{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 2.0, "eval_steps": 500, "global_step": 6502, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0030759766225776685, "grad_norm": 4.456279493923824, "learning_rate": 1.3803680981595093e-06, "loss": 0.7434, "step": 10 }, { "epoch": 0.006151953245155337, "grad_norm": 2.416076488507601, "learning_rate": 2.914110429447853e-06, "loss": 0.7131, "step": 20 }, { "epoch": 0.009227929867733005, "grad_norm": 0.8211134827544788, "learning_rate": 4.447852760736196e-06, "loss": 0.6716, "step": 30 }, { "epoch": 0.012303906490310674, "grad_norm": 0.5272491886841408, "learning_rate": 5.98159509202454e-06, "loss": 0.6432, "step": 40 }, { "epoch": 0.015379883112888341, "grad_norm": 0.4011191606652496, "learning_rate": 7.5153374233128836e-06, "loss": 0.626, "step": 50 }, { "epoch": 0.01845585973546601, "grad_norm": 0.30365747114416397, "learning_rate": 9.049079754601228e-06, "loss": 0.5971, "step": 60 }, { "epoch": 0.02153183635804368, "grad_norm": 0.3176596292426437, "learning_rate": 1.0582822085889571e-05, "loss": 0.5819, "step": 70 }, { "epoch": 0.024607812980621348, "grad_norm": 0.2873472746558865, "learning_rate": 1.2116564417177914e-05, "loss": 0.5788, "step": 80 }, { "epoch": 0.027683789603199015, "grad_norm": 0.30839629795913953, "learning_rate": 1.3650306748466258e-05, "loss": 0.5715, "step": 90 }, { "epoch": 0.030759766225776683, "grad_norm": 0.320988415113024, "learning_rate": 1.5184049079754603e-05, "loss": 0.566, "step": 100 }, { "epoch": 0.033835742848354354, "grad_norm": 0.31950095346844304, "learning_rate": 1.6717791411042948e-05, "loss": 0.5623, "step": 110 }, { "epoch": 0.03691171947093202, "grad_norm": 0.32079298223978464, "learning_rate": 1.825153374233129e-05, "loss": 0.5544, "step": 120 }, { "epoch": 0.03998769609350969, "grad_norm": 0.3873719211050776, "learning_rate": 1.978527607361963e-05, "loss": 0.5431, "step": 130 }, { "epoch": 0.04306367271608736, "grad_norm": 0.3972905501633235, "learning_rate": 2.1319018404907976e-05, "loss": 0.5389, "step": 140 }, { "epoch": 0.046139649338665024, "grad_norm": 0.3459282728250342, "learning_rate": 2.285276073619632e-05, "loss": 0.5442, "step": 150 }, { "epoch": 0.049215625961242696, "grad_norm": 0.3487860857948364, "learning_rate": 2.4386503067484666e-05, "loss": 0.5368, "step": 160 }, { "epoch": 0.05229160258382036, "grad_norm": 0.42840257622520156, "learning_rate": 2.5920245398773008e-05, "loss": 0.5293, "step": 170 }, { "epoch": 0.05536757920639803, "grad_norm": 0.49888399745420403, "learning_rate": 2.7453987730061353e-05, "loss": 0.5293, "step": 180 }, { "epoch": 0.0584435558289757, "grad_norm": 0.3839054307854075, "learning_rate": 2.8987730061349694e-05, "loss": 0.5277, "step": 190 }, { "epoch": 0.061519532451553366, "grad_norm": 0.4391073306825061, "learning_rate": 3.052147239263804e-05, "loss": 0.523, "step": 200 }, { "epoch": 0.06459550907413103, "grad_norm": 0.5230067156593188, "learning_rate": 3.205521472392638e-05, "loss": 0.5275, "step": 210 }, { "epoch": 0.06767148569670871, "grad_norm": 0.5104549933545504, "learning_rate": 3.3588957055214726e-05, "loss": 0.5221, "step": 220 }, { "epoch": 0.07074746231928637, "grad_norm": 0.5696593275922155, "learning_rate": 3.512269938650307e-05, "loss": 0.5185, "step": 230 }, { "epoch": 0.07382343894186404, "grad_norm": 0.5802329288728868, "learning_rate": 3.665644171779141e-05, "loss": 0.5176, "step": 240 }, { "epoch": 0.07689941556444171, "grad_norm": 0.5084361857850729, "learning_rate": 3.819018404907976e-05, "loss": 0.5137, "step": 250 }, { "epoch": 0.07997539218701938, "grad_norm": 0.5532148392799192, "learning_rate": 3.97239263803681e-05, "loss": 0.5121, "step": 260 }, { "epoch": 0.08305136880959704, "grad_norm": 0.3766193235656793, "learning_rate": 4.1257668711656444e-05, "loss": 0.5021, "step": 270 }, { "epoch": 0.08612734543217472, "grad_norm": 0.4763487735219595, "learning_rate": 4.279141104294479e-05, "loss": 0.5063, "step": 280 }, { "epoch": 0.08920332205475238, "grad_norm": 0.6030371460342505, "learning_rate": 4.432515337423313e-05, "loss": 0.5076, "step": 290 }, { "epoch": 0.09227929867733005, "grad_norm": 0.3997452584092274, "learning_rate": 4.585889570552148e-05, "loss": 0.5039, "step": 300 }, { "epoch": 0.09535527529990773, "grad_norm": 0.4636322549350364, "learning_rate": 4.739263803680982e-05, "loss": 0.5081, "step": 310 }, { "epoch": 0.09843125192248539, "grad_norm": 0.3942630294234095, "learning_rate": 4.892638036809816e-05, "loss": 0.5025, "step": 320 }, { "epoch": 0.10150722854506306, "grad_norm": 0.42935492172118667, "learning_rate": 4.99999708903081e-05, "loss": 0.5028, "step": 330 }, { "epoch": 0.10458320516764072, "grad_norm": 0.4965510263745532, "learning_rate": 4.99994533865601e-05, "loss": 0.4977, "step": 340 }, { "epoch": 0.1076591817902184, "grad_norm": 0.45192672776433745, "learning_rate": 4.9998289016182865e-05, "loss": 0.4969, "step": 350 }, { "epoch": 0.11073515841279606, "grad_norm": 0.4727041185163972, "learning_rate": 4.999647780930474e-05, "loss": 0.4921, "step": 360 }, { "epoch": 0.11381113503537373, "grad_norm": 0.36703560728579976, "learning_rate": 4.9994019812791134e-05, "loss": 0.4891, "step": 370 }, { "epoch": 0.1168871116579514, "grad_norm": 0.3427029620172874, "learning_rate": 4.999091509024326e-05, "loss": 0.4938, "step": 380 }, { "epoch": 0.11996308828052907, "grad_norm": 0.47530525926202183, "learning_rate": 4.9987163721996546e-05, "loss": 0.4954, "step": 390 }, { "epoch": 0.12303906490310673, "grad_norm": 0.436520722660001, "learning_rate": 4.99827658051185e-05, "loss": 0.4953, "step": 400 }, { "epoch": 0.1261150415256844, "grad_norm": 0.4523738498317269, "learning_rate": 4.9977721453406245e-05, "loss": 0.4877, "step": 410 }, { "epoch": 0.12919101814826206, "grad_norm": 0.45276667035749424, "learning_rate": 4.997203079738354e-05, "loss": 0.4829, "step": 420 }, { "epoch": 0.13226699477083975, "grad_norm": 0.41286487935503263, "learning_rate": 4.9965693984297424e-05, "loss": 0.485, "step": 430 }, { "epoch": 0.13534297139341742, "grad_norm": 0.3636058139394057, "learning_rate": 4.99587111781144e-05, "loss": 0.4893, "step": 440 }, { "epoch": 0.13841894801599508, "grad_norm": 0.3958790976522138, "learning_rate": 4.995108255951619e-05, "loss": 0.4794, "step": 450 }, { "epoch": 0.14149492463857274, "grad_norm": 0.3837356033266357, "learning_rate": 4.994280832589507e-05, "loss": 0.482, "step": 460 }, { "epoch": 0.1445709012611504, "grad_norm": 0.4477528111600026, "learning_rate": 4.993388869134873e-05, "loss": 0.4775, "step": 470 }, { "epoch": 0.14764687788372807, "grad_norm": 0.3635071085737522, "learning_rate": 4.9924323886674796e-05, "loss": 0.4779, "step": 480 }, { "epoch": 0.15072285450630576, "grad_norm": 0.32435188494720874, "learning_rate": 4.991411415936477e-05, "loss": 0.4798, "step": 490 }, { "epoch": 0.15379883112888343, "grad_norm": 0.34687414235299474, "learning_rate": 4.990325977359772e-05, "loss": 0.4854, "step": 500 }, { "epoch": 0.1568748077514611, "grad_norm": 0.3625865783740702, "learning_rate": 4.989176101023339e-05, "loss": 0.4745, "step": 510 }, { "epoch": 0.15995078437403876, "grad_norm": 0.33367134497542317, "learning_rate": 4.987961816680492e-05, "loss": 0.4778, "step": 520 }, { "epoch": 0.16302676099661642, "grad_norm": 0.378633106334601, "learning_rate": 4.9866831557511204e-05, "loss": 0.4739, "step": 530 }, { "epoch": 0.16610273761919409, "grad_norm": 0.35693391609522995, "learning_rate": 4.98534015132087e-05, "loss": 0.4736, "step": 540 }, { "epoch": 0.16917871424177175, "grad_norm": 0.3360440382653444, "learning_rate": 4.983932838140291e-05, "loss": 0.4652, "step": 550 }, { "epoch": 0.17225469086434944, "grad_norm": 0.30092370742829294, "learning_rate": 4.982461252623937e-05, "loss": 0.4755, "step": 560 }, { "epoch": 0.1753306674869271, "grad_norm": 0.3651402485706276, "learning_rate": 4.980925432849423e-05, "loss": 0.4676, "step": 570 }, { "epoch": 0.17840664410950477, "grad_norm": 0.3830570946443233, "learning_rate": 4.97932541855644e-05, "loss": 0.4721, "step": 580 }, { "epoch": 0.18148262073208243, "grad_norm": 0.3277447835828593, "learning_rate": 4.9776612511457264e-05, "loss": 0.4705, "step": 590 }, { "epoch": 0.1845585973546601, "grad_norm": 0.37646315313224266, "learning_rate": 4.9759329736780004e-05, "loss": 0.4698, "step": 600 }, { "epoch": 0.18763457397723776, "grad_norm": 0.29472033068268727, "learning_rate": 4.9741406308728386e-05, "loss": 0.4626, "step": 610 }, { "epoch": 0.19071055059981545, "grad_norm": 0.3694904391704802, "learning_rate": 4.9722842691075275e-05, "loss": 0.4684, "step": 620 }, { "epoch": 0.19378652722239312, "grad_norm": 0.42647271384298224, "learning_rate": 4.9703639364158535e-05, "loss": 0.4623, "step": 630 }, { "epoch": 0.19686250384497078, "grad_norm": 0.3153568813367577, "learning_rate": 4.96837968248687e-05, "loss": 0.4631, "step": 640 }, { "epoch": 0.19993848046754845, "grad_norm": 0.34466804588468647, "learning_rate": 4.966331558663605e-05, "loss": 0.4625, "step": 650 }, { "epoch": 0.2030144570901261, "grad_norm": 0.4110253242377377, "learning_rate": 4.9642196179417366e-05, "loss": 0.467, "step": 660 }, { "epoch": 0.20609043371270377, "grad_norm": 0.3368856296256786, "learning_rate": 4.962043914968218e-05, "loss": 0.4694, "step": 670 }, { "epoch": 0.20916641033528144, "grad_norm": 0.3297569110137202, "learning_rate": 4.9598045060398645e-05, "loss": 0.4549, "step": 680 }, { "epoch": 0.21224238695785913, "grad_norm": 0.3165614010746811, "learning_rate": 4.957501449101901e-05, "loss": 0.459, "step": 690 }, { "epoch": 0.2153183635804368, "grad_norm": 0.3076224912988227, "learning_rate": 4.955134803746457e-05, "loss": 0.457, "step": 700 }, { "epoch": 0.21839434020301446, "grad_norm": 0.3221087105734207, "learning_rate": 4.952704631211029e-05, "loss": 0.4635, "step": 710 }, { "epoch": 0.22147031682559212, "grad_norm": 0.3835223881324763, "learning_rate": 4.950210994376891e-05, "loss": 0.4603, "step": 720 }, { "epoch": 0.2245462934481698, "grad_norm": 0.30222683751046986, "learning_rate": 4.9476539577674715e-05, "loss": 0.4592, "step": 730 }, { "epoch": 0.22762227007074745, "grad_norm": 0.4053535631652962, "learning_rate": 4.945033587546683e-05, "loss": 0.4609, "step": 740 }, { "epoch": 0.23069824669332514, "grad_norm": 0.317144056919946, "learning_rate": 4.9423499515172136e-05, "loss": 0.4592, "step": 750 }, { "epoch": 0.2337742233159028, "grad_norm": 0.3191969207666928, "learning_rate": 4.9396031191187605e-05, "loss": 0.4599, "step": 760 }, { "epoch": 0.23685019993848047, "grad_norm": 0.35086990772034987, "learning_rate": 4.9367931614262496e-05, "loss": 0.4598, "step": 770 }, { "epoch": 0.23992617656105814, "grad_norm": 0.3346873499333926, "learning_rate": 4.9339201511479835e-05, "loss": 0.4662, "step": 780 }, { "epoch": 0.2430021531836358, "grad_norm": 0.44166727923078003, "learning_rate": 4.9309841626237674e-05, "loss": 0.4604, "step": 790 }, { "epoch": 0.24607812980621346, "grad_norm": 0.35655989908587465, "learning_rate": 4.9279852718229815e-05, "loss": 0.4589, "step": 800 }, { "epoch": 0.24915410642879113, "grad_norm": 0.3452321184804803, "learning_rate": 4.924923556342618e-05, "loss": 0.4573, "step": 810 }, { "epoch": 0.2522300830513688, "grad_norm": 0.34320067748833877, "learning_rate": 4.921799095405273e-05, "loss": 0.4629, "step": 820 }, { "epoch": 0.2553060596739465, "grad_norm": 0.3268056251668263, "learning_rate": 4.918611969857093e-05, "loss": 0.4574, "step": 830 }, { "epoch": 0.2583820362965241, "grad_norm": 0.33422877152197156, "learning_rate": 4.915362262165689e-05, "loss": 0.457, "step": 840 }, { "epoch": 0.2614580129191018, "grad_norm": 0.38245766605062903, "learning_rate": 4.912050056417998e-05, "loss": 0.4466, "step": 850 }, { "epoch": 0.2645339895416795, "grad_norm": 0.294069578357511, "learning_rate": 4.9086754383181076e-05, "loss": 0.4538, "step": 860 }, { "epoch": 0.26760996616425714, "grad_norm": 0.3113661216106174, "learning_rate": 4.90523849518504e-05, "loss": 0.4599, "step": 870 }, { "epoch": 0.27068594278683483, "grad_norm": 0.28569622910375203, "learning_rate": 4.901739315950494e-05, "loss": 0.4508, "step": 880 }, { "epoch": 0.27376191940941247, "grad_norm": 0.28632838920035375, "learning_rate": 4.8981779911565394e-05, "loss": 0.4559, "step": 890 }, { "epoch": 0.27683789603199016, "grad_norm": 0.2666014576222754, "learning_rate": 4.8945546129532785e-05, "loss": 0.4479, "step": 900 }, { "epoch": 0.27991387265456785, "grad_norm": 0.3097297115748936, "learning_rate": 4.890869275096457e-05, "loss": 0.4502, "step": 910 }, { "epoch": 0.2829898492771455, "grad_norm": 0.2994685593036194, "learning_rate": 4.887122072945045e-05, "loss": 0.4551, "step": 920 }, { "epoch": 0.2860658258997232, "grad_norm": 0.3344653097505205, "learning_rate": 4.8833131034587625e-05, "loss": 0.4524, "step": 930 }, { "epoch": 0.2891418025223008, "grad_norm": 0.293121047462174, "learning_rate": 4.879442465195575e-05, "loss": 0.4535, "step": 940 }, { "epoch": 0.2922177791448785, "grad_norm": 0.301545042317392, "learning_rate": 4.8755102583091405e-05, "loss": 0.4467, "step": 950 }, { "epoch": 0.29529375576745615, "grad_norm": 0.29167686488498656, "learning_rate": 4.871516584546221e-05, "loss": 0.4546, "step": 960 }, { "epoch": 0.29836973239003384, "grad_norm": 0.32797955439261095, "learning_rate": 4.867461547244048e-05, "loss": 0.4545, "step": 970 }, { "epoch": 0.30144570901261153, "grad_norm": 0.28686666669534316, "learning_rate": 4.8633452513276463e-05, "loss": 0.4482, "step": 980 }, { "epoch": 0.30452168563518917, "grad_norm": 0.31033938263904853, "learning_rate": 4.859167803307124e-05, "loss": 0.4497, "step": 990 }, { "epoch": 0.30759766225776686, "grad_norm": 0.33359714374945487, "learning_rate": 4.854929311274914e-05, "loss": 0.4515, "step": 1000 }, { "epoch": 0.3106736388803445, "grad_norm": 0.299671434949083, "learning_rate": 4.8506298849029764e-05, "loss": 0.4481, "step": 1010 }, { "epoch": 0.3137496155029222, "grad_norm": 0.35635459101655725, "learning_rate": 4.8462696354399597e-05, "loss": 0.4557, "step": 1020 }, { "epoch": 0.3168255921254998, "grad_norm": 0.30791585106018343, "learning_rate": 4.841848675708327e-05, "loss": 0.4448, "step": 1030 }, { "epoch": 0.3199015687480775, "grad_norm": 0.29344528554786065, "learning_rate": 4.837367120101432e-05, "loss": 0.4503, "step": 1040 }, { "epoch": 0.3229775453706552, "grad_norm": 0.31408742652535987, "learning_rate": 4.832825084580562e-05, "loss": 0.4452, "step": 1050 }, { "epoch": 0.32605352199323284, "grad_norm": 0.2729274327700221, "learning_rate": 4.828222686671933e-05, "loss": 0.4506, "step": 1060 }, { "epoch": 0.32912949861581053, "grad_norm": 0.29874742583482333, "learning_rate": 4.823560045463655e-05, "loss": 0.4492, "step": 1070 }, { "epoch": 0.33220547523838817, "grad_norm": 0.25133404592744546, "learning_rate": 4.818837281602645e-05, "loss": 0.4454, "step": 1080 }, { "epoch": 0.33528145186096586, "grad_norm": 0.35641582203541194, "learning_rate": 4.814054517291509e-05, "loss": 0.447, "step": 1090 }, { "epoch": 0.3383574284835435, "grad_norm": 0.28447280258301766, "learning_rate": 4.809211876285378e-05, "loss": 0.4411, "step": 1100 }, { "epoch": 0.3414334051061212, "grad_norm": 0.2877834531206639, "learning_rate": 4.804309483888706e-05, "loss": 0.4495, "step": 1110 }, { "epoch": 0.3445093817286989, "grad_norm": 0.3101176590856895, "learning_rate": 4.7993474669520296e-05, "loss": 0.4427, "step": 1120 }, { "epoch": 0.3475853583512765, "grad_norm": 0.28646654710530217, "learning_rate": 4.794325953868681e-05, "loss": 0.4358, "step": 1130 }, { "epoch": 0.3506613349738542, "grad_norm": 0.2832530554197153, "learning_rate": 4.7892450745714714e-05, "loss": 0.4458, "step": 1140 }, { "epoch": 0.35373731159643185, "grad_norm": 0.3184618740823372, "learning_rate": 4.784104960529327e-05, "loss": 0.4437, "step": 1150 }, { "epoch": 0.35681328821900954, "grad_norm": 0.3108942537985795, "learning_rate": 4.778905744743885e-05, "loss": 0.4437, "step": 1160 }, { "epoch": 0.35988926484158723, "grad_norm": 0.33463395215420433, "learning_rate": 4.773647561746052e-05, "loss": 0.4375, "step": 1170 }, { "epoch": 0.36296524146416487, "grad_norm": 0.29003571046163773, "learning_rate": 4.768330547592531e-05, "loss": 0.4478, "step": 1180 }, { "epoch": 0.36604121808674256, "grad_norm": 0.2802192963151693, "learning_rate": 4.76295483986229e-05, "loss": 0.431, "step": 1190 }, { "epoch": 0.3691171947093202, "grad_norm": 0.3694282361832342, "learning_rate": 4.7575205776530063e-05, "loss": 0.4364, "step": 1200 }, { "epoch": 0.3721931713318979, "grad_norm": 0.28258810921773164, "learning_rate": 4.752027901577471e-05, "loss": 0.4348, "step": 1210 }, { "epoch": 0.3752691479544755, "grad_norm": 0.2978797930477036, "learning_rate": 4.7464769537599454e-05, "loss": 0.437, "step": 1220 }, { "epoch": 0.3783451245770532, "grad_norm": 0.28837304996283497, "learning_rate": 4.740867877832486e-05, "loss": 0.439, "step": 1230 }, { "epoch": 0.3814211011996309, "grad_norm": 0.2503256116317833, "learning_rate": 4.735200818931228e-05, "loss": 0.4391, "step": 1240 }, { "epoch": 0.38449707782220854, "grad_norm": 0.28113222963271484, "learning_rate": 4.729475923692629e-05, "loss": 0.4355, "step": 1250 }, { "epoch": 0.38757305444478624, "grad_norm": 0.27284968888689665, "learning_rate": 4.723693340249674e-05, "loss": 0.4372, "step": 1260 }, { "epoch": 0.39064903106736387, "grad_norm": 0.27720042815202794, "learning_rate": 4.717853218228048e-05, "loss": 0.4335, "step": 1270 }, { "epoch": 0.39372500768994156, "grad_norm": 0.30018485883014734, "learning_rate": 4.711955708742253e-05, "loss": 0.4394, "step": 1280 }, { "epoch": 0.3968009843125192, "grad_norm": 0.25702698616058733, "learning_rate": 4.706000964391713e-05, "loss": 0.438, "step": 1290 }, { "epoch": 0.3998769609350969, "grad_norm": 0.27250234267389223, "learning_rate": 4.6999891392568084e-05, "loss": 0.4376, "step": 1300 }, { "epoch": 0.4029529375576746, "grad_norm": 0.2775035721093286, "learning_rate": 4.6939203888949065e-05, "loss": 0.4448, "step": 1310 }, { "epoch": 0.4060289141802522, "grad_norm": 0.3409517606625801, "learning_rate": 4.6877948703363236e-05, "loss": 0.4456, "step": 1320 }, { "epoch": 0.4091048908028299, "grad_norm": 0.29103883816022225, "learning_rate": 4.6816127420802656e-05, "loss": 0.4365, "step": 1330 }, { "epoch": 0.41218086742540755, "grad_norm": 0.2873311254395258, "learning_rate": 4.67537416409073e-05, "loss": 0.4357, "step": 1340 }, { "epoch": 0.41525684404798524, "grad_norm": 0.2797887582419444, "learning_rate": 4.669079297792362e-05, "loss": 0.4343, "step": 1350 }, { "epoch": 0.4183328206705629, "grad_norm": 0.30137863989673286, "learning_rate": 4.662728306066282e-05, "loss": 0.4364, "step": 1360 }, { "epoch": 0.42140879729314057, "grad_norm": 0.2389512309955969, "learning_rate": 4.6563213532458664e-05, "loss": 0.4302, "step": 1370 }, { "epoch": 0.42448477391571826, "grad_norm": 0.2775002014111214, "learning_rate": 4.649858605112498e-05, "loss": 0.4329, "step": 1380 }, { "epoch": 0.4275607505382959, "grad_norm": 0.30204892736472166, "learning_rate": 4.6433402288912795e-05, "loss": 0.4351, "step": 1390 }, { "epoch": 0.4306367271608736, "grad_norm": 0.28070504429613863, "learning_rate": 4.6367663932466986e-05, "loss": 0.4338, "step": 1400 }, { "epoch": 0.4337127037834512, "grad_norm": 0.2755938062030225, "learning_rate": 4.630137268278272e-05, "loss": 0.437, "step": 1410 }, { "epoch": 0.4367886804060289, "grad_norm": 0.2683496747287529, "learning_rate": 4.623453025516139e-05, "loss": 0.4291, "step": 1420 }, { "epoch": 0.4398646570286066, "grad_norm": 0.29866780918221186, "learning_rate": 4.616713837916624e-05, "loss": 0.4305, "step": 1430 }, { "epoch": 0.44294063365118425, "grad_norm": 0.2902476113743612, "learning_rate": 4.609919879857762e-05, "loss": 0.4348, "step": 1440 }, { "epoch": 0.44601661027376194, "grad_norm": 0.2855090666317932, "learning_rate": 4.603071327134788e-05, "loss": 0.4353, "step": 1450 }, { "epoch": 0.4490925868963396, "grad_norm": 0.29829918917864323, "learning_rate": 4.596168356955584e-05, "loss": 0.4311, "step": 1460 }, { "epoch": 0.45216856351891727, "grad_norm": 0.29575001434521603, "learning_rate": 4.589211147936098e-05, "loss": 0.4305, "step": 1470 }, { "epoch": 0.4552445401414949, "grad_norm": 0.2694513988614369, "learning_rate": 4.58219988009572e-05, "loss": 0.4318, "step": 1480 }, { "epoch": 0.4583205167640726, "grad_norm": 0.2700641593081542, "learning_rate": 4.575134734852623e-05, "loss": 0.4286, "step": 1490 }, { "epoch": 0.4613964933866503, "grad_norm": 0.3124957213690454, "learning_rate": 4.568015895019074e-05, "loss": 0.4326, "step": 1500 }, { "epoch": 0.4644724700092279, "grad_norm": 0.2796728519296287, "learning_rate": 4.560843544796696e-05, "loss": 0.426, "step": 1510 }, { "epoch": 0.4675484466318056, "grad_norm": 0.3124044567212998, "learning_rate": 4.553617869771708e-05, "loss": 0.4253, "step": 1520 }, { "epoch": 0.47062442325438325, "grad_norm": 0.28814015389028486, "learning_rate": 4.5463390569101185e-05, "loss": 0.4321, "step": 1530 }, { "epoch": 0.47370039987696094, "grad_norm": 0.2867142037524574, "learning_rate": 4.5390072945528914e-05, "loss": 0.4276, "step": 1540 }, { "epoch": 0.4767763764995386, "grad_norm": 0.3019089195202603, "learning_rate": 4.5316227724110725e-05, "loss": 0.4331, "step": 1550 }, { "epoch": 0.47985235312211627, "grad_norm": 0.26189949114436545, "learning_rate": 4.524185681560877e-05, "loss": 0.4317, "step": 1560 }, { "epoch": 0.48292832974469396, "grad_norm": 0.2806405934845335, "learning_rate": 4.5166962144387465e-05, "loss": 0.4312, "step": 1570 }, { "epoch": 0.4860043063672716, "grad_norm": 0.309272120250282, "learning_rate": 4.509154564836373e-05, "loss": 0.4243, "step": 1580 }, { "epoch": 0.4890802829898493, "grad_norm": 0.2866506228657855, "learning_rate": 4.501560927895682e-05, "loss": 0.432, "step": 1590 }, { "epoch": 0.4921562596124269, "grad_norm": 0.2981115995883811, "learning_rate": 4.493915500103782e-05, "loss": 0.4313, "step": 1600 }, { "epoch": 0.4952322362350046, "grad_norm": 0.3046683670557116, "learning_rate": 4.486218479287884e-05, "loss": 0.4306, "step": 1610 }, { "epoch": 0.49830821285758226, "grad_norm": 0.28099529765149395, "learning_rate": 4.478470064610176e-05, "loss": 0.4361, "step": 1620 }, { "epoch": 0.50138418948016, "grad_norm": 0.2728249464977267, "learning_rate": 4.4706704565626804e-05, "loss": 0.4263, "step": 1630 }, { "epoch": 0.5044601661027376, "grad_norm": 0.2884069985808534, "learning_rate": 4.462819856962055e-05, "loss": 0.4268, "step": 1640 }, { "epoch": 0.5075361427253153, "grad_norm": 0.28862375317235606, "learning_rate": 4.454918468944378e-05, "loss": 0.4217, "step": 1650 }, { "epoch": 0.510612119347893, "grad_norm": 0.293304100146446, "learning_rate": 4.446966496959888e-05, "loss": 0.4338, "step": 1660 }, { "epoch": 0.5136880959704706, "grad_norm": 0.3210060005529061, "learning_rate": 4.438964146767696e-05, "loss": 0.4304, "step": 1670 }, { "epoch": 0.5167640725930482, "grad_norm": 0.25736390216475247, "learning_rate": 4.430911625430463e-05, "loss": 0.4286, "step": 1680 }, { "epoch": 0.519840049215626, "grad_norm": 0.3100084339300098, "learning_rate": 4.4228091413090365e-05, "loss": 0.4283, "step": 1690 }, { "epoch": 0.5229160258382036, "grad_norm": 0.29674752065847176, "learning_rate": 4.414656904057065e-05, "loss": 0.4291, "step": 1700 }, { "epoch": 0.5259920024607813, "grad_norm": 0.27849614668375977, "learning_rate": 4.4064551246155693e-05, "loss": 0.4303, "step": 1710 }, { "epoch": 0.529067979083359, "grad_norm": 0.2557937167369403, "learning_rate": 4.398204015207487e-05, "loss": 0.4237, "step": 1720 }, { "epoch": 0.5321439557059366, "grad_norm": 0.276806087858016, "learning_rate": 4.389903789332178e-05, "loss": 0.4225, "step": 1730 }, { "epoch": 0.5352199323285143, "grad_norm": 0.28961531777612715, "learning_rate": 4.381554661759906e-05, "loss": 0.4246, "step": 1740 }, { "epoch": 0.5382959089510919, "grad_norm": 0.2686838716704818, "learning_rate": 4.373156848526273e-05, "loss": 0.4213, "step": 1750 }, { "epoch": 0.5413718855736697, "grad_norm": 0.26796810918098735, "learning_rate": 4.364710566926635e-05, "loss": 0.4206, "step": 1760 }, { "epoch": 0.5444478621962473, "grad_norm": 0.24561587768577053, "learning_rate": 4.3562160355104806e-05, "loss": 0.4209, "step": 1770 }, { "epoch": 0.5475238388188249, "grad_norm": 0.30373065638408564, "learning_rate": 4.347673474075772e-05, "loss": 0.4244, "step": 1780 }, { "epoch": 0.5505998154414027, "grad_norm": 0.2909424427294614, "learning_rate": 4.3390831036632565e-05, "loss": 0.4221, "step": 1790 }, { "epoch": 0.5536757920639803, "grad_norm": 0.2755534794729893, "learning_rate": 4.3304451465507554e-05, "loss": 0.4284, "step": 1800 }, { "epoch": 0.556751768686558, "grad_norm": 0.25580850559061413, "learning_rate": 4.321759826247401e-05, "loss": 0.4296, "step": 1810 }, { "epoch": 0.5598277453091357, "grad_norm": 0.25182227472605595, "learning_rate": 4.3130273674878626e-05, "loss": 0.4275, "step": 1820 }, { "epoch": 0.5629037219317133, "grad_norm": 0.2680112036288691, "learning_rate": 4.304247996226527e-05, "loss": 0.4209, "step": 1830 }, { "epoch": 0.565979698554291, "grad_norm": 0.26428863879664427, "learning_rate": 4.295421939631654e-05, "loss": 0.4239, "step": 1840 }, { "epoch": 0.5690556751768686, "grad_norm": 0.2859058952327525, "learning_rate": 4.286549426079495e-05, "loss": 0.425, "step": 1850 }, { "epoch": 0.5721316517994464, "grad_norm": 0.2647446607981528, "learning_rate": 4.2776306851483864e-05, "loss": 0.4169, "step": 1860 }, { "epoch": 0.575207628422024, "grad_norm": 0.28739837248493655, "learning_rate": 4.268665947612811e-05, "loss": 0.4209, "step": 1870 }, { "epoch": 0.5782836050446016, "grad_norm": 0.266509521099783, "learning_rate": 4.2596554454374215e-05, "loss": 0.4257, "step": 1880 }, { "epoch": 0.5813595816671794, "grad_norm": 0.2708177786642195, "learning_rate": 4.250599411771043e-05, "loss": 0.4251, "step": 1890 }, { "epoch": 0.584435558289757, "grad_norm": 0.2563176383381169, "learning_rate": 4.2414980809406366e-05, "loss": 0.4197, "step": 1900 }, { "epoch": 0.5875115349123347, "grad_norm": 0.258434026990292, "learning_rate": 4.232351688445241e-05, "loss": 0.4149, "step": 1910 }, { "epoch": 0.5905875115349123, "grad_norm": 0.23964946069935397, "learning_rate": 4.223160470949874e-05, "loss": 0.4223, "step": 1920 }, { "epoch": 0.59366348815749, "grad_norm": 0.33550568871040953, "learning_rate": 4.213924666279408e-05, "loss": 0.4269, "step": 1930 }, { "epoch": 0.5967394647800677, "grad_norm": 0.25815100276897995, "learning_rate": 4.204644513412425e-05, "loss": 0.4224, "step": 1940 }, { "epoch": 0.5998154414026453, "grad_norm": 0.27261416760284596, "learning_rate": 4.1953202524750215e-05, "loss": 0.4272, "step": 1950 }, { "epoch": 0.6028914180252231, "grad_norm": 0.24246446854409565, "learning_rate": 4.1859521247346033e-05, "loss": 0.4255, "step": 1960 }, { "epoch": 0.6059673946478007, "grad_norm": 0.26815232926971594, "learning_rate": 4.176540372593638e-05, "loss": 0.4193, "step": 1970 }, { "epoch": 0.6090433712703783, "grad_norm": 0.29144267958190073, "learning_rate": 4.167085239583386e-05, "loss": 0.4251, "step": 1980 }, { "epoch": 0.612119347892956, "grad_norm": 0.29469041650040917, "learning_rate": 4.1575869703575976e-05, "loss": 0.4242, "step": 1990 }, { "epoch": 0.6151953245155337, "grad_norm": 0.26992625318357616, "learning_rate": 4.148045810686182e-05, "loss": 0.419, "step": 2000 }, { "epoch": 0.6182713011381114, "grad_norm": 0.2835064966178822, "learning_rate": 4.1384620074488496e-05, "loss": 0.4134, "step": 2010 }, { "epoch": 0.621347277760689, "grad_norm": 0.25176009198407906, "learning_rate": 4.1288358086287214e-05, "loss": 0.4186, "step": 2020 }, { "epoch": 0.6244232543832667, "grad_norm": 0.2780815718431866, "learning_rate": 4.119167463305915e-05, "loss": 0.4147, "step": 2030 }, { "epoch": 0.6274992310058444, "grad_norm": 0.304888303864731, "learning_rate": 4.109457221651099e-05, "loss": 0.4219, "step": 2040 }, { "epoch": 0.630575207628422, "grad_norm": 0.24665420069182464, "learning_rate": 4.099705334919017e-05, "loss": 0.416, "step": 2050 }, { "epoch": 0.6336511842509996, "grad_norm": 0.2667809485718479, "learning_rate": 4.089912055441992e-05, "loss": 0.4224, "step": 2060 }, { "epoch": 0.6367271608735774, "grad_norm": 0.2720252636738378, "learning_rate": 4.08007763662339e-05, "loss": 0.417, "step": 2070 }, { "epoch": 0.639803137496155, "grad_norm": 0.2908643221842336, "learning_rate": 4.07020233293107e-05, "loss": 0.4298, "step": 2080 }, { "epoch": 0.6428791141187327, "grad_norm": 0.2675389903721083, "learning_rate": 4.060286399890795e-05, "loss": 0.4177, "step": 2090 }, { "epoch": 0.6459550907413104, "grad_norm": 0.2595208610042246, "learning_rate": 4.050330094079623e-05, "loss": 0.421, "step": 2100 }, { "epoch": 0.649031067363888, "grad_norm": 0.2601129211482316, "learning_rate": 4.0403336731192645e-05, "loss": 0.4234, "step": 2110 }, { "epoch": 0.6521070439864657, "grad_norm": 0.2590636735533898, "learning_rate": 4.030297395669422e-05, "loss": 0.4144, "step": 2120 }, { "epoch": 0.6551830206090433, "grad_norm": 0.2723319178738226, "learning_rate": 4.0202215214210906e-05, "loss": 0.4212, "step": 2130 }, { "epoch": 0.6582589972316211, "grad_norm": 0.2512412021325699, "learning_rate": 4.010106311089844e-05, "loss": 0.4194, "step": 2140 }, { "epoch": 0.6613349738541987, "grad_norm": 0.29474497932771493, "learning_rate": 3.999952026409085e-05, "loss": 0.419, "step": 2150 }, { "epoch": 0.6644109504767763, "grad_norm": 0.26693226583659074, "learning_rate": 3.9897589301232745e-05, "loss": 0.4219, "step": 2160 }, { "epoch": 0.6674869270993541, "grad_norm": 0.24327413178801496, "learning_rate": 3.9795272859811325e-05, "loss": 0.4254, "step": 2170 }, { "epoch": 0.6705629037219317, "grad_norm": 0.24090632847211016, "learning_rate": 3.969257358728815e-05, "loss": 0.4142, "step": 2180 }, { "epoch": 0.6736388803445094, "grad_norm": 0.23337091034022722, "learning_rate": 3.95894941410306e-05, "loss": 0.4186, "step": 2190 }, { "epoch": 0.676714856967087, "grad_norm": 0.2866816417835903, "learning_rate": 3.9486037188243154e-05, "loss": 0.4151, "step": 2200 }, { "epoch": 0.6797908335896647, "grad_norm": 0.27759374757577976, "learning_rate": 3.9382205405898355e-05, "loss": 0.4173, "step": 2210 }, { "epoch": 0.6828668102122424, "grad_norm": 0.2277653944278294, "learning_rate": 3.927800148066755e-05, "loss": 0.4224, "step": 2220 }, { "epoch": 0.68594278683482, "grad_norm": 0.22846672361732212, "learning_rate": 3.9173428108851354e-05, "loss": 0.4165, "step": 2230 }, { "epoch": 0.6890187634573978, "grad_norm": 0.2712078866602458, "learning_rate": 3.906848799630993e-05, "loss": 0.4182, "step": 2240 }, { "epoch": 0.6920947400799754, "grad_norm": 0.26350743851963254, "learning_rate": 3.896318385839291e-05, "loss": 0.4165, "step": 2250 }, { "epoch": 0.695170716702553, "grad_norm": 0.2792161712420128, "learning_rate": 3.885751841986919e-05, "loss": 0.4193, "step": 2260 }, { "epoch": 0.6982466933251307, "grad_norm": 0.2470926248319491, "learning_rate": 3.875149441485638e-05, "loss": 0.4149, "step": 2270 }, { "epoch": 0.7013226699477084, "grad_norm": 0.24712568706704063, "learning_rate": 3.864511458675011e-05, "loss": 0.4175, "step": 2280 }, { "epoch": 0.7043986465702861, "grad_norm": 0.2600685298484599, "learning_rate": 3.8538381688152977e-05, "loss": 0.4123, "step": 2290 }, { "epoch": 0.7074746231928637, "grad_norm": 0.24278853745590823, "learning_rate": 3.8431298480803386e-05, "loss": 0.4145, "step": 2300 }, { "epoch": 0.7105505998154414, "grad_norm": 0.24669107386536832, "learning_rate": 3.832386773550406e-05, "loss": 0.4153, "step": 2310 }, { "epoch": 0.7136265764380191, "grad_norm": 0.23958340167300854, "learning_rate": 3.821609223205034e-05, "loss": 0.4179, "step": 2320 }, { "epoch": 0.7167025530605967, "grad_norm": 0.25321432746985945, "learning_rate": 3.8107974759158264e-05, "loss": 0.4173, "step": 2330 }, { "epoch": 0.7197785296831745, "grad_norm": 0.2430554019073807, "learning_rate": 3.79995181143924e-05, "loss": 0.4183, "step": 2340 }, { "epoch": 0.7228545063057521, "grad_norm": 0.2460269478033551, "learning_rate": 3.7890725104093486e-05, "loss": 0.4117, "step": 2350 }, { "epoch": 0.7259304829283297, "grad_norm": 0.2646419157405838, "learning_rate": 3.7781598543305796e-05, "loss": 0.4158, "step": 2360 }, { "epoch": 0.7290064595509074, "grad_norm": 0.26660884764158416, "learning_rate": 3.767214125570427e-05, "loss": 0.4136, "step": 2370 }, { "epoch": 0.7320824361734851, "grad_norm": 0.24668870942489718, "learning_rate": 3.756235607352151e-05, "loss": 0.4111, "step": 2380 }, { "epoch": 0.7351584127960628, "grad_norm": 0.2534195005162289, "learning_rate": 3.745224583747446e-05, "loss": 0.4168, "step": 2390 }, { "epoch": 0.7382343894186404, "grad_norm": 0.24831235167002502, "learning_rate": 3.73418133966909e-05, "loss": 0.4117, "step": 2400 }, { "epoch": 0.7413103660412181, "grad_norm": 0.23308859468735887, "learning_rate": 3.723106160863573e-05, "loss": 0.408, "step": 2410 }, { "epoch": 0.7443863426637958, "grad_norm": 0.22357487232105802, "learning_rate": 3.711999333903705e-05, "loss": 0.4187, "step": 2420 }, { "epoch": 0.7474623192863734, "grad_norm": 0.2562056170804871, "learning_rate": 3.700861146181198e-05, "loss": 0.408, "step": 2430 }, { "epoch": 0.750538295908951, "grad_norm": 0.2812027787141308, "learning_rate": 3.689691885899231e-05, "loss": 0.4097, "step": 2440 }, { "epoch": 0.7536142725315288, "grad_norm": 0.2223760146036956, "learning_rate": 3.678491842064995e-05, "loss": 0.4068, "step": 2450 }, { "epoch": 0.7566902491541064, "grad_norm": 0.220593179168878, "learning_rate": 3.667261304482208e-05, "loss": 0.4108, "step": 2460 }, { "epoch": 0.7597662257766841, "grad_norm": 0.22545865998005973, "learning_rate": 3.656000563743623e-05, "loss": 0.4125, "step": 2470 }, { "epoch": 0.7628422023992618, "grad_norm": 0.258134478654878, "learning_rate": 3.6447099112235094e-05, "loss": 0.4154, "step": 2480 }, { "epoch": 0.7659181790218395, "grad_norm": 0.24860544187714256, "learning_rate": 3.6333896390701066e-05, "loss": 0.4111, "step": 2490 }, { "epoch": 0.7689941556444171, "grad_norm": 0.2311759783053848, "learning_rate": 3.622040040198072e-05, "loss": 0.4121, "step": 2500 }, { "epoch": 0.7720701322669947, "grad_norm": 0.2823607714207722, "learning_rate": 3.610661408280896e-05, "loss": 0.4058, "step": 2510 }, { "epoch": 0.7751461088895725, "grad_norm": 0.254251046094007, "learning_rate": 3.599254037743307e-05, "loss": 0.4141, "step": 2520 }, { "epoch": 0.7782220855121501, "grad_norm": 0.24200208387051883, "learning_rate": 3.587818223753653e-05, "loss": 0.413, "step": 2530 }, { "epoch": 0.7812980621347277, "grad_norm": 0.24817285559888938, "learning_rate": 3.5763542622162605e-05, "loss": 0.4091, "step": 2540 }, { "epoch": 0.7843740387573055, "grad_norm": 0.2504778073591915, "learning_rate": 3.564862449763783e-05, "loss": 0.4166, "step": 2550 }, { "epoch": 0.7874500153798831, "grad_norm": 0.23073846962303504, "learning_rate": 3.55334308374952e-05, "loss": 0.4181, "step": 2560 }, { "epoch": 0.7905259920024608, "grad_norm": 0.2466881159768463, "learning_rate": 3.541796462239727e-05, "loss": 0.4159, "step": 2570 }, { "epoch": 0.7936019686250384, "grad_norm": 0.23101253670744193, "learning_rate": 3.5302228840059026e-05, "loss": 0.4112, "step": 2580 }, { "epoch": 0.7966779452476161, "grad_norm": 0.2566964066697848, "learning_rate": 3.518622648517056e-05, "loss": 0.4135, "step": 2590 }, { "epoch": 0.7997539218701938, "grad_norm": 0.23846578593082762, "learning_rate": 3.5069960559319604e-05, "loss": 0.4122, "step": 2600 }, { "epoch": 0.8028298984927714, "grad_norm": 0.29760967434986807, "learning_rate": 3.495343407091382e-05, "loss": 0.416, "step": 2610 }, { "epoch": 0.8059058751153492, "grad_norm": 0.2848464381086534, "learning_rate": 3.4836650035103005e-05, "loss": 0.4084, "step": 2620 }, { "epoch": 0.8089818517379268, "grad_norm": 0.2658703949546632, "learning_rate": 3.471961147370106e-05, "loss": 0.4096, "step": 2630 }, { "epoch": 0.8120578283605044, "grad_norm": 0.2587501905149903, "learning_rate": 3.4602321415107784e-05, "loss": 0.4065, "step": 2640 }, { "epoch": 0.8151338049830821, "grad_norm": 0.24875135039760343, "learning_rate": 3.448478289423054e-05, "loss": 0.4095, "step": 2650 }, { "epoch": 0.8182097816056598, "grad_norm": 0.22433683269350105, "learning_rate": 3.4366998952405675e-05, "loss": 0.4082, "step": 2660 }, { "epoch": 0.8212857582282375, "grad_norm": 0.2206019902981266, "learning_rate": 3.42489726373199e-05, "loss": 0.4127, "step": 2670 }, { "epoch": 0.8243617348508151, "grad_norm": 0.236882558511157, "learning_rate": 3.4130707002931365e-05, "loss": 0.4131, "step": 2680 }, { "epoch": 0.8274377114733928, "grad_norm": 0.2172144618256848, "learning_rate": 3.401220510939068e-05, "loss": 0.4144, "step": 2690 }, { "epoch": 0.8305136880959705, "grad_norm": 0.2860569103720803, "learning_rate": 3.3893470022961696e-05, "loss": 0.411, "step": 2700 }, { "epoch": 0.8335896647185481, "grad_norm": 0.25500155307055566, "learning_rate": 3.377450481594218e-05, "loss": 0.4166, "step": 2710 }, { "epoch": 0.8366656413411258, "grad_norm": 0.23143712205670014, "learning_rate": 3.365531256658435e-05, "loss": 0.4074, "step": 2720 }, { "epoch": 0.8397416179637035, "grad_norm": 0.21721045242190162, "learning_rate": 3.353589635901519e-05, "loss": 0.4073, "step": 2730 }, { "epoch": 0.8428175945862811, "grad_norm": 0.23073033184257208, "learning_rate": 3.341625928315664e-05, "loss": 0.4088, "step": 2740 }, { "epoch": 0.8458935712088588, "grad_norm": 0.25288202036301016, "learning_rate": 3.3296404434645646e-05, "loss": 0.4142, "step": 2750 }, { "epoch": 0.8489695478314365, "grad_norm": 0.2517292621032714, "learning_rate": 3.317633491475411e-05, "loss": 0.4013, "step": 2760 }, { "epoch": 0.8520455244540142, "grad_norm": 0.21340857572189464, "learning_rate": 3.3056053830308575e-05, "loss": 0.4088, "step": 2770 }, { "epoch": 0.8551215010765918, "grad_norm": 0.24103800664537423, "learning_rate": 3.293556429360989e-05, "loss": 0.4054, "step": 2780 }, { "epoch": 0.8581974776991694, "grad_norm": 0.23719785070904892, "learning_rate": 3.2814869422352635e-05, "loss": 0.405, "step": 2790 }, { "epoch": 0.8612734543217472, "grad_norm": 0.2279572170828786, "learning_rate": 3.269397233954446e-05, "loss": 0.4072, "step": 2800 }, { "epoch": 0.8643494309443248, "grad_norm": 0.23747532079266317, "learning_rate": 3.2572876173425316e-05, "loss": 0.4053, "step": 2810 }, { "epoch": 0.8674254075669025, "grad_norm": 0.23036340303865266, "learning_rate": 3.2451584057386464e-05, "loss": 0.4086, "step": 2820 }, { "epoch": 0.8705013841894802, "grad_norm": 0.27163143312954097, "learning_rate": 3.233009912988941e-05, "loss": 0.404, "step": 2830 }, { "epoch": 0.8735773608120578, "grad_norm": 0.2943072032696799, "learning_rate": 3.2208424534384705e-05, "loss": 0.4061, "step": 2840 }, { "epoch": 0.8766533374346355, "grad_norm": 0.2384277602250472, "learning_rate": 3.208656341923061e-05, "loss": 0.4084, "step": 2850 }, { "epoch": 0.8797293140572132, "grad_norm": 0.2457729302604274, "learning_rate": 3.196451893761162e-05, "loss": 0.4017, "step": 2860 }, { "epoch": 0.8828052906797909, "grad_norm": 0.2595149545799868, "learning_rate": 3.184229424745687e-05, "loss": 0.4089, "step": 2870 }, { "epoch": 0.8858812673023685, "grad_norm": 0.247624819322109, "learning_rate": 3.171989251135846e-05, "loss": 0.4121, "step": 2880 }, { "epoch": 0.8889572439249461, "grad_norm": 0.2551365034365418, "learning_rate": 3.159731689648956e-05, "loss": 0.4064, "step": 2890 }, { "epoch": 0.8920332205475239, "grad_norm": 0.22332006637414484, "learning_rate": 3.147457057452251e-05, "loss": 0.4091, "step": 2900 }, { "epoch": 0.8951091971701015, "grad_norm": 0.22513340500213172, "learning_rate": 3.1351656721546744e-05, "loss": 0.408, "step": 2910 }, { "epoch": 0.8981851737926791, "grad_norm": 0.2454504772590956, "learning_rate": 3.122857851798658e-05, "loss": 0.4058, "step": 2920 }, { "epoch": 0.9012611504152569, "grad_norm": 0.26901765437679404, "learning_rate": 3.110533914851897e-05, "loss": 0.4048, "step": 2930 }, { "epoch": 0.9043371270378345, "grad_norm": 0.2393276786391303, "learning_rate": 3.0981941801991057e-05, "loss": 0.4082, "step": 2940 }, { "epoch": 0.9074131036604122, "grad_norm": 0.24675858141150653, "learning_rate": 3.085838967133766e-05, "loss": 0.3999, "step": 2950 }, { "epoch": 0.9104890802829898, "grad_norm": 0.23385699373025817, "learning_rate": 3.07346859534987e-05, "loss": 0.4045, "step": 2960 }, { "epoch": 0.9135650569055676, "grad_norm": 0.2550754084932932, "learning_rate": 3.061083384933645e-05, "loss": 0.4049, "step": 2970 }, { "epoch": 0.9166410335281452, "grad_norm": 0.21288581134209228, "learning_rate": 3.048683656355269e-05, "loss": 0.4056, "step": 2980 }, { "epoch": 0.9197170101507228, "grad_norm": 0.23691019206514222, "learning_rate": 3.0362697304605843e-05, "loss": 0.4076, "step": 2990 }, { "epoch": 0.9227929867733006, "grad_norm": 0.22991883250871126, "learning_rate": 3.0238419284627882e-05, "loss": 0.4079, "step": 3000 }, { "epoch": 0.9258689633958782, "grad_norm": 0.23663085267351897, "learning_rate": 3.0114005719341277e-05, "loss": 0.4025, "step": 3010 }, { "epoch": 0.9289449400184558, "grad_norm": 0.21563938174658423, "learning_rate": 2.9989459827975762e-05, "loss": 0.4052, "step": 3020 }, { "epoch": 0.9320209166410335, "grad_norm": 0.22188529217875697, "learning_rate": 2.9864784833185038e-05, "loss": 0.4079, "step": 3030 }, { "epoch": 0.9350968932636112, "grad_norm": 0.21859336697567935, "learning_rate": 2.973998396096338e-05, "loss": 0.4086, "step": 3040 }, { "epoch": 0.9381728698861889, "grad_norm": 0.22303751965457747, "learning_rate": 2.9615060440562176e-05, "loss": 0.4044, "step": 3050 }, { "epoch": 0.9412488465087665, "grad_norm": 0.23899236670405377, "learning_rate": 2.9490017504406365e-05, "loss": 0.4098, "step": 3060 }, { "epoch": 0.9443248231313442, "grad_norm": 0.24152166176050946, "learning_rate": 2.9364858388010796e-05, "loss": 0.4044, "step": 3070 }, { "epoch": 0.9474007997539219, "grad_norm": 0.24902767203934015, "learning_rate": 2.9239586329896513e-05, "loss": 0.4042, "step": 3080 }, { "epoch": 0.9504767763764995, "grad_norm": 0.2145465480553633, "learning_rate": 2.911420457150693e-05, "loss": 0.4081, "step": 3090 }, { "epoch": 0.9535527529990772, "grad_norm": 0.21060706120855768, "learning_rate": 2.8988716357124018e-05, "loss": 0.4073, "step": 3100 }, { "epoch": 0.9566287296216549, "grad_norm": 0.2262014915590459, "learning_rate": 2.886312493378429e-05, "loss": 0.4083, "step": 3110 }, { "epoch": 0.9597047062442325, "grad_norm": 0.2363250785648691, "learning_rate": 2.8737433551194833e-05, "loss": 0.4004, "step": 3120 }, { "epoch": 0.9627806828668102, "grad_norm": 0.25543818824634373, "learning_rate": 2.8611645461649187e-05, "loss": 0.4062, "step": 3130 }, { "epoch": 0.9658566594893879, "grad_norm": 0.23820817136588496, "learning_rate": 2.8485763919943226e-05, "loss": 0.4081, "step": 3140 }, { "epoch": 0.9689326361119656, "grad_norm": 0.22575359981124374, "learning_rate": 2.8359792183290907e-05, "loss": 0.4018, "step": 3150 }, { "epoch": 0.9720086127345432, "grad_norm": 0.22441300714698234, "learning_rate": 2.823373351124e-05, "loss": 0.4016, "step": 3160 }, { "epoch": 0.9750845893571208, "grad_norm": 0.21603060922214587, "learning_rate": 2.810759116558776e-05, "loss": 0.3984, "step": 3170 }, { "epoch": 0.9781605659796986, "grad_norm": 0.22012443684485428, "learning_rate": 2.798136841029651e-05, "loss": 0.4024, "step": 3180 }, { "epoch": 0.9812365426022762, "grad_norm": 0.1925840977398474, "learning_rate": 2.7855068511409182e-05, "loss": 0.3985, "step": 3190 }, { "epoch": 0.9843125192248539, "grad_norm": 0.24069946694197897, "learning_rate": 2.7728694736964832e-05, "loss": 0.4078, "step": 3200 }, { "epoch": 0.9873884958474316, "grad_norm": 0.2206709440758833, "learning_rate": 2.7602250356914054e-05, "loss": 0.4034, "step": 3210 }, { "epoch": 0.9904644724700092, "grad_norm": 0.21125282758790837, "learning_rate": 2.7475738643034382e-05, "loss": 0.4018, "step": 3220 }, { "epoch": 0.9935404490925869, "grad_norm": 0.2515166169796263, "learning_rate": 2.7349162868845636e-05, "loss": 0.4017, "step": 3230 }, { "epoch": 0.9966164257151645, "grad_norm": 0.20534779473090364, "learning_rate": 2.7222526309525175e-05, "loss": 0.4007, "step": 3240 }, { "epoch": 0.9996924023377423, "grad_norm": 0.23836700759024032, "learning_rate": 2.7095832241823237e-05, "loss": 0.4013, "step": 3250 }, { "epoch": 1.00276837896032, "grad_norm": 0.2467337038125098, "learning_rate": 2.6969083943978073e-05, "loss": 0.3892, "step": 3260 }, { "epoch": 1.0058443555828975, "grad_norm": 0.24959135073764682, "learning_rate": 2.684228469563116e-05, "loss": 0.391, "step": 3270 }, { "epoch": 1.0089203322054752, "grad_norm": 0.23523346074900453, "learning_rate": 2.671543777774233e-05, "loss": 0.3944, "step": 3280 }, { "epoch": 1.0119963088280528, "grad_norm": 0.24306836389344297, "learning_rate": 2.6588546472504865e-05, "loss": 0.3893, "step": 3290 }, { "epoch": 1.0150722854506307, "grad_norm": 0.27254167689062164, "learning_rate": 2.6461614063260604e-05, "loss": 0.3855, "step": 3300 }, { "epoch": 1.0181482620732083, "grad_norm": 0.2149471155178888, "learning_rate": 2.633464383441494e-05, "loss": 0.3902, "step": 3310 }, { "epoch": 1.021224238695786, "grad_norm": 0.21377055026303884, "learning_rate": 2.620763907135187e-05, "loss": 0.3853, "step": 3320 }, { "epoch": 1.0243002153183636, "grad_norm": 0.22316153778267103, "learning_rate": 2.6080603060348957e-05, "loss": 0.3887, "step": 3330 }, { "epoch": 1.0273761919409412, "grad_norm": 0.2311323871090799, "learning_rate": 2.5953539088492322e-05, "loss": 0.3975, "step": 3340 }, { "epoch": 1.0304521685635188, "grad_norm": 0.2153673006995378, "learning_rate": 2.5826450443591582e-05, "loss": 0.3906, "step": 3350 }, { "epoch": 1.0335281451860965, "grad_norm": 0.20650840678057683, "learning_rate": 2.5699340414094776e-05, "loss": 0.392, "step": 3360 }, { "epoch": 1.0366041218086743, "grad_norm": 0.2363486629818605, "learning_rate": 2.5572212289003266e-05, "loss": 0.3895, "step": 3370 }, { "epoch": 1.039680098431252, "grad_norm": 0.21399669366780968, "learning_rate": 2.544506935778664e-05, "loss": 0.3894, "step": 3380 }, { "epoch": 1.0427560750538296, "grad_norm": 0.22493686132013718, "learning_rate": 2.5317914910297603e-05, "loss": 0.3897, "step": 3390 }, { "epoch": 1.0458320516764072, "grad_norm": 0.20925778028659334, "learning_rate": 2.5190752236686848e-05, "loss": 0.3843, "step": 3400 }, { "epoch": 1.0489080282989849, "grad_norm": 0.2110063014054057, "learning_rate": 2.506358462731792e-05, "loss": 0.3915, "step": 3410 }, { "epoch": 1.0519840049215625, "grad_norm": 0.2831957829454395, "learning_rate": 2.4936415372682084e-05, "loss": 0.3961, "step": 3420 }, { "epoch": 1.0550599815441402, "grad_norm": 0.22561295367243484, "learning_rate": 2.480924776331316e-05, "loss": 0.3875, "step": 3430 }, { "epoch": 1.058135958166718, "grad_norm": 0.21791989494882766, "learning_rate": 2.4682085089702406e-05, "loss": 0.3971, "step": 3440 }, { "epoch": 1.0612119347892957, "grad_norm": 0.2191936786092157, "learning_rate": 2.455493064221337e-05, "loss": 0.3882, "step": 3450 }, { "epoch": 1.0642879114118733, "grad_norm": 0.22465570241423127, "learning_rate": 2.442778771099674e-05, "loss": 0.393, "step": 3460 }, { "epoch": 1.067363888034451, "grad_norm": 0.21021113287293816, "learning_rate": 2.4300659585905226e-05, "loss": 0.3943, "step": 3470 }, { "epoch": 1.0704398646570286, "grad_norm": 0.22797801906811005, "learning_rate": 2.4173549556408414e-05, "loss": 0.3911, "step": 3480 }, { "epoch": 1.0735158412796062, "grad_norm": 0.2179686580213672, "learning_rate": 2.4046460911507677e-05, "loss": 0.3842, "step": 3490 }, { "epoch": 1.0765918179021838, "grad_norm": 0.20448991216825352, "learning_rate": 2.3919396939651052e-05, "loss": 0.3915, "step": 3500 }, { "epoch": 1.0796677945247617, "grad_norm": 0.22657749337294794, "learning_rate": 2.3792360928648136e-05, "loss": 0.3847, "step": 3510 }, { "epoch": 1.0827437711473393, "grad_norm": 0.23068422564641294, "learning_rate": 2.3665356165585063e-05, "loss": 0.3925, "step": 3520 }, { "epoch": 1.085819747769917, "grad_norm": 0.24532810412440892, "learning_rate": 2.353838593673941e-05, "loss": 0.3913, "step": 3530 }, { "epoch": 1.0888957243924946, "grad_norm": 0.23891246355470658, "learning_rate": 2.341145352749514e-05, "loss": 0.3868, "step": 3540 }, { "epoch": 1.0919717010150722, "grad_norm": 0.24425814625874856, "learning_rate": 2.3284562222257685e-05, "loss": 0.3882, "step": 3550 }, { "epoch": 1.0950476776376499, "grad_norm": 0.2547176163387981, "learning_rate": 2.315771530436885e-05, "loss": 0.3873, "step": 3560 }, { "epoch": 1.0981236542602275, "grad_norm": 0.20709401823525675, "learning_rate": 2.3030916056021933e-05, "loss": 0.3931, "step": 3570 }, { "epoch": 1.1011996308828054, "grad_norm": 0.20343186992638976, "learning_rate": 2.290416775817677e-05, "loss": 0.387, "step": 3580 }, { "epoch": 1.104275607505383, "grad_norm": 0.21229858556017547, "learning_rate": 2.277747369047483e-05, "loss": 0.389, "step": 3590 }, { "epoch": 1.1073515841279606, "grad_norm": 0.23265317308042888, "learning_rate": 2.2650837131154373e-05, "loss": 0.3854, "step": 3600 }, { "epoch": 1.1104275607505383, "grad_norm": 0.2656995514540782, "learning_rate": 2.252426135696562e-05, "loss": 0.3871, "step": 3610 }, { "epoch": 1.113503537373116, "grad_norm": 0.2240940650010475, "learning_rate": 2.2397749643085948e-05, "loss": 0.3894, "step": 3620 }, { "epoch": 1.1165795139956936, "grad_norm": 0.21894858972497339, "learning_rate": 2.2271305263035174e-05, "loss": 0.3877, "step": 3630 }, { "epoch": 1.1196554906182712, "grad_norm": 0.20759001821798695, "learning_rate": 2.2144931488590824e-05, "loss": 0.3881, "step": 3640 }, { "epoch": 1.122731467240849, "grad_norm": 0.19817824275757262, "learning_rate": 2.2018631589703495e-05, "loss": 0.3865, "step": 3650 }, { "epoch": 1.1258074438634267, "grad_norm": 0.22912536495691446, "learning_rate": 2.1892408834412244e-05, "loss": 0.3904, "step": 3660 }, { "epoch": 1.1288834204860043, "grad_norm": 0.25205124385324884, "learning_rate": 2.1766266488760002e-05, "loss": 0.3945, "step": 3670 }, { "epoch": 1.131959397108582, "grad_norm": 0.21246182458391616, "learning_rate": 2.1640207816709096e-05, "loss": 0.3892, "step": 3680 }, { "epoch": 1.1350353737311596, "grad_norm": 0.24696778914604994, "learning_rate": 2.1514236080056777e-05, "loss": 0.3845, "step": 3690 }, { "epoch": 1.1381113503537372, "grad_norm": 0.20414042073355126, "learning_rate": 2.1388354538350815e-05, "loss": 0.389, "step": 3700 }, { "epoch": 1.1411873269763149, "grad_norm": 0.20439231916009581, "learning_rate": 2.1262566448805177e-05, "loss": 0.3873, "step": 3710 }, { "epoch": 1.1442633035988927, "grad_norm": 0.2161471336296496, "learning_rate": 2.1136875066215716e-05, "loss": 0.3901, "step": 3720 }, { "epoch": 1.1473392802214704, "grad_norm": 0.20421713162763266, "learning_rate": 2.101128364287599e-05, "loss": 0.3836, "step": 3730 }, { "epoch": 1.150415256844048, "grad_norm": 0.22657303182320004, "learning_rate": 2.0885795428493076e-05, "loss": 0.3904, "step": 3740 }, { "epoch": 1.1534912334666256, "grad_norm": 0.23271974714770877, "learning_rate": 2.07604136701035e-05, "loss": 0.3839, "step": 3750 }, { "epoch": 1.1565672100892033, "grad_norm": 0.21214136802454994, "learning_rate": 2.063514161198921e-05, "loss": 0.3875, "step": 3760 }, { "epoch": 1.159643186711781, "grad_norm": 0.2158380324727783, "learning_rate": 2.0509982495593637e-05, "loss": 0.3839, "step": 3770 }, { "epoch": 1.1627191633343585, "grad_norm": 0.22166572193772419, "learning_rate": 2.038493955943783e-05, "loss": 0.3834, "step": 3780 }, { "epoch": 1.1657951399569364, "grad_norm": 0.22002460344621405, "learning_rate": 2.0260016039036624e-05, "loss": 0.3852, "step": 3790 }, { "epoch": 1.168871116579514, "grad_norm": 0.22140746855162755, "learning_rate": 2.0135215166814968e-05, "loss": 0.3924, "step": 3800 }, { "epoch": 1.1719470932020917, "grad_norm": 0.21826330474873426, "learning_rate": 2.0010540172024243e-05, "loss": 0.3909, "step": 3810 }, { "epoch": 1.1750230698246693, "grad_norm": 0.19384955146668895, "learning_rate": 1.988599428065873e-05, "loss": 0.3841, "step": 3820 }, { "epoch": 1.178099046447247, "grad_norm": 0.1954014979650703, "learning_rate": 1.9761580715372124e-05, "loss": 0.3833, "step": 3830 }, { "epoch": 1.1811750230698246, "grad_norm": 0.227505376782934, "learning_rate": 1.963730269539416e-05, "loss": 0.3832, "step": 3840 }, { "epoch": 1.1842509996924022, "grad_norm": 0.23354864757228005, "learning_rate": 1.9513163436447306e-05, "loss": 0.3866, "step": 3850 }, { "epoch": 1.18732697631498, "grad_norm": 0.19240652070904704, "learning_rate": 1.938916615066355e-05, "loss": 0.3839, "step": 3860 }, { "epoch": 1.1904029529375577, "grad_norm": 0.21890809696557617, "learning_rate": 1.9265314046501297e-05, "loss": 0.39, "step": 3870 }, { "epoch": 1.1934789295601353, "grad_norm": 0.1976676642844691, "learning_rate": 1.9141610328662343e-05, "loss": 0.382, "step": 3880 }, { "epoch": 1.196554906182713, "grad_norm": 0.22547320555894454, "learning_rate": 1.9018058198008953e-05, "loss": 0.3866, "step": 3890 }, { "epoch": 1.1996308828052906, "grad_norm": 0.20489398615619359, "learning_rate": 1.889466085148104e-05, "loss": 0.3868, "step": 3900 }, { "epoch": 1.2027068594278683, "grad_norm": 0.1984957456686172, "learning_rate": 1.8771421482013428e-05, "loss": 0.3862, "step": 3910 }, { "epoch": 1.205782836050446, "grad_norm": 0.2027680483455971, "learning_rate": 1.8648343278453272e-05, "loss": 0.3852, "step": 3920 }, { "epoch": 1.2088588126730238, "grad_norm": 0.20619765232468662, "learning_rate": 1.8525429425477504e-05, "loss": 0.3907, "step": 3930 }, { "epoch": 1.2119347892956014, "grad_norm": 0.22837865573576374, "learning_rate": 1.8402683103510454e-05, "loss": 0.3897, "step": 3940 }, { "epoch": 1.215010765918179, "grad_norm": 0.20322659579048194, "learning_rate": 1.828010748864155e-05, "loss": 0.3869, "step": 3950 }, { "epoch": 1.2180867425407567, "grad_norm": 0.21312000026583883, "learning_rate": 1.815770575254313e-05, "loss": 0.3865, "step": 3960 }, { "epoch": 1.2211627191633343, "grad_norm": 0.19993659262572672, "learning_rate": 1.8035481062388386e-05, "loss": 0.3867, "step": 3970 }, { "epoch": 1.224238695785912, "grad_norm": 0.18631738206574236, "learning_rate": 1.7913436580769393e-05, "loss": 0.3872, "step": 3980 }, { "epoch": 1.2273146724084896, "grad_norm": 0.20082920518173658, "learning_rate": 1.7791575465615294e-05, "loss": 0.3876, "step": 3990 }, { "epoch": 1.2303906490310674, "grad_norm": 0.19562238959728473, "learning_rate": 1.76699008701106e-05, "loss": 0.3828, "step": 4000 }, { "epoch": 1.233466625653645, "grad_norm": 0.20731136186347882, "learning_rate": 1.7548415942613545e-05, "loss": 0.3919, "step": 4010 }, { "epoch": 1.2365426022762227, "grad_norm": 0.19542369091635767, "learning_rate": 1.7427123826574687e-05, "loss": 0.3815, "step": 4020 }, { "epoch": 1.2396185788988003, "grad_norm": 0.19176201000179355, "learning_rate": 1.7306027660455544e-05, "loss": 0.3887, "step": 4030 }, { "epoch": 1.242694555521378, "grad_norm": 0.21038302347242005, "learning_rate": 1.7185130577647374e-05, "loss": 0.3879, "step": 4040 }, { "epoch": 1.2457705321439556, "grad_norm": 0.19223972753036964, "learning_rate": 1.706443570639011e-05, "loss": 0.3825, "step": 4050 }, { "epoch": 1.2488465087665335, "grad_norm": 0.21141702267841592, "learning_rate": 1.694394616969142e-05, "loss": 0.3913, "step": 4060 }, { "epoch": 1.251922485389111, "grad_norm": 0.2121508025435292, "learning_rate": 1.6823665085245894e-05, "loss": 0.3868, "step": 4070 }, { "epoch": 1.2549984620116887, "grad_norm": 0.2346257177517735, "learning_rate": 1.6703595565354363e-05, "loss": 0.3872, "step": 4080 }, { "epoch": 1.2580744386342664, "grad_norm": 0.1986767027549385, "learning_rate": 1.658374071684337e-05, "loss": 0.3814, "step": 4090 }, { "epoch": 1.261150415256844, "grad_norm": 0.2191573036304933, "learning_rate": 1.646410364098482e-05, "loss": 0.3839, "step": 4100 }, { "epoch": 1.2642263918794217, "grad_norm": 0.22504715617187088, "learning_rate": 1.6344687433415657e-05, "loss": 0.3867, "step": 4110 }, { "epoch": 1.2673023685019995, "grad_norm": 0.21110461544341425, "learning_rate": 1.6225495184057832e-05, "loss": 0.389, "step": 4120 }, { "epoch": 1.270378345124577, "grad_norm": 0.214706858550216, "learning_rate": 1.610652997703832e-05, "loss": 0.3844, "step": 4130 }, { "epoch": 1.2734543217471548, "grad_norm": 0.19310840544648109, "learning_rate": 1.598779489060933e-05, "loss": 0.3904, "step": 4140 }, { "epoch": 1.2765302983697324, "grad_norm": 0.19397519118000897, "learning_rate": 1.5869292997068634e-05, "loss": 0.385, "step": 4150 }, { "epoch": 1.27960627499231, "grad_norm": 0.2009464878574868, "learning_rate": 1.5751027362680103e-05, "loss": 0.3819, "step": 4160 }, { "epoch": 1.2826822516148877, "grad_norm": 0.20339638395387397, "learning_rate": 1.5633001047594324e-05, "loss": 0.3837, "step": 4170 }, { "epoch": 1.2857582282374653, "grad_norm": 0.19840082796094954, "learning_rate": 1.5515217105769468e-05, "loss": 0.3831, "step": 4180 }, { "epoch": 1.2888342048600432, "grad_norm": 0.19903140769004213, "learning_rate": 1.5397678584892218e-05, "loss": 0.3841, "step": 4190 }, { "epoch": 1.2919101814826206, "grad_norm": 0.2156717812756053, "learning_rate": 1.528038852629895e-05, "loss": 0.3881, "step": 4200 }, { "epoch": 1.2949861581051985, "grad_norm": 0.22815609465354866, "learning_rate": 1.5163349964897e-05, "loss": 0.3923, "step": 4210 }, { "epoch": 1.298062134727776, "grad_norm": 0.20566147938052048, "learning_rate": 1.504656592908619e-05, "loss": 0.3825, "step": 4220 }, { "epoch": 1.3011381113503537, "grad_norm": 0.20194865630889147, "learning_rate": 1.4930039440680405e-05, "loss": 0.3884, "step": 4230 }, { "epoch": 1.3042140879729314, "grad_norm": 0.19551574938447552, "learning_rate": 1.4813773514829437e-05, "loss": 0.3808, "step": 4240 }, { "epoch": 1.307290064595509, "grad_norm": 0.20167265012269547, "learning_rate": 1.4697771159940977e-05, "loss": 0.3846, "step": 4250 }, { "epoch": 1.3103660412180869, "grad_norm": 0.1949331440469729, "learning_rate": 1.4582035377602737e-05, "loss": 0.3882, "step": 4260 }, { "epoch": 1.3134420178406643, "grad_norm": 0.20597576717851226, "learning_rate": 1.4466569162504806e-05, "loss": 0.3831, "step": 4270 }, { "epoch": 1.3165179944632421, "grad_norm": 0.1975542819016877, "learning_rate": 1.4351375502362178e-05, "loss": 0.385, "step": 4280 }, { "epoch": 1.3195939710858198, "grad_norm": 0.2018732578971448, "learning_rate": 1.4236457377837397e-05, "loss": 0.3826, "step": 4290 }, { "epoch": 1.3226699477083974, "grad_norm": 0.19462859934712165, "learning_rate": 1.412181776246348e-05, "loss": 0.3816, "step": 4300 }, { "epoch": 1.325745924330975, "grad_norm": 0.18470197363579477, "learning_rate": 1.4007459622566931e-05, "loss": 0.3738, "step": 4310 }, { "epoch": 1.3288219009535527, "grad_norm": 0.22075856733024019, "learning_rate": 1.3893385917191049e-05, "loss": 0.3875, "step": 4320 }, { "epoch": 1.3318978775761305, "grad_norm": 0.20808552863680496, "learning_rate": 1.3779599598019282e-05, "loss": 0.3843, "step": 4330 }, { "epoch": 1.334973854198708, "grad_norm": 0.2025453660003593, "learning_rate": 1.3666103609298935e-05, "loss": 0.3827, "step": 4340 }, { "epoch": 1.3380498308212858, "grad_norm": 0.1883220047932982, "learning_rate": 1.3552900887764915e-05, "loss": 0.3849, "step": 4350 }, { "epoch": 1.3411258074438634, "grad_norm": 0.20112183106164316, "learning_rate": 1.3439994362563773e-05, "loss": 0.3844, "step": 4360 }, { "epoch": 1.344201784066441, "grad_norm": 0.20480360254745844, "learning_rate": 1.3327386955177937e-05, "loss": 0.3848, "step": 4370 }, { "epoch": 1.3472777606890187, "grad_norm": 0.20998994795310907, "learning_rate": 1.3215081579350058e-05, "loss": 0.381, "step": 4380 }, { "epoch": 1.3503537373115964, "grad_norm": 0.1943536770799362, "learning_rate": 1.3103081141007692e-05, "loss": 0.3848, "step": 4390 }, { "epoch": 1.3534297139341742, "grad_norm": 0.18424640038238516, "learning_rate": 1.299138853818802e-05, "loss": 0.387, "step": 4400 }, { "epoch": 1.3565056905567516, "grad_norm": 0.1834929490843933, "learning_rate": 1.2880006660962957e-05, "loss": 0.3837, "step": 4410 }, { "epoch": 1.3595816671793295, "grad_norm": 0.19574125983689916, "learning_rate": 1.276893839136428e-05, "loss": 0.3872, "step": 4420 }, { "epoch": 1.3626576438019071, "grad_norm": 0.1944698772590701, "learning_rate": 1.2658186603309109e-05, "loss": 0.388, "step": 4430 }, { "epoch": 1.3657336204244848, "grad_norm": 0.18524039454282745, "learning_rate": 1.2547754162525549e-05, "loss": 0.3874, "step": 4440 }, { "epoch": 1.3688095970470624, "grad_norm": 0.18769215926583024, "learning_rate": 1.243764392647849e-05, "loss": 0.391, "step": 4450 }, { "epoch": 1.37188557366964, "grad_norm": 0.20254110195383346, "learning_rate": 1.2327858744295734e-05, "loss": 0.3869, "step": 4460 }, { "epoch": 1.374961550292218, "grad_norm": 0.1870015436618236, "learning_rate": 1.2218401456694203e-05, "loss": 0.3902, "step": 4470 }, { "epoch": 1.3780375269147955, "grad_norm": 0.1971754624154372, "learning_rate": 1.2109274895906523e-05, "loss": 0.386, "step": 4480 }, { "epoch": 1.3811135035373732, "grad_norm": 0.1758816201671691, "learning_rate": 1.2000481885607606e-05, "loss": 0.3814, "step": 4490 }, { "epoch": 1.3841894801599508, "grad_norm": 0.1975636310895604, "learning_rate": 1.189202524084175e-05, "loss": 0.3769, "step": 4500 }, { "epoch": 1.3872654567825284, "grad_norm": 0.199724185746266, "learning_rate": 1.1783907767949667e-05, "loss": 0.39, "step": 4510 }, { "epoch": 1.390341433405106, "grad_norm": 0.191185866478401, "learning_rate": 1.1676132264495949e-05, "loss": 0.388, "step": 4520 }, { "epoch": 1.3934174100276837, "grad_norm": 0.1989264397989822, "learning_rate": 1.1568701519196615e-05, "loss": 0.3806, "step": 4530 }, { "epoch": 1.3964933866502616, "grad_norm": 0.1877046086108535, "learning_rate": 1.1461618311847031e-05, "loss": 0.3815, "step": 4540 }, { "epoch": 1.3995693632728392, "grad_norm": 0.19691738584801066, "learning_rate": 1.1354885413249902e-05, "loss": 0.3855, "step": 4550 }, { "epoch": 1.4026453398954168, "grad_norm": 0.18729594765550173, "learning_rate": 1.1248505585143617e-05, "loss": 0.3829, "step": 4560 }, { "epoch": 1.4057213165179945, "grad_norm": 0.19183289561993067, "learning_rate": 1.1142481580130814e-05, "loss": 0.3839, "step": 4570 }, { "epoch": 1.4087972931405721, "grad_norm": 0.20430723945638488, "learning_rate": 1.1036816141607086e-05, "loss": 0.3835, "step": 4580 }, { "epoch": 1.4118732697631498, "grad_norm": 0.20005815929351267, "learning_rate": 1.0931512003690075e-05, "loss": 0.3796, "step": 4590 }, { "epoch": 1.4149492463857274, "grad_norm": 0.18393456883385553, "learning_rate": 1.0826571891148644e-05, "loss": 0.3812, "step": 4600 }, { "epoch": 1.4180252230083052, "grad_norm": 0.17849759957904504, "learning_rate": 1.072199851933246e-05, "loss": 0.3814, "step": 4610 }, { "epoch": 1.4211011996308829, "grad_norm": 0.19388173782019105, "learning_rate": 1.0617794594101654e-05, "loss": 0.3884, "step": 4620 }, { "epoch": 1.4241771762534605, "grad_norm": 0.19320960423670805, "learning_rate": 1.0513962811756848e-05, "loss": 0.3843, "step": 4630 }, { "epoch": 1.4272531528760382, "grad_norm": 0.18594676635406407, "learning_rate": 1.0410505858969405e-05, "loss": 0.379, "step": 4640 }, { "epoch": 1.4303291294986158, "grad_norm": 0.189448993998703, "learning_rate": 1.0307426412711848e-05, "loss": 0.3872, "step": 4650 }, { "epoch": 1.4334051061211934, "grad_norm": 0.19765048594617932, "learning_rate": 1.0204727140188672e-05, "loss": 0.3816, "step": 4660 }, { "epoch": 1.436481082743771, "grad_norm": 0.19897027824148575, "learning_rate": 1.0102410698767262e-05, "loss": 0.3806, "step": 4670 }, { "epoch": 1.439557059366349, "grad_norm": 0.18104326950011984, "learning_rate": 1.000047973590916e-05, "loss": 0.3793, "step": 4680 }, { "epoch": 1.4426330359889266, "grad_norm": 0.1838991914200798, "learning_rate": 9.898936889101565e-06, "loss": 0.38, "step": 4690 }, { "epoch": 1.4457090126115042, "grad_norm": 0.1746085659630021, "learning_rate": 9.797784785789102e-06, "loss": 0.3866, "step": 4700 }, { "epoch": 1.4487849892340818, "grad_norm": 0.18200476657398937, "learning_rate": 9.697026043305784e-06, "loss": 0.3826, "step": 4710 }, { "epoch": 1.4518609658566595, "grad_norm": 0.18218393693178678, "learning_rate": 9.596663268807357e-06, "loss": 0.3788, "step": 4720 }, { "epoch": 1.454936942479237, "grad_norm": 0.17749228025386887, "learning_rate": 9.496699059203782e-06, "loss": 0.3857, "step": 4730 }, { "epoch": 1.4580129191018147, "grad_norm": 0.18296700283462913, "learning_rate": 9.397136001092053e-06, "loss": 0.3855, "step": 4740 }, { "epoch": 1.4610888957243926, "grad_norm": 0.1787824565676016, "learning_rate": 9.29797667068931e-06, "loss": 0.3797, "step": 4750 }, { "epoch": 1.4641648723469702, "grad_norm": 0.17819896978272476, "learning_rate": 9.199223633766105e-06, "loss": 0.3832, "step": 4760 }, { "epoch": 1.4672408489695479, "grad_norm": 0.1819088078220807, "learning_rate": 9.10087944558009e-06, "loss": 0.3789, "step": 4770 }, { "epoch": 1.4703168255921255, "grad_norm": 0.17734397583383743, "learning_rate": 9.002946650809829e-06, "loss": 0.3774, "step": 4780 }, { "epoch": 1.4733928022147031, "grad_norm": 0.1859932173142885, "learning_rate": 8.905427783489015e-06, "loss": 0.3848, "step": 4790 }, { "epoch": 1.4764687788372808, "grad_norm": 0.18458255474314855, "learning_rate": 8.808325366940848e-06, "loss": 0.3832, "step": 4800 }, { "epoch": 1.4795447554598584, "grad_norm": 0.17781262616472937, "learning_rate": 8.711641913712787e-06, "loss": 0.3787, "step": 4810 }, { "epoch": 1.4826207320824363, "grad_norm": 0.18221194794428386, "learning_rate": 8.61537992551151e-06, "loss": 0.3806, "step": 4820 }, { "epoch": 1.485696708705014, "grad_norm": 0.18104267852415398, "learning_rate": 8.51954189313818e-06, "loss": 0.3808, "step": 4830 }, { "epoch": 1.4887726853275915, "grad_norm": 0.1757759186001299, "learning_rate": 8.42413029642403e-06, "loss": 0.3759, "step": 4840 }, { "epoch": 1.4918486619501692, "grad_norm": 0.17963632764425608, "learning_rate": 8.329147604166141e-06, "loss": 0.3812, "step": 4850 }, { "epoch": 1.4949246385727468, "grad_norm": 0.18958582199499202, "learning_rate": 8.234596274063624e-06, "loss": 0.3815, "step": 4860 }, { "epoch": 1.4980006151953245, "grad_norm": 0.1817637093203124, "learning_rate": 8.140478752653977e-06, "loss": 0.3801, "step": 4870 }, { "epoch": 1.501076591817902, "grad_norm": 0.18452109012171894, "learning_rate": 8.046797475249793e-06, "loss": 0.3852, "step": 4880 }, { "epoch": 1.50415256844048, "grad_norm": 0.17918219978503566, "learning_rate": 7.953554865875753e-06, "loss": 0.3804, "step": 4890 }, { "epoch": 1.5072285450630574, "grad_norm": 0.18123345402497515, "learning_rate": 7.860753337205923e-06, "loss": 0.3801, "step": 4900 }, { "epoch": 1.5103045216856352, "grad_norm": 0.1881162660434552, "learning_rate": 7.768395290501269e-06, "loss": 0.3823, "step": 4910 }, { "epoch": 1.5133804983082129, "grad_norm": 0.17377100168237414, "learning_rate": 7.676483115547592e-06, "loss": 0.3826, "step": 4920 }, { "epoch": 1.5164564749307905, "grad_norm": 0.17534636421053884, "learning_rate": 7.585019190593639e-06, "loss": 0.3797, "step": 4930 }, { "epoch": 1.5195324515533684, "grad_norm": 0.19069154947005085, "learning_rate": 7.494005882289576e-06, "loss": 0.3815, "step": 4940 }, { "epoch": 1.5226084281759458, "grad_norm": 0.17095332706482907, "learning_rate": 7.403445545625793e-06, "loss": 0.3744, "step": 4950 }, { "epoch": 1.5256844047985236, "grad_norm": 0.17970390946663692, "learning_rate": 7.313340523871895e-06, "loss": 0.3773, "step": 4960 }, { "epoch": 1.528760381421101, "grad_norm": 0.18698656857950285, "learning_rate": 7.223693148516142e-06, "loss": 0.3785, "step": 4970 }, { "epoch": 1.531836358043679, "grad_norm": 0.17938802785709124, "learning_rate": 7.1345057392050555e-06, "loss": 0.3796, "step": 4980 }, { "epoch": 1.5349123346662565, "grad_norm": 0.18162474454893016, "learning_rate": 7.045780603683466e-06, "loss": 0.379, "step": 4990 }, { "epoch": 1.5379883112888342, "grad_norm": 0.18198091440471087, "learning_rate": 6.9575200377347355e-06, "loss": 0.3813, "step": 5000 }, { "epoch": 1.541064287911412, "grad_norm": 0.18419941706837514, "learning_rate": 6.869726325121378e-06, "loss": 0.3785, "step": 5010 }, { "epoch": 1.5441402645339894, "grad_norm": 0.16661901807619756, "learning_rate": 6.782401737526001e-06, "loss": 0.383, "step": 5020 }, { "epoch": 1.5472162411565673, "grad_norm": 0.17453093032211522, "learning_rate": 6.695548534492452e-06, "loss": 0.3779, "step": 5030 }, { "epoch": 1.5502922177791447, "grad_norm": 0.17711909055093328, "learning_rate": 6.609168963367435e-06, "loss": 0.3788, "step": 5040 }, { "epoch": 1.5533681944017226, "grad_norm": 0.18263806478054573, "learning_rate": 6.523265259242281e-06, "loss": 0.3774, "step": 5050 }, { "epoch": 1.5564441710243002, "grad_norm": 0.1696090151410719, "learning_rate": 6.437839644895199e-06, "loss": 0.3811, "step": 5060 }, { "epoch": 1.5595201476468779, "grad_norm": 0.1737953495096369, "learning_rate": 6.352894330733653e-06, "loss": 0.381, "step": 5070 }, { "epoch": 1.5625961242694557, "grad_norm": 0.1694945119981669, "learning_rate": 6.268431514737283e-06, "loss": 0.3748, "step": 5080 }, { "epoch": 1.5656721008920331, "grad_norm": 0.17262233384252543, "learning_rate": 6.1844533824009485e-06, "loss": 0.3827, "step": 5090 }, { "epoch": 1.568748077514611, "grad_norm": 0.1793899748233061, "learning_rate": 6.100962106678224e-06, "loss": 0.3796, "step": 5100 }, { "epoch": 1.5718240541371884, "grad_norm": 0.17130098181554668, "learning_rate": 6.0179598479251365e-06, "loss": 0.3801, "step": 5110 }, { "epoch": 1.5749000307597663, "grad_norm": 0.18012331974555248, "learning_rate": 5.935448753844314e-06, "loss": 0.381, "step": 5120 }, { "epoch": 1.577976007382344, "grad_norm": 0.1711371460831584, "learning_rate": 5.853430959429359e-06, "loss": 0.3781, "step": 5130 }, { "epoch": 1.5810519840049215, "grad_norm": 0.1774474117143097, "learning_rate": 5.771908586909638e-06, "loss": 0.3795, "step": 5140 }, { "epoch": 1.5841279606274994, "grad_norm": 0.17278171688199767, "learning_rate": 5.6908837456953774e-06, "loss": 0.3787, "step": 5150 }, { "epoch": 1.5872039372500768, "grad_norm": 0.18348100615480664, "learning_rate": 5.61035853232304e-06, "loss": 0.3761, "step": 5160 }, { "epoch": 1.5902799138726547, "grad_norm": 0.16745127720861464, "learning_rate": 5.530335030401129e-06, "loss": 0.3754, "step": 5170 }, { "epoch": 1.593355890495232, "grad_norm": 0.1750464693379638, "learning_rate": 5.450815310556226e-06, "loss": 0.3752, "step": 5180 }, { "epoch": 1.59643186711781, "grad_norm": 0.1733092253571523, "learning_rate": 5.371801430379452e-06, "loss": 0.3725, "step": 5190 }, { "epoch": 1.5995078437403876, "grad_norm": 0.19021470802855867, "learning_rate": 5.293295434373202e-06, "loss": 0.3815, "step": 5200 }, { "epoch": 1.6025838203629652, "grad_norm": 0.17604261468067514, "learning_rate": 5.21529935389824e-06, "loss": 0.3812, "step": 5210 }, { "epoch": 1.605659796985543, "grad_norm": 0.17662891681036957, "learning_rate": 5.137815207121174e-06, "loss": 0.3796, "step": 5220 }, { "epoch": 1.6087357736081205, "grad_norm": 0.18070750229446214, "learning_rate": 5.06084499896218e-06, "loss": 0.3811, "step": 5230 }, { "epoch": 1.6118117502306983, "grad_norm": 0.181090287867875, "learning_rate": 4.984390721043186e-06, "loss": 0.3829, "step": 5240 }, { "epoch": 1.6148877268532758, "grad_norm": 0.17869753928912405, "learning_rate": 4.908454351636274e-06, "loss": 0.3798, "step": 5250 }, { "epoch": 1.6179637034758536, "grad_norm": 0.17792714065463655, "learning_rate": 4.833037855612544e-06, "loss": 0.376, "step": 5260 }, { "epoch": 1.6210396800984312, "grad_norm": 0.1698114512961887, "learning_rate": 4.758143184391236e-06, "loss": 0.3812, "step": 5270 }, { "epoch": 1.6241156567210089, "grad_norm": 0.17332522343723983, "learning_rate": 4.683772275889276e-06, "loss": 0.382, "step": 5280 }, { "epoch": 1.6271916333435867, "grad_norm": 0.17508239300736642, "learning_rate": 4.609927054471083e-06, "loss": 0.3793, "step": 5290 }, { "epoch": 1.6302676099661642, "grad_norm": 0.17358296907254872, "learning_rate": 4.536609430898825e-06, "loss": 0.3816, "step": 5300 }, { "epoch": 1.633343586588742, "grad_norm": 0.16890470291506013, "learning_rate": 4.463821302282936e-06, "loss": 0.3778, "step": 5310 }, { "epoch": 1.6364195632113194, "grad_norm": 0.17693540150854822, "learning_rate": 4.391564552033048e-06, "loss": 0.374, "step": 5320 }, { "epoch": 1.6394955398338973, "grad_norm": 0.17516513163275893, "learning_rate": 4.319841049809267e-06, "loss": 0.3741, "step": 5330 }, { "epoch": 1.642571516456475, "grad_norm": 0.1624965132468124, "learning_rate": 4.248652651473769e-06, "loss": 0.3788, "step": 5340 }, { "epoch": 1.6456474930790526, "grad_norm": 0.17573131491276656, "learning_rate": 4.178001199042811e-06, "loss": 0.379, "step": 5350 }, { "epoch": 1.6487234697016304, "grad_norm": 0.17424714706820227, "learning_rate": 4.107888520639022e-06, "loss": 0.3805, "step": 5360 }, { "epoch": 1.6517994463242078, "grad_norm": 0.17108082923481854, "learning_rate": 4.038316430444164e-06, "loss": 0.3774, "step": 5370 }, { "epoch": 1.6548754229467857, "grad_norm": 0.16500066706057875, "learning_rate": 3.969286728652122e-06, "loss": 0.378, "step": 5380 }, { "epoch": 1.6579513995693633, "grad_norm": 0.1781193527124994, "learning_rate": 3.90080120142238e-06, "loss": 0.3779, "step": 5390 }, { "epoch": 1.661027376191941, "grad_norm": 0.163603120211928, "learning_rate": 3.832861620833766e-06, "loss": 0.3723, "step": 5400 }, { "epoch": 1.6641033528145186, "grad_norm": 0.17733238803436224, "learning_rate": 3.7654697448386123e-06, "loss": 0.3801, "step": 5410 }, { "epoch": 1.6671793294370962, "grad_norm": 0.17106340647524798, "learning_rate": 3.698627317217282e-06, "loss": 0.3776, "step": 5420 }, { "epoch": 1.670255306059674, "grad_norm": 0.16950104587650286, "learning_rate": 3.6323360675330124e-06, "loss": 0.3756, "step": 5430 }, { "epoch": 1.6733312826822515, "grad_norm": 0.1651954155857552, "learning_rate": 3.5665977110872077e-06, "loss": 0.3811, "step": 5440 }, { "epoch": 1.6764072593048294, "grad_norm": 0.1635332832589143, "learning_rate": 3.501413948875021e-06, "loss": 0.3784, "step": 5450 }, { "epoch": 1.679483235927407, "grad_norm": 0.1613166226797925, "learning_rate": 3.4367864675413477e-06, "loss": 0.3772, "step": 5460 }, { "epoch": 1.6825592125499846, "grad_norm": 0.16964918011551358, "learning_rate": 3.372716939337184e-06, "loss": 0.3767, "step": 5470 }, { "epoch": 1.6856351891725623, "grad_norm": 0.17228959128915589, "learning_rate": 3.3092070220763798e-06, "loss": 0.3794, "step": 5480 }, { "epoch": 1.68871116579514, "grad_norm": 0.1679461184222492, "learning_rate": 3.2462583590926993e-06, "loss": 0.3789, "step": 5490 }, { "epoch": 1.6917871424177178, "grad_norm": 0.17638000505832302, "learning_rate": 3.1838725791973446e-06, "loss": 0.3853, "step": 5500 }, { "epoch": 1.6948631190402952, "grad_norm": 0.15772893887103714, "learning_rate": 3.1220512966367715e-06, "loss": 0.3855, "step": 5510 }, { "epoch": 1.697939095662873, "grad_norm": 0.17788389154452022, "learning_rate": 3.060796111050934e-06, "loss": 0.3762, "step": 5520 }, { "epoch": 1.7010150722854507, "grad_norm": 0.16495460017983163, "learning_rate": 3.00010860743192e-06, "loss": 0.376, "step": 5530 }, { "epoch": 1.7040910489080283, "grad_norm": 0.1594931530936976, "learning_rate": 2.9399903560828805e-06, "loss": 0.3796, "step": 5540 }, { "epoch": 1.707167025530606, "grad_norm": 0.173314711242124, "learning_rate": 2.8804429125774717e-06, "loss": 0.3853, "step": 5550 }, { "epoch": 1.7102430021531836, "grad_norm": 0.17123036632116867, "learning_rate": 2.821467817719528e-06, "loss": 0.3756, "step": 5560 }, { "epoch": 1.7133189787757614, "grad_norm": 0.17035499657669817, "learning_rate": 2.7630665975032584e-06, "loss": 0.3731, "step": 5570 }, { "epoch": 1.7163949553983389, "grad_norm": 0.16483800826752656, "learning_rate": 2.7052407630737187e-06, "loss": 0.3795, "step": 5580 }, { "epoch": 1.7194709320209167, "grad_norm": 0.16200292362470808, "learning_rate": 2.647991810687722e-06, "loss": 0.3771, "step": 5590 }, { "epoch": 1.7225469086434944, "grad_norm": 0.1658753293468661, "learning_rate": 2.5913212216751444e-06, "loss": 0.3856, "step": 5600 }, { "epoch": 1.725622885266072, "grad_norm": 0.1648362593305203, "learning_rate": 2.535230462400548e-06, "loss": 0.3772, "step": 5610 }, { "epoch": 1.7286988618886496, "grad_norm": 0.16932296728113527, "learning_rate": 2.479720984225292e-06, "loss": 0.3793, "step": 5620 }, { "epoch": 1.7317748385112273, "grad_norm": 0.16280451658882483, "learning_rate": 2.424794223469937e-06, "loss": 0.3794, "step": 5630 }, { "epoch": 1.7348508151338051, "grad_norm": 0.16717841333490555, "learning_rate": 2.3704516013771076e-06, "loss": 0.3784, "step": 5640 }, { "epoch": 1.7379267917563825, "grad_norm": 0.1679225136248305, "learning_rate": 2.316694524074689e-06, "loss": 0.3736, "step": 5650 }, { "epoch": 1.7410027683789604, "grad_norm": 0.16311949396572148, "learning_rate": 2.263524382539481e-06, "loss": 0.375, "step": 5660 }, { "epoch": 1.744078745001538, "grad_norm": 0.16719834298613814, "learning_rate": 2.2109425525611628e-06, "loss": 0.3804, "step": 5670 }, { "epoch": 1.7471547216241157, "grad_norm": 0.1718886856461429, "learning_rate": 2.1589503947067353e-06, "loss": 0.3785, "step": 5680 }, { "epoch": 1.7502306982466933, "grad_norm": 0.16120546686010728, "learning_rate": 2.107549254285285e-06, "loss": 0.3812, "step": 5690 }, { "epoch": 1.753306674869271, "grad_norm": 0.16213786125928695, "learning_rate": 2.0567404613131945e-06, "loss": 0.3776, "step": 5700 }, { "epoch": 1.7563826514918488, "grad_norm": 0.1773547685814576, "learning_rate": 2.006525330479711e-06, "loss": 0.3855, "step": 5710 }, { "epoch": 1.7594586281144262, "grad_norm": 0.17036753885332126, "learning_rate": 1.9569051611129373e-06, "loss": 0.3765, "step": 5720 }, { "epoch": 1.762534604737004, "grad_norm": 0.17178948070084854, "learning_rate": 1.907881237146225e-06, "loss": 0.3802, "step": 5730 }, { "epoch": 1.7656105813595817, "grad_norm": 0.15713951933485215, "learning_rate": 1.8594548270849111e-06, "loss": 0.3788, "step": 5740 }, { "epoch": 1.7686865579821593, "grad_norm": 0.1577333245783215, "learning_rate": 1.8116271839735549e-06, "loss": 0.3801, "step": 5750 }, { "epoch": 1.771762534604737, "grad_norm": 0.16883802845846965, "learning_rate": 1.7643995453634544e-06, "loss": 0.3819, "step": 5760 }, { "epoch": 1.7748385112273146, "grad_norm": 0.16433365820545723, "learning_rate": 1.717773133280673e-06, "loss": 0.3792, "step": 5770 }, { "epoch": 1.7779144878498925, "grad_norm": 0.168855174200017, "learning_rate": 1.6717491541943852e-06, "loss": 0.3816, "step": 5780 }, { "epoch": 1.78099046447247, "grad_norm": 0.16694439318774887, "learning_rate": 1.626328798985674e-06, "loss": 0.3835, "step": 5790 }, { "epoch": 1.7840664410950478, "grad_norm": 0.15848527525721867, "learning_rate": 1.5815132429167296e-06, "loss": 0.3825, "step": 5800 }, { "epoch": 1.7871424177176254, "grad_norm": 0.15962380636045553, "learning_rate": 1.537303645600402e-06, "loss": 0.3746, "step": 5810 }, { "epoch": 1.790218394340203, "grad_norm": 0.15782946059082317, "learning_rate": 1.493701150970242e-06, "loss": 0.3829, "step": 5820 }, { "epoch": 1.7932943709627807, "grad_norm": 0.1666239867639945, "learning_rate": 1.4507068872508605e-06, "loss": 0.3771, "step": 5830 }, { "epoch": 1.7963703475853583, "grad_norm": 0.15671683723505944, "learning_rate": 1.4083219669287634e-06, "loss": 0.3779, "step": 5840 }, { "epoch": 1.7994463242079362, "grad_norm": 0.16141093778323723, "learning_rate": 1.3665474867235407e-06, "loss": 0.379, "step": 5850 }, { "epoch": 1.8025223008305136, "grad_norm": 0.17103425516662168, "learning_rate": 1.3253845275595283e-06, "loss": 0.3769, "step": 5860 }, { "epoch": 1.8055982774530914, "grad_norm": 0.160259772467565, "learning_rate": 1.2848341545377895e-06, "loss": 0.379, "step": 5870 }, { "epoch": 1.808674254075669, "grad_norm": 0.15982189312052736, "learning_rate": 1.2448974169085969e-06, "loss": 0.3734, "step": 5880 }, { "epoch": 1.8117502306982467, "grad_norm": 0.15742534806025435, "learning_rate": 1.2055753480442578e-06, "loss": 0.378, "step": 5890 }, { "epoch": 1.8148262073208243, "grad_norm": 0.16850465310904617, "learning_rate": 1.1668689654123765e-06, "loss": 0.3792, "step": 5900 }, { "epoch": 1.817902183943402, "grad_norm": 0.163396736245504, "learning_rate": 1.1287792705495542e-06, "loss": 0.3797, "step": 5910 }, { "epoch": 1.8209781605659798, "grad_norm": 0.16061127005265838, "learning_rate": 1.091307249035431e-06, "loss": 0.3765, "step": 5920 }, { "epoch": 1.8240541371885572, "grad_norm": 0.15656667923287182, "learning_rate": 1.054453870467223e-06, "loss": 0.3761, "step": 5930 }, { "epoch": 1.827130113811135, "grad_norm": 0.16450212878978707, "learning_rate": 1.0182200884346044e-06, "loss": 0.3743, "step": 5940 }, { "epoch": 1.8302060904337127, "grad_norm": 0.15511980735925096, "learning_rate": 9.826068404950594e-07, "loss": 0.374, "step": 5950 }, { "epoch": 1.8332820670562904, "grad_norm": 0.161355127326318, "learning_rate": 9.476150481495971e-07, "loss": 0.3803, "step": 5960 }, { "epoch": 1.836358043678868, "grad_norm": 0.1541570973035994, "learning_rate": 9.13245616818928e-07, "loss": 0.3753, "step": 5970 }, { "epoch": 1.8394340203014456, "grad_norm": 0.1533692278143353, "learning_rate": 8.794994358200248e-07, "loss": 0.3767, "step": 5980 }, { "epoch": 1.8425099969240235, "grad_norm": 0.160449666444894, "learning_rate": 8.463773783431078e-07, "loss": 0.3764, "step": 5990 }, { "epoch": 1.845585973546601, "grad_norm": 0.16207676542778404, "learning_rate": 8.13880301429068e-07, "loss": 0.3785, "step": 6000 }, { "epoch": 1.8486619501691788, "grad_norm": 0.16307596948796624, "learning_rate": 7.820090459472712e-07, "loss": 0.378, "step": 6010 }, { "epoch": 1.8517379267917564, "grad_norm": 0.1585871114887087, "learning_rate": 7.507644365738197e-07, "loss": 0.3793, "step": 6020 }, { "epoch": 1.854813903414334, "grad_norm": 0.16769146290304218, "learning_rate": 7.201472817701894e-07, "loss": 0.3758, "step": 6030 }, { "epoch": 1.8578898800369117, "grad_norm": 0.15386680624417517, "learning_rate": 6.901583737623341e-07, "loss": 0.3786, "step": 6040 }, { "epoch": 1.8609658566594893, "grad_norm": 0.16246077624362118, "learning_rate": 6.607984885201674e-07, "loss": 0.3809, "step": 6050 }, { "epoch": 1.8640418332820672, "grad_norm": 0.1564918937329813, "learning_rate": 6.320683857375081e-07, "loss": 0.3706, "step": 6060 }, { "epoch": 1.8671178099046446, "grad_norm": 0.159271402817885, "learning_rate": 6.039688088123941e-07, "loss": 0.3789, "step": 6070 }, { "epoch": 1.8701937865272225, "grad_norm": 0.16053385713870535, "learning_rate": 5.765004848278715e-07, "loss": 0.373, "step": 6080 }, { "epoch": 1.8732697631498, "grad_norm": 0.15494612129849972, "learning_rate": 5.49664124533164e-07, "loss": 0.3772, "step": 6090 }, { "epoch": 1.8763457397723777, "grad_norm": 0.1612327779699864, "learning_rate": 5.234604223252893e-07, "loss": 0.3767, "step": 6100 }, { "epoch": 1.8794217163949554, "grad_norm": 0.1592580533960582, "learning_rate": 4.978900562310984e-07, "loss": 0.3791, "step": 6110 }, { "epoch": 1.882497693017533, "grad_norm": 0.15812148016787322, "learning_rate": 4.7295368788971286e-07, "loss": 0.3712, "step": 6120 }, { "epoch": 1.8855736696401109, "grad_norm": 0.15445243480155127, "learning_rate": 4.486519625354263e-07, "loss": 0.3799, "step": 6130 }, { "epoch": 1.8886496462626883, "grad_norm": 0.16256832353710218, "learning_rate": 4.2498550898099063e-07, "loss": 0.3778, "step": 6140 }, { "epoch": 1.8917256228852661, "grad_norm": 0.15597837474948165, "learning_rate": 4.0195493960135945e-07, "loss": 0.3826, "step": 6150 }, { "epoch": 1.8948015995078438, "grad_norm": 0.15724350447008198, "learning_rate": 3.7956085031783107e-07, "loss": 0.3789, "step": 6160 }, { "epoch": 1.8978775761304214, "grad_norm": 0.15346594817900477, "learning_rate": 3.5780382058263895e-07, "loss": 0.3862, "step": 6170 }, { "epoch": 1.900953552752999, "grad_norm": 0.157046432768475, "learning_rate": 3.366844133639496e-07, "loss": 0.3785, "step": 6180 }, { "epoch": 1.9040295293755767, "grad_norm": 0.1625388168086969, "learning_rate": 3.1620317513130214e-07, "loss": 0.387, "step": 6190 }, { "epoch": 1.9071055059981545, "grad_norm": 0.15449033096445805, "learning_rate": 2.9636063584146944e-07, "loss": 0.3772, "step": 6200 }, { "epoch": 1.910181482620732, "grad_norm": 0.16221473374256964, "learning_rate": 2.7715730892473033e-07, "loss": 0.3837, "step": 6210 }, { "epoch": 1.9132574592433098, "grad_norm": 0.1568747287847085, "learning_rate": 2.5859369127161084e-07, "loss": 0.3808, "step": 6220 }, { "epoch": 1.9163334358658874, "grad_norm": 0.1536619429160919, "learning_rate": 2.4067026321999976e-07, "loss": 0.3735, "step": 6230 }, { "epoch": 1.919409412488465, "grad_norm": 0.16261220928672063, "learning_rate": 2.2338748854273672e-07, "loss": 0.372, "step": 6240 }, { "epoch": 1.9224853891110427, "grad_norm": 0.1578747819889161, "learning_rate": 2.0674581443561047e-07, "loss": 0.3763, "step": 6250 }, { "epoch": 1.9255613657336204, "grad_norm": 0.15586846057316872, "learning_rate": 1.9074567150577648e-07, "loss": 0.3909, "step": 6260 }, { "epoch": 1.9286373423561982, "grad_norm": 0.15504903969001876, "learning_rate": 1.7538747376063257e-07, "loss": 0.3821, "step": 6270 }, { "epoch": 1.9317133189787756, "grad_norm": 0.15460242263279653, "learning_rate": 1.6067161859709135e-07, "loss": 0.3798, "step": 6280 }, { "epoch": 1.9347892956013535, "grad_norm": 0.15982468896170426, "learning_rate": 1.465984867912995e-07, "loss": 0.3828, "step": 6290 }, { "epoch": 1.9378652722239311, "grad_norm": 0.1582656822827826, "learning_rate": 1.3316844248879577e-07, "loss": 0.3762, "step": 6300 }, { "epoch": 1.9409412488465088, "grad_norm": 0.1525511060491875, "learning_rate": 1.2038183319507955e-07, "loss": 0.3783, "step": 6310 }, { "epoch": 1.9440172254690864, "grad_norm": 0.15638320065161287, "learning_rate": 1.0823898976661251e-07, "loss": 0.379, "step": 6320 }, { "epoch": 1.947093202091664, "grad_norm": 0.15867121532402426, "learning_rate": 9.67402264022782e-08, "loss": 0.3835, "step": 6330 }, { "epoch": 1.950169178714242, "grad_norm": 0.15829109403310837, "learning_rate": 8.58858406352303e-08, "loss": 0.3793, "step": 6340 }, { "epoch": 1.9532451553368193, "grad_norm": 0.15178495151721638, "learning_rate": 7.567611332520985e-08, "loss": 0.3829, "step": 6350 }, { "epoch": 1.9563211319593972, "grad_norm": 0.1616185737689612, "learning_rate": 6.611130865126769e-08, "loss": 0.3821, "step": 6360 }, { "epoch": 1.9593971085819748, "grad_norm": 0.15918562294781835, "learning_rate": 5.7191674104933865e-08, "loss": 0.3752, "step": 6370 }, { "epoch": 1.9624730852045524, "grad_norm": 0.15217614338697685, "learning_rate": 4.891744048380886e-08, "loss": 0.3786, "step": 6380 }, { "epoch": 1.96554906182713, "grad_norm": 0.1529525979109221, "learning_rate": 4.128882188560168e-08, "loss": 0.3721, "step": 6390 }, { "epoch": 1.9686250384497077, "grad_norm": 0.15057630261444405, "learning_rate": 3.4306015702581515e-08, "loss": 0.3793, "step": 6400 }, { "epoch": 1.9717010150722856, "grad_norm": 0.15869219008096552, "learning_rate": 2.7969202616465185e-08, "loss": 0.3751, "step": 6410 }, { "epoch": 1.974776991694863, "grad_norm": 0.1522888626925477, "learning_rate": 2.2278546593759718e-08, "loss": 0.3693, "step": 6420 }, { "epoch": 1.9778529683174408, "grad_norm": 0.1582933144931208, "learning_rate": 1.7234194881501907e-08, "loss": 0.3804, "step": 6430 }, { "epoch": 1.9809289449400185, "grad_norm": 0.15145601383485022, "learning_rate": 1.2836278003458546e-08, "loss": 0.3755, "step": 6440 }, { "epoch": 1.9840049215625961, "grad_norm": 0.1570613980082519, "learning_rate": 9.084909756740257e-09, "loss": 0.3758, "step": 6450 }, { "epoch": 1.9870808981851737, "grad_norm": 0.15128811614827967, "learning_rate": 5.980187208870503e-09, "loss": 0.3804, "step": 6460 }, { "epoch": 1.9901568748077514, "grad_norm": 0.15835559199003538, "learning_rate": 3.522190695262606e-09, "loss": 0.3753, "step": 6470 }, { "epoch": 1.9932328514303292, "grad_norm": 0.1516173757473364, "learning_rate": 1.7109838171408542e-09, "loss": 0.3752, "step": 6480 }, { "epoch": 1.9963088280529067, "grad_norm": 0.15693991708009467, "learning_rate": 5.466134399056966e-10, "loss": 0.376, "step": 6490 }, { "epoch": 1.9993848046754845, "grad_norm": 0.14596753576888694, "learning_rate": 2.910969190417223e-11, "loss": 0.3762, "step": 6500 }, { "epoch": 2.0, "step": 6502, "total_flos": 7602235458453504.0, "train_loss": 0.4130896302561729, "train_runtime": 242271.9548, "train_samples_per_second": 2.576, "train_steps_per_second": 0.027 } ], "logging_steps": 10, "max_steps": 6502, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 1000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 7602235458453504.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }