0.98, - "learning_rate": 1.0264107570560162e-06, - "loss": 3.0993, - "step": 274400 + "learning_rate": 1.0364368444599096e-06, + "loss": 3.2318, + "step": 295500 }, { "epoch": 0.98, - "learning_rate": 1.008563239110337e-06, - "loss": 3.1064, - "step": 274500 + "learning_rate": 1.0198671107355305e-06, + "loss": 3.247, + "step": 295600 }, { "epoch": 0.98, - "learning_rate": 9.907157211646578e-07, - "loss": 3.0878, - "step": 274600 + "learning_rate": 1.0032973770111515e-06, + "loss": 3.252, + "step": 295700 }, { "epoch": 0.98, - "learning_rate": 9.728682032189783e-07, - "loss": 3.0917, - "step": 274700 + "learning_rate": 9.867276432867723e-07, + "loss": 3.2537, + "step": 295800 }, { "epoch": 0.98, - "learning_rate": 9.550206852732991e-07, - "loss": 3.1037, - "step": 274800 + "learning_rate": 9.701579095623934e-07, + "loss": 3.2519, + "step": 295900 }, { "epoch": 0.98, - "learning_rate": 9.371731673276198e-07, - "loss": 3.1, - "step": 274900 + "learning_rate": 9.535881758380143e-07, + "loss": 3.2559, + "step": 296000 }, { "epoch": 0.98, - "learning_rate": 9.193256493819405e-07, - "loss": 3.0929, - "step": 275000 + "learning_rate": 9.370184421136352e-07, + "loss": 3.2399, + "step": 296100 }, { "epoch": 0.98, - "learning_rate": 9.014781314362612e-07, - "loss": 3.0918, - "step": 275100 + "learning_rate": 9.204487083892562e-07, + "loss": 3.2606, + "step": 296200 }, { "epoch": 0.98, - "learning_rate": 8.836306134905818e-07, - "loss": 3.0877, - "step": 275200 + "learning_rate": 9.038789746648771e-07, + "loss": 3.2415, + "step": 296300 }, { "epoch": 0.98, - "learning_rate": 8.657830955449026e-07, - "loss": 3.0932, - "step": 275300 + "learning_rate": 8.873092409404982e-07, + "loss": 3.2532, + "step": 296400 }, { "epoch": 0.98, - "learning_rate": 8.479355775992234e-07, - "loss": 3.0964, - "step": 275400 + "learning_rate": 8.70739507216119e-07, + "loss": 3.2429, + "step": 296500 }, { "epoch": 0.98, - "learning_rate": 8.300880596535439e-07, - "loss": 3.0975, - "step": 275500 + "learning_rate": 8.541697734917401e-07, + "loss": 3.2389, + "step": 296600 }, { "epoch": 0.98, - "learning_rate": 8.122405417078647e-07, - "loss": 3.0968, - "step": 275600 + "learning_rate": 8.37600039767361e-07, + "loss": 3.2571, + "step": 296700 }, { "epoch": 0.98, - "learning_rate": 7.943930237621855e-07, - "loss": 3.0987, - "step": 275700 + "learning_rate": 8.21030306042982e-07, + "loss": 3.2467, + "step": 296800 }, { "epoch": 0.98, - "learning_rate": 7.765455058165062e-07, - "loss": 3.0936, - "step": 275800 + "learning_rate": 8.044605723186029e-07, + "loss": 3.2457, + "step": 296900 }, { "epoch": 0.98, - "learning_rate": 7.586979878708269e-07, - "loss": 3.1055, - "step": 275900 + "learning_rate": 7.878908385942239e-07, + "loss": 3.2513, + "step": 297000 + }, + { + "epoch": 0.98, + "learning_rate": 7.713211048698447e-07, + "loss": 3.2431, + "step": 297100 + }, + { + "epoch": 0.98, + "learning_rate": 7.547513711454657e-07, + "loss": 3.2323, + "step": 297200 }, { "epoch": 0.99, - "learning_rate": 7.408504699251476e-07, - "loss": 3.0948, - "step": 276000 + "learning_rate": 7.381816374210867e-07, + "loss": 3.2588, + "step": 297300 }, { "epoch": 0.99, - "learning_rate": 7.230029519794683e-07, - "loss": 3.1012, - "step": 276100 + "learning_rate": 7.216119036967077e-07, + "loss": 3.2404, + "step": 297400 }, { "epoch": 0.99, - "learning_rate": 7.05155434033789e-07, - "loss": 3.0992, - "step": 276200 + "learning_rate": 7.050421699723286e-07, + "loss": 3.2661, + "step": 297500 }, { "epoch": 0.99, - "learning_rate": 6.873079160881096e-07, - "loss": 3.1026, - "step": 276300 + "learning_rate": 6.884724362479495e-07, + "loss": 3.2386, + "step": 297600 }, { "epoch": 0.99, - "learning_rate": 6.694603981424303e-07, - "loss": 3.098, - "step": 276400 + "learning_rate": 6.719027025235705e-07, + "loss": 3.2304, + "step": 297700 }, { "epoch": 0.99, - "learning_rate": 6.51612880196751e-07, - "loss": 3.0975, - "step": 276500 + "learning_rate": 6.553329687991914e-07, + "loss": 3.2572, + "step": 297800 }, { "epoch": 0.99, - "learning_rate": 6.337653622510718e-07, - "loss": 3.0945, - "step": 276600 + "learning_rate": 6.387632350748124e-07, + "loss": 3.2481, + "step": 297900 }, { "epoch": 0.99, - "learning_rate": 6.159178443053925e-07, - "loss": 3.1005, - "step": 276700 + "learning_rate": 6.221935013504333e-07, + "loss": 3.241, + "step": 298000 }, { "epoch": 0.99, - "learning_rate": 5.980703263597132e-07, - "loss": 3.1036, - "step": 276800 + "learning_rate": 6.056237676260542e-07, + "loss": 3.2435, + "step": 298100 }, { "epoch": 0.99, - "learning_rate": 5.802228084140338e-07, - "loss": 3.0928, - "step": 276900 + "learning_rate": 5.890540339016752e-07, + "loss": 3.2394, + "step": 298200 }, { "epoch": 0.99, - "learning_rate": 5.623752904683546e-07, - "loss": 3.1021, - "step": 277000 + "learning_rate": 5.724843001772962e-07, + "loss": 3.2528, + "step": 298300 }, { "epoch": 0.99, - "learning_rate": 5.445277725226753e-07, - "loss": 3.1014, - "step": 277100 + "learning_rate": 5.559145664529171e-07, + "loss": 3.2504, + "step": 298400 }, { "epoch": 0.99, - "learning_rate": 5.26680254576996e-07, - "loss": 3.0928, - "step": 277200 + "learning_rate": 5.393448327285381e-07, + "loss": 3.242, + "step": 298500 }, { "epoch": 0.99, - "learning_rate": 5.088327366313167e-07, - "loss": 3.0892, - "step": 277300 + "learning_rate": 5.22775099004159e-07, + "loss": 3.2582, + "step": 298600 }, { "epoch": 0.99, - "learning_rate": 4.909852186856375e-07, - "loss": 3.1042, - "step": 277400 + "learning_rate": 5.0620536527978e-07, + "loss": 3.2659, + "step": 298700 }, { "epoch": 0.99, - "learning_rate": 4.731377007399581e-07, - "loss": 3.0971, - "step": 277500 + "learning_rate": 4.89635631555401e-07, + "loss": 3.2437, + "step": 298800 }, { "epoch": 0.99, - "learning_rate": 4.552901827942788e-07, - "loss": 3.1077, - "step": 277600 + "learning_rate": 4.730658978310219e-07, + "loss": 3.2421, + "step": 298900 }, { "epoch": 0.99, - "learning_rate": 4.374426648485995e-07, - "loss": 3.1002, - "step": 277700 + "learning_rate": 4.564961641066429e-07, + "loss": 3.2466, + "step": 299000 }, { "epoch": 0.99, - "learning_rate": 4.195951469029203e-07, - "loss": 3.0958, - "step": 277800 + "learning_rate": 4.399264303822637e-07, + "loss": 3.2463, + "step": 299100 }, { "epoch": 0.99, - "learning_rate": 4.0174762895724097e-07, - "loss": 3.1002, - "step": 277900 + "learning_rate": 4.233566966578847e-07, + "loss": 3.2505, + "step": 299200 }, { "epoch": 0.99, - "learning_rate": 3.8390011101156165e-07, - "loss": 3.1059, - "step": 278000 + "learning_rate": 4.0678696293350564e-07, + "loss": 3.2535, + "step": 299300 }, { "epoch": 0.99, - "learning_rate": 3.6605259306588234e-07, - "loss": 3.1042, - "step": 278100 + "learning_rate": 3.9021722920912663e-07, + "loss": 3.2542, + "step": 299400 }, { "epoch": 0.99, - "learning_rate": 3.48205075120203e-07, - "loss": 3.0953, - "step": 278200 + "learning_rate": 3.7364749548474757e-07, + "loss": 3.244, + "step": 299500 }, { "epoch": 0.99, - "learning_rate": 3.3035755717452376e-07, - "loss": 3.1002, - "step": 278300 + "learning_rate": 3.570777617603685e-07, + "loss": 3.2536, + "step": 299600 }, { "epoch": 0.99, - "learning_rate": 3.1251003922884445e-07, - "loss": 3.1014, - "step": 278400 + "learning_rate": 3.405080280359895e-07, + "loss": 3.2654, + "step": 299700 }, { "epoch": 0.99, - "learning_rate": 2.946625212831652e-07, - "loss": 3.0988, - "step": 278500 + "learning_rate": 3.2393829431161043e-07, + "loss": 3.2592, + "step": 299800 }, { "epoch": 0.99, - "learning_rate": 2.7681500333748587e-07, - "loss": 3.1071, - "step": 278600 + "learning_rate": 3.0736856058723137e-07, + "loss": 3.2447, + "step": 299900 }, { "epoch": 0.99, - "learning_rate": 2.589674853918066e-07, - "loss": 3.1024, - "step": 278700 + "learning_rate": 2.9079882686285236e-07, + "loss": 3.245, + "step": 300000 + }, + { + "epoch": 0.99, + "learning_rate": 2.7422909313847324e-07, + "loss": 3.2474, + "step": 300100 + }, + { + "epoch": 0.99, + "learning_rate": 2.5765935941409423e-07, + "loss": 3.2475, + "step": 300200 }, { "epoch": 1.0, - "learning_rate": 2.411199674461273e-07, - "loss": 3.098, - "step": 278800 + "learning_rate": 2.4108962568971517e-07, + "loss": 3.2604, + "step": 300300 }, { "epoch": 1.0, - "learning_rate": 2.23272449500448e-07, - "loss": 3.0921, - "step": 278900 + "learning_rate": 2.2451989196533614e-07, + "loss": 3.2533, + "step": 300400 }, { "epoch": 1.0, - "learning_rate": 2.0542493155476867e-07, - "loss": 3.0935, - "step": 279000 + "learning_rate": 2.0795015824095707e-07, + "loss": 3.2473, + "step": 300500 }, { "epoch": 1.0, - "learning_rate": 1.8757741360908938e-07, - "loss": 3.0989, - "step": 279100 + "learning_rate": 1.91380424516578e-07, + "loss": 3.2491, + "step": 300600 }, { "epoch": 1.0, - "learning_rate": 1.697298956634101e-07, - "loss": 3.0934, - "step": 279200 + "learning_rate": 1.7481069079219898e-07, + "loss": 3.255, + "step": 300700 }, { "epoch": 1.0, - "learning_rate": 1.518823777177308e-07, - "loss": 3.0939, - "step": 279300 + "learning_rate": 1.5824095706781994e-07, + "loss": 3.2404, + "step": 300800 }, { "epoch": 1.0, - "learning_rate": 1.340348597720515e-07, - "loss": 3.0998, - "step": 279400 + "learning_rate": 1.4167122334344088e-07, + "loss": 3.2458, + "step": 300900 }, { "epoch": 1.0, - "learning_rate": 1.1618734182637223e-07, - "loss": 3.0921, - "step": 279500 + "learning_rate": 1.2510148961906181e-07, + "loss": 3.2493, + "step": 301000 }, { "epoch": 1.0, - "learning_rate": 9.833982388069292e-08, - "loss": 3.0903, - "step": 279600 + "learning_rate": 1.0853175589468278e-07, + "loss": 3.249, + "step": 301100 }, { "epoch": 1.0, - "learning_rate": 8.049230593501362e-08, - "loss": 3.0992, - "step": 279700 + "learning_rate": 9.196202217030373e-08, + "loss": 3.2519, + "step": 301200 }, { "epoch": 1.0, - "learning_rate": 6.264478798933432e-08, - "loss": 3.1015, - "step": 279800 + "learning_rate": 7.539228844592467e-08, + "loss": 3.2445, + "step": 301300 }, { "epoch": 1.0, - "learning_rate": 4.4797270043655027e-08, - "loss": 3.105, - "step": 279900 + "learning_rate": 5.882255472154563e-08, + "loss": 3.2429, + "step": 301400 }, { "epoch": 1.0, - "learning_rate": 2.6949752097975735e-08, - "loss": 3.1008, - "step": 280000 + "learning_rate": 4.2252820997166576e-08, + "loss": 3.2521, + "step": 301500 } ], - "max_steps": 280151, + "max_steps": 301755, "num_train_epochs": 1, - "total_flos": 2.39216457940992e+18, + "total_flos": 2.575848645328896e+18, "trial_name": null, "trial_params": null }