| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.02707275803722504, |
| "eval_steps": 500, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 10.69199342727661, |
| "epoch": 0.00013536379018612522, |
| "grad_norm": 11.5625, |
| "learning_rate": 2e-06, |
| "loss": 10.8479, |
| "mean_token_accuracy": 0.0, |
| "num_tokens": 12791.0, |
| "step": 5 |
| }, |
| { |
| "entropy": 10.691878128051759, |
| "epoch": 0.00027072758037225043, |
| "grad_norm": 11.0, |
| "learning_rate": 4.5e-06, |
| "loss": 10.8142, |
| "mean_token_accuracy": 0.0, |
| "num_tokens": 26683.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 10.691429710388183, |
| "epoch": 0.0004060913705583756, |
| "grad_norm": 9.3125, |
| "learning_rate": 7e-06, |
| "loss": 10.5672, |
| "mean_token_accuracy": 0.011101403925567865, |
| "num_tokens": 39347.0, |
| "step": 15 |
| }, |
| { |
| "entropy": 10.686277675628663, |
| "epoch": 0.0005414551607445009, |
| "grad_norm": 5.375, |
| "learning_rate": 9.5e-06, |
| "loss": 10.3174, |
| "mean_token_accuracy": 0.030114291980862618, |
| "num_tokens": 54329.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 10.660668087005615, |
| "epoch": 0.0006768189509306261, |
| "grad_norm": 4.09375, |
| "learning_rate": 1.2e-05, |
| "loss": 10.0145, |
| "mean_token_accuracy": 0.032822173461318015, |
| "num_tokens": 67393.0, |
| "step": 25 |
| }, |
| { |
| "entropy": 10.637198734283448, |
| "epoch": 0.0008121827411167512, |
| "grad_norm": 3.0625, |
| "learning_rate": 1.4500000000000002e-05, |
| "loss": 9.8798, |
| "mean_token_accuracy": 0.03450996596366167, |
| "num_tokens": 81383.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 10.631521320343017, |
| "epoch": 0.0009475465313028764, |
| "grad_norm": 2.515625, |
| "learning_rate": 1.7000000000000003e-05, |
| "loss": 9.8183, |
| "mean_token_accuracy": 0.03217146322131157, |
| "num_tokens": 95991.0, |
| "step": 35 |
| }, |
| { |
| "entropy": 10.626516151428223, |
| "epoch": 0.0010829103214890017, |
| "grad_norm": 2.515625, |
| "learning_rate": 1.95e-05, |
| "loss": 9.7088, |
| "mean_token_accuracy": 0.03352573178708553, |
| "num_tokens": 108504.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 10.627447319030761, |
| "epoch": 0.001218274111675127, |
| "grad_norm": 2.1875, |
| "learning_rate": 2.2e-05, |
| "loss": 9.7785, |
| "mean_token_accuracy": 0.030551478266716003, |
| "num_tokens": 123286.0, |
| "step": 45 |
| }, |
| { |
| "entropy": 10.629091835021972, |
| "epoch": 0.0013536379018612521, |
| "grad_norm": 2.296875, |
| "learning_rate": 2.4500000000000003e-05, |
| "loss": 9.6538, |
| "mean_token_accuracy": 0.03104141727089882, |
| "num_tokens": 135493.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 10.618868160247803, |
| "epoch": 0.0014890016920473773, |
| "grad_norm": 2.078125, |
| "learning_rate": 2.7e-05, |
| "loss": 9.6537, |
| "mean_token_accuracy": 0.03736583907157183, |
| "num_tokens": 150376.0, |
| "step": 55 |
| }, |
| { |
| "entropy": 10.596181201934815, |
| "epoch": 0.0016243654822335025, |
| "grad_norm": 2.109375, |
| "learning_rate": 2.95e-05, |
| "loss": 9.5976, |
| "mean_token_accuracy": 0.03170219026505947, |
| "num_tokens": 165805.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 10.606531143188477, |
| "epoch": 0.0017597292724196277, |
| "grad_norm": 2.09375, |
| "learning_rate": 3.2e-05, |
| "loss": 9.4608, |
| "mean_token_accuracy": 0.03743585981428623, |
| "num_tokens": 179043.0, |
| "step": 65 |
| }, |
| { |
| "entropy": 10.577856731414794, |
| "epoch": 0.0018950930626057529, |
| "grad_norm": 2.09375, |
| "learning_rate": 3.4500000000000005e-05, |
| "loss": 9.3947, |
| "mean_token_accuracy": 0.03445138856768608, |
| "num_tokens": 191847.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 10.561034107208252, |
| "epoch": 0.0020304568527918783, |
| "grad_norm": 2.125, |
| "learning_rate": 3.7e-05, |
| "loss": 9.2778, |
| "mean_token_accuracy": 0.03577356971800327, |
| "num_tokens": 207116.0, |
| "step": 75 |
| }, |
| { |
| "entropy": 10.546807861328125, |
| "epoch": 0.0021658206429780035, |
| "grad_norm": 2.03125, |
| "learning_rate": 3.95e-05, |
| "loss": 9.2156, |
| "mean_token_accuracy": 0.03288109693676233, |
| "num_tokens": 219651.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 10.532037448883056, |
| "epoch": 0.0023011844331641287, |
| "grad_norm": 2.015625, |
| "learning_rate": 4.2000000000000004e-05, |
| "loss": 9.16, |
| "mean_token_accuracy": 0.03139570262283087, |
| "num_tokens": 233183.0, |
| "step": 85 |
| }, |
| { |
| "entropy": 10.499158573150634, |
| "epoch": 0.002436548223350254, |
| "grad_norm": 2.0625, |
| "learning_rate": 4.45e-05, |
| "loss": 8.9864, |
| "mean_token_accuracy": 0.0376906756311655, |
| "num_tokens": 246291.0, |
| "step": 90 |
| }, |
| { |
| "entropy": 10.423231887817384, |
| "epoch": 0.002571912013536379, |
| "grad_norm": 2.15625, |
| "learning_rate": 4.7000000000000004e-05, |
| "loss": 8.8533, |
| "mean_token_accuracy": 0.04000245779752731, |
| "num_tokens": 259606.0, |
| "step": 95 |
| }, |
| { |
| "entropy": 10.371912956237793, |
| "epoch": 0.0027072758037225042, |
| "grad_norm": 2.0, |
| "learning_rate": 4.9500000000000004e-05, |
| "loss": 8.7521, |
| "mean_token_accuracy": 0.04012820441275835, |
| "num_tokens": 275174.0, |
| "step": 100 |
| }, |
| { |
| "entropy": 10.304845333099365, |
| "epoch": 0.0028426395939086294, |
| "grad_norm": 2.25, |
| "learning_rate": 5.2e-05, |
| "loss": 8.5952, |
| "mean_token_accuracy": 0.04803745746612549, |
| "num_tokens": 287873.0, |
| "step": 105 |
| }, |
| { |
| "entropy": 10.202454662322998, |
| "epoch": 0.0029780033840947546, |
| "grad_norm": 1.9453125, |
| "learning_rate": 5.45e-05, |
| "loss": 8.4264, |
| "mean_token_accuracy": 0.052891625463962554, |
| "num_tokens": 301243.0, |
| "step": 110 |
| }, |
| { |
| "entropy": 10.146648788452149, |
| "epoch": 0.00311336717428088, |
| "grad_norm": 2.140625, |
| "learning_rate": 5.7e-05, |
| "loss": 8.3599, |
| "mean_token_accuracy": 0.04921769984066486, |
| "num_tokens": 314246.0, |
| "step": 115 |
| }, |
| { |
| "entropy": 9.991413021087647, |
| "epoch": 0.003248730964467005, |
| "grad_norm": 1.671875, |
| "learning_rate": 5.9499999999999996e-05, |
| "loss": 8.1824, |
| "mean_token_accuracy": 0.05792190656065941, |
| "num_tokens": 327131.0, |
| "step": 120 |
| }, |
| { |
| "entropy": 9.899451637268067, |
| "epoch": 0.00338409475465313, |
| "grad_norm": 1.7734375, |
| "learning_rate": 6.2e-05, |
| "loss": 8.0577, |
| "mean_token_accuracy": 0.054864197969436646, |
| "num_tokens": 340932.0, |
| "step": 125 |
| }, |
| { |
| "entropy": 9.722916507720948, |
| "epoch": 0.0035194585448392554, |
| "grad_norm": 1.671875, |
| "learning_rate": 6.450000000000001e-05, |
| "loss": 7.9419, |
| "mean_token_accuracy": 0.05465308241546154, |
| "num_tokens": 355280.0, |
| "step": 130 |
| }, |
| { |
| "entropy": 9.517075347900391, |
| "epoch": 0.0036548223350253805, |
| "grad_norm": 1.546875, |
| "learning_rate": 6.7e-05, |
| "loss": 7.863, |
| "mean_token_accuracy": 0.06392355933785439, |
| "num_tokens": 370159.0, |
| "step": 135 |
| }, |
| { |
| "entropy": 9.312166881561279, |
| "epoch": 0.0037901861252115057, |
| "grad_norm": 1.4609375, |
| "learning_rate": 6.950000000000001e-05, |
| "loss": 7.7284, |
| "mean_token_accuracy": 0.060528535023331644, |
| "num_tokens": 385660.0, |
| "step": 140 |
| }, |
| { |
| "entropy": 9.113211154937744, |
| "epoch": 0.003925549915397631, |
| "grad_norm": 1.3359375, |
| "learning_rate": 7.2e-05, |
| "loss": 7.6437, |
| "mean_token_accuracy": 0.05836181789636612, |
| "num_tokens": 401147.0, |
| "step": 145 |
| }, |
| { |
| "entropy": 8.787345790863037, |
| "epoch": 0.0040609137055837565, |
| "grad_norm": 1.5625, |
| "learning_rate": 7.45e-05, |
| "loss": 7.4136, |
| "mean_token_accuracy": 0.07278152294456959, |
| "num_tokens": 413888.0, |
| "step": 150 |
| }, |
| { |
| "entropy": 8.64449052810669, |
| "epoch": 0.004196277495769882, |
| "grad_norm": 1.40625, |
| "learning_rate": 7.7e-05, |
| "loss": 7.3884, |
| "mean_token_accuracy": 0.06653538607060909, |
| "num_tokens": 427538.0, |
| "step": 155 |
| }, |
| { |
| "entropy": 8.441664218902588, |
| "epoch": 0.004331641285956007, |
| "grad_norm": 2.125, |
| "learning_rate": 7.950000000000001e-05, |
| "loss": 7.3251, |
| "mean_token_accuracy": 0.069814383238554, |
| "num_tokens": 441236.0, |
| "step": 160 |
| }, |
| { |
| "entropy": 8.356950950622558, |
| "epoch": 0.004467005076142132, |
| "grad_norm": 1.3984375, |
| "learning_rate": 8.2e-05, |
| "loss": 7.4254, |
| "mean_token_accuracy": 0.0740208551287651, |
| "num_tokens": 454231.0, |
| "step": 165 |
| }, |
| { |
| "entropy": 8.19385576248169, |
| "epoch": 0.004602368866328257, |
| "grad_norm": 1.5234375, |
| "learning_rate": 8.450000000000001e-05, |
| "loss": 7.2457, |
| "mean_token_accuracy": 0.07566015087068081, |
| "num_tokens": 468791.0, |
| "step": 170 |
| }, |
| { |
| "entropy": 8.173048114776611, |
| "epoch": 0.0047377326565143825, |
| "grad_norm": 1.6328125, |
| "learning_rate": 8.7e-05, |
| "loss": 7.3934, |
| "mean_token_accuracy": 0.06828283667564392, |
| "num_tokens": 481866.0, |
| "step": 175 |
| }, |
| { |
| "entropy": 8.059328603744508, |
| "epoch": 0.004873096446700508, |
| "grad_norm": 1.4296875, |
| "learning_rate": 8.95e-05, |
| "loss": 7.2376, |
| "mean_token_accuracy": 0.07703411132097245, |
| "num_tokens": 495060.0, |
| "step": 180 |
| }, |
| { |
| "entropy": 8.006558561325074, |
| "epoch": 0.005008460236886633, |
| "grad_norm": 1.2890625, |
| "learning_rate": 9.2e-05, |
| "loss": 7.1953, |
| "mean_token_accuracy": 0.07884187921881676, |
| "num_tokens": 508485.0, |
| "step": 185 |
| }, |
| { |
| "entropy": 7.988453817367554, |
| "epoch": 0.005143824027072758, |
| "grad_norm": 1.3984375, |
| "learning_rate": 9.45e-05, |
| "loss": 7.2074, |
| "mean_token_accuracy": 0.07364003024995328, |
| "num_tokens": 522642.0, |
| "step": 190 |
| }, |
| { |
| "entropy": 7.911316013336181, |
| "epoch": 0.005279187817258883, |
| "grad_norm": 1.234375, |
| "learning_rate": 9.7e-05, |
| "loss": 7.1742, |
| "mean_token_accuracy": 0.07427211254835128, |
| "num_tokens": 536967.0, |
| "step": 195 |
| }, |
| { |
| "entropy": 7.899316692352295, |
| "epoch": 0.0054145516074450084, |
| "grad_norm": 1.4296875, |
| "learning_rate": 9.95e-05, |
| "loss": 7.1728, |
| "mean_token_accuracy": 0.0805082306265831, |
| "num_tokens": 548389.0, |
| "step": 200 |
| }, |
| { |
| "entropy": 7.799197435379028, |
| "epoch": 0.005549915397631134, |
| "grad_norm": 1.296875, |
| "learning_rate": 0.000102, |
| "loss": 7.1509, |
| "mean_token_accuracy": 0.07738717347383499, |
| "num_tokens": 560609.0, |
| "step": 205 |
| }, |
| { |
| "entropy": 7.819343090057373, |
| "epoch": 0.005685279187817259, |
| "grad_norm": 1.3046875, |
| "learning_rate": 0.00010449999999999999, |
| "loss": 7.1254, |
| "mean_token_accuracy": 0.07640378400683404, |
| "num_tokens": 574689.0, |
| "step": 210 |
| }, |
| { |
| "entropy": 7.777826452255249, |
| "epoch": 0.005820642978003384, |
| "grad_norm": 1.3515625, |
| "learning_rate": 0.000107, |
| "loss": 7.0691, |
| "mean_token_accuracy": 0.07349300533533096, |
| "num_tokens": 588789.0, |
| "step": 215 |
| }, |
| { |
| "entropy": 7.698786115646362, |
| "epoch": 0.005956006768189509, |
| "grad_norm": 1.3125, |
| "learning_rate": 0.0001095, |
| "loss": 7.1439, |
| "mean_token_accuracy": 0.07730361446738243, |
| "num_tokens": 603609.0, |
| "step": 220 |
| }, |
| { |
| "entropy": 7.7466569423675535, |
| "epoch": 0.006091370558375634, |
| "grad_norm": 1.4453125, |
| "learning_rate": 0.000112, |
| "loss": 7.0113, |
| "mean_token_accuracy": 0.07942908927798271, |
| "num_tokens": 616403.0, |
| "step": 225 |
| }, |
| { |
| "entropy": 7.682626628875733, |
| "epoch": 0.00622673434856176, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.0001145, |
| "loss": 7.1202, |
| "mean_token_accuracy": 0.08443130478262902, |
| "num_tokens": 630831.0, |
| "step": 230 |
| }, |
| { |
| "entropy": 7.731028842926025, |
| "epoch": 0.006362098138747885, |
| "grad_norm": 1.5078125, |
| "learning_rate": 0.00011700000000000001, |
| "loss": 7.0225, |
| "mean_token_accuracy": 0.08779790177941323, |
| "num_tokens": 646501.0, |
| "step": 235 |
| }, |
| { |
| "entropy": 7.661398029327392, |
| "epoch": 0.00649746192893401, |
| "grad_norm": 1.8671875, |
| "learning_rate": 0.00011949999999999999, |
| "loss": 7.0941, |
| "mean_token_accuracy": 0.08079206757247448, |
| "num_tokens": 661193.0, |
| "step": 240 |
| }, |
| { |
| "entropy": 7.572637605667114, |
| "epoch": 0.006632825719120135, |
| "grad_norm": 1.734375, |
| "learning_rate": 0.000122, |
| "loss": 7.0787, |
| "mean_token_accuracy": 0.08005881682038307, |
| "num_tokens": 675523.0, |
| "step": 245 |
| }, |
| { |
| "entropy": 7.636332321166992, |
| "epoch": 0.00676818950930626, |
| "grad_norm": 1.5859375, |
| "learning_rate": 0.0001245, |
| "loss": 7.0674, |
| "mean_token_accuracy": 0.07794632315635681, |
| "num_tokens": 691106.0, |
| "step": 250 |
| }, |
| { |
| "entropy": 7.519766235351563, |
| "epoch": 0.0069035532994923855, |
| "grad_norm": 1.3671875, |
| "learning_rate": 0.000127, |
| "loss": 6.9381, |
| "mean_token_accuracy": 0.08541512936353683, |
| "num_tokens": 704312.0, |
| "step": 255 |
| }, |
| { |
| "entropy": 7.561954641342163, |
| "epoch": 0.007038917089678511, |
| "grad_norm": 1.4375, |
| "learning_rate": 0.0001295, |
| "loss": 6.9601, |
| "mean_token_accuracy": 0.0883929617702961, |
| "num_tokens": 717026.0, |
| "step": 260 |
| }, |
| { |
| "entropy": 7.570081567764282, |
| "epoch": 0.007174280879864636, |
| "grad_norm": 1.328125, |
| "learning_rate": 0.000132, |
| "loss": 6.9123, |
| "mean_token_accuracy": 0.08829773366451263, |
| "num_tokens": 729605.0, |
| "step": 265 |
| }, |
| { |
| "entropy": 7.463983678817749, |
| "epoch": 0.007309644670050761, |
| "grad_norm": 1.2421875, |
| "learning_rate": 0.00013450000000000002, |
| "loss": 6.9353, |
| "mean_token_accuracy": 0.09122553616762161, |
| "num_tokens": 743208.0, |
| "step": 270 |
| }, |
| { |
| "entropy": 7.550097227096558, |
| "epoch": 0.007445008460236886, |
| "grad_norm": 1.2578125, |
| "learning_rate": 0.00013700000000000002, |
| "loss": 6.9287, |
| "mean_token_accuracy": 0.08519787713885307, |
| "num_tokens": 755127.0, |
| "step": 275 |
| }, |
| { |
| "entropy": 7.398041200637818, |
| "epoch": 0.0075803722504230115, |
| "grad_norm": 1.53125, |
| "learning_rate": 0.0001395, |
| "loss": 6.8231, |
| "mean_token_accuracy": 0.08911917060613632, |
| "num_tokens": 769725.0, |
| "step": 280 |
| }, |
| { |
| "entropy": 7.364175844192505, |
| "epoch": 0.007715736040609137, |
| "grad_norm": 1.2109375, |
| "learning_rate": 0.00014199999999999998, |
| "loss": 6.7527, |
| "mean_token_accuracy": 0.09069294035434723, |
| "num_tokens": 783788.0, |
| "step": 285 |
| }, |
| { |
| "entropy": 7.450532627105713, |
| "epoch": 0.007851099830795263, |
| "grad_norm": 1.171875, |
| "learning_rate": 0.0001445, |
| "loss": 6.934, |
| "mean_token_accuracy": 0.08614907264709473, |
| "num_tokens": 797214.0, |
| "step": 290 |
| }, |
| { |
| "entropy": 7.43695821762085, |
| "epoch": 0.007986463620981387, |
| "grad_norm": 1.6328125, |
| "learning_rate": 0.000147, |
| "loss": 6.897, |
| "mean_token_accuracy": 0.09108028039336205, |
| "num_tokens": 809731.0, |
| "step": 295 |
| }, |
| { |
| "entropy": 7.286933469772339, |
| "epoch": 0.008121827411167513, |
| "grad_norm": 1.4296875, |
| "learning_rate": 0.0001495, |
| "loss": 6.8591, |
| "mean_token_accuracy": 0.09137310981750488, |
| "num_tokens": 825021.0, |
| "step": 300 |
| }, |
| { |
| "entropy": 7.2696253776550295, |
| "epoch": 0.008257191201353637, |
| "grad_norm": 1.40625, |
| "learning_rate": 0.000152, |
| "loss": 6.9029, |
| "mean_token_accuracy": 0.09101672545075416, |
| "num_tokens": 839153.0, |
| "step": 305 |
| }, |
| { |
| "entropy": 7.386481237411499, |
| "epoch": 0.008392554991539763, |
| "grad_norm": 1.3984375, |
| "learning_rate": 0.00015450000000000001, |
| "loss": 6.8276, |
| "mean_token_accuracy": 0.08859616219997406, |
| "num_tokens": 853120.0, |
| "step": 310 |
| }, |
| { |
| "entropy": 7.337709522247314, |
| "epoch": 0.008527918781725888, |
| "grad_norm": 1.21875, |
| "learning_rate": 0.000157, |
| "loss": 6.8448, |
| "mean_token_accuracy": 0.08571028485894203, |
| "num_tokens": 867268.0, |
| "step": 315 |
| }, |
| { |
| "entropy": 7.340923023223877, |
| "epoch": 0.008663282571912014, |
| "grad_norm": 1.3515625, |
| "learning_rate": 0.0001595, |
| "loss": 6.8255, |
| "mean_token_accuracy": 0.09267906844615936, |
| "num_tokens": 879062.0, |
| "step": 320 |
| }, |
| { |
| "entropy": 7.282296800613404, |
| "epoch": 0.008798646362098138, |
| "grad_norm": 1.4140625, |
| "learning_rate": 0.000162, |
| "loss": 6.7932, |
| "mean_token_accuracy": 0.09626845642924309, |
| "num_tokens": 892178.0, |
| "step": 325 |
| }, |
| { |
| "entropy": 7.201563024520874, |
| "epoch": 0.008934010152284264, |
| "grad_norm": 1.3125, |
| "learning_rate": 0.00016450000000000001, |
| "loss": 6.671, |
| "mean_token_accuracy": 0.09671695902943611, |
| "num_tokens": 904809.0, |
| "step": 330 |
| }, |
| { |
| "entropy": 7.275315999984741, |
| "epoch": 0.009069373942470389, |
| "grad_norm": 1.2734375, |
| "learning_rate": 0.00016700000000000002, |
| "loss": 6.8034, |
| "mean_token_accuracy": 0.09026706293225288, |
| "num_tokens": 917660.0, |
| "step": 335 |
| }, |
| { |
| "entropy": 7.179704904556274, |
| "epoch": 0.009204737732656515, |
| "grad_norm": 1.328125, |
| "learning_rate": 0.00016950000000000003, |
| "loss": 6.6849, |
| "mean_token_accuracy": 0.09763308465480805, |
| "num_tokens": 932773.0, |
| "step": 340 |
| }, |
| { |
| "entropy": 7.1569760799407955, |
| "epoch": 0.009340101522842639, |
| "grad_norm": 1.3359375, |
| "learning_rate": 0.00017199999999999998, |
| "loss": 6.707, |
| "mean_token_accuracy": 0.09705711230635643, |
| "num_tokens": 946688.0, |
| "step": 345 |
| }, |
| { |
| "entropy": 7.123394393920899, |
| "epoch": 0.009475465313028765, |
| "grad_norm": 1.3671875, |
| "learning_rate": 0.00017449999999999999, |
| "loss": 6.6188, |
| "mean_token_accuracy": 0.10255519598722458, |
| "num_tokens": 960621.0, |
| "step": 350 |
| }, |
| { |
| "entropy": 7.114657831192017, |
| "epoch": 0.00961082910321489, |
| "grad_norm": 1.2734375, |
| "learning_rate": 0.000177, |
| "loss": 6.7525, |
| "mean_token_accuracy": 0.0939077839255333, |
| "num_tokens": 976705.0, |
| "step": 355 |
| }, |
| { |
| "entropy": 7.13629846572876, |
| "epoch": 0.009746192893401015, |
| "grad_norm": 1.234375, |
| "learning_rate": 0.0001795, |
| "loss": 6.6798, |
| "mean_token_accuracy": 0.09904273673892021, |
| "num_tokens": 989175.0, |
| "step": 360 |
| }, |
| { |
| "entropy": 7.18667254447937, |
| "epoch": 0.00988155668358714, |
| "grad_norm": 1.25, |
| "learning_rate": 0.000182, |
| "loss": 6.7875, |
| "mean_token_accuracy": 0.095027344673872, |
| "num_tokens": 1003899.0, |
| "step": 365 |
| }, |
| { |
| "entropy": 7.018054962158203, |
| "epoch": 0.010016920473773266, |
| "grad_norm": 1.4765625, |
| "learning_rate": 0.0001845, |
| "loss": 6.6248, |
| "mean_token_accuracy": 0.09302543699741364, |
| "num_tokens": 1017823.0, |
| "step": 370 |
| }, |
| { |
| "entropy": 7.214749193191528, |
| "epoch": 0.01015228426395939, |
| "grad_norm": 1.234375, |
| "learning_rate": 0.000187, |
| "loss": 6.8025, |
| "mean_token_accuracy": 0.0944581039249897, |
| "num_tokens": 1031556.0, |
| "step": 375 |
| }, |
| { |
| "entropy": 7.06955304145813, |
| "epoch": 0.010287648054145516, |
| "grad_norm": 1.375, |
| "learning_rate": 0.0001895, |
| "loss": 6.6582, |
| "mean_token_accuracy": 0.10281435176730155, |
| "num_tokens": 1044245.0, |
| "step": 380 |
| }, |
| { |
| "entropy": 7.121717023849487, |
| "epoch": 0.01042301184433164, |
| "grad_norm": 1.3671875, |
| "learning_rate": 0.000192, |
| "loss": 6.6908, |
| "mean_token_accuracy": 0.09887115061283111, |
| "num_tokens": 1058288.0, |
| "step": 385 |
| }, |
| { |
| "entropy": 7.069799566268921, |
| "epoch": 0.010558375634517767, |
| "grad_norm": 1.546875, |
| "learning_rate": 0.0001945, |
| "loss": 6.623, |
| "mean_token_accuracy": 0.09829980209469795, |
| "num_tokens": 1072234.0, |
| "step": 390 |
| }, |
| { |
| "entropy": 7.062967205047608, |
| "epoch": 0.010693739424703893, |
| "grad_norm": 1.484375, |
| "learning_rate": 0.00019700000000000002, |
| "loss": 6.6287, |
| "mean_token_accuracy": 0.0978606753051281, |
| "num_tokens": 1085463.0, |
| "step": 395 |
| }, |
| { |
| "entropy": 6.952229833602905, |
| "epoch": 0.010829103214890017, |
| "grad_norm": 1.4375, |
| "learning_rate": 0.00019950000000000002, |
| "loss": 6.6629, |
| "mean_token_accuracy": 0.09642241895198822, |
| "num_tokens": 1101393.0, |
| "step": 400 |
| }, |
| { |
| "entropy": 7.105423212051392, |
| "epoch": 0.010964467005076143, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.000202, |
| "loss": 6.6263, |
| "mean_token_accuracy": 0.09685642644762993, |
| "num_tokens": 1117150.0, |
| "step": 405 |
| }, |
| { |
| "entropy": 6.972289943695069, |
| "epoch": 0.011099830795262267, |
| "grad_norm": 1.3515625, |
| "learning_rate": 0.00020449999999999998, |
| "loss": 6.6594, |
| "mean_token_accuracy": 0.10496844202280045, |
| "num_tokens": 1130674.0, |
| "step": 410 |
| }, |
| { |
| "entropy": 7.087021827697754, |
| "epoch": 0.011235194585448393, |
| "grad_norm": 1.171875, |
| "learning_rate": 0.000207, |
| "loss": 6.6508, |
| "mean_token_accuracy": 0.09535380229353904, |
| "num_tokens": 1144016.0, |
| "step": 415 |
| }, |
| { |
| "entropy": 6.9751802444458, |
| "epoch": 0.011370558375634518, |
| "grad_norm": 1.1484375, |
| "learning_rate": 0.0002095, |
| "loss": 6.646, |
| "mean_token_accuracy": 0.09546661153435707, |
| "num_tokens": 1160200.0, |
| "step": 420 |
| }, |
| { |
| "entropy": 7.048429536819458, |
| "epoch": 0.011505922165820644, |
| "grad_norm": 1.484375, |
| "learning_rate": 0.000212, |
| "loss": 6.5651, |
| "mean_token_accuracy": 0.1022900827229023, |
| "num_tokens": 1173266.0, |
| "step": 425 |
| }, |
| { |
| "entropy": 6.974373769760132, |
| "epoch": 0.011641285956006768, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.0002145, |
| "loss": 6.6353, |
| "mean_token_accuracy": 0.09445997178554535, |
| "num_tokens": 1187977.0, |
| "step": 430 |
| }, |
| { |
| "entropy": 6.9971846580505375, |
| "epoch": 0.011776649746192894, |
| "grad_norm": 1.21875, |
| "learning_rate": 0.00021700000000000002, |
| "loss": 6.6389, |
| "mean_token_accuracy": 0.09972369968891144, |
| "num_tokens": 1202369.0, |
| "step": 435 |
| }, |
| { |
| "entropy": 6.966669607162475, |
| "epoch": 0.011912013536379018, |
| "grad_norm": 1.3203125, |
| "learning_rate": 0.0002195, |
| "loss": 6.5354, |
| "mean_token_accuracy": 0.09552454426884652, |
| "num_tokens": 1216956.0, |
| "step": 440 |
| }, |
| { |
| "entropy": 6.981910848617554, |
| "epoch": 0.012047377326565144, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.000222, |
| "loss": 6.6403, |
| "mean_token_accuracy": 0.09657183811068534, |
| "num_tokens": 1230958.0, |
| "step": 445 |
| }, |
| { |
| "entropy": 6.972163391113281, |
| "epoch": 0.012182741116751269, |
| "grad_norm": 1.3671875, |
| "learning_rate": 0.0002245, |
| "loss": 6.5568, |
| "mean_token_accuracy": 0.1032287061214447, |
| "num_tokens": 1244512.0, |
| "step": 450 |
| }, |
| { |
| "entropy": 6.940069246292114, |
| "epoch": 0.012318104906937395, |
| "grad_norm": 1.5078125, |
| "learning_rate": 0.00022700000000000002, |
| "loss": 6.4972, |
| "mean_token_accuracy": 0.10796320661902428, |
| "num_tokens": 1257469.0, |
| "step": 455 |
| }, |
| { |
| "entropy": 6.870718479156494, |
| "epoch": 0.01245346869712352, |
| "grad_norm": 1.203125, |
| "learning_rate": 0.00022950000000000002, |
| "loss": 6.5861, |
| "mean_token_accuracy": 0.10574530512094497, |
| "num_tokens": 1273533.0, |
| "step": 460 |
| }, |
| { |
| "entropy": 6.932940578460693, |
| "epoch": 0.012588832487309645, |
| "grad_norm": 1.25, |
| "learning_rate": 0.00023200000000000003, |
| "loss": 6.5387, |
| "mean_token_accuracy": 0.10031782239675521, |
| "num_tokens": 1288385.0, |
| "step": 465 |
| }, |
| { |
| "entropy": 6.920595693588257, |
| "epoch": 0.01272419627749577, |
| "grad_norm": 1.3203125, |
| "learning_rate": 0.00023449999999999998, |
| "loss": 6.6012, |
| "mean_token_accuracy": 0.10496116429567337, |
| "num_tokens": 1300721.0, |
| "step": 470 |
| }, |
| { |
| "entropy": 6.878480577468872, |
| "epoch": 0.012859560067681896, |
| "grad_norm": 1.2421875, |
| "learning_rate": 0.000237, |
| "loss": 6.4915, |
| "mean_token_accuracy": 0.1057609498500824, |
| "num_tokens": 1313125.0, |
| "step": 475 |
| }, |
| { |
| "entropy": 6.905995321273804, |
| "epoch": 0.01299492385786802, |
| "grad_norm": 1.296875, |
| "learning_rate": 0.0002395, |
| "loss": 6.5534, |
| "mean_token_accuracy": 0.09937024191021919, |
| "num_tokens": 1326226.0, |
| "step": 480 |
| }, |
| { |
| "entropy": 6.928886890411377, |
| "epoch": 0.013130287648054146, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.000242, |
| "loss": 6.4614, |
| "mean_token_accuracy": 0.10791765451431275, |
| "num_tokens": 1339932.0, |
| "step": 485 |
| }, |
| { |
| "entropy": 6.82708158493042, |
| "epoch": 0.01326565143824027, |
| "grad_norm": 1.3359375, |
| "learning_rate": 0.0002445, |
| "loss": 6.5553, |
| "mean_token_accuracy": 0.09961838722229004, |
| "num_tokens": 1354015.0, |
| "step": 490 |
| }, |
| { |
| "entropy": 6.846263122558594, |
| "epoch": 0.013401015228426396, |
| "grad_norm": 1.2734375, |
| "learning_rate": 0.000247, |
| "loss": 6.5473, |
| "mean_token_accuracy": 0.100076574832201, |
| "num_tokens": 1369333.0, |
| "step": 495 |
| }, |
| { |
| "entropy": 6.777434158325195, |
| "epoch": 0.01353637901861252, |
| "grad_norm": 1.2734375, |
| "learning_rate": 0.0002495, |
| "loss": 6.5092, |
| "mean_token_accuracy": 0.10239997878670692, |
| "num_tokens": 1383141.0, |
| "step": 500 |
| }, |
| { |
| "entropy": 6.814955854415894, |
| "epoch": 0.013671742808798647, |
| "grad_norm": 1.2890625, |
| "learning_rate": 0.000252, |
| "loss": 6.5148, |
| "mean_token_accuracy": 0.10957075208425522, |
| "num_tokens": 1398273.0, |
| "step": 505 |
| }, |
| { |
| "entropy": 6.813977956771851, |
| "epoch": 0.013807106598984771, |
| "grad_norm": 1.21875, |
| "learning_rate": 0.0002545, |
| "loss": 6.4406, |
| "mean_token_accuracy": 0.10602880343794822, |
| "num_tokens": 1412562.0, |
| "step": 510 |
| }, |
| { |
| "entropy": 6.782559490203857, |
| "epoch": 0.013942470389170897, |
| "grad_norm": 1.203125, |
| "learning_rate": 0.000257, |
| "loss": 6.4008, |
| "mean_token_accuracy": 0.1101540595293045, |
| "num_tokens": 1426024.0, |
| "step": 515 |
| }, |
| { |
| "entropy": 6.743443441390991, |
| "epoch": 0.014077834179357021, |
| "grad_norm": 1.171875, |
| "learning_rate": 0.0002595, |
| "loss": 6.4539, |
| "mean_token_accuracy": 0.10084594711661339, |
| "num_tokens": 1439774.0, |
| "step": 520 |
| }, |
| { |
| "entropy": 6.744311380386352, |
| "epoch": 0.014213197969543147, |
| "grad_norm": 1.296875, |
| "learning_rate": 0.000262, |
| "loss": 6.386, |
| "mean_token_accuracy": 0.11141050532460213, |
| "num_tokens": 1453041.0, |
| "step": 525 |
| }, |
| { |
| "entropy": 6.779989385604859, |
| "epoch": 0.014348561759729272, |
| "grad_norm": 1.25, |
| "learning_rate": 0.00026450000000000003, |
| "loss": 6.3421, |
| "mean_token_accuracy": 0.10815011188387871, |
| "num_tokens": 1466487.0, |
| "step": 530 |
| }, |
| { |
| "entropy": 6.666443109512329, |
| "epoch": 0.014483925549915398, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.00026700000000000004, |
| "loss": 6.4193, |
| "mean_token_accuracy": 0.107712272554636, |
| "num_tokens": 1480142.0, |
| "step": 535 |
| }, |
| { |
| "entropy": 6.692905330657959, |
| "epoch": 0.014619289340101522, |
| "grad_norm": 1.2109375, |
| "learning_rate": 0.00026950000000000005, |
| "loss": 6.3428, |
| "mean_token_accuracy": 0.1036965548992157, |
| "num_tokens": 1493427.0, |
| "step": 540 |
| }, |
| { |
| "entropy": 6.6241538524627686, |
| "epoch": 0.014754653130287648, |
| "grad_norm": 1.21875, |
| "learning_rate": 0.00027200000000000005, |
| "loss": 6.3301, |
| "mean_token_accuracy": 0.11499745398759842, |
| "num_tokens": 1506055.0, |
| "step": 545 |
| }, |
| { |
| "entropy": 6.726637983322144, |
| "epoch": 0.014890016920473773, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.0002745, |
| "loss": 6.4916, |
| "mean_token_accuracy": 0.10548164397478103, |
| "num_tokens": 1519239.0, |
| "step": 550 |
| }, |
| { |
| "entropy": 6.79321608543396, |
| "epoch": 0.015025380710659899, |
| "grad_norm": 1.2109375, |
| "learning_rate": 0.000277, |
| "loss": 6.4433, |
| "mean_token_accuracy": 0.10511932224035263, |
| "num_tokens": 1533630.0, |
| "step": 555 |
| }, |
| { |
| "entropy": 6.68529486656189, |
| "epoch": 0.015160744500846023, |
| "grad_norm": 1.4375, |
| "learning_rate": 0.0002795, |
| "loss": 6.3701, |
| "mean_token_accuracy": 0.11614254266023635, |
| "num_tokens": 1546749.0, |
| "step": 560 |
| }, |
| { |
| "entropy": 6.61783242225647, |
| "epoch": 0.015296108291032149, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.00028199999999999997, |
| "loss": 6.3126, |
| "mean_token_accuracy": 0.11469681560993195, |
| "num_tokens": 1560568.0, |
| "step": 565 |
| }, |
| { |
| "entropy": 6.697822999954224, |
| "epoch": 0.015431472081218273, |
| "grad_norm": 1.2734375, |
| "learning_rate": 0.0002845, |
| "loss": 6.383, |
| "mean_token_accuracy": 0.10437465310096741, |
| "num_tokens": 1574414.0, |
| "step": 570 |
| }, |
| { |
| "entropy": 6.622760200500489, |
| "epoch": 0.0155668358714044, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.000287, |
| "loss": 6.3839, |
| "mean_token_accuracy": 0.10195678994059562, |
| "num_tokens": 1588906.0, |
| "step": 575 |
| }, |
| { |
| "entropy": 6.643900966644287, |
| "epoch": 0.015702199661590525, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.0002895, |
| "loss": 6.3656, |
| "mean_token_accuracy": 0.11110272482037545, |
| "num_tokens": 1603181.0, |
| "step": 580 |
| }, |
| { |
| "entropy": 6.722048425674439, |
| "epoch": 0.01583756345177665, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.000292, |
| "loss": 6.365, |
| "mean_token_accuracy": 0.1083282358944416, |
| "num_tokens": 1617262.0, |
| "step": 585 |
| }, |
| { |
| "entropy": 6.704953336715699, |
| "epoch": 0.015972927241962774, |
| "grad_norm": 1.21875, |
| "learning_rate": 0.0002945, |
| "loss": 6.4147, |
| "mean_token_accuracy": 0.10933435037732124, |
| "num_tokens": 1631618.0, |
| "step": 590 |
| }, |
| { |
| "entropy": 6.532735300064087, |
| "epoch": 0.016108291032148902, |
| "grad_norm": 1.28125, |
| "learning_rate": 0.000297, |
| "loss": 6.1685, |
| "mean_token_accuracy": 0.11916324943304062, |
| "num_tokens": 1644717.0, |
| "step": 595 |
| }, |
| { |
| "entropy": 6.565193223953247, |
| "epoch": 0.016243654822335026, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.0002995, |
| "loss": 6.3201, |
| "mean_token_accuracy": 0.1078986182808876, |
| "num_tokens": 1661888.0, |
| "step": 600 |
| }, |
| { |
| "entropy": 6.5602422714233395, |
| "epoch": 0.01637901861252115, |
| "grad_norm": 1.3203125, |
| "learning_rate": 0.000302, |
| "loss": 6.3369, |
| "mean_token_accuracy": 0.11532969921827316, |
| "num_tokens": 1676103.0, |
| "step": 605 |
| }, |
| { |
| "entropy": 6.621259689331055, |
| "epoch": 0.016514382402707275, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.0003045, |
| "loss": 6.3879, |
| "mean_token_accuracy": 0.10770049318671227, |
| "num_tokens": 1690902.0, |
| "step": 610 |
| }, |
| { |
| "entropy": 6.530938911437988, |
| "epoch": 0.016649746192893403, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.000307, |
| "loss": 6.3262, |
| "mean_token_accuracy": 0.11129384264349937, |
| "num_tokens": 1705861.0, |
| "step": 615 |
| }, |
| { |
| "entropy": 6.601020479202271, |
| "epoch": 0.016785109983079527, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.0003095, |
| "loss": 6.2688, |
| "mean_token_accuracy": 0.1109300784766674, |
| "num_tokens": 1719893.0, |
| "step": 620 |
| }, |
| { |
| "entropy": 6.542957210540772, |
| "epoch": 0.01692047377326565, |
| "grad_norm": 1.2109375, |
| "learning_rate": 0.000312, |
| "loss": 6.2874, |
| "mean_token_accuracy": 0.10827434211969375, |
| "num_tokens": 1733411.0, |
| "step": 625 |
| }, |
| { |
| "entropy": 6.561354637145996, |
| "epoch": 0.017055837563451776, |
| "grad_norm": 1.2421875, |
| "learning_rate": 0.0003145, |
| "loss": 6.2397, |
| "mean_token_accuracy": 0.11391478329896927, |
| "num_tokens": 1747374.0, |
| "step": 630 |
| }, |
| { |
| "entropy": 6.587129735946656, |
| "epoch": 0.017191201353637903, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.000317, |
| "loss": 6.3487, |
| "mean_token_accuracy": 0.11469378024339676, |
| "num_tokens": 1761520.0, |
| "step": 635 |
| }, |
| { |
| "entropy": 6.594478893280029, |
| "epoch": 0.017326565143824028, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.0003195, |
| "loss": 6.3577, |
| "mean_token_accuracy": 0.10972927659749984, |
| "num_tokens": 1777499.0, |
| "step": 640 |
| }, |
| { |
| "entropy": 6.581266975402832, |
| "epoch": 0.017461928934010152, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.000322, |
| "loss": 6.2463, |
| "mean_token_accuracy": 0.12096798866987228, |
| "num_tokens": 1791308.0, |
| "step": 645 |
| }, |
| { |
| "entropy": 6.4111003398895265, |
| "epoch": 0.017597292724196276, |
| "grad_norm": 1.25, |
| "learning_rate": 0.00032450000000000003, |
| "loss": 6.1953, |
| "mean_token_accuracy": 0.11683537811040878, |
| "num_tokens": 1804545.0, |
| "step": 650 |
| }, |
| { |
| "entropy": 6.54813027381897, |
| "epoch": 0.017732656514382404, |
| "grad_norm": 1.2421875, |
| "learning_rate": 0.00032700000000000003, |
| "loss": 6.2866, |
| "mean_token_accuracy": 0.11415853798389435, |
| "num_tokens": 1818499.0, |
| "step": 655 |
| }, |
| { |
| "entropy": 6.5606420040130615, |
| "epoch": 0.01786802030456853, |
| "grad_norm": 1.125, |
| "learning_rate": 0.00032950000000000004, |
| "loss": 6.2876, |
| "mean_token_accuracy": 0.10897349566221237, |
| "num_tokens": 1833582.0, |
| "step": 660 |
| }, |
| { |
| "entropy": 6.524020147323609, |
| "epoch": 0.018003384094754653, |
| "grad_norm": 1.296875, |
| "learning_rate": 0.00033200000000000005, |
| "loss": 6.26, |
| "mean_token_accuracy": 0.11666257977485657, |
| "num_tokens": 1847514.0, |
| "step": 665 |
| }, |
| { |
| "entropy": 6.450877380371094, |
| "epoch": 0.018138747884940777, |
| "grad_norm": 1.2109375, |
| "learning_rate": 0.00033450000000000005, |
| "loss": 6.2948, |
| "mean_token_accuracy": 0.11785768866539001, |
| "num_tokens": 1860177.0, |
| "step": 670 |
| }, |
| { |
| "entropy": 6.518109226226807, |
| "epoch": 0.018274111675126905, |
| "grad_norm": 1.21875, |
| "learning_rate": 0.000337, |
| "loss": 6.3086, |
| "mean_token_accuracy": 0.11776039749383926, |
| "num_tokens": 1873317.0, |
| "step": 675 |
| }, |
| { |
| "entropy": 6.405819511413574, |
| "epoch": 0.01840947546531303, |
| "grad_norm": 1.1640625, |
| "learning_rate": 0.0003395, |
| "loss": 6.1447, |
| "mean_token_accuracy": 0.11899075359106064, |
| "num_tokens": 1885974.0, |
| "step": 680 |
| }, |
| { |
| "entropy": 6.473683166503906, |
| "epoch": 0.018544839255499154, |
| "grad_norm": 1.125, |
| "learning_rate": 0.000342, |
| "loss": 6.3167, |
| "mean_token_accuracy": 0.11156651675701142, |
| "num_tokens": 1901894.0, |
| "step": 685 |
| }, |
| { |
| "entropy": 6.5223006248474125, |
| "epoch": 0.018680203045685278, |
| "grad_norm": 1.234375, |
| "learning_rate": 0.00034449999999999997, |
| "loss": 6.2982, |
| "mean_token_accuracy": 0.11568359285593033, |
| "num_tokens": 1916276.0, |
| "step": 690 |
| }, |
| { |
| "entropy": 6.437406921386719, |
| "epoch": 0.018815566835871406, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.000347, |
| "loss": 6.3, |
| "mean_token_accuracy": 0.10904626250267029, |
| "num_tokens": 1929574.0, |
| "step": 695 |
| }, |
| { |
| "entropy": 6.493116617202759, |
| "epoch": 0.01895093062605753, |
| "grad_norm": 1.2265625, |
| "learning_rate": 0.0003495, |
| "loss": 6.2389, |
| "mean_token_accuracy": 0.10819176211953163, |
| "num_tokens": 1943220.0, |
| "step": 700 |
| }, |
| { |
| "entropy": 6.54621901512146, |
| "epoch": 0.019086294416243654, |
| "grad_norm": 1.2265625, |
| "learning_rate": 0.000352, |
| "loss": 6.2556, |
| "mean_token_accuracy": 0.10982774049043656, |
| "num_tokens": 1957834.0, |
| "step": 705 |
| }, |
| { |
| "entropy": 6.512110996246338, |
| "epoch": 0.01922165820642978, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0003545, |
| "loss": 6.3302, |
| "mean_token_accuracy": 0.11116872280836106, |
| "num_tokens": 1972649.0, |
| "step": 710 |
| }, |
| { |
| "entropy": 6.418754625320434, |
| "epoch": 0.019357021996615906, |
| "grad_norm": 1.265625, |
| "learning_rate": 0.000357, |
| "loss": 6.1538, |
| "mean_token_accuracy": 0.12162703573703766, |
| "num_tokens": 1984181.0, |
| "step": 715 |
| }, |
| { |
| "entropy": 6.399659919738769, |
| "epoch": 0.01949238578680203, |
| "grad_norm": 0.92578125, |
| "learning_rate": 0.0003595, |
| "loss": 6.2047, |
| "mean_token_accuracy": 0.11393127739429473, |
| "num_tokens": 2000616.0, |
| "step": 720 |
| }, |
| { |
| "entropy": 6.4549713134765625, |
| "epoch": 0.019627749576988155, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.000362, |
| "loss": 6.1698, |
| "mean_token_accuracy": 0.11860272511839867, |
| "num_tokens": 2015344.0, |
| "step": 725 |
| }, |
| { |
| "entropy": 6.458272075653076, |
| "epoch": 0.01976311336717428, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.0003645, |
| "loss": 6.2536, |
| "mean_token_accuracy": 0.11021775305271149, |
| "num_tokens": 2029823.0, |
| "step": 730 |
| }, |
| { |
| "entropy": 6.360110950469971, |
| "epoch": 0.019898477157360407, |
| "grad_norm": 1.234375, |
| "learning_rate": 0.000367, |
| "loss": 6.1363, |
| "mean_token_accuracy": 0.11379259899258613, |
| "num_tokens": 2043680.0, |
| "step": 735 |
| }, |
| { |
| "entropy": 6.4546263217926025, |
| "epoch": 0.02003384094754653, |
| "grad_norm": 1.2890625, |
| "learning_rate": 0.0003695, |
| "loss": 6.2118, |
| "mean_token_accuracy": 0.11678453311324119, |
| "num_tokens": 2056211.0, |
| "step": 740 |
| }, |
| { |
| "entropy": 6.301215696334839, |
| "epoch": 0.020169204737732656, |
| "grad_norm": 1.3125, |
| "learning_rate": 0.000372, |
| "loss": 6.2223, |
| "mean_token_accuracy": 0.11474345549941063, |
| "num_tokens": 2069775.0, |
| "step": 745 |
| }, |
| { |
| "entropy": 6.343719387054444, |
| "epoch": 0.02030456852791878, |
| "grad_norm": 1.2109375, |
| "learning_rate": 0.0003745, |
| "loss": 6.0669, |
| "mean_token_accuracy": 0.12363717705011368, |
| "num_tokens": 2084423.0, |
| "step": 750 |
| }, |
| { |
| "entropy": 6.379573202133178, |
| "epoch": 0.020439932318104908, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.000377, |
| "loss": 6.2006, |
| "mean_token_accuracy": 0.11517359465360641, |
| "num_tokens": 2099702.0, |
| "step": 755 |
| }, |
| { |
| "entropy": 6.35660948753357, |
| "epoch": 0.020575296108291032, |
| "grad_norm": 0.98046875, |
| "learning_rate": 0.0003795, |
| "loss": 6.1424, |
| "mean_token_accuracy": 0.116712386906147, |
| "num_tokens": 2114938.0, |
| "step": 760 |
| }, |
| { |
| "entropy": 6.33174843788147, |
| "epoch": 0.020710659898477157, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.000382, |
| "loss": 6.0715, |
| "mean_token_accuracy": 0.12017848417162895, |
| "num_tokens": 2128039.0, |
| "step": 765 |
| }, |
| { |
| "entropy": 6.483924388885498, |
| "epoch": 0.02084602368866328, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.0003845, |
| "loss": 6.2675, |
| "mean_token_accuracy": 0.11350229382514954, |
| "num_tokens": 2144244.0, |
| "step": 770 |
| }, |
| { |
| "entropy": 6.299388790130616, |
| "epoch": 0.02098138747884941, |
| "grad_norm": 1.1875, |
| "learning_rate": 0.00038700000000000003, |
| "loss": 6.0745, |
| "mean_token_accuracy": 0.12214050814509392, |
| "num_tokens": 2156050.0, |
| "step": 775 |
| }, |
| { |
| "entropy": 6.339807558059692, |
| "epoch": 0.021116751269035533, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.00038950000000000003, |
| "loss": 6.1324, |
| "mean_token_accuracy": 0.11614297851920127, |
| "num_tokens": 2170083.0, |
| "step": 780 |
| }, |
| { |
| "entropy": 6.346547555923462, |
| "epoch": 0.021252115059221657, |
| "grad_norm": 1.1484375, |
| "learning_rate": 0.00039200000000000004, |
| "loss": 6.1194, |
| "mean_token_accuracy": 0.12128575146198273, |
| "num_tokens": 2184536.0, |
| "step": 785 |
| }, |
| { |
| "entropy": 6.332412433624268, |
| "epoch": 0.021387478849407785, |
| "grad_norm": 0.94140625, |
| "learning_rate": 0.00039450000000000005, |
| "loss": 6.1629, |
| "mean_token_accuracy": 0.11224813610315323, |
| "num_tokens": 2199324.0, |
| "step": 790 |
| }, |
| { |
| "entropy": 6.236615514755249, |
| "epoch": 0.02152284263959391, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.00039700000000000005, |
| "loss": 6.1244, |
| "mean_token_accuracy": 0.1139693059027195, |
| "num_tokens": 2215191.0, |
| "step": 795 |
| }, |
| { |
| "entropy": 6.423162221908569, |
| "epoch": 0.021658206429780034, |
| "grad_norm": 1.2109375, |
| "learning_rate": 0.0003995, |
| "loss": 6.1789, |
| "mean_token_accuracy": 0.11178024560213089, |
| "num_tokens": 2229354.0, |
| "step": 800 |
| }, |
| { |
| "entropy": 6.281933403015136, |
| "epoch": 0.021793570219966158, |
| "grad_norm": 1.0, |
| "learning_rate": 0.000402, |
| "loss": 6.1912, |
| "mean_token_accuracy": 0.11805299371480941, |
| "num_tokens": 2243804.0, |
| "step": 805 |
| }, |
| { |
| "entropy": 6.288844728469849, |
| "epoch": 0.021928934010152286, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.0004045, |
| "loss": 6.0841, |
| "mean_token_accuracy": 0.11569216102361679, |
| "num_tokens": 2258267.0, |
| "step": 810 |
| }, |
| { |
| "entropy": 6.315207052230835, |
| "epoch": 0.02206429780033841, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.00040699999999999997, |
| "loss": 6.1319, |
| "mean_token_accuracy": 0.12272850275039673, |
| "num_tokens": 2271854.0, |
| "step": 815 |
| }, |
| { |
| "entropy": 6.263217782974243, |
| "epoch": 0.022199661590524535, |
| "grad_norm": 1.1484375, |
| "learning_rate": 0.0004095, |
| "loss": 6.1651, |
| "mean_token_accuracy": 0.11350240483880043, |
| "num_tokens": 2285897.0, |
| "step": 820 |
| }, |
| { |
| "entropy": 6.2891233444213865, |
| "epoch": 0.02233502538071066, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.000412, |
| "loss": 6.1208, |
| "mean_token_accuracy": 0.11810638681054116, |
| "num_tokens": 2299354.0, |
| "step": 825 |
| }, |
| { |
| "entropy": 6.323483896255493, |
| "epoch": 0.022470389170896787, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.0004145, |
| "loss": 6.1693, |
| "mean_token_accuracy": 0.1183534987270832, |
| "num_tokens": 2313111.0, |
| "step": 830 |
| }, |
| { |
| "entropy": 6.299751424789429, |
| "epoch": 0.02260575296108291, |
| "grad_norm": 1.21875, |
| "learning_rate": 0.000417, |
| "loss": 6.1459, |
| "mean_token_accuracy": 0.12177513241767883, |
| "num_tokens": 2325556.0, |
| "step": 835 |
| }, |
| { |
| "entropy": 6.354130220413208, |
| "epoch": 0.022741116751269035, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.0004195, |
| "loss": 6.1991, |
| "mean_token_accuracy": 0.11779833287000656, |
| "num_tokens": 2340033.0, |
| "step": 840 |
| }, |
| { |
| "entropy": 6.290956926345825, |
| "epoch": 0.02287648054145516, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.000422, |
| "loss": 6.1439, |
| "mean_token_accuracy": 0.12168726176023484, |
| "num_tokens": 2353916.0, |
| "step": 845 |
| }, |
| { |
| "entropy": 6.26514630317688, |
| "epoch": 0.023011844331641287, |
| "grad_norm": 1.125, |
| "learning_rate": 0.0004245, |
| "loss": 6.1255, |
| "mean_token_accuracy": 0.12298965677618981, |
| "num_tokens": 2367161.0, |
| "step": 850 |
| }, |
| { |
| "entropy": 6.297455596923828, |
| "epoch": 0.02314720812182741, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.000427, |
| "loss": 6.1707, |
| "mean_token_accuracy": 0.11453822180628777, |
| "num_tokens": 2382562.0, |
| "step": 855 |
| }, |
| { |
| "entropy": 6.278497695922852, |
| "epoch": 0.023282571912013536, |
| "grad_norm": 1.21875, |
| "learning_rate": 0.0004295, |
| "loss": 6.084, |
| "mean_token_accuracy": 0.12197378650307655, |
| "num_tokens": 2395671.0, |
| "step": 860 |
| }, |
| { |
| "entropy": 6.201052713394165, |
| "epoch": 0.02341793570219966, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.000432, |
| "loss": 6.1328, |
| "mean_token_accuracy": 0.11925875097513199, |
| "num_tokens": 2409902.0, |
| "step": 865 |
| }, |
| { |
| "entropy": 6.319374704360962, |
| "epoch": 0.023553299492385788, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.0004345, |
| "loss": 6.1155, |
| "mean_token_accuracy": 0.11418568938970566, |
| "num_tokens": 2424405.0, |
| "step": 870 |
| }, |
| { |
| "entropy": 6.211519432067871, |
| "epoch": 0.023688663282571912, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.000437, |
| "loss": 6.0401, |
| "mean_token_accuracy": 0.11908271163702011, |
| "num_tokens": 2440256.0, |
| "step": 875 |
| }, |
| { |
| "entropy": 6.258747959136963, |
| "epoch": 0.023824027072758037, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.0004395, |
| "loss": 6.1066, |
| "mean_token_accuracy": 0.11787782683968544, |
| "num_tokens": 2453224.0, |
| "step": 880 |
| }, |
| { |
| "entropy": 6.132023286819458, |
| "epoch": 0.02395939086294416, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.000442, |
| "loss": 5.9843, |
| "mean_token_accuracy": 0.1226534366607666, |
| "num_tokens": 2468101.0, |
| "step": 885 |
| }, |
| { |
| "entropy": 6.3332679271698, |
| "epoch": 0.02409475465313029, |
| "grad_norm": 0.99609375, |
| "learning_rate": 0.0004445, |
| "loss": 6.2065, |
| "mean_token_accuracy": 0.12027881368994713, |
| "num_tokens": 2483221.0, |
| "step": 890 |
| }, |
| { |
| "entropy": 6.218679809570313, |
| "epoch": 0.024230118443316413, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.000447, |
| "loss": 6.0992, |
| "mean_token_accuracy": 0.11610312834382057, |
| "num_tokens": 2496389.0, |
| "step": 895 |
| }, |
| { |
| "entropy": 6.1929422378540036, |
| "epoch": 0.024365482233502538, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.00044950000000000003, |
| "loss": 6.0435, |
| "mean_token_accuracy": 0.11607689782977104, |
| "num_tokens": 2510988.0, |
| "step": 900 |
| }, |
| { |
| "entropy": 6.248309087753296, |
| "epoch": 0.024500846023688662, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.00045200000000000004, |
| "loss": 6.1425, |
| "mean_token_accuracy": 0.12013140320777893, |
| "num_tokens": 2525341.0, |
| "step": 905 |
| }, |
| { |
| "entropy": 6.198721647262573, |
| "epoch": 0.02463620981387479, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.00045450000000000004, |
| "loss": 6.1277, |
| "mean_token_accuracy": 0.11830744370818139, |
| "num_tokens": 2538706.0, |
| "step": 910 |
| }, |
| { |
| "entropy": 6.277400732040405, |
| "epoch": 0.024771573604060914, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.00045700000000000005, |
| "loss": 6.1407, |
| "mean_token_accuracy": 0.1180431790649891, |
| "num_tokens": 2554056.0, |
| "step": 915 |
| }, |
| { |
| "entropy": 6.122376012802124, |
| "epoch": 0.02490693739424704, |
| "grad_norm": 1.2109375, |
| "learning_rate": 0.00045950000000000006, |
| "loss": 6.0363, |
| "mean_token_accuracy": 0.12817837595939635, |
| "num_tokens": 2569073.0, |
| "step": 920 |
| }, |
| { |
| "entropy": 6.23994255065918, |
| "epoch": 0.025042301184433163, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.000462, |
| "loss": 6.0807, |
| "mean_token_accuracy": 0.12659804597496987, |
| "num_tokens": 2582519.0, |
| "step": 925 |
| }, |
| { |
| "entropy": 6.254793930053711, |
| "epoch": 0.02517766497461929, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.0004645, |
| "loss": 6.138, |
| "mean_token_accuracy": 0.11910348609089852, |
| "num_tokens": 2597308.0, |
| "step": 930 |
| }, |
| { |
| "entropy": 6.186693382263184, |
| "epoch": 0.025313028764805415, |
| "grad_norm": 1.125, |
| "learning_rate": 0.000467, |
| "loss": 6.1146, |
| "mean_token_accuracy": 0.12513377815485, |
| "num_tokens": 2610388.0, |
| "step": 935 |
| }, |
| { |
| "entropy": 6.133151054382324, |
| "epoch": 0.02544839255499154, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.0004695, |
| "loss": 5.9744, |
| "mean_token_accuracy": 0.1229440450668335, |
| "num_tokens": 2624701.0, |
| "step": 940 |
| }, |
| { |
| "entropy": 6.227858448028565, |
| "epoch": 0.025583756345177663, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.000472, |
| "loss": 6.1629, |
| "mean_token_accuracy": 0.11275116056203842, |
| "num_tokens": 2639582.0, |
| "step": 945 |
| }, |
| { |
| "entropy": 6.088177108764649, |
| "epoch": 0.02571912013536379, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.0004745, |
| "loss": 5.9973, |
| "mean_token_accuracy": 0.12648221775889396, |
| "num_tokens": 2653808.0, |
| "step": 950 |
| }, |
| { |
| "entropy": 6.13272876739502, |
| "epoch": 0.025854483925549916, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.000477, |
| "loss": 6.001, |
| "mean_token_accuracy": 0.12153996378183365, |
| "num_tokens": 2667423.0, |
| "step": 955 |
| }, |
| { |
| "entropy": 6.150818300247193, |
| "epoch": 0.02598984771573604, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.0004795, |
| "loss": 6.0237, |
| "mean_token_accuracy": 0.12148027569055557, |
| "num_tokens": 2683296.0, |
| "step": 960 |
| }, |
| { |
| "entropy": 6.043711376190186, |
| "epoch": 0.026125211505922164, |
| "grad_norm": 1.1640625, |
| "learning_rate": 0.000482, |
| "loss": 5.9768, |
| "mean_token_accuracy": 0.13035187423229216, |
| "num_tokens": 2697230.0, |
| "step": 965 |
| }, |
| { |
| "entropy": 6.165330123901367, |
| "epoch": 0.026260575296108292, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.0004845, |
| "loss": 5.9685, |
| "mean_token_accuracy": 0.1219008818268776, |
| "num_tokens": 2711689.0, |
| "step": 970 |
| }, |
| { |
| "entropy": 6.072505140304566, |
| "epoch": 0.026395939086294416, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.000487, |
| "loss": 6.0051, |
| "mean_token_accuracy": 0.12370155230164528, |
| "num_tokens": 2725786.0, |
| "step": 975 |
| }, |
| { |
| "entropy": 6.097587728500367, |
| "epoch": 0.02653130287648054, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0004895, |
| "loss": 6.0078, |
| "mean_token_accuracy": 0.12946900948882104, |
| "num_tokens": 2739444.0, |
| "step": 980 |
| }, |
| { |
| "entropy": 6.165721845626831, |
| "epoch": 0.02666666666666667, |
| "grad_norm": 0.9140625, |
| "learning_rate": 0.000492, |
| "loss": 5.9966, |
| "mean_token_accuracy": 0.12653872296214103, |
| "num_tokens": 2754692.0, |
| "step": 985 |
| }, |
| { |
| "entropy": 6.010534715652466, |
| "epoch": 0.026802030456852793, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.0004945, |
| "loss": 5.9195, |
| "mean_token_accuracy": 0.1301392510533333, |
| "num_tokens": 2767847.0, |
| "step": 990 |
| }, |
| { |
| "entropy": 6.176916885375976, |
| "epoch": 0.026937394247038917, |
| "grad_norm": 0.984375, |
| "learning_rate": 0.000497, |
| "loss": 6.147, |
| "mean_token_accuracy": 0.11529367789626122, |
| "num_tokens": 2783919.0, |
| "step": 995 |
| }, |
| { |
| "entropy": 6.178207778930664, |
| "epoch": 0.02707275803722504, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.0004995, |
| "loss": 6.049, |
| "mean_token_accuracy": 0.11618730947375297, |
| "num_tokens": 2797758.0, |
| "step": 1000 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 4000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4989469335552000.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
