Upload shakespearean_L16_a150 seed_42 (final adapter + all intermediate checkpoints)
f09ad50 verified | { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 7.0, | |
| "eval_steps": 500, | |
| "global_step": 5201, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "entropy": 1.148803424835205, | |
| "epoch": 0.013458950201884253, | |
| "grad_norm": 3.8571324348449707, | |
| "learning_rate": 2.4193548387096776e-06, | |
| "loss": 0.5379337310791016, | |
| "mean_token_accuracy": 0.8677904605865479, | |
| "num_tokens": 206424.0, | |
| "step": 10 | |
| }, | |
| { | |
| "entropy": 1.1465779304504395, | |
| "epoch": 0.026917900403768506, | |
| "grad_norm": 3.910707712173462, | |
| "learning_rate": 5.1075268817204305e-06, | |
| "loss": 0.512223768234253, | |
| "mean_token_accuracy": 0.8692944288253784, | |
| "num_tokens": 413440.0, | |
| "step": 20 | |
| }, | |
| { | |
| "entropy": 1.1525423288345338, | |
| "epoch": 0.040376850605652756, | |
| "grad_norm": 1.4944534301757812, | |
| "learning_rate": 7.795698924731183e-06, | |
| "loss": 0.3680122852325439, | |
| "mean_token_accuracy": 0.8862209141254425, | |
| "num_tokens": 620527.0, | |
| "step": 30 | |
| }, | |
| { | |
| "entropy": 1.1328181862831115, | |
| "epoch": 0.05383580080753701, | |
| "grad_norm": 0.6623373031616211, | |
| "learning_rate": 1.0483870967741936e-05, | |
| "loss": 0.2167149305343628, | |
| "mean_token_accuracy": 0.9302092254161834, | |
| "num_tokens": 827181.0, | |
| "step": 40 | |
| }, | |
| { | |
| "entropy": 1.1270673632621766, | |
| "epoch": 0.06729475100942127, | |
| "grad_norm": 0.475289911031723, | |
| "learning_rate": 1.3172043010752688e-05, | |
| "loss": 0.16388083696365358, | |
| "mean_token_accuracy": 0.9458359956741333, | |
| "num_tokens": 1034474.0, | |
| "step": 50 | |
| }, | |
| { | |
| "entropy": 1.1342731595039368, | |
| "epoch": 0.08075370121130551, | |
| "grad_norm": 0.3283269703388214, | |
| "learning_rate": 1.586021505376344e-05, | |
| "loss": 0.1500812292098999, | |
| "mean_token_accuracy": 0.9489317536354065, | |
| "num_tokens": 1241682.0, | |
| "step": 60 | |
| }, | |
| { | |
| "entropy": 1.1313621759414674, | |
| "epoch": 0.09421265141318977, | |
| "grad_norm": 0.26236599683761597, | |
| "learning_rate": 1.8548387096774193e-05, | |
| "loss": 0.1297295331954956, | |
| "mean_token_accuracy": 0.9544126331806183, | |
| "num_tokens": 1448340.0, | |
| "step": 70 | |
| }, | |
| { | |
| "entropy": 1.1243879675865174, | |
| "epoch": 0.10767160161507403, | |
| "grad_norm": 0.3455806374549866, | |
| "learning_rate": 2.1236559139784946e-05, | |
| "loss": 0.12099775075912475, | |
| "mean_token_accuracy": 0.957859605550766, | |
| "num_tokens": 1655485.0, | |
| "step": 80 | |
| }, | |
| { | |
| "entropy": 1.1236204266548158, | |
| "epoch": 0.12113055181695828, | |
| "grad_norm": 0.34308287501335144, | |
| "learning_rate": 2.39247311827957e-05, | |
| "loss": 0.12203640937805176, | |
| "mean_token_accuracy": 0.9569462358951568, | |
| "num_tokens": 1862721.0, | |
| "step": 90 | |
| }, | |
| { | |
| "entropy": 1.1212542057037354, | |
| "epoch": 0.13458950201884254, | |
| "grad_norm": 0.4861944913864136, | |
| "learning_rate": 2.661290322580645e-05, | |
| "loss": 0.11177135705947876, | |
| "mean_token_accuracy": 0.9603476166725159, | |
| "num_tokens": 2070235.0, | |
| "step": 100 | |
| }, | |
| { | |
| "entropy": 1.1195749163627624, | |
| "epoch": 0.1480484522207268, | |
| "grad_norm": 0.45371124148368835, | |
| "learning_rate": 2.9301075268817207e-05, | |
| "loss": 0.10732686519622803, | |
| "mean_token_accuracy": 0.9610694587230683, | |
| "num_tokens": 2276699.0, | |
| "step": 110 | |
| }, | |
| { | |
| "entropy": 1.117960274219513, | |
| "epoch": 0.16150740242261102, | |
| "grad_norm": 0.34547603130340576, | |
| "learning_rate": 3.198924731182796e-05, | |
| "loss": 0.10359159708023072, | |
| "mean_token_accuracy": 0.9620514333248138, | |
| "num_tokens": 2483409.0, | |
| "step": 120 | |
| }, | |
| { | |
| "entropy": 1.1100458979606629, | |
| "epoch": 0.17496635262449528, | |
| "grad_norm": 0.4161316752433777, | |
| "learning_rate": 3.467741935483872e-05, | |
| "loss": 0.09693117141723633, | |
| "mean_token_accuracy": 0.9630799531936646, | |
| "num_tokens": 2689832.0, | |
| "step": 130 | |
| }, | |
| { | |
| "entropy": 1.104417872428894, | |
| "epoch": 0.18842530282637954, | |
| "grad_norm": 0.36697497963905334, | |
| "learning_rate": 3.736559139784947e-05, | |
| "loss": 0.08809277415275574, | |
| "mean_token_accuracy": 0.966953593492508, | |
| "num_tokens": 2896836.0, | |
| "step": 140 | |
| }, | |
| { | |
| "entropy": 1.1028227806091309, | |
| "epoch": 0.2018842530282638, | |
| "grad_norm": 0.44922295212745667, | |
| "learning_rate": 4.005376344086022e-05, | |
| "loss": 0.08628258109092712, | |
| "mean_token_accuracy": 0.9677423119544983, | |
| "num_tokens": 3103952.0, | |
| "step": 150 | |
| }, | |
| { | |
| "entropy": 1.1022148132324219, | |
| "epoch": 0.21534320323014805, | |
| "grad_norm": 0.49055221676826477, | |
| "learning_rate": 4.2741935483870973e-05, | |
| "loss": 0.08765531778335571, | |
| "mean_token_accuracy": 0.9671335756778717, | |
| "num_tokens": 3310678.0, | |
| "step": 160 | |
| }, | |
| { | |
| "entropy": 1.1029130339622497, | |
| "epoch": 0.2288021534320323, | |
| "grad_norm": 0.9099652767181396, | |
| "learning_rate": 4.543010752688172e-05, | |
| "loss": 0.08238034844398498, | |
| "mean_token_accuracy": 0.9691508829593658, | |
| "num_tokens": 3517265.0, | |
| "step": 170 | |
| }, | |
| { | |
| "entropy": 1.1018678188323974, | |
| "epoch": 0.24226110363391656, | |
| "grad_norm": 0.6304323673248291, | |
| "learning_rate": 4.811827956989248e-05, | |
| "loss": 0.0836961030960083, | |
| "mean_token_accuracy": 0.9679419934749603, | |
| "num_tokens": 3724354.0, | |
| "step": 180 | |
| }, | |
| { | |
| "entropy": 1.0950765252113341, | |
| "epoch": 0.2557200538358008, | |
| "grad_norm": 0.6410331130027771, | |
| "learning_rate": 5.080645161290323e-05, | |
| "loss": 0.08708053231239318, | |
| "mean_token_accuracy": 0.9672979772090912, | |
| "num_tokens": 3931323.0, | |
| "step": 190 | |
| }, | |
| { | |
| "entropy": 1.1028541207313538, | |
| "epoch": 0.2691790040376851, | |
| "grad_norm": 0.5233514904975891, | |
| "learning_rate": 5.349462365591398e-05, | |
| "loss": 0.09297683238983154, | |
| "mean_token_accuracy": 0.9647954285144806, | |
| "num_tokens": 4137581.0, | |
| "step": 200 | |
| }, | |
| { | |
| "entropy": 1.0980924248695374, | |
| "epoch": 0.28263795423956933, | |
| "grad_norm": 0.452391117811203, | |
| "learning_rate": 5.618279569892473e-05, | |
| "loss": 0.07667996883392333, | |
| "mean_token_accuracy": 0.9710327327251435, | |
| "num_tokens": 4344516.0, | |
| "step": 210 | |
| }, | |
| { | |
| "entropy": 1.094509518146515, | |
| "epoch": 0.2960969044414536, | |
| "grad_norm": 0.36206117272377014, | |
| "learning_rate": 5.887096774193549e-05, | |
| "loss": 0.0823606014251709, | |
| "mean_token_accuracy": 0.9687092125415802, | |
| "num_tokens": 4551381.0, | |
| "step": 220 | |
| }, | |
| { | |
| "entropy": 1.100801420211792, | |
| "epoch": 0.30955585464333785, | |
| "grad_norm": 0.5433716177940369, | |
| "learning_rate": 6.155913978494624e-05, | |
| "loss": 0.07860409021377564, | |
| "mean_token_accuracy": 0.9693577349185943, | |
| "num_tokens": 4757696.0, | |
| "step": 230 | |
| }, | |
| { | |
| "entropy": 1.0913572549819945, | |
| "epoch": 0.32301480484522205, | |
| "grad_norm": 0.49431684613227844, | |
| "learning_rate": 6.4247311827957e-05, | |
| "loss": 0.07448963522911071, | |
| "mean_token_accuracy": 0.9722888886928558, | |
| "num_tokens": 4964472.0, | |
| "step": 240 | |
| }, | |
| { | |
| "entropy": 1.09194358587265, | |
| "epoch": 0.3364737550471063, | |
| "grad_norm": 0.49218472838401794, | |
| "learning_rate": 6.693548387096774e-05, | |
| "loss": 0.07904107570648193, | |
| "mean_token_accuracy": 0.9706218123435975, | |
| "num_tokens": 5171079.0, | |
| "step": 250 | |
| }, | |
| { | |
| "entropy": 1.0910104513168335, | |
| "epoch": 0.34993270524899056, | |
| "grad_norm": 0.4496209919452667, | |
| "learning_rate": 6.962365591397851e-05, | |
| "loss": 0.07965055108070374, | |
| "mean_token_accuracy": 0.9694360017776489, | |
| "num_tokens": 5377563.0, | |
| "step": 260 | |
| }, | |
| { | |
| "entropy": 1.0903191208839416, | |
| "epoch": 0.3633916554508748, | |
| "grad_norm": 0.6361143589019775, | |
| "learning_rate": 7.231182795698926e-05, | |
| "loss": 0.07528930306434631, | |
| "mean_token_accuracy": 0.9712541162967682, | |
| "num_tokens": 5584588.0, | |
| "step": 270 | |
| }, | |
| { | |
| "entropy": 1.088301658630371, | |
| "epoch": 0.3768506056527591, | |
| "grad_norm": 0.48176145553588867, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.07463239431381226, | |
| "mean_token_accuracy": 0.9709499478340149, | |
| "num_tokens": 5791987.0, | |
| "step": 280 | |
| }, | |
| { | |
| "entropy": 1.0902979731559754, | |
| "epoch": 0.39030955585464333, | |
| "grad_norm": 0.3715272843837738, | |
| "learning_rate": 7.768817204301076e-05, | |
| "loss": 0.07689260840415954, | |
| "mean_token_accuracy": 0.9711870729923249, | |
| "num_tokens": 5999048.0, | |
| "step": 290 | |
| }, | |
| { | |
| "entropy": 1.0841062188148498, | |
| "epoch": 0.4037685060565276, | |
| "grad_norm": 0.41488343477249146, | |
| "learning_rate": 8.037634408602151e-05, | |
| "loss": 0.07187070846557617, | |
| "mean_token_accuracy": 0.9723010718822479, | |
| "num_tokens": 6206324.0, | |
| "step": 300 | |
| }, | |
| { | |
| "entropy": 1.0855528712272644, | |
| "epoch": 0.41722745625841184, | |
| "grad_norm": 0.46184614300727844, | |
| "learning_rate": 8.306451612903227e-05, | |
| "loss": 0.07177088856697082, | |
| "mean_token_accuracy": 0.9727262139320374, | |
| "num_tokens": 6412954.0, | |
| "step": 310 | |
| }, | |
| { | |
| "entropy": 1.082417607307434, | |
| "epoch": 0.4306864064602961, | |
| "grad_norm": 0.4955524206161499, | |
| "learning_rate": 8.575268817204302e-05, | |
| "loss": 0.07426758408546448, | |
| "mean_token_accuracy": 0.9719507157802582, | |
| "num_tokens": 6619325.0, | |
| "step": 320 | |
| }, | |
| { | |
| "entropy": 1.079432439804077, | |
| "epoch": 0.44414535666218036, | |
| "grad_norm": 0.4565524458885193, | |
| "learning_rate": 8.844086021505377e-05, | |
| "loss": 0.07158007621765136, | |
| "mean_token_accuracy": 0.9722371101379395, | |
| "num_tokens": 6825686.0, | |
| "step": 330 | |
| }, | |
| { | |
| "entropy": 1.0759860038757325, | |
| "epoch": 0.4576043068640646, | |
| "grad_norm": 0.3511630892753601, | |
| "learning_rate": 9.112903225806452e-05, | |
| "loss": 0.06483781337738037, | |
| "mean_token_accuracy": 0.9750715494155884, | |
| "num_tokens": 7033233.0, | |
| "step": 340 | |
| }, | |
| { | |
| "entropy": 1.0776028990745545, | |
| "epoch": 0.47106325706594887, | |
| "grad_norm": 0.4951312243938446, | |
| "learning_rate": 9.381720430107528e-05, | |
| "loss": 0.06857329607009888, | |
| "mean_token_accuracy": 0.973279458284378, | |
| "num_tokens": 7240102.0, | |
| "step": 350 | |
| }, | |
| { | |
| "entropy": 1.0731443285942077, | |
| "epoch": 0.4845222072678331, | |
| "grad_norm": 0.4344209134578705, | |
| "learning_rate": 9.650537634408603e-05, | |
| "loss": 0.06759830713272094, | |
| "mean_token_accuracy": 0.9735908925533294, | |
| "num_tokens": 7446371.0, | |
| "step": 360 | |
| }, | |
| { | |
| "entropy": 1.0724977254867554, | |
| "epoch": 0.4979811574697174, | |
| "grad_norm": 0.366580605506897, | |
| "learning_rate": 9.919354838709678e-05, | |
| "loss": 0.07093892097473145, | |
| "mean_token_accuracy": 0.9729514002799988, | |
| "num_tokens": 7653471.0, | |
| "step": 370 | |
| }, | |
| { | |
| "entropy": 1.0748721718788148, | |
| "epoch": 0.5114401076716016, | |
| "grad_norm": 0.5749452710151672, | |
| "learning_rate": 9.999975729865971e-05, | |
| "loss": 0.07341647148132324, | |
| "mean_token_accuracy": 0.9716718792915344, | |
| "num_tokens": 7859948.0, | |
| "step": 380 | |
| }, | |
| { | |
| "entropy": 1.0717879056930542, | |
| "epoch": 0.5248990578734859, | |
| "grad_norm": 0.3533707857131958, | |
| "learning_rate": 9.999856856307314e-05, | |
| "loss": 0.0660275936126709, | |
| "mean_token_accuracy": 0.9741848886013031, | |
| "num_tokens": 8066342.0, | |
| "step": 390 | |
| }, | |
| { | |
| "entropy": 1.06906156539917, | |
| "epoch": 0.5383580080753702, | |
| "grad_norm": 0.37785258889198303, | |
| "learning_rate": 9.999638923896533e-05, | |
| "loss": 0.07019535303115845, | |
| "mean_token_accuracy": 0.9730446755886077, | |
| "num_tokens": 8273143.0, | |
| "step": 400 | |
| }, | |
| { | |
| "entropy": 1.0653064250946045, | |
| "epoch": 0.5518169582772544, | |
| "grad_norm": 0.5148960947990417, | |
| "learning_rate": 9.999321936951374e-05, | |
| "loss": 0.06534629464149475, | |
| "mean_token_accuracy": 0.9743636608123779, | |
| "num_tokens": 8479886.0, | |
| "step": 410 | |
| }, | |
| { | |
| "entropy": 1.0702444195747376, | |
| "epoch": 0.5652759084791387, | |
| "grad_norm": 0.3438984453678131, | |
| "learning_rate": 9.998905901752091e-05, | |
| "loss": 0.07364909052848816, | |
| "mean_token_accuracy": 0.9711242079734802, | |
| "num_tokens": 8686924.0, | |
| "step": 420 | |
| }, | |
| { | |
| "entropy": 1.0661863446235658, | |
| "epoch": 0.5787348586810229, | |
| "grad_norm": 0.406575083732605, | |
| "learning_rate": 9.998390826541315e-05, | |
| "loss": 0.07197093963623047, | |
| "mean_token_accuracy": 0.9721520006656647, | |
| "num_tokens": 8894083.0, | |
| "step": 430 | |
| }, | |
| { | |
| "entropy": 1.0637916922569275, | |
| "epoch": 0.5921938088829072, | |
| "grad_norm": 0.428232878446579, | |
| "learning_rate": 9.997776721523888e-05, | |
| "loss": 0.06615663766860962, | |
| "mean_token_accuracy": 0.9749840319156646, | |
| "num_tokens": 9101394.0, | |
| "step": 440 | |
| }, | |
| { | |
| "entropy": 1.0706895470619202, | |
| "epoch": 0.6056527590847914, | |
| "grad_norm": 0.4631795585155487, | |
| "learning_rate": 9.99706359886667e-05, | |
| "loss": 0.06901694536209106, | |
| "mean_token_accuracy": 0.9723595201969146, | |
| "num_tokens": 9307988.0, | |
| "step": 450 | |
| }, | |
| { | |
| "entropy": 1.0587412118911743, | |
| "epoch": 0.6191117092866757, | |
| "grad_norm": 0.34737110137939453, | |
| "learning_rate": 9.996251472698281e-05, | |
| "loss": 0.060923701524734496, | |
| "mean_token_accuracy": 0.9760171294212341, | |
| "num_tokens": 9515151.0, | |
| "step": 460 | |
| }, | |
| { | |
| "entropy": 1.0579840540885925, | |
| "epoch": 0.6325706594885598, | |
| "grad_norm": 0.45198148488998413, | |
| "learning_rate": 9.995340359108844e-05, | |
| "loss": 0.06548458337783813, | |
| "mean_token_accuracy": 0.9744683504104614, | |
| "num_tokens": 9721875.0, | |
| "step": 470 | |
| }, | |
| { | |
| "entropy": 1.0573879599571228, | |
| "epoch": 0.6460296096904441, | |
| "grad_norm": 0.3072788715362549, | |
| "learning_rate": 9.994330276149649e-05, | |
| "loss": 0.06333011984825135, | |
| "mean_token_accuracy": 0.9758989095687867, | |
| "num_tokens": 9928940.0, | |
| "step": 480 | |
| }, | |
| { | |
| "entropy": 1.053052794933319, | |
| "epoch": 0.6594885598923284, | |
| "grad_norm": 0.36213016510009766, | |
| "learning_rate": 9.993221243832797e-05, | |
| "loss": 0.06300820708274842, | |
| "mean_token_accuracy": 0.9755940675735474, | |
| "num_tokens": 10136064.0, | |
| "step": 490 | |
| }, | |
| { | |
| "entropy": 1.0509449362754821, | |
| "epoch": 0.6729475100942126, | |
| "grad_norm": 0.3727293610572815, | |
| "learning_rate": 9.992013284130816e-05, | |
| "loss": 0.0638339638710022, | |
| "mean_token_accuracy": 0.9754894852638245, | |
| "num_tokens": 10343159.0, | |
| "step": 500 | |
| }, | |
| { | |
| "entropy": 1.0530992031097413, | |
| "epoch": 0.6864064602960969, | |
| "grad_norm": 0.3802219331264496, | |
| "learning_rate": 9.990706420976206e-05, | |
| "loss": 0.06384505033493042, | |
| "mean_token_accuracy": 0.9755050659179687, | |
| "num_tokens": 10550244.0, | |
| "step": 510 | |
| }, | |
| { | |
| "entropy": 1.0434999823570252, | |
| "epoch": 0.6998654104979811, | |
| "grad_norm": 0.3587857186794281, | |
| "learning_rate": 9.989300680260985e-05, | |
| "loss": 0.06402989625930786, | |
| "mean_token_accuracy": 0.9750327467918396, | |
| "num_tokens": 10756685.0, | |
| "step": 520 | |
| }, | |
| { | |
| "entropy": 1.0373775839805603, | |
| "epoch": 0.7133243606998654, | |
| "grad_norm": 0.5431106686592102, | |
| "learning_rate": 9.98779608983616e-05, | |
| "loss": 0.06214879155158996, | |
| "mean_token_accuracy": 0.975670325756073, | |
| "num_tokens": 10963777.0, | |
| "step": 530 | |
| }, | |
| { | |
| "entropy": 1.042518949508667, | |
| "epoch": 0.7267833109017496, | |
| "grad_norm": 0.42488718032836914, | |
| "learning_rate": 9.986192679511189e-05, | |
| "loss": 0.06648873090744019, | |
| "mean_token_accuracy": 0.9741427898406982, | |
| "num_tokens": 11170113.0, | |
| "step": 540 | |
| }, | |
| { | |
| "entropy": 1.0383589148521424, | |
| "epoch": 0.7402422611036339, | |
| "grad_norm": 0.4388017952442169, | |
| "learning_rate": 9.984490481053372e-05, | |
| "loss": 0.06373496651649475, | |
| "mean_token_accuracy": 0.9753153324127197, | |
| "num_tokens": 11377177.0, | |
| "step": 550 | |
| }, | |
| { | |
| "entropy": 1.030055034160614, | |
| "epoch": 0.7537012113055181, | |
| "grad_norm": 0.5177302360534668, | |
| "learning_rate": 9.982689528187244e-05, | |
| "loss": 0.06524116396903992, | |
| "mean_token_accuracy": 0.974441123008728, | |
| "num_tokens": 11584297.0, | |
| "step": 560 | |
| }, | |
| { | |
| "entropy": 1.0238368034362793, | |
| "epoch": 0.7671601615074024, | |
| "grad_norm": 0.3689085841178894, | |
| "learning_rate": 9.98078985659389e-05, | |
| "loss": 0.057816171646118165, | |
| "mean_token_accuracy": 0.9771308839321137, | |
| "num_tokens": 11791221.0, | |
| "step": 570 | |
| }, | |
| { | |
| "entropy": 1.0260837078094482, | |
| "epoch": 0.7806191117092867, | |
| "grad_norm": 0.5362858772277832, | |
| "learning_rate": 9.978791503910246e-05, | |
| "loss": 0.07015071511268615, | |
| "mean_token_accuracy": 0.9720354020595551, | |
| "num_tokens": 11997267.0, | |
| "step": 580 | |
| }, | |
| { | |
| "entropy": 1.0203055262565612, | |
| "epoch": 0.7940780619111709, | |
| "grad_norm": 0.3500514328479767, | |
| "learning_rate": 9.97669450972835e-05, | |
| "loss": 0.0703177034854889, | |
| "mean_token_accuracy": 0.9722893536090851, | |
| "num_tokens": 12204122.0, | |
| "step": 590 | |
| }, | |
| { | |
| "entropy": 1.0201836228370667, | |
| "epoch": 0.8075370121130552, | |
| "grad_norm": 0.4321291744709015, | |
| "learning_rate": 9.974498915594557e-05, | |
| "loss": 0.06507774591445922, | |
| "mean_token_accuracy": 0.9742036819458008, | |
| "num_tokens": 12410976.0, | |
| "step": 600 | |
| }, | |
| { | |
| "entropy": 1.016060435771942, | |
| "epoch": 0.8209959623149394, | |
| "grad_norm": 0.30269697308540344, | |
| "learning_rate": 9.97220476500872e-05, | |
| "loss": 0.06292833685874939, | |
| "mean_token_accuracy": 0.9752326369285583, | |
| "num_tokens": 12617715.0, | |
| "step": 610 | |
| }, | |
| { | |
| "entropy": 1.0146049499511718, | |
| "epoch": 0.8344549125168237, | |
| "grad_norm": 0.3690892457962036, | |
| "learning_rate": 9.969812103423325e-05, | |
| "loss": 0.06385961771011353, | |
| "mean_token_accuracy": 0.9751694440841675, | |
| "num_tokens": 12824043.0, | |
| "step": 620 | |
| }, | |
| { | |
| "entropy": 1.0002728581428528, | |
| "epoch": 0.847913862718708, | |
| "grad_norm": 0.38600072264671326, | |
| "learning_rate": 9.967320978242592e-05, | |
| "loss": 0.0620916485786438, | |
| "mean_token_accuracy": 0.9763328671455384, | |
| "num_tokens": 13031364.0, | |
| "step": 630 | |
| }, | |
| { | |
| "entropy": 1.0015868484973907, | |
| "epoch": 0.8613728129205922, | |
| "grad_norm": 0.2936280369758606, | |
| "learning_rate": 9.964731438821533e-05, | |
| "loss": 0.05919194221496582, | |
| "mean_token_accuracy": 0.9767723500728607, | |
| "num_tokens": 13238320.0, | |
| "step": 640 | |
| }, | |
| { | |
| "entropy": 0.9941371619701386, | |
| "epoch": 0.8748317631224765, | |
| "grad_norm": 0.3988257050514221, | |
| "learning_rate": 9.962043536464978e-05, | |
| "loss": 0.06394914388656617, | |
| "mean_token_accuracy": 0.9750961601734162, | |
| "num_tokens": 13444929.0, | |
| "step": 650 | |
| }, | |
| { | |
| "entropy": 0.9894050359725952, | |
| "epoch": 0.8882907133243607, | |
| "grad_norm": 0.373199462890625, | |
| "learning_rate": 9.959257324426556e-05, | |
| "loss": 0.062080603837966916, | |
| "mean_token_accuracy": 0.9750838100910186, | |
| "num_tokens": 13652058.0, | |
| "step": 660 | |
| }, | |
| { | |
| "entropy": 0.9806465029716491, | |
| "epoch": 0.901749663526245, | |
| "grad_norm": 0.4831550121307373, | |
| "learning_rate": 9.95637285790764e-05, | |
| "loss": 0.058683907985687254, | |
| "mean_token_accuracy": 0.9773052394390106, | |
| "num_tokens": 13859138.0, | |
| "step": 670 | |
| }, | |
| { | |
| "entropy": 0.9766267120838166, | |
| "epoch": 0.9152086137281292, | |
| "grad_norm": 0.2987309396266937, | |
| "learning_rate": 9.953390194056258e-05, | |
| "loss": 0.05572218298912048, | |
| "mean_token_accuracy": 0.9783341228961945, | |
| "num_tokens": 14066689.0, | |
| "step": 680 | |
| }, | |
| { | |
| "entropy": 0.9726546585559845, | |
| "epoch": 0.9286675639300135, | |
| "grad_norm": 0.49207931756973267, | |
| "learning_rate": 9.950309391965947e-05, | |
| "loss": 0.060380947589874265, | |
| "mean_token_accuracy": 0.9769295156002045, | |
| "num_tokens": 14273683.0, | |
| "step": 690 | |
| }, | |
| { | |
| "entropy": 0.9802318632602691, | |
| "epoch": 0.9421265141318977, | |
| "grad_norm": 0.45118796825408936, | |
| "learning_rate": 9.947130512674602e-05, | |
| "loss": 0.061833739280700684, | |
| "mean_token_accuracy": 0.9755691647529602, | |
| "num_tokens": 14480450.0, | |
| "step": 700 | |
| }, | |
| { | |
| "entropy": 0.9772093653678894, | |
| "epoch": 0.955585464333782, | |
| "grad_norm": 0.32441404461860657, | |
| "learning_rate": 9.943853619163255e-05, | |
| "loss": 0.06221691370010376, | |
| "mean_token_accuracy": 0.97582648396492, | |
| "num_tokens": 14687394.0, | |
| "step": 710 | |
| }, | |
| { | |
| "entropy": 0.9712013483047486, | |
| "epoch": 0.9690444145356663, | |
| "grad_norm": 0.4250052273273468, | |
| "learning_rate": 9.94047877635482e-05, | |
| "loss": 0.06065620183944702, | |
| "mean_token_accuracy": 0.9765822350978851, | |
| "num_tokens": 14894507.0, | |
| "step": 720 | |
| }, | |
| { | |
| "entropy": 0.9658361196517944, | |
| "epoch": 0.9825033647375505, | |
| "grad_norm": 0.32111653685569763, | |
| "learning_rate": 9.93700605111283e-05, | |
| "loss": 0.05561348795890808, | |
| "mean_token_accuracy": 0.977992582321167, | |
| "num_tokens": 15101391.0, | |
| "step": 730 | |
| }, | |
| { | |
| "entropy": 0.9521977305412292, | |
| "epoch": 0.9959623149394348, | |
| "grad_norm": 0.4938078224658966, | |
| "learning_rate": 9.933435512240084e-05, | |
| "loss": 0.054716891050338744, | |
| "mean_token_accuracy": 0.9787404000759125, | |
| "num_tokens": 15308546.0, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_entropy": 0.953010377610565, | |
| "eval_loss": 0.057268138974905014, | |
| "eval_mean_token_accuracy": 0.9773533947908195, | |
| "eval_num_tokens": 15370753.0, | |
| "eval_runtime": 14.2376, | |
| "eval_samples_per_second": 351.183, | |
| "eval_steps_per_second": 11.027, | |
| "step": 743 | |
| }, | |
| { | |
| "entropy": 0.9481509625911713, | |
| "epoch": 1.009421265141319, | |
| "grad_norm": 0.45019322633743286, | |
| "learning_rate": 9.929767230477305e-05, | |
| "loss": 0.05444328188896179, | |
| "mean_token_accuracy": 0.9790198564529419, | |
| "num_tokens": 15516109.0, | |
| "step": 750 | |
| }, | |
| { | |
| "entropy": 0.9414805412292481, | |
| "epoch": 1.0228802153432033, | |
| "grad_norm": 0.4308762848377228, | |
| "learning_rate": 9.92600127850173e-05, | |
| "loss": 0.05448293685913086, | |
| "mean_token_accuracy": 0.9784913420677185, | |
| "num_tokens": 15723217.0, | |
| "step": 760 | |
| }, | |
| { | |
| "entropy": 0.9518636524677276, | |
| "epoch": 1.0363391655450875, | |
| "grad_norm": 0.35742712020874023, | |
| "learning_rate": 9.922137730925673e-05, | |
| "loss": 0.050360894203186034, | |
| "mean_token_accuracy": 0.9803691744804383, | |
| "num_tokens": 15929676.0, | |
| "step": 770 | |
| }, | |
| { | |
| "entropy": 0.9442292392253876, | |
| "epoch": 1.0497981157469718, | |
| "grad_norm": 0.3914043605327606, | |
| "learning_rate": 9.918176664295041e-05, | |
| "loss": 0.049952417612075806, | |
| "mean_token_accuracy": 0.9808734893798828, | |
| "num_tokens": 16136561.0, | |
| "step": 780 | |
| }, | |
| { | |
| "entropy": 0.9437739491462708, | |
| "epoch": 1.063257065948856, | |
| "grad_norm": 0.5056980848312378, | |
| "learning_rate": 9.914118157087824e-05, | |
| "loss": 0.04833500385284424, | |
| "mean_token_accuracy": 0.9812267363071442, | |
| "num_tokens": 16343444.0, | |
| "step": 790 | |
| }, | |
| { | |
| "entropy": 0.9437163591384887, | |
| "epoch": 1.0767160161507403, | |
| "grad_norm": 0.4277653396129608, | |
| "learning_rate": 9.909962289712538e-05, | |
| "loss": 0.04925972819328308, | |
| "mean_token_accuracy": 0.9810784041881562, | |
| "num_tokens": 16550530.0, | |
| "step": 800 | |
| }, | |
| { | |
| "entropy": 0.9458538055419922, | |
| "epoch": 1.0901749663526246, | |
| "grad_norm": 0.3851556181907654, | |
| "learning_rate": 9.905709144506629e-05, | |
| "loss": 0.05031745433807373, | |
| "mean_token_accuracy": 0.9802758753299713, | |
| "num_tokens": 16757340.0, | |
| "step": 810 | |
| }, | |
| { | |
| "entropy": 0.9309192001819611, | |
| "epoch": 1.1036339165545088, | |
| "grad_norm": 0.3910880982875824, | |
| "learning_rate": 9.901358805734846e-05, | |
| "loss": 0.052798688411712646, | |
| "mean_token_accuracy": 0.9791285336017609, | |
| "num_tokens": 16963736.0, | |
| "step": 820 | |
| }, | |
| { | |
| "entropy": 0.9286812126636506, | |
| "epoch": 1.117092866756393, | |
| "grad_norm": 0.40629255771636963, | |
| "learning_rate": 9.89691135958757e-05, | |
| "loss": 0.0501678466796875, | |
| "mean_token_accuracy": 0.9807449519634247, | |
| "num_tokens": 17170342.0, | |
| "step": 830 | |
| }, | |
| { | |
| "entropy": 0.9351256549358368, | |
| "epoch": 1.1305518169582773, | |
| "grad_norm": 0.43279024958610535, | |
| "learning_rate": 9.892366894179105e-05, | |
| "loss": 0.054589086771011354, | |
| "mean_token_accuracy": 0.9786225914955139, | |
| "num_tokens": 17377459.0, | |
| "step": 840 | |
| }, | |
| { | |
| "entropy": 0.9256517946720123, | |
| "epoch": 1.1440107671601616, | |
| "grad_norm": 0.34225529432296753, | |
| "learning_rate": 9.887725499545937e-05, | |
| "loss": 0.05118160843849182, | |
| "mean_token_accuracy": 0.9801044940948487, | |
| "num_tokens": 17584121.0, | |
| "step": 850 | |
| }, | |
| { | |
| "entropy": 0.9092171311378479, | |
| "epoch": 1.1574697173620458, | |
| "grad_norm": 0.4391540586948395, | |
| "learning_rate": 9.882987267644939e-05, | |
| "loss": 0.050338762998580935, | |
| "mean_token_accuracy": 0.9804662644863129, | |
| "num_tokens": 17791221.0, | |
| "step": 860 | |
| }, | |
| { | |
| "entropy": 0.9084291815757751, | |
| "epoch": 1.17092866756393, | |
| "grad_norm": 0.36910438537597656, | |
| "learning_rate": 9.878152292351563e-05, | |
| "loss": 0.05027775764465332, | |
| "mean_token_accuracy": 0.9796700894832611, | |
| "num_tokens": 17997756.0, | |
| "step": 870 | |
| }, | |
| { | |
| "entropy": 0.9082553148269653, | |
| "epoch": 1.1843876177658144, | |
| "grad_norm": 0.6938081383705139, | |
| "learning_rate": 9.873220669457975e-05, | |
| "loss": 0.0528791606426239, | |
| "mean_token_accuracy": 0.9790813088417053, | |
| "num_tokens": 18204162.0, | |
| "step": 880 | |
| }, | |
| { | |
| "entropy": 0.9058304250240325, | |
| "epoch": 1.1978465679676986, | |
| "grad_norm": 0.45121562480926514, | |
| "learning_rate": 9.868192496671147e-05, | |
| "loss": 0.05375846028327942, | |
| "mean_token_accuracy": 0.978945928812027, | |
| "num_tokens": 18410866.0, | |
| "step": 890 | |
| }, | |
| { | |
| "entropy": 0.8980253875255585, | |
| "epoch": 1.2113055181695827, | |
| "grad_norm": 0.38418707251548767, | |
| "learning_rate": 9.86306787361094e-05, | |
| "loss": 0.04832733869552612, | |
| "mean_token_accuracy": 0.981135094165802, | |
| "num_tokens": 18617340.0, | |
| "step": 900 | |
| }, | |
| { | |
| "entropy": 0.9037271738052368, | |
| "epoch": 1.224764468371467, | |
| "grad_norm": 0.4018036127090454, | |
| "learning_rate": 9.857846901808117e-05, | |
| "loss": 0.0564426064491272, | |
| "mean_token_accuracy": 0.978033185005188, | |
| "num_tokens": 18823367.0, | |
| "step": 910 | |
| }, | |
| { | |
| "entropy": 0.8979138970375061, | |
| "epoch": 1.2382234185733512, | |
| "grad_norm": 0.40662312507629395, | |
| "learning_rate": 9.852529684702329e-05, | |
| "loss": 0.051144140958786014, | |
| "mean_token_accuracy": 0.9796078085899353, | |
| "num_tokens": 19030313.0, | |
| "step": 920 | |
| }, | |
| { | |
| "entropy": 0.8905315518379211, | |
| "epoch": 1.2516823687752354, | |
| "grad_norm": 0.4605758786201477, | |
| "learning_rate": 9.847116327640082e-05, | |
| "loss": 0.04797832369804382, | |
| "mean_token_accuracy": 0.9815882265567779, | |
| "num_tokens": 19237742.0, | |
| "step": 930 | |
| }, | |
| { | |
| "entropy": 0.8781926572322846, | |
| "epoch": 1.2651413189771197, | |
| "grad_norm": 0.41945287585258484, | |
| "learning_rate": 9.841606937872632e-05, | |
| "loss": 0.05179686546325683, | |
| "mean_token_accuracy": 0.9793125987052917, | |
| "num_tokens": 19444394.0, | |
| "step": 940 | |
| }, | |
| { | |
| "entropy": 0.8800916612148285, | |
| "epoch": 1.278600269179004, | |
| "grad_norm": 0.44151630997657776, | |
| "learning_rate": 9.836001624553869e-05, | |
| "loss": 0.05166807770729065, | |
| "mean_token_accuracy": 0.97959805727005, | |
| "num_tokens": 19651243.0, | |
| "step": 950 | |
| }, | |
| { | |
| "entropy": 0.8785765290260314, | |
| "epoch": 1.2920592193808882, | |
| "grad_norm": 0.35568565130233765, | |
| "learning_rate": 9.830300498738152e-05, | |
| "loss": 0.05172090530395508, | |
| "mean_token_accuracy": 0.9796277642250061, | |
| "num_tokens": 19858323.0, | |
| "step": 960 | |
| }, | |
| { | |
| "entropy": 0.8748304843902588, | |
| "epoch": 1.3055181695827724, | |
| "grad_norm": 0.5144789814949036, | |
| "learning_rate": 9.824503673378112e-05, | |
| "loss": 0.05269254446029663, | |
| "mean_token_accuracy": 0.9794202625751496, | |
| "num_tokens": 20064779.0, | |
| "step": 970 | |
| }, | |
| { | |
| "entropy": 0.878674441576004, | |
| "epoch": 1.3189771197846567, | |
| "grad_norm": 0.3717172145843506, | |
| "learning_rate": 9.81861126332241e-05, | |
| "loss": 0.05027352571487427, | |
| "mean_token_accuracy": 0.9804058611392975, | |
| "num_tokens": 20271663.0, | |
| "step": 980 | |
| }, | |
| { | |
| "entropy": 0.874711400270462, | |
| "epoch": 1.332436069986541, | |
| "grad_norm": 0.5428106784820557, | |
| "learning_rate": 9.812623385313461e-05, | |
| "loss": 0.04746338129043579, | |
| "mean_token_accuracy": 0.9809837818145752, | |
| "num_tokens": 20479093.0, | |
| "step": 990 | |
| }, | |
| { | |
| "entropy": 0.8767077684402466, | |
| "epoch": 1.3458950201884252, | |
| "grad_norm": 0.4203868806362152, | |
| "learning_rate": 9.806540157985131e-05, | |
| "loss": 0.047260144352912904, | |
| "mean_token_accuracy": 0.981168121099472, | |
| "num_tokens": 20686058.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "entropy": 0.8626155018806457, | |
| "epoch": 1.3593539703903095, | |
| "grad_norm": 0.5116966962814331, | |
| "learning_rate": 9.800361701860368e-05, | |
| "loss": 0.04717045724391937, | |
| "mean_token_accuracy": 0.9814311504364014, | |
| "num_tokens": 20892972.0, | |
| "step": 1010 | |
| }, | |
| { | |
| "entropy": 0.8597043097019196, | |
| "epoch": 1.3728129205921937, | |
| "grad_norm": 0.5143622159957886, | |
| "learning_rate": 9.794088139348835e-05, | |
| "loss": 0.04667789340019226, | |
| "mean_token_accuracy": 0.9814274728298187, | |
| "num_tokens": 21100415.0, | |
| "step": 1020 | |
| }, | |
| { | |
| "entropy": 0.8572463095188141, | |
| "epoch": 1.386271870794078, | |
| "grad_norm": 0.553600549697876, | |
| "learning_rate": 9.787719594744468e-05, | |
| "loss": 0.050517672300338747, | |
| "mean_token_accuracy": 0.9801969349384307, | |
| "num_tokens": 21307218.0, | |
| "step": 1030 | |
| }, | |
| { | |
| "entropy": 0.8552091658115387, | |
| "epoch": 1.3997308209959622, | |
| "grad_norm": 0.4543687403202057, | |
| "learning_rate": 9.781256194223023e-05, | |
| "loss": 0.05095386505126953, | |
| "mean_token_accuracy": 0.9798394560813903, | |
| "num_tokens": 21514406.0, | |
| "step": 1040 | |
| }, | |
| { | |
| "entropy": 0.8547879338264466, | |
| "epoch": 1.4131897711978465, | |
| "grad_norm": 0.3877199590206146, | |
| "learning_rate": 9.774698065839577e-05, | |
| "loss": 0.05205919742584229, | |
| "mean_token_accuracy": 0.9795322000980378, | |
| "num_tokens": 21721292.0, | |
| "step": 1050 | |
| }, | |
| { | |
| "entropy": 0.8591440379619598, | |
| "epoch": 1.4266487213997308, | |
| "grad_norm": 0.4777373671531677, | |
| "learning_rate": 9.768045339525979e-05, | |
| "loss": 0.04756388366222382, | |
| "mean_token_accuracy": 0.9814973652362824, | |
| "num_tokens": 21927753.0, | |
| "step": 1060 | |
| }, | |
| { | |
| "entropy": 0.83706636428833, | |
| "epoch": 1.440107671601615, | |
| "grad_norm": 0.3106399178504944, | |
| "learning_rate": 9.76129814708829e-05, | |
| "loss": 0.04771801829338074, | |
| "mean_token_accuracy": 0.9811239123344422, | |
| "num_tokens": 22134047.0, | |
| "step": 1070 | |
| }, | |
| { | |
| "entropy": 0.8355492770671844, | |
| "epoch": 1.4535666218034993, | |
| "grad_norm": 0.5079196691513062, | |
| "learning_rate": 9.754456622204167e-05, | |
| "loss": 0.04518579244613648, | |
| "mean_token_accuracy": 0.9819768607616425, | |
| "num_tokens": 22340843.0, | |
| "step": 1080 | |
| }, | |
| { | |
| "entropy": 0.8377915918827057, | |
| "epoch": 1.4670255720053835, | |
| "grad_norm": 0.38823193311691284, | |
| "learning_rate": 9.747520900420209e-05, | |
| "loss": 0.04822598397731781, | |
| "mean_token_accuracy": 0.9811451613903046, | |
| "num_tokens": 22547662.0, | |
| "step": 1090 | |
| }, | |
| { | |
| "entropy": 0.8314657747745514, | |
| "epoch": 1.4804845222072678, | |
| "grad_norm": 0.6800487041473389, | |
| "learning_rate": 9.740491119149277e-05, | |
| "loss": 0.04973709583282471, | |
| "mean_token_accuracy": 0.9797703623771667, | |
| "num_tokens": 22754487.0, | |
| "step": 1100 | |
| }, | |
| { | |
| "entropy": 0.8429964482784271, | |
| "epoch": 1.493943472409152, | |
| "grad_norm": 0.46988436579704285, | |
| "learning_rate": 9.733367417667773e-05, | |
| "loss": 0.0486497312784195, | |
| "mean_token_accuracy": 0.9810753047466279, | |
| "num_tokens": 22961947.0, | |
| "step": 1110 | |
| }, | |
| { | |
| "entropy": 0.8371677458286285, | |
| "epoch": 1.5074024226110363, | |
| "grad_norm": 0.4881710410118103, | |
| "learning_rate": 9.726149937112873e-05, | |
| "loss": 0.04747593402862549, | |
| "mean_token_accuracy": 0.9815979599952698, | |
| "num_tokens": 23169342.0, | |
| "step": 1120 | |
| }, | |
| { | |
| "entropy": 0.8210869550704956, | |
| "epoch": 1.5208613728129206, | |
| "grad_norm": 0.4130207896232605, | |
| "learning_rate": 9.718838820479743e-05, | |
| "loss": 0.049933090806007385, | |
| "mean_token_accuracy": 0.9803601801395416, | |
| "num_tokens": 23376509.0, | |
| "step": 1130 | |
| }, | |
| { | |
| "entropy": 0.8233297169208527, | |
| "epoch": 1.5343203230148048, | |
| "grad_norm": 0.47688028216362, | |
| "learning_rate": 9.711434212618691e-05, | |
| "loss": 0.049675410985946654, | |
| "mean_token_accuracy": 0.9803059160709381, | |
| "num_tokens": 23582681.0, | |
| "step": 1140 | |
| }, | |
| { | |
| "entropy": 0.8203558087348938, | |
| "epoch": 1.547779273216689, | |
| "grad_norm": 0.45380693674087524, | |
| "learning_rate": 9.703936260232308e-05, | |
| "loss": 0.04854576587677002, | |
| "mean_token_accuracy": 0.9805228471755981, | |
| "num_tokens": 23789426.0, | |
| "step": 1150 | |
| }, | |
| { | |
| "entropy": 0.8290607392787933, | |
| "epoch": 1.5612382234185733, | |
| "grad_norm": 0.4461262822151184, | |
| "learning_rate": 9.696345111872557e-05, | |
| "loss": 0.04563935399055481, | |
| "mean_token_accuracy": 0.9819368541240692, | |
| "num_tokens": 23996347.0, | |
| "step": 1160 | |
| }, | |
| { | |
| "entropy": 0.8161819994449615, | |
| "epoch": 1.5746971736204576, | |
| "grad_norm": 0.46854355931282043, | |
| "learning_rate": 9.688660917937838e-05, | |
| "loss": 0.04675787091255188, | |
| "mean_token_accuracy": 0.98145791888237, | |
| "num_tokens": 24203599.0, | |
| "step": 1170 | |
| }, | |
| { | |
| "entropy": 0.8060347080230713, | |
| "epoch": 1.5881561238223418, | |
| "grad_norm": 0.41180017590522766, | |
| "learning_rate": 9.68088383066999e-05, | |
| "loss": 0.04404969215393066, | |
| "mean_token_accuracy": 0.9832783460617065, | |
| "num_tokens": 24410522.0, | |
| "step": 1180 | |
| }, | |
| { | |
| "entropy": 0.8048585295677185, | |
| "epoch": 1.601615074024226, | |
| "grad_norm": 0.491583913564682, | |
| "learning_rate": 9.673014004151292e-05, | |
| "loss": 0.045036160945892335, | |
| "mean_token_accuracy": 0.9821190059185028, | |
| "num_tokens": 24617845.0, | |
| "step": 1190 | |
| }, | |
| { | |
| "entropy": 0.8028138160705567, | |
| "epoch": 1.6150740242261103, | |
| "grad_norm": 0.4175598919391632, | |
| "learning_rate": 9.665051594301407e-05, | |
| "loss": 0.04619626402854919, | |
| "mean_token_accuracy": 0.9816527247428894, | |
| "num_tokens": 24824416.0, | |
| "step": 1200 | |
| }, | |
| { | |
| "entropy": 0.8100907325744628, | |
| "epoch": 1.6285329744279946, | |
| "grad_norm": 0.4809361696243286, | |
| "learning_rate": 9.656996758874284e-05, | |
| "loss": 0.04774007797241211, | |
| "mean_token_accuracy": 0.9811590790748597, | |
| "num_tokens": 25031469.0, | |
| "step": 1210 | |
| }, | |
| { | |
| "entropy": 0.8034710586071014, | |
| "epoch": 1.6419919246298789, | |
| "grad_norm": 0.37044280767440796, | |
| "learning_rate": 9.648849657455044e-05, | |
| "loss": 0.0478478193283081, | |
| "mean_token_accuracy": 0.9812443971633911, | |
| "num_tokens": 25238653.0, | |
| "step": 1220 | |
| }, | |
| { | |
| "entropy": 0.816223555803299, | |
| "epoch": 1.6554508748317631, | |
| "grad_norm": 0.3459724187850952, | |
| "learning_rate": 9.640610451456811e-05, | |
| "loss": 0.047498634457588194, | |
| "mean_token_accuracy": 0.9809110701084137, | |
| "num_tokens": 25445715.0, | |
| "step": 1230 | |
| }, | |
| { | |
| "entropy": 0.8094809174537658, | |
| "epoch": 1.6689098250336474, | |
| "grad_norm": 0.4526945650577545, | |
| "learning_rate": 9.632279304117517e-05, | |
| "loss": 0.04413290619850159, | |
| "mean_token_accuracy": 0.9828720092773438, | |
| "num_tokens": 25652990.0, | |
| "step": 1240 | |
| }, | |
| { | |
| "entropy": 0.8075843989849091, | |
| "epoch": 1.6823687752355316, | |
| "grad_norm": 0.3427794575691223, | |
| "learning_rate": 9.623856380496664e-05, | |
| "loss": 0.04015462398529053, | |
| "mean_token_accuracy": 0.984161913394928, | |
| "num_tokens": 25859529.0, | |
| "step": 1250 | |
| }, | |
| { | |
| "entropy": 0.7957218885421753, | |
| "epoch": 1.695827725437416, | |
| "grad_norm": 0.4648391902446747, | |
| "learning_rate": 9.615341847472059e-05, | |
| "loss": 0.04236364960670471, | |
| "mean_token_accuracy": 0.9831009984016419, | |
| "num_tokens": 26066638.0, | |
| "step": 1260 | |
| }, | |
| { | |
| "entropy": 0.7911267936229706, | |
| "epoch": 1.7092866756393001, | |
| "grad_norm": 0.35517409443855286, | |
| "learning_rate": 9.606735873736505e-05, | |
| "loss": 0.04558713436126709, | |
| "mean_token_accuracy": 0.982138192653656, | |
| "num_tokens": 26273299.0, | |
| "step": 1270 | |
| }, | |
| { | |
| "entropy": 0.7834631562232971, | |
| "epoch": 1.7227456258411844, | |
| "grad_norm": 0.4664056599140167, | |
| "learning_rate": 9.598038629794461e-05, | |
| "loss": 0.04543980956077576, | |
| "mean_token_accuracy": 0.9820871353149414, | |
| "num_tokens": 26480619.0, | |
| "step": 1280 | |
| }, | |
| { | |
| "entropy": 0.7766066193580627, | |
| "epoch": 1.7362045760430687, | |
| "grad_norm": 0.46915021538734436, | |
| "learning_rate": 9.589250287958657e-05, | |
| "loss": 0.048852354288101196, | |
| "mean_token_accuracy": 0.9804103672504425, | |
| "num_tokens": 26687502.0, | |
| "step": 1290 | |
| }, | |
| { | |
| "entropy": 0.7885740280151368, | |
| "epoch": 1.749663526244953, | |
| "grad_norm": 0.5565235614776611, | |
| "learning_rate": 9.580371022346693e-05, | |
| "loss": 0.04616362452507019, | |
| "mean_token_accuracy": 0.9811102449893951, | |
| "num_tokens": 26894776.0, | |
| "step": 1300 | |
| }, | |
| { | |
| "entropy": 0.7828902661800384, | |
| "epoch": 1.7631224764468372, | |
| "grad_norm": 0.5803515911102295, | |
| "learning_rate": 9.571401008877572e-05, | |
| "loss": 0.04636417329311371, | |
| "mean_token_accuracy": 0.9814817011356354, | |
| "num_tokens": 27101361.0, | |
| "step": 1310 | |
| }, | |
| { | |
| "entropy": 0.7779680609703064, | |
| "epoch": 1.7765814266487214, | |
| "grad_norm": 0.46953341364860535, | |
| "learning_rate": 9.562340425268233e-05, | |
| "loss": 0.043124464154243466, | |
| "mean_token_accuracy": 0.9823956906795501, | |
| "num_tokens": 27308139.0, | |
| "step": 1320 | |
| }, | |
| { | |
| "entropy": 0.7818998336791992, | |
| "epoch": 1.7900403768506057, | |
| "grad_norm": 0.43444475531578064, | |
| "learning_rate": 9.553189451030019e-05, | |
| "loss": 0.04699342250823975, | |
| "mean_token_accuracy": 0.981617671251297, | |
| "num_tokens": 27515135.0, | |
| "step": 1330 | |
| }, | |
| { | |
| "entropy": 0.7814963579177856, | |
| "epoch": 1.80349932705249, | |
| "grad_norm": 0.7200784087181091, | |
| "learning_rate": 9.543948267465115e-05, | |
| "loss": 0.04428764283657074, | |
| "mean_token_accuracy": 0.9820694208145142, | |
| "num_tokens": 27722318.0, | |
| "step": 1340 | |
| }, | |
| { | |
| "entropy": 0.7804880917072297, | |
| "epoch": 1.8169582772543742, | |
| "grad_norm": 0.4098879396915436, | |
| "learning_rate": 9.534617057662977e-05, | |
| "loss": 0.04612208902835846, | |
| "mean_token_accuracy": 0.981588214635849, | |
| "num_tokens": 27929006.0, | |
| "step": 1350 | |
| }, | |
| { | |
| "entropy": 0.7731973230838776, | |
| "epoch": 1.8304172274562585, | |
| "grad_norm": 0.46128687262535095, | |
| "learning_rate": 9.525196006496679e-05, | |
| "loss": 0.04260898232460022, | |
| "mean_token_accuracy": 0.9835397064685821, | |
| "num_tokens": 28136443.0, | |
| "step": 1360 | |
| }, | |
| { | |
| "entropy": 0.7819123864173889, | |
| "epoch": 1.8438761776581427, | |
| "grad_norm": 0.41956645250320435, | |
| "learning_rate": 9.515685300619271e-05, | |
| "loss": 0.045637202262878415, | |
| "mean_token_accuracy": 0.981810599565506, | |
| "num_tokens": 28343644.0, | |
| "step": 1370 | |
| }, | |
| { | |
| "entropy": 0.7694122910499572, | |
| "epoch": 1.857335127860027, | |
| "grad_norm": 0.3839203417301178, | |
| "learning_rate": 9.506085128460065e-05, | |
| "loss": 0.044372576475143435, | |
| "mean_token_accuracy": 0.9824269771575928, | |
| "num_tokens": 28550070.0, | |
| "step": 1380 | |
| }, | |
| { | |
| "entropy": 0.7737328886985779, | |
| "epoch": 1.8707940780619112, | |
| "grad_norm": 0.3746931254863739, | |
| "learning_rate": 9.496395680220918e-05, | |
| "loss": 0.043450570106506346, | |
| "mean_token_accuracy": 0.9827447474002838, | |
| "num_tokens": 28756798.0, | |
| "step": 1390 | |
| }, | |
| { | |
| "entropy": 0.783908200263977, | |
| "epoch": 1.8842530282637955, | |
| "grad_norm": 0.4228839874267578, | |
| "learning_rate": 9.486617147872446e-05, | |
| "loss": 0.04549018144607544, | |
| "mean_token_accuracy": 0.9819923400878906, | |
| "num_tokens": 28963808.0, | |
| "step": 1400 | |
| }, | |
| { | |
| "entropy": 0.7758362650871277, | |
| "epoch": 1.8977119784656797, | |
| "grad_norm": 0.5251613855361938, | |
| "learning_rate": 9.476749725150235e-05, | |
| "loss": 0.04514434039592743, | |
| "mean_token_accuracy": 0.9820655703544616, | |
| "num_tokens": 29170348.0, | |
| "step": 1410 | |
| }, | |
| { | |
| "entropy": 0.7961021900177002, | |
| "epoch": 1.911170928667564, | |
| "grad_norm": 0.3529505133628845, | |
| "learning_rate": 9.466793607550995e-05, | |
| "loss": 0.044498777389526366, | |
| "mean_token_accuracy": 0.9821643531322479, | |
| "num_tokens": 29377369.0, | |
| "step": 1420 | |
| }, | |
| { | |
| "entropy": 0.7776929080486298, | |
| "epoch": 1.9246298788694483, | |
| "grad_norm": 0.6512665152549744, | |
| "learning_rate": 9.45674899232869e-05, | |
| "loss": 0.043723279237747194, | |
| "mean_token_accuracy": 0.9822627186775208, | |
| "num_tokens": 29583698.0, | |
| "step": 1430 | |
| }, | |
| { | |
| "entropy": 0.7827112972736359, | |
| "epoch": 1.9380888290713325, | |
| "grad_norm": 0.42146649956703186, | |
| "learning_rate": 9.446616078490626e-05, | |
| "loss": 0.04473748207092285, | |
| "mean_token_accuracy": 0.9821819305419922, | |
| "num_tokens": 29790624.0, | |
| "step": 1440 | |
| }, | |
| { | |
| "entropy": 0.7946831583976746, | |
| "epoch": 1.9515477792732168, | |
| "grad_norm": 0.47883015871047974, | |
| "learning_rate": 9.436395066793518e-05, | |
| "loss": 0.04658020734786987, | |
| "mean_token_accuracy": 0.9815436899662018, | |
| "num_tokens": 29997548.0, | |
| "step": 1450 | |
| }, | |
| { | |
| "entropy": 0.7833279132843017, | |
| "epoch": 1.965006729475101, | |
| "grad_norm": 0.4905496835708618, | |
| "learning_rate": 9.426086159739496e-05, | |
| "loss": 0.04289662837982178, | |
| "mean_token_accuracy": 0.9827987909317016, | |
| "num_tokens": 30203894.0, | |
| "step": 1460 | |
| }, | |
| { | |
| "entropy": 0.7804967284202575, | |
| "epoch": 1.9784656796769853, | |
| "grad_norm": 0.3333725929260254, | |
| "learning_rate": 9.415689561572107e-05, | |
| "loss": 0.044277578592300415, | |
| "mean_token_accuracy": 0.982471638917923, | |
| "num_tokens": 30410743.0, | |
| "step": 1470 | |
| }, | |
| { | |
| "entropy": 0.7721736073493958, | |
| "epoch": 1.9919246298788695, | |
| "grad_norm": 0.5358064770698547, | |
| "learning_rate": 9.405205478272267e-05, | |
| "loss": 0.042890912294387816, | |
| "mean_token_accuracy": 0.9828305661678314, | |
| "num_tokens": 30617524.0, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_entropy": 0.7763412169590118, | |
| "eval_loss": 0.045948393642902374, | |
| "eval_mean_token_accuracy": 0.9816623083345449, | |
| "eval_num_tokens": 30741532.0, | |
| "eval_runtime": 13.9729, | |
| "eval_samples_per_second": 357.835, | |
| "eval_steps_per_second": 11.236, | |
| "step": 1486 | |
| }, | |
| { | |
| "entropy": 0.7704778194427491, | |
| "epoch": 2.005383580080754, | |
| "grad_norm": 0.4395267367362976, | |
| "learning_rate": 9.394634117554173e-05, | |
| "loss": 0.04141359925270081, | |
| "mean_token_accuracy": 0.9836697518825531, | |
| "num_tokens": 30824156.0, | |
| "step": 1490 | |
| }, | |
| { | |
| "entropy": 0.7459299206733704, | |
| "epoch": 2.018842530282638, | |
| "grad_norm": 0.4781450629234314, | |
| "learning_rate": 9.38397568886119e-05, | |
| "loss": 0.03474531769752502, | |
| "mean_token_accuracy": 0.9868264079093934, | |
| "num_tokens": 31031057.0, | |
| "step": 1500 | |
| }, | |
| { | |
| "entropy": 0.7422619521617889, | |
| "epoch": 2.0323014804845223, | |
| "grad_norm": 0.47168222069740295, | |
| "learning_rate": 9.373230403361712e-05, | |
| "loss": 0.03591993451118469, | |
| "mean_token_accuracy": 0.9855878591537476, | |
| "num_tokens": 31238416.0, | |
| "step": 1510 | |
| }, | |
| { | |
| "entropy": 0.7497646749019623, | |
| "epoch": 2.0457604306864066, | |
| "grad_norm": 0.37677422165870667, | |
| "learning_rate": 9.362398473944958e-05, | |
| "loss": 0.03205449879169464, | |
| "mean_token_accuracy": 0.9876303613185883, | |
| "num_tokens": 31445048.0, | |
| "step": 1520 | |
| }, | |
| { | |
| "entropy": 0.7456450223922729, | |
| "epoch": 2.059219380888291, | |
| "grad_norm": 0.4814225733280182, | |
| "learning_rate": 9.35148011521677e-05, | |
| "loss": 0.03433309197425842, | |
| "mean_token_accuracy": 0.9864069163799286, | |
| "num_tokens": 31652249.0, | |
| "step": 1530 | |
| }, | |
| { | |
| "entropy": 0.7520359694957733, | |
| "epoch": 2.072678331090175, | |
| "grad_norm": 0.5464296936988831, | |
| "learning_rate": 9.340475543495364e-05, | |
| "loss": 0.03631590604782105, | |
| "mean_token_accuracy": 0.9858682453632355, | |
| "num_tokens": 31859054.0, | |
| "step": 1540 | |
| }, | |
| { | |
| "entropy": 0.754530417919159, | |
| "epoch": 2.0861372812920593, | |
| "grad_norm": 0.4758802652359009, | |
| "learning_rate": 9.329384976807023e-05, | |
| "loss": 0.03384111821651459, | |
| "mean_token_accuracy": 0.9866842925548553, | |
| "num_tokens": 32066326.0, | |
| "step": 1550 | |
| }, | |
| { | |
| "entropy": 0.7495070815086364, | |
| "epoch": 2.0995962314939436, | |
| "grad_norm": 0.4748813211917877, | |
| "learning_rate": 9.318208634881802e-05, | |
| "loss": 0.03490318655967713, | |
| "mean_token_accuracy": 0.9859294176101685, | |
| "num_tokens": 32273034.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "entropy": 0.7660306870937348, | |
| "epoch": 2.113055181695828, | |
| "grad_norm": 0.41709309816360474, | |
| "learning_rate": 9.306946739149161e-05, | |
| "loss": 0.03640688955783844, | |
| "mean_token_accuracy": 0.9853965878486634, | |
| "num_tokens": 32480411.0, | |
| "step": 1570 | |
| }, | |
| { | |
| "entropy": 0.7681133329868317, | |
| "epoch": 2.126514131897712, | |
| "grad_norm": 0.5109054446220398, | |
| "learning_rate": 9.29559951273358e-05, | |
| "loss": 0.03681868314743042, | |
| "mean_token_accuracy": 0.9852465927600861, | |
| "num_tokens": 32687538.0, | |
| "step": 1580 | |
| }, | |
| { | |
| "entropy": 0.7571729898452759, | |
| "epoch": 2.1399730820995964, | |
| "grad_norm": 0.5264601707458496, | |
| "learning_rate": 9.284167180450141e-05, | |
| "loss": 0.035235798358917235, | |
| "mean_token_accuracy": 0.9863873898983002, | |
| "num_tokens": 32894684.0, | |
| "step": 1590 | |
| }, | |
| { | |
| "entropy": 0.7517239153385162, | |
| "epoch": 2.1534320323014806, | |
| "grad_norm": 0.44705790281295776, | |
| "learning_rate": 9.272649968800069e-05, | |
| "loss": 0.0375944584608078, | |
| "mean_token_accuracy": 0.9852746367454529, | |
| "num_tokens": 33101905.0, | |
| "step": 1600 | |
| }, | |
| { | |
| "entropy": 0.763954496383667, | |
| "epoch": 2.166890982503365, | |
| "grad_norm": 0.42811813950538635, | |
| "learning_rate": 9.26104810596625e-05, | |
| "loss": 0.03505580127239227, | |
| "mean_token_accuracy": 0.9862452685832978, | |
| "num_tokens": 33308533.0, | |
| "step": 1610 | |
| }, | |
| { | |
| "entropy": 0.766820102930069, | |
| "epoch": 2.180349932705249, | |
| "grad_norm": 0.4892241656780243, | |
| "learning_rate": 9.249361821808708e-05, | |
| "loss": 0.03619093894958496, | |
| "mean_token_accuracy": 0.9859104573726654, | |
| "num_tokens": 33515373.0, | |
| "step": 1620 | |
| }, | |
| { | |
| "entropy": 0.7709326684474945, | |
| "epoch": 2.1938088829071334, | |
| "grad_norm": 0.5112985372543335, | |
| "learning_rate": 9.237591347860052e-05, | |
| "loss": 0.03710994720458984, | |
| "mean_token_accuracy": 0.9851432621479035, | |
| "num_tokens": 33722411.0, | |
| "step": 1630 | |
| }, | |
| { | |
| "entropy": 0.7663405299186706, | |
| "epoch": 2.2072678331090176, | |
| "grad_norm": 0.4687499403953552, | |
| "learning_rate": 9.225736917320886e-05, | |
| "loss": 0.034553620219230655, | |
| "mean_token_accuracy": 0.986689567565918, | |
| "num_tokens": 33929078.0, | |
| "step": 1640 | |
| }, | |
| { | |
| "entropy": 0.7591994524002075, | |
| "epoch": 2.220726783310902, | |
| "grad_norm": 0.4145253598690033, | |
| "learning_rate": 9.213798765055187e-05, | |
| "loss": 0.0364462822675705, | |
| "mean_token_accuracy": 0.9857377469539642, | |
| "num_tokens": 34136005.0, | |
| "step": 1650 | |
| }, | |
| { | |
| "entropy": 0.7645731925964355, | |
| "epoch": 2.234185733512786, | |
| "grad_norm": 0.41732943058013916, | |
| "learning_rate": 9.20177712758566e-05, | |
| "loss": 0.034900492429733275, | |
| "mean_token_accuracy": 0.9864438831806183, | |
| "num_tokens": 34342605.0, | |
| "step": 1660 | |
| }, | |
| { | |
| "entropy": 0.769444328546524, | |
| "epoch": 2.2476446837146704, | |
| "grad_norm": 0.5293087959289551, | |
| "learning_rate": 9.189672243089046e-05, | |
| "loss": 0.03702518343925476, | |
| "mean_token_accuracy": 0.9857267081737519, | |
| "num_tokens": 34549514.0, | |
| "step": 1670 | |
| }, | |
| { | |
| "entropy": 0.7718922853469848, | |
| "epoch": 2.2611036339165547, | |
| "grad_norm": 0.469811350107193, | |
| "learning_rate": 9.177484351391402e-05, | |
| "loss": 0.03630037009716034, | |
| "mean_token_accuracy": 0.9853004455566406, | |
| "num_tokens": 34756057.0, | |
| "step": 1680 | |
| }, | |
| { | |
| "entropy": 0.7716727793216706, | |
| "epoch": 2.274562584118439, | |
| "grad_norm": 0.6152373552322388, | |
| "learning_rate": 9.165213693963355e-05, | |
| "loss": 0.033915793895721434, | |
| "mean_token_accuracy": 0.9866912722587585, | |
| "num_tokens": 34962988.0, | |
| "step": 1690 | |
| }, | |
| { | |
| "entropy": 0.7670650899410247, | |
| "epoch": 2.288021534320323, | |
| "grad_norm": 0.7092661261558533, | |
| "learning_rate": 9.152860513915314e-05, | |
| "loss": 0.03407727777957916, | |
| "mean_token_accuracy": 0.9864597499370575, | |
| "num_tokens": 35169933.0, | |
| "step": 1700 | |
| }, | |
| { | |
| "entropy": 0.7746156573295593, | |
| "epoch": 2.3014804845222074, | |
| "grad_norm": 0.4469820261001587, | |
| "learning_rate": 9.140425055992648e-05, | |
| "loss": 0.03753764033317566, | |
| "mean_token_accuracy": 0.9847545504570008, | |
| "num_tokens": 35376647.0, | |
| "step": 1710 | |
| }, | |
| { | |
| "entropy": 0.7733055353164673, | |
| "epoch": 2.3149394347240917, | |
| "grad_norm": 0.46848854422569275, | |
| "learning_rate": 9.127907566570853e-05, | |
| "loss": 0.033966490626335145, | |
| "mean_token_accuracy": 0.9865934252738953, | |
| "num_tokens": 35583818.0, | |
| "step": 1720 | |
| }, | |
| { | |
| "entropy": 0.7706968247890472, | |
| "epoch": 2.328398384925976, | |
| "grad_norm": 0.5058269500732422, | |
| "learning_rate": 9.115308293650653e-05, | |
| "loss": 0.033354413509368894, | |
| "mean_token_accuracy": 0.9870194375514985, | |
| "num_tokens": 35791234.0, | |
| "step": 1730 | |
| }, | |
| { | |
| "entropy": 0.7614737451076508, | |
| "epoch": 2.34185733512786, | |
| "grad_norm": 0.3979508578777313, | |
| "learning_rate": 9.102627486853099e-05, | |
| "loss": 0.03707956075668335, | |
| "mean_token_accuracy": 0.9849399268627167, | |
| "num_tokens": 35997886.0, | |
| "step": 1740 | |
| }, | |
| { | |
| "entropy": 0.7629947364330292, | |
| "epoch": 2.3553162853297445, | |
| "grad_norm": 0.5079808831214905, | |
| "learning_rate": 9.089865397414614e-05, | |
| "loss": 0.03364085555076599, | |
| "mean_token_accuracy": 0.9865766227245331, | |
| "num_tokens": 36204490.0, | |
| "step": 1750 | |
| }, | |
| { | |
| "entropy": 0.7689139068126678, | |
| "epoch": 2.3687752355316287, | |
| "grad_norm": 0.5184679627418518, | |
| "learning_rate": 9.077022278182024e-05, | |
| "loss": 0.03795020878314972, | |
| "mean_token_accuracy": 0.9854429662227631, | |
| "num_tokens": 36411233.0, | |
| "step": 1760 | |
| }, | |
| { | |
| "entropy": 0.7789969980716706, | |
| "epoch": 2.382234185733513, | |
| "grad_norm": 0.4910341203212738, | |
| "learning_rate": 9.064098383607545e-05, | |
| "loss": 0.036249291896820066, | |
| "mean_token_accuracy": 0.9861413240432739, | |
| "num_tokens": 36618763.0, | |
| "step": 1770 | |
| }, | |
| { | |
| "entropy": 0.7814954161643982, | |
| "epoch": 2.3956931359353972, | |
| "grad_norm": 0.5686230659484863, | |
| "learning_rate": 9.051093969743738e-05, | |
| "loss": 0.036424264311790466, | |
| "mean_token_accuracy": 0.9857628643512726, | |
| "num_tokens": 36825280.0, | |
| "step": 1780 | |
| }, | |
| { | |
| "entropy": 0.7767263531684876, | |
| "epoch": 2.409152086137281, | |
| "grad_norm": 0.453492134809494, | |
| "learning_rate": 9.03800929423844e-05, | |
| "loss": 0.03373002707958221, | |
| "mean_token_accuracy": 0.9867543041706085, | |
| "num_tokens": 37032080.0, | |
| "step": 1790 | |
| }, | |
| { | |
| "entropy": 0.7687392771244049, | |
| "epoch": 2.4226110363391653, | |
| "grad_norm": 0.558427631855011, | |
| "learning_rate": 9.024844616329662e-05, | |
| "loss": 0.03517001271247864, | |
| "mean_token_accuracy": 0.9863903641700744, | |
| "num_tokens": 37238601.0, | |
| "step": 1800 | |
| }, | |
| { | |
| "entropy": 0.7732832372188568, | |
| "epoch": 2.4360699865410496, | |
| "grad_norm": 0.5509903430938721, | |
| "learning_rate": 9.011600196840447e-05, | |
| "loss": 0.036943814158439635, | |
| "mean_token_accuracy": 0.9852350294589997, | |
| "num_tokens": 37445537.0, | |
| "step": 1810 | |
| }, | |
| { | |
| "entropy": 0.7711590051651, | |
| "epoch": 2.449528936742934, | |
| "grad_norm": 0.4789018929004669, | |
| "learning_rate": 8.998276298173707e-05, | |
| "loss": 0.03290043473243713, | |
| "mean_token_accuracy": 0.986678397655487, | |
| "num_tokens": 37652275.0, | |
| "step": 1820 | |
| }, | |
| { | |
| "entropy": 0.7612685561180115, | |
| "epoch": 2.462987886944818, | |
| "grad_norm": 0.4346236288547516, | |
| "learning_rate": 8.984873184307017e-05, | |
| "loss": 0.034582901000976565, | |
| "mean_token_accuracy": 0.986914598941803, | |
| "num_tokens": 37858877.0, | |
| "step": 1830 | |
| }, | |
| { | |
| "entropy": 0.756990659236908, | |
| "epoch": 2.4764468371467023, | |
| "grad_norm": 0.49942365288734436, | |
| "learning_rate": 8.971391120787397e-05, | |
| "loss": 0.03583601713180542, | |
| "mean_token_accuracy": 0.9852246820926667, | |
| "num_tokens": 38065791.0, | |
| "step": 1840 | |
| }, | |
| { | |
| "entropy": 0.7551932036876678, | |
| "epoch": 2.4899057873485866, | |
| "grad_norm": 0.6017034649848938, | |
| "learning_rate": 8.957830374726042e-05, | |
| "loss": 0.0383810430765152, | |
| "mean_token_accuracy": 0.9845924258232117, | |
| "num_tokens": 38272316.0, | |
| "step": 1850 | |
| }, | |
| { | |
| "entropy": 0.7488674581050873, | |
| "epoch": 2.503364737550471, | |
| "grad_norm": 0.40909528732299805, | |
| "learning_rate": 8.944191214793028e-05, | |
| "loss": 0.03308407068252563, | |
| "mean_token_accuracy": 0.9869977355003356, | |
| "num_tokens": 38479157.0, | |
| "step": 1860 | |
| }, | |
| { | |
| "entropy": 0.7536681890487671, | |
| "epoch": 2.516823687752355, | |
| "grad_norm": 0.6133081912994385, | |
| "learning_rate": 8.930473911212e-05, | |
| "loss": 0.036927449703216556, | |
| "mean_token_accuracy": 0.9848987877368927, | |
| "num_tokens": 38685562.0, | |
| "step": 1870 | |
| }, | |
| { | |
| "entropy": 0.7497753620147705, | |
| "epoch": 2.5302826379542394, | |
| "grad_norm": 0.4397526681423187, | |
| "learning_rate": 8.916678735754809e-05, | |
| "loss": 0.03293933868408203, | |
| "mean_token_accuracy": 0.9865592002868653, | |
| "num_tokens": 38892182.0, | |
| "step": 1880 | |
| }, | |
| { | |
| "entropy": 0.768702232837677, | |
| "epoch": 2.5437415881561236, | |
| "grad_norm": 0.35570991039276123, | |
| "learning_rate": 8.902805961736123e-05, | |
| "loss": 0.03172276020050049, | |
| "mean_token_accuracy": 0.9870541751384735, | |
| "num_tokens": 39098643.0, | |
| "step": 1890 | |
| }, | |
| { | |
| "entropy": 0.7794657349586487, | |
| "epoch": 2.557200538358008, | |
| "grad_norm": 0.39434006810188293, | |
| "learning_rate": 8.88885586400803e-05, | |
| "loss": 0.032149982452392575, | |
| "mean_token_accuracy": 0.9873526275157929, | |
| "num_tokens": 39305419.0, | |
| "step": 1900 | |
| }, | |
| { | |
| "entropy": 0.7983768939971924, | |
| "epoch": 2.570659488559892, | |
| "grad_norm": 0.4141407907009125, | |
| "learning_rate": 8.874828718954576e-05, | |
| "loss": 0.03556913733482361, | |
| "mean_token_accuracy": 0.986035841703415, | |
| "num_tokens": 39512111.0, | |
| "step": 1910 | |
| }, | |
| { | |
| "entropy": 0.8069267928600311, | |
| "epoch": 2.5841184387617764, | |
| "grad_norm": 0.5249026417732239, | |
| "learning_rate": 8.86072480448629e-05, | |
| "loss": 0.035189300775527954, | |
| "mean_token_accuracy": 0.9859413146972656, | |
| "num_tokens": 39718796.0, | |
| "step": 1920 | |
| }, | |
| { | |
| "entropy": 0.8054641425609589, | |
| "epoch": 2.5975773889636606, | |
| "grad_norm": 0.341441810131073, | |
| "learning_rate": 8.84654440003469e-05, | |
| "loss": 0.035634788870811465, | |
| "mean_token_accuracy": 0.9858911037445068, | |
| "num_tokens": 39925706.0, | |
| "step": 1930 | |
| }, | |
| { | |
| "entropy": 0.791653448343277, | |
| "epoch": 2.611036339165545, | |
| "grad_norm": 0.4683961272239685, | |
| "learning_rate": 8.83228778654674e-05, | |
| "loss": 0.031418097019195554, | |
| "mean_token_accuracy": 0.9873055160045624, | |
| "num_tokens": 40132455.0, | |
| "step": 1940 | |
| }, | |
| { | |
| "entropy": 0.7851328790187836, | |
| "epoch": 2.624495289367429, | |
| "grad_norm": 0.5501745343208313, | |
| "learning_rate": 8.817955246479276e-05, | |
| "loss": 0.03469682037830353, | |
| "mean_token_accuracy": 0.9861454546451569, | |
| "num_tokens": 40339095.0, | |
| "step": 1950 | |
| }, | |
| { | |
| "entropy": 0.7846890926361084, | |
| "epoch": 2.6379542395693134, | |
| "grad_norm": 0.46256187558174133, | |
| "learning_rate": 8.803547063793422e-05, | |
| "loss": 0.03551913499832153, | |
| "mean_token_accuracy": 0.9861681580543518, | |
| "num_tokens": 40545821.0, | |
| "step": 1960 | |
| }, | |
| { | |
| "entropy": 0.7767995774745942, | |
| "epoch": 2.6514131897711977, | |
| "grad_norm": 0.3970808684825897, | |
| "learning_rate": 8.789063523948958e-05, | |
| "loss": 0.031726115942001344, | |
| "mean_token_accuracy": 0.9874750375747681, | |
| "num_tokens": 40753075.0, | |
| "step": 1970 | |
| }, | |
| { | |
| "entropy": 0.771297287940979, | |
| "epoch": 2.664872139973082, | |
| "grad_norm": 0.5771340727806091, | |
| "learning_rate": 8.774504913898663e-05, | |
| "loss": 0.033945786952972415, | |
| "mean_token_accuracy": 0.9866833508014679, | |
| "num_tokens": 40960109.0, | |
| "step": 1980 | |
| }, | |
| { | |
| "entropy": 0.7735596299171448, | |
| "epoch": 2.678331090174966, | |
| "grad_norm": 0.5560683012008667, | |
| "learning_rate": 8.75987152208264e-05, | |
| "loss": 0.033962175250053406, | |
| "mean_token_accuracy": 0.9866875231266021, | |
| "num_tokens": 41167093.0, | |
| "step": 1990 | |
| }, | |
| { | |
| "entropy": 0.769331830739975, | |
| "epoch": 2.6917900403768504, | |
| "grad_norm": 0.4328141510486603, | |
| "learning_rate": 8.745163638422583e-05, | |
| "loss": 0.03420340120792389, | |
| "mean_token_accuracy": 0.986853563785553, | |
| "num_tokens": 41373741.0, | |
| "step": 2000 | |
| }, | |
| { | |
| "entropy": 0.7721189796924591, | |
| "epoch": 2.7052489905787347, | |
| "grad_norm": 0.5219032764434814, | |
| "learning_rate": 8.730381554316051e-05, | |
| "loss": 0.03331426382064819, | |
| "mean_token_accuracy": 0.9866217851638794, | |
| "num_tokens": 41580817.0, | |
| "step": 2010 | |
| }, | |
| { | |
| "entropy": 0.7982444167137146, | |
| "epoch": 2.718707940780619, | |
| "grad_norm": 0.4722937345504761, | |
| "learning_rate": 8.715525562630687e-05, | |
| "loss": 0.034999901056289674, | |
| "mean_token_accuracy": 0.9859172761440277, | |
| "num_tokens": 41787433.0, | |
| "step": 2020 | |
| }, | |
| { | |
| "entropy": 0.796376746892929, | |
| "epoch": 2.732166890982503, | |
| "grad_norm": 0.4517671465873718, | |
| "learning_rate": 8.700595957698411e-05, | |
| "loss": 0.03431849479675293, | |
| "mean_token_accuracy": 0.9859098434448242, | |
| "num_tokens": 41994291.0, | |
| "step": 2030 | |
| }, | |
| { | |
| "entropy": 0.7885730385780334, | |
| "epoch": 2.7456258411843875, | |
| "grad_norm": 0.4771164357662201, | |
| "learning_rate": 8.685593035309598e-05, | |
| "loss": 0.03396539688110352, | |
| "mean_token_accuracy": 0.9864761888980865, | |
| "num_tokens": 42200986.0, | |
| "step": 2040 | |
| }, | |
| { | |
| "entropy": 0.7897965848445893, | |
| "epoch": 2.7590847913862717, | |
| "grad_norm": 0.35293588042259216, | |
| "learning_rate": 8.670517092707213e-05, | |
| "loss": 0.03421284556388855, | |
| "mean_token_accuracy": 0.9866907477378846, | |
| "num_tokens": 42407972.0, | |
| "step": 2050 | |
| }, | |
| { | |
| "entropy": 0.7963090658187866, | |
| "epoch": 2.772543741588156, | |
| "grad_norm": 0.480851948261261, | |
| "learning_rate": 8.655368428580919e-05, | |
| "loss": 0.03702861964702606, | |
| "mean_token_accuracy": 0.9853508174419403, | |
| "num_tokens": 42615046.0, | |
| "step": 2060 | |
| }, | |
| { | |
| "entropy": 0.7992978096008301, | |
| "epoch": 2.7860026917900402, | |
| "grad_norm": 0.5696701407432556, | |
| "learning_rate": 8.640147343061165e-05, | |
| "loss": 0.034851402044296265, | |
| "mean_token_accuracy": 0.9860165119171143, | |
| "num_tokens": 42821882.0, | |
| "step": 2070 | |
| }, | |
| { | |
| "entropy": 0.7952683210372925, | |
| "epoch": 2.7994616419919245, | |
| "grad_norm": 0.4716683030128479, | |
| "learning_rate": 8.624854137713234e-05, | |
| "loss": 0.03539964556694031, | |
| "mean_token_accuracy": 0.9860508978366852, | |
| "num_tokens": 43028269.0, | |
| "step": 2080 | |
| }, | |
| { | |
| "entropy": 0.787241518497467, | |
| "epoch": 2.8129205921938087, | |
| "grad_norm": 0.6041930913925171, | |
| "learning_rate": 8.609489115531278e-05, | |
| "loss": 0.033989882469177245, | |
| "mean_token_accuracy": 0.9860147058963775, | |
| "num_tokens": 43235021.0, | |
| "step": 2090 | |
| }, | |
| { | |
| "entropy": 0.7926058828830719, | |
| "epoch": 2.826379542395693, | |
| "grad_norm": 0.5247143507003784, | |
| "learning_rate": 8.594052580932301e-05, | |
| "loss": 0.03367411494255066, | |
| "mean_token_accuracy": 0.9865197122097016, | |
| "num_tokens": 43442265.0, | |
| "step": 2100 | |
| }, | |
| { | |
| "entropy": 0.7915597558021545, | |
| "epoch": 2.8398384925975773, | |
| "grad_norm": 0.48869433999061584, | |
| "learning_rate": 8.578544839750141e-05, | |
| "loss": 0.03161753416061401, | |
| "mean_token_accuracy": 0.9873407542705536, | |
| "num_tokens": 43648881.0, | |
| "step": 2110 | |
| }, | |
| { | |
| "entropy": 0.7891027152538299, | |
| "epoch": 2.8532974427994615, | |
| "grad_norm": 0.6239877939224243, | |
| "learning_rate": 8.562966199229399e-05, | |
| "loss": 0.03200874626636505, | |
| "mean_token_accuracy": 0.9873006939888, | |
| "num_tokens": 43855736.0, | |
| "step": 2120 | |
| }, | |
| { | |
| "entropy": 0.7923749804496765, | |
| "epoch": 2.8667563930013458, | |
| "grad_norm": 0.42834678292274475, | |
| "learning_rate": 8.547316968019363e-05, | |
| "loss": 0.03362695872783661, | |
| "mean_token_accuracy": 0.9866919219493866, | |
| "num_tokens": 44062736.0, | |
| "step": 2130 | |
| }, | |
| { | |
| "entropy": 0.7924418032169342, | |
| "epoch": 2.88021534320323, | |
| "grad_norm": 0.41659072041511536, | |
| "learning_rate": 8.531597456167885e-05, | |
| "loss": 0.032884901762008666, | |
| "mean_token_accuracy": 0.9865517973899841, | |
| "num_tokens": 44269673.0, | |
| "step": 2140 | |
| }, | |
| { | |
| "entropy": 0.7898743569850921, | |
| "epoch": 2.8936742934051143, | |
| "grad_norm": 0.5111353397369385, | |
| "learning_rate": 8.515807975115239e-05, | |
| "loss": 0.032617968320846555, | |
| "mean_token_accuracy": 0.9871149003505707, | |
| "num_tokens": 44477238.0, | |
| "step": 2150 | |
| }, | |
| { | |
| "entropy": 0.8053750157356262, | |
| "epoch": 2.9071332436069985, | |
| "grad_norm": 0.5145390033721924, | |
| "learning_rate": 8.499948837687959e-05, | |
| "loss": 0.035998404026031494, | |
| "mean_token_accuracy": 0.985955685377121, | |
| "num_tokens": 44684355.0, | |
| "step": 2160 | |
| }, | |
| { | |
| "entropy": 0.8018061518669128, | |
| "epoch": 2.920592193808883, | |
| "grad_norm": 0.5930307507514954, | |
| "learning_rate": 8.484020358092625e-05, | |
| "loss": 0.03492251336574555, | |
| "mean_token_accuracy": 0.9859745800495148, | |
| "num_tokens": 44891085.0, | |
| "step": 2170 | |
| }, | |
| { | |
| "entropy": 0.7959860146045685, | |
| "epoch": 2.934051144010767, | |
| "grad_norm": 0.527142345905304, | |
| "learning_rate": 8.468022851909657e-05, | |
| "loss": 0.032577240467071535, | |
| "mean_token_accuracy": 0.9865381300449372, | |
| "num_tokens": 45098305.0, | |
| "step": 2180 | |
| }, | |
| { | |
| "entropy": 0.797534954547882, | |
| "epoch": 2.9475100942126513, | |
| "grad_norm": 0.3939096927642822, | |
| "learning_rate": 8.451956636087046e-05, | |
| "loss": 0.03261285424232483, | |
| "mean_token_accuracy": 0.9867972791194916, | |
| "num_tokens": 45305134.0, | |
| "step": 2190 | |
| }, | |
| { | |
| "entropy": 0.7963755249977111, | |
| "epoch": 2.9609690444145356, | |
| "grad_norm": 0.37216880917549133, | |
| "learning_rate": 8.435822028934087e-05, | |
| "loss": 0.033119088411331175, | |
| "mean_token_accuracy": 0.987492960691452, | |
| "num_tokens": 45512139.0, | |
| "step": 2200 | |
| }, | |
| { | |
| "entropy": 0.7935790359973908, | |
| "epoch": 2.97442799461642, | |
| "grad_norm": 0.5378938317298889, | |
| "learning_rate": 8.41961935011506e-05, | |
| "loss": 0.033530765771865846, | |
| "mean_token_accuracy": 0.986775541305542, | |
| "num_tokens": 45718897.0, | |
| "step": 2210 | |
| }, | |
| { | |
| "entropy": 0.7964731454849243, | |
| "epoch": 2.987886944818304, | |
| "grad_norm": 0.5635746121406555, | |
| "learning_rate": 8.403348920642911e-05, | |
| "loss": 0.03444778919219971, | |
| "mean_token_accuracy": 0.9864307165145874, | |
| "num_tokens": 45925982.0, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_entropy": 0.7897109795527854, | |
| "eval_loss": 0.045999836176633835, | |
| "eval_mean_token_accuracy": 0.9822407535686615, | |
| "eval_num_tokens": 46112342.0, | |
| "eval_runtime": 13.9838, | |
| "eval_samples_per_second": 357.557, | |
| "eval_steps_per_second": 11.227, | |
| "step": 2229 | |
| }, | |
| { | |
| "entropy": 0.7922163069248199, | |
| "epoch": 3.0013458950201883, | |
| "grad_norm": 0.5085620284080505, | |
| "learning_rate": 8.387011062872883e-05, | |
| "loss": 0.03196645081043244, | |
| "mean_token_accuracy": 0.9873932301998138, | |
| "num_tokens": 46133123.0, | |
| "step": 2230 | |
| }, | |
| { | |
| "entropy": 0.7857943475246429, | |
| "epoch": 3.0148048452220726, | |
| "grad_norm": 0.7587371468544006, | |
| "learning_rate": 8.370606100496128e-05, | |
| "loss": 0.024139750003814697, | |
| "mean_token_accuracy": 0.9905063509941101, | |
| "num_tokens": 46339878.0, | |
| "step": 2240 | |
| }, | |
| { | |
| "entropy": 0.7751803815364837, | |
| "epoch": 3.028263795423957, | |
| "grad_norm": 0.648463249206543, | |
| "learning_rate": 8.354134358533301e-05, | |
| "loss": 0.027016639709472656, | |
| "mean_token_accuracy": 0.9895779073238373, | |
| "num_tokens": 46546959.0, | |
| "step": 2250 | |
| }, | |
| { | |
| "entropy": 0.7765661358833313, | |
| "epoch": 3.041722745625841, | |
| "grad_norm": 0.5772325992584229, | |
| "learning_rate": 8.337596163328114e-05, | |
| "loss": 0.023444092273712157, | |
| "mean_token_accuracy": 0.9911140978336335, | |
| "num_tokens": 46753901.0, | |
| "step": 2260 | |
| }, | |
| { | |
| "entropy": 0.7815487205982208, | |
| "epoch": 3.0551816958277254, | |
| "grad_norm": 0.5210555791854858, | |
| "learning_rate": 8.320991842540875e-05, | |
| "loss": 0.025440862774848937, | |
| "mean_token_accuracy": 0.9899839282035827, | |
| "num_tokens": 46960507.0, | |
| "step": 2270 | |
| }, | |
| { | |
| "entropy": 0.7857287228107452, | |
| "epoch": 3.0686406460296096, | |
| "grad_norm": 0.41927286982536316, | |
| "learning_rate": 8.304321725141995e-05, | |
| "loss": 0.024293258786201477, | |
| "mean_token_accuracy": 0.9906916856765747, | |
| "num_tokens": 47167445.0, | |
| "step": 2280 | |
| }, | |
| { | |
| "entropy": 0.7888360917568207, | |
| "epoch": 3.082099596231494, | |
| "grad_norm": 0.4237120747566223, | |
| "learning_rate": 8.287586141405464e-05, | |
| "loss": 0.025221824645996094, | |
| "mean_token_accuracy": 0.99046990275383, | |
| "num_tokens": 47374418.0, | |
| "step": 2290 | |
| }, | |
| { | |
| "entropy": 0.7833469033241272, | |
| "epoch": 3.095558546433378, | |
| "grad_norm": 0.4873560070991516, | |
| "learning_rate": 8.27078542290232e-05, | |
| "loss": 0.025454607605934144, | |
| "mean_token_accuracy": 0.9896302163600922, | |
| "num_tokens": 47580519.0, | |
| "step": 2300 | |
| }, | |
| { | |
| "entropy": 0.7796760380268097, | |
| "epoch": 3.1090174966352624, | |
| "grad_norm": 0.5142725110054016, | |
| "learning_rate": 8.253919902494071e-05, | |
| "loss": 0.026190632581710817, | |
| "mean_token_accuracy": 0.9899985671043396, | |
| "num_tokens": 47786773.0, | |
| "step": 2310 | |
| }, | |
| { | |
| "entropy": 0.7891262769699097, | |
| "epoch": 3.1224764468371466, | |
| "grad_norm": 0.46983572840690613, | |
| "learning_rate": 8.236989914326101e-05, | |
| "loss": 0.02558264136314392, | |
| "mean_token_accuracy": 0.9899591863155365, | |
| "num_tokens": 47993610.0, | |
| "step": 2320 | |
| }, | |
| { | |
| "entropy": 0.7877647399902343, | |
| "epoch": 3.135935397039031, | |
| "grad_norm": 0.3744112253189087, | |
| "learning_rate": 8.21999579382105e-05, | |
| "loss": 0.026258507370948793, | |
| "mean_token_accuracy": 0.9900372087955475, | |
| "num_tokens": 48200562.0, | |
| "step": 2330 | |
| }, | |
| { | |
| "entropy": 0.7951374232769013, | |
| "epoch": 3.149394347240915, | |
| "grad_norm": 0.430062472820282, | |
| "learning_rate": 8.202937877672175e-05, | |
| "loss": 0.025594598054885863, | |
| "mean_token_accuracy": 0.9902561128139495, | |
| "num_tokens": 48406674.0, | |
| "step": 2340 | |
| }, | |
| { | |
| "entropy": 0.7907680094242096, | |
| "epoch": 3.1628532974427994, | |
| "grad_norm": 0.4720000624656677, | |
| "learning_rate": 8.185816503836665e-05, | |
| "loss": 0.02532147169113159, | |
| "mean_token_accuracy": 0.9900774240493775, | |
| "num_tokens": 48613281.0, | |
| "step": 2350 | |
| }, | |
| { | |
| "entropy": 0.7871745467185974, | |
| "epoch": 3.1763122476446837, | |
| "grad_norm": 0.5302978157997131, | |
| "learning_rate": 8.168632011528961e-05, | |
| "loss": 0.024092340469360353, | |
| "mean_token_accuracy": 0.9907279312610626, | |
| "num_tokens": 48820645.0, | |
| "step": 2360 | |
| }, | |
| { | |
| "entropy": 0.7865763783454895, | |
| "epoch": 3.189771197846568, | |
| "grad_norm": 0.40404385328292847, | |
| "learning_rate": 8.15138474121403e-05, | |
| "loss": 0.026713091135025024, | |
| "mean_token_accuracy": 0.9897278249263763, | |
| "num_tokens": 49028272.0, | |
| "step": 2370 | |
| }, | |
| { | |
| "entropy": 0.7893508970737457, | |
| "epoch": 3.203230148048452, | |
| "grad_norm": 0.5449444651603699, | |
| "learning_rate": 8.134075034600609e-05, | |
| "loss": 0.02622288465499878, | |
| "mean_token_accuracy": 0.9898015022277832, | |
| "num_tokens": 49235527.0, | |
| "step": 2380 | |
| }, | |
| { | |
| "entropy": 0.7904633581638336, | |
| "epoch": 3.2166890982503364, | |
| "grad_norm": 0.5542995929718018, | |
| "learning_rate": 8.116703234634453e-05, | |
| "loss": 0.026536452770233154, | |
| "mean_token_accuracy": 0.9896604716777802, | |
| "num_tokens": 49442369.0, | |
| "step": 2390 | |
| }, | |
| { | |
| "entropy": 0.7914480745792389, | |
| "epoch": 3.2301480484522207, | |
| "grad_norm": 0.37255948781967163, | |
| "learning_rate": 8.099269685491528e-05, | |
| "loss": 0.027568697929382324, | |
| "mean_token_accuracy": 0.9894173204898834, | |
| "num_tokens": 49649512.0, | |
| "step": 2400 | |
| }, | |
| { | |
| "entropy": 0.7816898763179779, | |
| "epoch": 3.243606998654105, | |
| "grad_norm": 0.4851721525192261, | |
| "learning_rate": 8.081774732571196e-05, | |
| "loss": 0.023995181918144225, | |
| "mean_token_accuracy": 0.9908584892749787, | |
| "num_tokens": 49856522.0, | |
| "step": 2410 | |
| }, | |
| { | |
| "entropy": 0.7849020719528198, | |
| "epoch": 3.257065948855989, | |
| "grad_norm": 0.5768998265266418, | |
| "learning_rate": 8.06421872248937e-05, | |
| "loss": 0.02669338583946228, | |
| "mean_token_accuracy": 0.9900073111057281, | |
| "num_tokens": 50062538.0, | |
| "step": 2420 | |
| }, | |
| { | |
| "entropy": 0.7905935168266296, | |
| "epoch": 3.2705248990578735, | |
| "grad_norm": 0.49046942591667175, | |
| "learning_rate": 8.046602003071648e-05, | |
| "loss": 0.026200637221336365, | |
| "mean_token_accuracy": 0.9896903157234191, | |
| "num_tokens": 50269493.0, | |
| "step": 2430 | |
| }, | |
| { | |
| "entropy": 0.7887889266014099, | |
| "epoch": 3.2839838492597577, | |
| "grad_norm": 0.6130094528198242, | |
| "learning_rate": 8.028924923346426e-05, | |
| "loss": 0.02587394416332245, | |
| "mean_token_accuracy": 0.9894962787628174, | |
| "num_tokens": 50476453.0, | |
| "step": 2440 | |
| }, | |
| { | |
| "entropy": 0.7816741824150085, | |
| "epoch": 3.297442799461642, | |
| "grad_norm": 0.47344231605529785, | |
| "learning_rate": 8.011187833537972e-05, | |
| "loss": 0.025678065419197083, | |
| "mean_token_accuracy": 0.9897482633590698, | |
| "num_tokens": 50683361.0, | |
| "step": 2450 | |
| }, | |
| { | |
| "entropy": 0.7746505677700043, | |
| "epoch": 3.3109017496635262, | |
| "grad_norm": 0.46171092987060547, | |
| "learning_rate": 7.993391085059502e-05, | |
| "loss": 0.026066750288009644, | |
| "mean_token_accuracy": 0.9896942138671875, | |
| "num_tokens": 50890676.0, | |
| "step": 2460 | |
| }, | |
| { | |
| "entropy": 0.7777635037899018, | |
| "epoch": 3.3243606998654105, | |
| "grad_norm": 0.48620864748954773, | |
| "learning_rate": 7.975535030506203e-05, | |
| "loss": 0.02398068457841873, | |
| "mean_token_accuracy": 0.9904903531074524, | |
| "num_tokens": 51097653.0, | |
| "step": 2470 | |
| }, | |
| { | |
| "entropy": 0.7784659445285798, | |
| "epoch": 3.3378196500672948, | |
| "grad_norm": 0.6068832874298096, | |
| "learning_rate": 7.957620023648256e-05, | |
| "loss": 0.02655583620071411, | |
| "mean_token_accuracy": 0.989698976278305, | |
| "num_tokens": 51304259.0, | |
| "step": 2480 | |
| }, | |
| { | |
| "entropy": 0.776263278722763, | |
| "epoch": 3.351278600269179, | |
| "grad_norm": 0.3608818054199219, | |
| "learning_rate": 7.939646419423826e-05, | |
| "loss": 0.025072038173675537, | |
| "mean_token_accuracy": 0.9902963459491729, | |
| "num_tokens": 51510973.0, | |
| "step": 2490 | |
| }, | |
| { | |
| "entropy": 0.7764017939567566, | |
| "epoch": 3.3647375504710633, | |
| "grad_norm": 0.4125957489013672, | |
| "learning_rate": 7.92161457393203e-05, | |
| "loss": 0.0256451278924942, | |
| "mean_token_accuracy": 0.990142571926117, | |
| "num_tokens": 51717824.0, | |
| "step": 2500 | |
| }, | |
| { | |
| "entropy": 0.7756951570510864, | |
| "epoch": 3.3781965006729475, | |
| "grad_norm": 0.4129035770893097, | |
| "learning_rate": 7.903524844425878e-05, | |
| "loss": 0.025212505459785463, | |
| "mean_token_accuracy": 0.9900435447692871, | |
| "num_tokens": 51924442.0, | |
| "step": 2510 | |
| }, | |
| { | |
| "entropy": 0.7646311402320862, | |
| "epoch": 3.391655450874832, | |
| "grad_norm": 0.47579509019851685, | |
| "learning_rate": 7.885377589305197e-05, | |
| "loss": 0.02700415551662445, | |
| "mean_token_accuracy": 0.9895658552646637, | |
| "num_tokens": 52131314.0, | |
| "step": 2520 | |
| }, | |
| { | |
| "entropy": 0.7609292089939117, | |
| "epoch": 3.405114401076716, | |
| "grad_norm": 0.4114918112754822, | |
| "learning_rate": 7.867173168109534e-05, | |
| "loss": 0.024971812963485718, | |
| "mean_token_accuracy": 0.9904350519180298, | |
| "num_tokens": 52337910.0, | |
| "step": 2530 | |
| }, | |
| { | |
| "entropy": 0.7537091553211213, | |
| "epoch": 3.4185733512786003, | |
| "grad_norm": 0.3902633786201477, | |
| "learning_rate": 7.84891194151103e-05, | |
| "loss": 0.02551236152648926, | |
| "mean_token_accuracy": 0.990143883228302, | |
| "num_tokens": 52545485.0, | |
| "step": 2540 | |
| }, | |
| { | |
| "entropy": 0.7640065968036651, | |
| "epoch": 3.4320323014804845, | |
| "grad_norm": 0.5460127592086792, | |
| "learning_rate": 7.830594271307267e-05, | |
| "loss": 0.029222273826599122, | |
| "mean_token_accuracy": 0.9886435449123383, | |
| "num_tokens": 52751594.0, | |
| "step": 2550 | |
| }, | |
| { | |
| "entropy": 0.763840240240097, | |
| "epoch": 3.445491251682369, | |
| "grad_norm": 0.35068443417549133, | |
| "learning_rate": 7.812220520414115e-05, | |
| "loss": 0.024993129074573517, | |
| "mean_token_accuracy": 0.9905041277408599, | |
| "num_tokens": 52958485.0, | |
| "step": 2560 | |
| }, | |
| { | |
| "entropy": 0.764543867111206, | |
| "epoch": 3.458950201884253, | |
| "grad_norm": 0.38305431604385376, | |
| "learning_rate": 7.793791052858528e-05, | |
| "loss": 0.024963854253292082, | |
| "mean_token_accuracy": 0.9902342796325684, | |
| "num_tokens": 53165775.0, | |
| "step": 2570 | |
| }, | |
| { | |
| "entropy": 0.7618798077106476, | |
| "epoch": 3.4724091520861373, | |
| "grad_norm": 0.3988240659236908, | |
| "learning_rate": 7.775306233771343e-05, | |
| "loss": 0.025615721940994263, | |
| "mean_token_accuracy": 0.9900647640228272, | |
| "num_tokens": 53373241.0, | |
| "step": 2580 | |
| }, | |
| { | |
| "entropy": 0.7694470942020416, | |
| "epoch": 3.4858681022880216, | |
| "grad_norm": 0.40997764468193054, | |
| "learning_rate": 7.756766429380033e-05, | |
| "loss": 0.02432440221309662, | |
| "mean_token_accuracy": 0.9905587792396545, | |
| "num_tokens": 53580570.0, | |
| "step": 2590 | |
| }, | |
| { | |
| "entropy": 0.7734194874763489, | |
| "epoch": 3.499327052489906, | |
| "grad_norm": 0.5883393883705139, | |
| "learning_rate": 7.738172007001465e-05, | |
| "loss": 0.0254077672958374, | |
| "mean_token_accuracy": 0.9899859607219696, | |
| "num_tokens": 53786644.0, | |
| "step": 2600 | |
| }, | |
| { | |
| "entropy": 0.770265918970108, | |
| "epoch": 3.51278600269179, | |
| "grad_norm": 0.5596480965614319, | |
| "learning_rate": 7.719523335034612e-05, | |
| "loss": 0.025699737668037414, | |
| "mean_token_accuracy": 0.9896622657775879, | |
| "num_tokens": 53993906.0, | |
| "step": 2610 | |
| }, | |
| { | |
| "entropy": 0.7764162719249725, | |
| "epoch": 3.5262449528936743, | |
| "grad_norm": 0.5137752294540405, | |
| "learning_rate": 7.70082078295326e-05, | |
| "loss": 0.02807466983795166, | |
| "mean_token_accuracy": 0.9887792706489563, | |
| "num_tokens": 54200102.0, | |
| "step": 2620 | |
| }, | |
| { | |
| "entropy": 0.7647269427776336, | |
| "epoch": 3.5397039030955586, | |
| "grad_norm": 0.46396756172180176, | |
| "learning_rate": 7.682064721298683e-05, | |
| "loss": 0.026442068815231323, | |
| "mean_token_accuracy": 0.9896844685077667, | |
| "num_tokens": 54406930.0, | |
| "step": 2630 | |
| }, | |
| { | |
| "entropy": 0.7612848520278931, | |
| "epoch": 3.553162853297443, | |
| "grad_norm": 0.45611244440078735, | |
| "learning_rate": 7.663255521672308e-05, | |
| "loss": 0.025213491916656495, | |
| "mean_token_accuracy": 0.990059632062912, | |
| "num_tokens": 54613415.0, | |
| "step": 2640 | |
| }, | |
| { | |
| "entropy": 0.7642963767051697, | |
| "epoch": 3.566621803499327, | |
| "grad_norm": 0.40814533829689026, | |
| "learning_rate": 7.64439355672835e-05, | |
| "loss": 0.025692886114120482, | |
| "mean_token_accuracy": 0.9896343588829041, | |
| "num_tokens": 54820508.0, | |
| "step": 2650 | |
| }, | |
| { | |
| "entropy": 0.7696209371089935, | |
| "epoch": 3.5800807537012114, | |
| "grad_norm": 0.5956735014915466, | |
| "learning_rate": 7.625479200166425e-05, | |
| "loss": 0.024135774374008177, | |
| "mean_token_accuracy": 0.990184074640274, | |
| "num_tokens": 55027129.0, | |
| "step": 2660 | |
| }, | |
| { | |
| "entropy": 0.7715358138084412, | |
| "epoch": 3.5935397039030956, | |
| "grad_norm": 0.4354693293571472, | |
| "learning_rate": 7.606512826724155e-05, | |
| "loss": 0.026834815740585327, | |
| "mean_token_accuracy": 0.9893686950206757, | |
| "num_tokens": 55233486.0, | |
| "step": 2670 | |
| }, | |
| { | |
| "entropy": 0.7687399387359619, | |
| "epoch": 3.60699865410498, | |
| "grad_norm": 0.4370516836643219, | |
| "learning_rate": 7.587494812169728e-05, | |
| "loss": 0.02458384484052658, | |
| "mean_token_accuracy": 0.9904316484928131, | |
| "num_tokens": 55440146.0, | |
| "step": 2680 | |
| }, | |
| { | |
| "entropy": 0.7663004577159882, | |
| "epoch": 3.620457604306864, | |
| "grad_norm": 0.4597774147987366, | |
| "learning_rate": 7.568425533294476e-05, | |
| "loss": 0.02627093195915222, | |
| "mean_token_accuracy": 0.9895556032657623, | |
| "num_tokens": 55646688.0, | |
| "step": 2690 | |
| }, | |
| { | |
| "entropy": 0.763479220867157, | |
| "epoch": 3.6339165545087484, | |
| "grad_norm": 0.6173406839370728, | |
| "learning_rate": 7.549305367905385e-05, | |
| "loss": 0.02632114291191101, | |
| "mean_token_accuracy": 0.9895108163356781, | |
| "num_tokens": 55854045.0, | |
| "step": 2700 | |
| }, | |
| { | |
| "entropy": 0.7665097296237946, | |
| "epoch": 3.6473755047106327, | |
| "grad_norm": 0.6147279143333435, | |
| "learning_rate": 7.53013469481763e-05, | |
| "loss": 0.026433029770851137, | |
| "mean_token_accuracy": 0.9895636439323425, | |
| "num_tokens": 56060469.0, | |
| "step": 2710 | |
| }, | |
| { | |
| "entropy": 0.7681903898715973, | |
| "epoch": 3.660834454912517, | |
| "grad_norm": 0.6082019209861755, | |
| "learning_rate": 7.510913893847058e-05, | |
| "loss": 0.024667418003082274, | |
| "mean_token_accuracy": 0.9905052244663238, | |
| "num_tokens": 56267217.0, | |
| "step": 2720 | |
| }, | |
| { | |
| "entropy": 0.7673894047737122, | |
| "epoch": 3.674293405114401, | |
| "grad_norm": 0.5873395800590515, | |
| "learning_rate": 7.491643345802667e-05, | |
| "loss": 0.026074895262718202, | |
| "mean_token_accuracy": 0.9895181894302368, | |
| "num_tokens": 56473879.0, | |
| "step": 2730 | |
| }, | |
| { | |
| "entropy": 0.76564120054245, | |
| "epoch": 3.6877523553162854, | |
| "grad_norm": 0.39172571897506714, | |
| "learning_rate": 7.472323432479062e-05, | |
| "loss": 0.02590138018131256, | |
| "mean_token_accuracy": 0.9894755899906158, | |
| "num_tokens": 56680576.0, | |
| "step": 2740 | |
| }, | |
| { | |
| "entropy": 0.7723122954368591, | |
| "epoch": 3.7012113055181697, | |
| "grad_norm": 0.45653218030929565, | |
| "learning_rate": 7.452954536648888e-05, | |
| "loss": 0.02483226954936981, | |
| "mean_token_accuracy": 0.98988236784935, | |
| "num_tokens": 56887721.0, | |
| "step": 2750 | |
| }, | |
| { | |
| "entropy": 0.7695056736469269, | |
| "epoch": 3.714670255720054, | |
| "grad_norm": 0.522171139717102, | |
| "learning_rate": 7.433537042055248e-05, | |
| "loss": 0.025389373302459717, | |
| "mean_token_accuracy": 0.9898433744907379, | |
| "num_tokens": 57094335.0, | |
| "step": 2760 | |
| }, | |
| { | |
| "entropy": 0.7618607759475708, | |
| "epoch": 3.728129205921938, | |
| "grad_norm": 0.4176262319087982, | |
| "learning_rate": 7.414071333404104e-05, | |
| "loss": 0.025304454565048217, | |
| "mean_token_accuracy": 0.9903385758399963, | |
| "num_tokens": 57301425.0, | |
| "step": 2770 | |
| }, | |
| { | |
| "entropy": 0.7558614552021027, | |
| "epoch": 3.7415881561238225, | |
| "grad_norm": 0.35137420892715454, | |
| "learning_rate": 7.394557796356644e-05, | |
| "loss": 0.023388701677322387, | |
| "mean_token_accuracy": 0.990731543302536, | |
| "num_tokens": 57508536.0, | |
| "step": 2780 | |
| }, | |
| { | |
| "entropy": 0.7547170579433441, | |
| "epoch": 3.7550471063257067, | |
| "grad_norm": 0.4727605879306793, | |
| "learning_rate": 7.374996817521653e-05, | |
| "loss": 0.02676147222518921, | |
| "mean_token_accuracy": 0.9894650936126709, | |
| "num_tokens": 57715682.0, | |
| "step": 2790 | |
| }, | |
| { | |
| "entropy": 0.7561111927032471, | |
| "epoch": 3.768506056527591, | |
| "grad_norm": 0.42272260785102844, | |
| "learning_rate": 7.35538878444785e-05, | |
| "loss": 0.02376638352870941, | |
| "mean_token_accuracy": 0.9906246423721313, | |
| "num_tokens": 57922961.0, | |
| "step": 2800 | |
| }, | |
| { | |
| "entropy": 0.765377151966095, | |
| "epoch": 3.781965006729475, | |
| "grad_norm": 0.4535030424594879, | |
| "learning_rate": 7.335734085616206e-05, | |
| "loss": 0.025309956073760985, | |
| "mean_token_accuracy": 0.990121603012085, | |
| "num_tokens": 58130145.0, | |
| "step": 2810 | |
| }, | |
| { | |
| "entropy": 0.7608742535114288, | |
| "epoch": 3.7954239569313595, | |
| "grad_norm": 0.45810800790786743, | |
| "learning_rate": 7.316033110432249e-05, | |
| "loss": 0.025189366936683655, | |
| "mean_token_accuracy": 0.9903482019901275, | |
| "num_tokens": 58337200.0, | |
| "step": 2820 | |
| }, | |
| { | |
| "entropy": 0.7654636561870575, | |
| "epoch": 3.8088829071332437, | |
| "grad_norm": 0.44589853286743164, | |
| "learning_rate": 7.296286249218352e-05, | |
| "loss": 0.023104313015937804, | |
| "mean_token_accuracy": 0.9910144686698914, | |
| "num_tokens": 58544177.0, | |
| "step": 2830 | |
| }, | |
| { | |
| "entropy": 0.7657354652881623, | |
| "epoch": 3.822341857335128, | |
| "grad_norm": 0.4494393765926361, | |
| "learning_rate": 7.276493893205995e-05, | |
| "loss": 0.024192404747009278, | |
| "mean_token_accuracy": 0.9902793347835541, | |
| "num_tokens": 58751848.0, | |
| "step": 2840 | |
| }, | |
| { | |
| "entropy": 0.7766771256923676, | |
| "epoch": 3.8358008075370122, | |
| "grad_norm": 0.4393499493598938, | |
| "learning_rate": 7.256656434528018e-05, | |
| "loss": 0.02485754042863846, | |
| "mean_token_accuracy": 0.9902261734008789, | |
| "num_tokens": 58958848.0, | |
| "step": 2850 | |
| }, | |
| { | |
| "entropy": 0.7848943591117858, | |
| "epoch": 3.8492597577388965, | |
| "grad_norm": 0.3587435185909271, | |
| "learning_rate": 7.236774266210852e-05, | |
| "loss": 0.026044368743896484, | |
| "mean_token_accuracy": 0.9900348424911499, | |
| "num_tokens": 59165462.0, | |
| "step": 2860 | |
| }, | |
| { | |
| "entropy": 0.7800885438919067, | |
| "epoch": 3.8627187079407808, | |
| "grad_norm": 0.6072045564651489, | |
| "learning_rate": 7.216847782166727e-05, | |
| "loss": 0.025104761123657227, | |
| "mean_token_accuracy": 0.9903142392635346, | |
| "num_tokens": 59372176.0, | |
| "step": 2870 | |
| }, | |
| { | |
| "entropy": 0.7828551828861237, | |
| "epoch": 3.876177658142665, | |
| "grad_norm": 0.3913317620754242, | |
| "learning_rate": 7.196877377185872e-05, | |
| "loss": 0.022907453775405883, | |
| "mean_token_accuracy": 0.9911571919918061, | |
| "num_tokens": 59578745.0, | |
| "step": 2880 | |
| }, | |
| { | |
| "entropy": 0.7775038599967956, | |
| "epoch": 3.8896366083445493, | |
| "grad_norm": 0.590624988079071, | |
| "learning_rate": 7.176863446928694e-05, | |
| "loss": 0.025417977571487428, | |
| "mean_token_accuracy": 0.990390133857727, | |
| "num_tokens": 59786043.0, | |
| "step": 2890 | |
| }, | |
| { | |
| "entropy": 0.7806641340255738, | |
| "epoch": 3.9030955585464335, | |
| "grad_norm": 0.5686063766479492, | |
| "learning_rate": 7.156806387917937e-05, | |
| "loss": 0.026116243004798888, | |
| "mean_token_accuracy": 0.9900750458240509, | |
| "num_tokens": 59992818.0, | |
| "step": 2900 | |
| }, | |
| { | |
| "entropy": 0.7746634542942047, | |
| "epoch": 3.916554508748318, | |
| "grad_norm": 0.4476391673088074, | |
| "learning_rate": 7.136706597530825e-05, | |
| "loss": 0.025634783506393432, | |
| "mean_token_accuracy": 0.990031260251999, | |
| "num_tokens": 60200512.0, | |
| "step": 2910 | |
| }, | |
| { | |
| "entropy": 0.7778063654899597, | |
| "epoch": 3.930013458950202, | |
| "grad_norm": 0.45968928933143616, | |
| "learning_rate": 7.116564473991192e-05, | |
| "loss": 0.023689424991607665, | |
| "mean_token_accuracy": 0.9907764077186585, | |
| "num_tokens": 60407416.0, | |
| "step": 2920 | |
| }, | |
| { | |
| "entropy": 0.7707861483097076, | |
| "epoch": 3.9434724091520863, | |
| "grad_norm": 0.43096625804901123, | |
| "learning_rate": 7.096380416361588e-05, | |
| "loss": 0.026516634225845336, | |
| "mean_token_accuracy": 0.9897350788116455, | |
| "num_tokens": 60614233.0, | |
| "step": 2930 | |
| }, | |
| { | |
| "entropy": 0.7748425483703614, | |
| "epoch": 3.9569313593539706, | |
| "grad_norm": 0.4846278131008148, | |
| "learning_rate": 7.076154824535381e-05, | |
| "loss": 0.024681851267814636, | |
| "mean_token_accuracy": 0.9901362180709838, | |
| "num_tokens": 60821054.0, | |
| "step": 2940 | |
| }, | |
| { | |
| "entropy": 0.7784582912921906, | |
| "epoch": 3.970390309555855, | |
| "grad_norm": 0.5366997122764587, | |
| "learning_rate": 7.055888099228825e-05, | |
| "loss": 0.02371453642845154, | |
| "mean_token_accuracy": 0.9906255662441253, | |
| "num_tokens": 61027779.0, | |
| "step": 2950 | |
| }, | |
| { | |
| "entropy": 0.7729446291923523, | |
| "epoch": 3.983849259757739, | |
| "grad_norm": 0.4675896167755127, | |
| "learning_rate": 7.035580641973119e-05, | |
| "loss": 0.025786811113357545, | |
| "mean_token_accuracy": 0.9903778076171875, | |
| "num_tokens": 61234796.0, | |
| "step": 2960 | |
| }, | |
| { | |
| "entropy": 0.7831340730190277, | |
| "epoch": 3.9973082099596233, | |
| "grad_norm": 0.5064438581466675, | |
| "learning_rate": 7.015232855106468e-05, | |
| "loss": 0.025132563710212708, | |
| "mean_token_accuracy": 0.9904121816158294, | |
| "num_tokens": 61441775.0, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_entropy": 0.7909596406730117, | |
| "eval_loss": 0.041984885931015015, | |
| "eval_mean_token_accuracy": 0.9838614156291743, | |
| "eval_num_tokens": 61483186.0, | |
| "eval_runtime": 13.9502, | |
| "eval_samples_per_second": 358.417, | |
| "eval_steps_per_second": 11.254, | |
| "step": 2972 | |
| }, | |
| { | |
| "entropy": 0.7836226105690003, | |
| "epoch": 4.010767160161508, | |
| "grad_norm": 0.4120180606842041, | |
| "learning_rate": 6.994845141766093e-05, | |
| "loss": 0.020024305582046507, | |
| "mean_token_accuracy": 0.9928817927837372, | |
| "num_tokens": 61648895.0, | |
| "step": 2980 | |
| }, | |
| { | |
| "entropy": 0.7865998208522796, | |
| "epoch": 4.024226110363392, | |
| "grad_norm": 0.5804464817047119, | |
| "learning_rate": 6.974417905880255e-05, | |
| "loss": 0.01588797867298126, | |
| "mean_token_accuracy": 0.9940837860107422, | |
| "num_tokens": 61855674.0, | |
| "step": 2990 | |
| }, | |
| { | |
| "entropy": 0.791904878616333, | |
| "epoch": 4.037685060565276, | |
| "grad_norm": 0.5396016836166382, | |
| "learning_rate": 6.953951552160248e-05, | |
| "loss": 0.016767729818820954, | |
| "mean_token_accuracy": 0.9937978744506836, | |
| "num_tokens": 62063108.0, | |
| "step": 3000 | |
| }, | |
| { | |
| "entropy": 0.7812646925449371, | |
| "epoch": 4.05114401076716, | |
| "grad_norm": 0.42720192670822144, | |
| "learning_rate": 6.933446486092381e-05, | |
| "loss": 0.017768773436546325, | |
| "mean_token_accuracy": 0.9928662478923798, | |
| "num_tokens": 62269786.0, | |
| "step": 3010 | |
| }, | |
| { | |
| "entropy": 0.7833780586719513, | |
| "epoch": 4.064602960969045, | |
| "grad_norm": 0.4398343861103058, | |
| "learning_rate": 6.912903113929947e-05, | |
| "loss": 0.01689823865890503, | |
| "mean_token_accuracy": 0.9940429389476776, | |
| "num_tokens": 62476729.0, | |
| "step": 3020 | |
| }, | |
| { | |
| "entropy": 0.7901590645313263, | |
| "epoch": 4.078061911170929, | |
| "grad_norm": 0.4574897289276123, | |
| "learning_rate": 6.892321842685171e-05, | |
| "loss": 0.018462637066841127, | |
| "mean_token_accuracy": 0.9929858446121216, | |
| "num_tokens": 62683484.0, | |
| "step": 3030 | |
| }, | |
| { | |
| "entropy": 0.7843089640140534, | |
| "epoch": 4.091520861372813, | |
| "grad_norm": 0.4095018208026886, | |
| "learning_rate": 6.871703080121148e-05, | |
| "loss": 0.01854866147041321, | |
| "mean_token_accuracy": 0.9926708579063416, | |
| "num_tokens": 62890197.0, | |
| "step": 3040 | |
| }, | |
| { | |
| "entropy": 0.7845255315303803, | |
| "epoch": 4.104979811574697, | |
| "grad_norm": 0.49721238017082214, | |
| "learning_rate": 6.851047234743763e-05, | |
| "loss": 0.017842569947242738, | |
| "mean_token_accuracy": 0.9929874241352081, | |
| "num_tokens": 63096782.0, | |
| "step": 3050 | |
| }, | |
| { | |
| "entropy": 0.8012731611728668, | |
| "epoch": 4.118438761776582, | |
| "grad_norm": 0.3944236636161804, | |
| "learning_rate": 6.830354715793598e-05, | |
| "loss": 0.017182928323745728, | |
| "mean_token_accuracy": 0.9936406493186951, | |
| "num_tokens": 63302887.0, | |
| "step": 3060 | |
| }, | |
| { | |
| "entropy": 0.8002919495105744, | |
| "epoch": 4.131897711978466, | |
| "grad_norm": 0.4541427493095398, | |
| "learning_rate": 6.809625933237826e-05, | |
| "loss": 0.016480381786823272, | |
| "mean_token_accuracy": 0.9933510184288025, | |
| "num_tokens": 63509930.0, | |
| "step": 3070 | |
| }, | |
| { | |
| "entropy": 0.8035316348075867, | |
| "epoch": 4.14535666218035, | |
| "grad_norm": 0.44510146975517273, | |
| "learning_rate": 6.788861297762086e-05, | |
| "loss": 0.01899719089269638, | |
| "mean_token_accuracy": 0.99237060546875, | |
| "num_tokens": 63716805.0, | |
| "step": 3080 | |
| }, | |
| { | |
| "entropy": 0.7973145604133606, | |
| "epoch": 4.158815612382234, | |
| "grad_norm": 0.4416787624359131, | |
| "learning_rate": 6.768061220762345e-05, | |
| "loss": 0.017631854116916656, | |
| "mean_token_accuracy": 0.993181437253952, | |
| "num_tokens": 63923594.0, | |
| "step": 3090 | |
| }, | |
| { | |
| "entropy": 0.785740852355957, | |
| "epoch": 4.172274562584119, | |
| "grad_norm": 0.44484615325927734, | |
| "learning_rate": 6.747226114336753e-05, | |
| "loss": 0.017793142795562746, | |
| "mean_token_accuracy": 0.9931233644485473, | |
| "num_tokens": 64130006.0, | |
| "step": 3100 | |
| }, | |
| { | |
| "entropy": 0.769168746471405, | |
| "epoch": 4.185733512786003, | |
| "grad_norm": 0.5192431807518005, | |
| "learning_rate": 6.726356391277471e-05, | |
| "loss": 0.017981474101543427, | |
| "mean_token_accuracy": 0.9931439876556396, | |
| "num_tokens": 64337175.0, | |
| "step": 3110 | |
| }, | |
| { | |
| "entropy": 0.7719715535640717, | |
| "epoch": 4.199192462987887, | |
| "grad_norm": 0.6079246401786804, | |
| "learning_rate": 6.7054524650625e-05, | |
| "loss": 0.01674233376979828, | |
| "mean_token_accuracy": 0.9935880184173584, | |
| "num_tokens": 64544044.0, | |
| "step": 3120 | |
| }, | |
| { | |
| "entropy": 0.7753833174705506, | |
| "epoch": 4.212651413189771, | |
| "grad_norm": 0.4159577786922455, | |
| "learning_rate": 6.684514749847482e-05, | |
| "loss": 0.01796432286500931, | |
| "mean_token_accuracy": 0.992877596616745, | |
| "num_tokens": 64751161.0, | |
| "step": 3130 | |
| }, | |
| { | |
| "entropy": 0.7759944558143616, | |
| "epoch": 4.226110363391656, | |
| "grad_norm": 0.5487306714057922, | |
| "learning_rate": 6.663543660457503e-05, | |
| "loss": 0.019616091251373292, | |
| "mean_token_accuracy": 0.9922689974308014, | |
| "num_tokens": 64957845.0, | |
| "step": 3140 | |
| }, | |
| { | |
| "entropy": 0.7630272626876831, | |
| "epoch": 4.23956931359354, | |
| "grad_norm": 0.5038378238677979, | |
| "learning_rate": 6.642539612378863e-05, | |
| "loss": 0.01772879660129547, | |
| "mean_token_accuracy": 0.9931340932846069, | |
| "num_tokens": 65165108.0, | |
| "step": 3150 | |
| }, | |
| { | |
| "entropy": 0.7629122614860535, | |
| "epoch": 4.253028263795424, | |
| "grad_norm": 0.4874984622001648, | |
| "learning_rate": 6.621503021750858e-05, | |
| "loss": 0.018539264798164368, | |
| "mean_token_accuracy": 0.9927669823169708, | |
| "num_tokens": 65371838.0, | |
| "step": 3160 | |
| }, | |
| { | |
| "entropy": 0.764429771900177, | |
| "epoch": 4.2664872139973085, | |
| "grad_norm": 0.4427169859409332, | |
| "learning_rate": 6.600434305357521e-05, | |
| "loss": 0.01739906668663025, | |
| "mean_token_accuracy": 0.9933329343795776, | |
| "num_tokens": 65578601.0, | |
| "step": 3170 | |
| }, | |
| { | |
| "entropy": 0.77511927485466, | |
| "epoch": 4.279946164199193, | |
| "grad_norm": 0.6782849431037903, | |
| "learning_rate": 6.579333880619376e-05, | |
| "loss": 0.017153051495552064, | |
| "mean_token_accuracy": 0.9933244109153747, | |
| "num_tokens": 65785157.0, | |
| "step": 3180 | |
| }, | |
| { | |
| "entropy": 0.7763962566852569, | |
| "epoch": 4.293405114401077, | |
| "grad_norm": 0.3921811878681183, | |
| "learning_rate": 6.558202165585161e-05, | |
| "loss": 0.01766786277294159, | |
| "mean_token_accuracy": 0.9931640028953552, | |
| "num_tokens": 65992605.0, | |
| "step": 3190 | |
| }, | |
| { | |
| "entropy": 0.7710970163345336, | |
| "epoch": 4.306864064602961, | |
| "grad_norm": 0.4926285147666931, | |
| "learning_rate": 6.53703957892355e-05, | |
| "loss": 0.017494969069957733, | |
| "mean_token_accuracy": 0.993228965997696, | |
| "num_tokens": 66199512.0, | |
| "step": 3200 | |
| }, | |
| { | |
| "entropy": 0.7679614186286926, | |
| "epoch": 4.3203230148048455, | |
| "grad_norm": 0.4171614646911621, | |
| "learning_rate": 6.515846539914854e-05, | |
| "loss": 0.018978503346443177, | |
| "mean_token_accuracy": 0.9928891599178314, | |
| "num_tokens": 66405729.0, | |
| "step": 3210 | |
| }, | |
| { | |
| "entropy": 0.7584276318550109, | |
| "epoch": 4.33378196500673, | |
| "grad_norm": 0.45492124557495117, | |
| "learning_rate": 6.494623468442718e-05, | |
| "loss": 0.017702722549438478, | |
| "mean_token_accuracy": 0.993442302942276, | |
| "num_tokens": 66612712.0, | |
| "step": 3220 | |
| }, | |
| { | |
| "entropy": 0.7790658175945282, | |
| "epoch": 4.347240915208614, | |
| "grad_norm": 0.49954837560653687, | |
| "learning_rate": 6.473370784985798e-05, | |
| "loss": 0.016838689148426057, | |
| "mean_token_accuracy": 0.9936484694480896, | |
| "num_tokens": 66819289.0, | |
| "step": 3230 | |
| }, | |
| { | |
| "entropy": 0.8013432800769806, | |
| "epoch": 4.360699865410498, | |
| "grad_norm": 0.46975138783454895, | |
| "learning_rate": 6.452088910609436e-05, | |
| "loss": 0.0176068514585495, | |
| "mean_token_accuracy": 0.9932349562644959, | |
| "num_tokens": 67025841.0, | |
| "step": 3240 | |
| }, | |
| { | |
| "entropy": 0.7898520290851593, | |
| "epoch": 4.3741588156123825, | |
| "grad_norm": 0.38737940788269043, | |
| "learning_rate": 6.430778266957312e-05, | |
| "loss": 0.01757241189479828, | |
| "mean_token_accuracy": 0.9932108998298645, | |
| "num_tokens": 67232968.0, | |
| "step": 3250 | |
| }, | |
| { | |
| "entropy": 0.7705098152160644, | |
| "epoch": 4.387617765814267, | |
| "grad_norm": 0.4774077832698822, | |
| "learning_rate": 6.409439276243092e-05, | |
| "loss": 0.02002309709787369, | |
| "mean_token_accuracy": 0.9923814833164215, | |
| "num_tokens": 67439528.0, | |
| "step": 3260 | |
| }, | |
| { | |
| "entropy": 0.7659395933151245, | |
| "epoch": 4.401076716016151, | |
| "grad_norm": 0.551794171333313, | |
| "learning_rate": 6.388072361242067e-05, | |
| "loss": 0.019037923216819762, | |
| "mean_token_accuracy": 0.9924685060977936, | |
| "num_tokens": 67646641.0, | |
| "step": 3270 | |
| }, | |
| { | |
| "entropy": 0.7678803563117981, | |
| "epoch": 4.414535666218035, | |
| "grad_norm": 0.742902934551239, | |
| "learning_rate": 6.366677945282769e-05, | |
| "loss": 0.019253468513488768, | |
| "mean_token_accuracy": 0.9927851676940918, | |
| "num_tokens": 67853488.0, | |
| "step": 3280 | |
| }, | |
| { | |
| "entropy": 0.765274178981781, | |
| "epoch": 4.4279946164199195, | |
| "grad_norm": 0.4489310085773468, | |
| "learning_rate": 6.345256452238591e-05, | |
| "loss": 0.019601096212863923, | |
| "mean_token_accuracy": 0.9925384223461151, | |
| "num_tokens": 68060312.0, | |
| "step": 3290 | |
| }, | |
| { | |
| "entropy": 0.7568464636802673, | |
| "epoch": 4.441453566621804, | |
| "grad_norm": 0.5335469841957092, | |
| "learning_rate": 6.323808306519385e-05, | |
| "loss": 0.01803976595401764, | |
| "mean_token_accuracy": 0.9932062149047851, | |
| "num_tokens": 68267066.0, | |
| "step": 3300 | |
| }, | |
| { | |
| "entropy": 0.7597867846488953, | |
| "epoch": 4.454912516823688, | |
| "grad_norm": 0.5096181035041809, | |
| "learning_rate": 6.302333933063057e-05, | |
| "loss": 0.017728343605995178, | |
| "mean_token_accuracy": 0.9933403611183167, | |
| "num_tokens": 68474119.0, | |
| "step": 3310 | |
| }, | |
| { | |
| "entropy": 0.7647906184196472, | |
| "epoch": 4.468371467025572, | |
| "grad_norm": 0.5999929904937744, | |
| "learning_rate": 6.280833757327142e-05, | |
| "loss": 0.01955530196428299, | |
| "mean_token_accuracy": 0.9925283312797546, | |
| "num_tokens": 68680905.0, | |
| "step": 3320 | |
| }, | |
| { | |
| "entropy": 0.7616272032260895, | |
| "epoch": 4.481830417227457, | |
| "grad_norm": 0.4349266588687897, | |
| "learning_rate": 6.259308205280383e-05, | |
| "loss": 0.018944016098976134, | |
| "mean_token_accuracy": 0.9924477934837341, | |
| "num_tokens": 68887234.0, | |
| "step": 3330 | |
| }, | |
| { | |
| "entropy": 0.7569435834884644, | |
| "epoch": 4.495289367429341, | |
| "grad_norm": 0.5471845865249634, | |
| "learning_rate": 6.237757703394283e-05, | |
| "loss": 0.016963809728622437, | |
| "mean_token_accuracy": 0.9936882734298706, | |
| "num_tokens": 69094075.0, | |
| "step": 3340 | |
| }, | |
| { | |
| "entropy": 0.7671379745006561, | |
| "epoch": 4.508748317631225, | |
| "grad_norm": 0.5381366610527039, | |
| "learning_rate": 6.216182678634664e-05, | |
| "loss": 0.016747696697711943, | |
| "mean_token_accuracy": 0.9936853110790252, | |
| "num_tokens": 69300893.0, | |
| "step": 3350 | |
| }, | |
| { | |
| "entropy": 0.7783296048641205, | |
| "epoch": 4.522207267833109, | |
| "grad_norm": 0.5440670251846313, | |
| "learning_rate": 6.194583558453199e-05, | |
| "loss": 0.017477567493915557, | |
| "mean_token_accuracy": 0.9932597935199737, | |
| "num_tokens": 69508129.0, | |
| "step": 3360 | |
| }, | |
| { | |
| "entropy": 0.7844888031482696, | |
| "epoch": 4.535666218034994, | |
| "grad_norm": 0.5029262900352478, | |
| "learning_rate": 6.172960770778948e-05, | |
| "loss": 0.016931781172752382, | |
| "mean_token_accuracy": 0.99377281665802, | |
| "num_tokens": 69714928.0, | |
| "step": 3370 | |
| }, | |
| { | |
| "entropy": 0.794099646806717, | |
| "epoch": 4.549125168236878, | |
| "grad_norm": 0.48055407404899597, | |
| "learning_rate": 6.151314744009885e-05, | |
| "loss": 0.018056708574295043, | |
| "mean_token_accuracy": 0.9930496513843536, | |
| "num_tokens": 69921790.0, | |
| "step": 3380 | |
| }, | |
| { | |
| "entropy": 0.7762019991874695, | |
| "epoch": 4.562584118438762, | |
| "grad_norm": 0.5742813944816589, | |
| "learning_rate": 6.129645907004395e-05, | |
| "loss": 0.018931837379932405, | |
| "mean_token_accuracy": 0.9926802217960358, | |
| "num_tokens": 70128934.0, | |
| "step": 3390 | |
| }, | |
| { | |
| "entropy": 0.7701474964618683, | |
| "epoch": 4.576043068640646, | |
| "grad_norm": 0.4316072463989258, | |
| "learning_rate": 6.107954689072796e-05, | |
| "loss": 0.017746394872665404, | |
| "mean_token_accuracy": 0.9927630186080932, | |
| "num_tokens": 70336124.0, | |
| "step": 3400 | |
| }, | |
| { | |
| "entropy": 0.7807201445102692, | |
| "epoch": 4.589502018842531, | |
| "grad_norm": 0.4106089174747467, | |
| "learning_rate": 6.086241519968822e-05, | |
| "loss": 0.01805357336997986, | |
| "mean_token_accuracy": 0.9930870115756989, | |
| "num_tokens": 70542565.0, | |
| "step": 3410 | |
| }, | |
| { | |
| "entropy": 0.7832616925239563, | |
| "epoch": 4.602960969044415, | |
| "grad_norm": 0.443533331155777, | |
| "learning_rate": 6.064506829881109e-05, | |
| "loss": 0.018582865595817566, | |
| "mean_token_accuracy": 0.9929667472839355, | |
| "num_tokens": 70749808.0, | |
| "step": 3420 | |
| }, | |
| { | |
| "entropy": 0.7755731046199799, | |
| "epoch": 4.616419919246299, | |
| "grad_norm": 0.3619384169578552, | |
| "learning_rate": 6.042751049424675e-05, | |
| "loss": 0.01779957562685013, | |
| "mean_token_accuracy": 0.9932062923908234, | |
| "num_tokens": 70956795.0, | |
| "step": 3430 | |
| }, | |
| { | |
| "entropy": 0.7820507228374481, | |
| "epoch": 4.629878869448183, | |
| "grad_norm": 0.4131346344947815, | |
| "learning_rate": 6.02097460963239e-05, | |
| "loss": 0.01847451776266098, | |
| "mean_token_accuracy": 0.9929662108421325, | |
| "num_tokens": 71163524.0, | |
| "step": 3440 | |
| }, | |
| { | |
| "entropy": 0.7895468533039093, | |
| "epoch": 4.643337819650068, | |
| "grad_norm": 0.5880967378616333, | |
| "learning_rate": 5.999177941946429e-05, | |
| "loss": 0.018063023686408997, | |
| "mean_token_accuracy": 0.9928370118141174, | |
| "num_tokens": 71370916.0, | |
| "step": 3450 | |
| }, | |
| { | |
| "entropy": 0.7732610762119293, | |
| "epoch": 4.656796769851952, | |
| "grad_norm": 0.4882413148880005, | |
| "learning_rate": 5.977361478209732e-05, | |
| "loss": 0.01768999993801117, | |
| "mean_token_accuracy": 0.9935171842575073, | |
| "num_tokens": 71577910.0, | |
| "step": 3460 | |
| }, | |
| { | |
| "entropy": 0.7638017177581787, | |
| "epoch": 4.670255720053836, | |
| "grad_norm": 0.36234211921691895, | |
| "learning_rate": 5.955525650657444e-05, | |
| "loss": 0.01707223504781723, | |
| "mean_token_accuracy": 0.9930117666721344, | |
| "num_tokens": 71784872.0, | |
| "step": 3470 | |
| }, | |
| { | |
| "entropy": 0.7676116108894349, | |
| "epoch": 4.68371467025572, | |
| "grad_norm": 0.4788723587989807, | |
| "learning_rate": 5.933670891908355e-05, | |
| "loss": 0.018473857641220094, | |
| "mean_token_accuracy": 0.9927574157714844, | |
| "num_tokens": 71991745.0, | |
| "step": 3480 | |
| }, | |
| { | |
| "entropy": 0.7711163818836212, | |
| "epoch": 4.697173620457605, | |
| "grad_norm": 0.4580574333667755, | |
| "learning_rate": 5.9117976349563206e-05, | |
| "loss": 0.017843346297740936, | |
| "mean_token_accuracy": 0.9930699467658997, | |
| "num_tokens": 72198649.0, | |
| "step": 3490 | |
| }, | |
| { | |
| "entropy": 0.7644717395305634, | |
| "epoch": 4.710632570659489, | |
| "grad_norm": 0.6007668375968933, | |
| "learning_rate": 5.889906313161696e-05, | |
| "loss": 0.019403815269470215, | |
| "mean_token_accuracy": 0.9927784681320191, | |
| "num_tokens": 72405701.0, | |
| "step": 3500 | |
| }, | |
| { | |
| "entropy": 0.7628248929977417, | |
| "epoch": 4.724091520861373, | |
| "grad_norm": 0.37293317914009094, | |
| "learning_rate": 5.8679973602427376e-05, | |
| "loss": 0.017194029688835145, | |
| "mean_token_accuracy": 0.9929509341716767, | |
| "num_tokens": 72612800.0, | |
| "step": 3510 | |
| }, | |
| { | |
| "entropy": 0.7724367201328277, | |
| "epoch": 4.737550471063257, | |
| "grad_norm": 0.3919832706451416, | |
| "learning_rate": 5.846071210267018e-05, | |
| "loss": 0.018434235453605653, | |
| "mean_token_accuracy": 0.9928217232227325, | |
| "num_tokens": 72819618.0, | |
| "step": 3520 | |
| }, | |
| { | |
| "entropy": 0.7768795371055603, | |
| "epoch": 4.751009421265142, | |
| "grad_norm": 0.5469701886177063, | |
| "learning_rate": 5.824128297642823e-05, | |
| "loss": 0.017534643411636353, | |
| "mean_token_accuracy": 0.9931679129600525, | |
| "num_tokens": 73026521.0, | |
| "step": 3530 | |
| }, | |
| { | |
| "entropy": 0.7600254356861115, | |
| "epoch": 4.764468371467026, | |
| "grad_norm": 0.4579508602619171, | |
| "learning_rate": 5.802169057110548e-05, | |
| "loss": 0.018480783700942992, | |
| "mean_token_accuracy": 0.9927056908607483, | |
| "num_tokens": 73233512.0, | |
| "step": 3540 | |
| }, | |
| { | |
| "entropy": 0.750648146867752, | |
| "epoch": 4.77792732166891, | |
| "grad_norm": 0.5560661554336548, | |
| "learning_rate": 5.7801939237340786e-05, | |
| "loss": 0.01876264363527298, | |
| "mean_token_accuracy": 0.9926550030708313, | |
| "num_tokens": 73440515.0, | |
| "step": 3550 | |
| }, | |
| { | |
| "entropy": 0.7545541048049926, | |
| "epoch": 4.7913862718707945, | |
| "grad_norm": 0.45055732131004333, | |
| "learning_rate": 5.758203332892177e-05, | |
| "loss": 0.01602725088596344, | |
| "mean_token_accuracy": 0.993874579668045, | |
| "num_tokens": 73647478.0, | |
| "step": 3560 | |
| }, | |
| { | |
| "entropy": 0.7609083950519562, | |
| "epoch": 4.804845222072679, | |
| "grad_norm": 0.549947202205658, | |
| "learning_rate": 5.736197720269855e-05, | |
| "loss": 0.01784185767173767, | |
| "mean_token_accuracy": 0.9930622160434723, | |
| "num_tokens": 73854294.0, | |
| "step": 3570 | |
| }, | |
| { | |
| "entropy": 0.7656745433807373, | |
| "epoch": 4.818304172274562, | |
| "grad_norm": 0.4915235936641693, | |
| "learning_rate": 5.714177521849736e-05, | |
| "loss": 0.01744186580181122, | |
| "mean_token_accuracy": 0.9929351925849914, | |
| "num_tokens": 74060324.0, | |
| "step": 3580 | |
| }, | |
| { | |
| "entropy": 0.7592082619667053, | |
| "epoch": 4.831763122476447, | |
| "grad_norm": 0.5766359567642212, | |
| "learning_rate": 5.69214317390343e-05, | |
| "loss": 0.018355701863765717, | |
| "mean_token_accuracy": 0.9929331362247467, | |
| "num_tokens": 74267384.0, | |
| "step": 3590 | |
| }, | |
| { | |
| "entropy": 0.7560055673122406, | |
| "epoch": 4.845222072678331, | |
| "grad_norm": 0.4810236990451813, | |
| "learning_rate": 5.670095112982875e-05, | |
| "loss": 0.01801997423171997, | |
| "mean_token_accuracy": 0.9928223788738251, | |
| "num_tokens": 74474563.0, | |
| "step": 3600 | |
| }, | |
| { | |
| "entropy": 0.7539739072322845, | |
| "epoch": 4.858681022880216, | |
| "grad_norm": 0.39908966422080994, | |
| "learning_rate": 5.648033775911701e-05, | |
| "loss": 0.017030759155750273, | |
| "mean_token_accuracy": 0.9934890806674957, | |
| "num_tokens": 74681852.0, | |
| "step": 3610 | |
| }, | |
| { | |
| "entropy": 0.7632683336734771, | |
| "epoch": 4.872139973082099, | |
| "grad_norm": 0.4063929319381714, | |
| "learning_rate": 5.625959599776564e-05, | |
| "loss": 0.017804598808288573, | |
| "mean_token_accuracy": 0.9931166589260101, | |
| "num_tokens": 74888593.0, | |
| "step": 3620 | |
| }, | |
| { | |
| "entropy": 0.7684237122535705, | |
| "epoch": 4.885598923283984, | |
| "grad_norm": 0.4352034628391266, | |
| "learning_rate": 5.603873021918493e-05, | |
| "loss": 0.016362884640693666, | |
| "mean_token_accuracy": 0.9936956346035004, | |
| "num_tokens": 75096000.0, | |
| "step": 3630 | |
| }, | |
| { | |
| "entropy": 0.7725315749645233, | |
| "epoch": 4.899057873485868, | |
| "grad_norm": 0.5453092455863953, | |
| "learning_rate": 5.581774479924229e-05, | |
| "loss": 0.016236093640327454, | |
| "mean_token_accuracy": 0.993706214427948, | |
| "num_tokens": 75302578.0, | |
| "step": 3640 | |
| }, | |
| { | |
| "entropy": 0.7653468787670136, | |
| "epoch": 4.912516823687753, | |
| "grad_norm": 0.668065071105957, | |
| "learning_rate": 5.5596644116175444e-05, | |
| "loss": 0.016758397221565247, | |
| "mean_token_accuracy": 0.9932759523391723, | |
| "num_tokens": 75509213.0, | |
| "step": 3650 | |
| }, | |
| { | |
| "entropy": 0.7591579735279084, | |
| "epoch": 4.925975773889636, | |
| "grad_norm": 0.5401139259338379, | |
| "learning_rate": 5.537543255050579e-05, | |
| "loss": 0.017928582429885865, | |
| "mean_token_accuracy": 0.9927070438861847, | |
| "num_tokens": 75716260.0, | |
| "step": 3660 | |
| }, | |
| { | |
| "entropy": 0.7587584853172302, | |
| "epoch": 4.939434724091521, | |
| "grad_norm": 0.4384903609752655, | |
| "learning_rate": 5.5154114484951556e-05, | |
| "loss": 0.017501908540725707, | |
| "mean_token_accuracy": 0.9937355935573577, | |
| "num_tokens": 75923089.0, | |
| "step": 3670 | |
| }, | |
| { | |
| "entropy": 0.7553621172904968, | |
| "epoch": 4.952893674293405, | |
| "grad_norm": 0.5839459896087646, | |
| "learning_rate": 5.4932694304340985e-05, | |
| "loss": 0.016943465173244476, | |
| "mean_token_accuracy": 0.9933674991130829, | |
| "num_tokens": 76129808.0, | |
| "step": 3680 | |
| }, | |
| { | |
| "entropy": 0.7534486532211304, | |
| "epoch": 4.96635262449529, | |
| "grad_norm": 0.5708627700805664, | |
| "learning_rate": 5.471117639552543e-05, | |
| "loss": 0.01732933968305588, | |
| "mean_token_accuracy": 0.993400925397873, | |
| "num_tokens": 76336215.0, | |
| "step": 3690 | |
| }, | |
| { | |
| "entropy": 0.7495142102241517, | |
| "epoch": 4.979811574697173, | |
| "grad_norm": 0.6189046502113342, | |
| "learning_rate": 5.448956514729251e-05, | |
| "loss": 0.01899988055229187, | |
| "mean_token_accuracy": 0.9925648808479309, | |
| "num_tokens": 76543715.0, | |
| "step": 3700 | |
| }, | |
| { | |
| "entropy": 0.751545512676239, | |
| "epoch": 4.993270524899058, | |
| "grad_norm": 0.5944417715072632, | |
| "learning_rate": 5.426786495027908e-05, | |
| "loss": 0.017178787291049956, | |
| "mean_token_accuracy": 0.9932264804840087, | |
| "num_tokens": 76750375.0, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_entropy": 0.7505513182870901, | |
| "eval_loss": 0.044372886419296265, | |
| "eval_mean_token_accuracy": 0.984428718591192, | |
| "eval_num_tokens": 76853983.0, | |
| "eval_runtime": 13.9555, | |
| "eval_samples_per_second": 358.281, | |
| "eval_steps_per_second": 11.25, | |
| "step": 3715 | |
| }, | |
| { | |
| "entropy": 0.7473571479320527, | |
| "epoch": 5.006729475100942, | |
| "grad_norm": 0.3315245509147644, | |
| "learning_rate": 5.404608019688432e-05, | |
| "loss": 0.013754059374332429, | |
| "mean_token_accuracy": 0.9947969734668731, | |
| "num_tokens": 76957311.0, | |
| "step": 3720 | |
| }, | |
| { | |
| "entropy": 0.7534472703933716, | |
| "epoch": 5.020188425302826, | |
| "grad_norm": 0.5313814282417297, | |
| "learning_rate": 5.382421528118262e-05, | |
| "loss": 0.01147187352180481, | |
| "mean_token_accuracy": 0.9957284986972809, | |
| "num_tokens": 77164715.0, | |
| "step": 3730 | |
| }, | |
| { | |
| "entropy": 0.801529586315155, | |
| "epoch": 5.03364737550471, | |
| "grad_norm": 0.4467467665672302, | |
| "learning_rate": 5.360227459883662e-05, | |
| "loss": 0.010463708639144897, | |
| "mean_token_accuracy": 0.9959668934345245, | |
| "num_tokens": 77371640.0, | |
| "step": 3740 | |
| }, | |
| { | |
| "entropy": 0.828974598646164, | |
| "epoch": 5.0471063257065945, | |
| "grad_norm": 0.5245316624641418, | |
| "learning_rate": 5.338026254701003e-05, | |
| "loss": 0.011523199081420899, | |
| "mean_token_accuracy": 0.9956273198127746, | |
| "num_tokens": 77577924.0, | |
| "step": 3750 | |
| }, | |
| { | |
| "entropy": 0.7982487976551056, | |
| "epoch": 5.060565275908479, | |
| "grad_norm": 0.39915889501571655, | |
| "learning_rate": 5.31581835242806e-05, | |
| "loss": 0.011306057125329972, | |
| "mean_token_accuracy": 0.9958861231803894, | |
| "num_tokens": 77784880.0, | |
| "step": 3760 | |
| }, | |
| { | |
| "entropy": 0.7692394316196441, | |
| "epoch": 5.074024226110363, | |
| "grad_norm": 0.34463298320770264, | |
| "learning_rate": 5.293604193055289e-05, | |
| "loss": 0.012429548054933548, | |
| "mean_token_accuracy": 0.995696759223938, | |
| "num_tokens": 77992197.0, | |
| "step": 3770 | |
| }, | |
| { | |
| "entropy": 0.7731356203556061, | |
| "epoch": 5.087483176312247, | |
| "grad_norm": 0.46471163630485535, | |
| "learning_rate": 5.2713842166971165e-05, | |
| "loss": 0.011507495492696761, | |
| "mean_token_accuracy": 0.9956724286079407, | |
| "num_tokens": 78199265.0, | |
| "step": 3780 | |
| }, | |
| { | |
| "entropy": 0.7799284398555756, | |
| "epoch": 5.1009421265141315, | |
| "grad_norm": 0.3777540326118469, | |
| "learning_rate": 5.249158863583216e-05, | |
| "loss": 0.01075114607810974, | |
| "mean_token_accuracy": 0.9960379660129547, | |
| "num_tokens": 78406087.0, | |
| "step": 3790 | |
| }, | |
| { | |
| "entropy": 0.7837011277675628, | |
| "epoch": 5.114401076716016, | |
| "grad_norm": 0.4946545660495758, | |
| "learning_rate": 5.2269285740497876e-05, | |
| "loss": 0.012666209042072296, | |
| "mean_token_accuracy": 0.995057487487793, | |
| "num_tokens": 78613260.0, | |
| "step": 3800 | |
| }, | |
| { | |
| "entropy": 0.7703280210494995, | |
| "epoch": 5.1278600269179, | |
| "grad_norm": 0.32546892762184143, | |
| "learning_rate": 5.204693788530832e-05, | |
| "loss": 0.01195569708943367, | |
| "mean_token_accuracy": 0.9958400011062623, | |
| "num_tokens": 78819967.0, | |
| "step": 3810 | |
| }, | |
| { | |
| "entropy": 0.7721941411495209, | |
| "epoch": 5.141318977119784, | |
| "grad_norm": 0.5005202293395996, | |
| "learning_rate": 5.182454947549428e-05, | |
| "loss": 0.010894721746444702, | |
| "mean_token_accuracy": 0.9959119021892547, | |
| "num_tokens": 79026842.0, | |
| "step": 3820 | |
| }, | |
| { | |
| "entropy": 0.7904182612895966, | |
| "epoch": 5.1547779273216685, | |
| "grad_norm": 0.37900179624557495, | |
| "learning_rate": 5.160212491709002e-05, | |
| "loss": 0.010722023993730545, | |
| "mean_token_accuracy": 0.9961172580718994, | |
| "num_tokens": 79234103.0, | |
| "step": 3830 | |
| }, | |
| { | |
| "entropy": 0.7988847613334655, | |
| "epoch": 5.168236877523553, | |
| "grad_norm": 0.43181365728378296, | |
| "learning_rate": 5.1379668616845975e-05, | |
| "loss": 0.010627251863479615, | |
| "mean_token_accuracy": 0.9959731698036194, | |
| "num_tokens": 79440411.0, | |
| "step": 3840 | |
| }, | |
| { | |
| "entropy": 0.7862568140029907, | |
| "epoch": 5.181695827725437, | |
| "grad_norm": 0.3639049232006073, | |
| "learning_rate": 5.115718498214148e-05, | |
| "loss": 0.010891681909561158, | |
| "mean_token_accuracy": 0.9956743359565735, | |
| "num_tokens": 79647596.0, | |
| "step": 3850 | |
| }, | |
| { | |
| "entropy": 0.7846800267696381, | |
| "epoch": 5.195154777927321, | |
| "grad_norm": 0.5998150110244751, | |
| "learning_rate": 5.093467842089742e-05, | |
| "loss": 0.011233718693256378, | |
| "mean_token_accuracy": 0.9956465005874634, | |
| "num_tokens": 79854600.0, | |
| "step": 3860 | |
| }, | |
| { | |
| "entropy": 0.7855194449424744, | |
| "epoch": 5.2086137281292055, | |
| "grad_norm": 0.48699286580085754, | |
| "learning_rate": 5.071215334148891e-05, | |
| "loss": 0.011192862689495087, | |
| "mean_token_accuracy": 0.9958138644695282, | |
| "num_tokens": 80061989.0, | |
| "step": 3870 | |
| }, | |
| { | |
| "entropy": 0.7742628574371337, | |
| "epoch": 5.22207267833109, | |
| "grad_norm": 0.5599384307861328, | |
| "learning_rate": 5.048961415265797e-05, | |
| "loss": 0.011506590247154235, | |
| "mean_token_accuracy": 0.9957414209842682, | |
| "num_tokens": 80268385.0, | |
| "step": 3880 | |
| }, | |
| { | |
| "entropy": 0.7598394274711608, | |
| "epoch": 5.235531628532974, | |
| "grad_norm": 0.4192953407764435, | |
| "learning_rate": 5.0267065263426125e-05, | |
| "loss": 0.012534248828887939, | |
| "mean_token_accuracy": 0.9951974868774414, | |
| "num_tokens": 80475339.0, | |
| "step": 3890 | |
| }, | |
| { | |
| "entropy": 0.7494603753089905, | |
| "epoch": 5.248990578734858, | |
| "grad_norm": 0.6345610022544861, | |
| "learning_rate": 5.00445110830071e-05, | |
| "loss": 0.01246308833360672, | |
| "mean_token_accuracy": 0.9951446115970611, | |
| "num_tokens": 80682026.0, | |
| "step": 3900 | |
| }, | |
| { | |
| "entropy": 0.7482762694358825, | |
| "epoch": 5.262449528936743, | |
| "grad_norm": 0.3931730389595032, | |
| "learning_rate": 4.9821956020719474e-05, | |
| "loss": 0.012075445801019668, | |
| "mean_token_accuracy": 0.9952457189559937, | |
| "num_tokens": 80888988.0, | |
| "step": 3910 | |
| }, | |
| { | |
| "entropy": 0.7452390134334564, | |
| "epoch": 5.275908479138627, | |
| "grad_norm": 0.4273200035095215, | |
| "learning_rate": 4.959940448589928e-05, | |
| "loss": 0.012490732222795486, | |
| "mean_token_accuracy": 0.9952689290046692, | |
| "num_tokens": 81095986.0, | |
| "step": 3920 | |
| }, | |
| { | |
| "entropy": 0.752661383152008, | |
| "epoch": 5.289367429340511, | |
| "grad_norm": 0.48054444789886475, | |
| "learning_rate": 4.9376860887812666e-05, | |
| "loss": 0.01093846783041954, | |
| "mean_token_accuracy": 0.9958311855793, | |
| "num_tokens": 81303243.0, | |
| "step": 3930 | |
| }, | |
| { | |
| "entropy": 0.7650678336620331, | |
| "epoch": 5.302826379542395, | |
| "grad_norm": 0.44087842106819153, | |
| "learning_rate": 4.915432963556853e-05, | |
| "loss": 0.011806166172027588, | |
| "mean_token_accuracy": 0.9957118093967438, | |
| "num_tokens": 81510139.0, | |
| "step": 3940 | |
| }, | |
| { | |
| "entropy": 0.7748130619525909, | |
| "epoch": 5.31628532974428, | |
| "grad_norm": 0.4736451804637909, | |
| "learning_rate": 4.8931815138031173e-05, | |
| "loss": 0.010728248953819275, | |
| "mean_token_accuracy": 0.9961952686309814, | |
| "num_tokens": 81717034.0, | |
| "step": 3950 | |
| }, | |
| { | |
| "entropy": 0.7736305713653564, | |
| "epoch": 5.329744279946164, | |
| "grad_norm": 0.4647705852985382, | |
| "learning_rate": 4.870932180373296e-05, | |
| "loss": 0.01173371821641922, | |
| "mean_token_accuracy": 0.9954262256622315, | |
| "num_tokens": 81924216.0, | |
| "step": 3960 | |
| }, | |
| { | |
| "entropy": 0.7643655180931092, | |
| "epoch": 5.343203230148048, | |
| "grad_norm": 0.5442004799842834, | |
| "learning_rate": 4.8486854040786926e-05, | |
| "loss": 0.011154447495937348, | |
| "mean_token_accuracy": 0.9956519722938537, | |
| "num_tokens": 82130859.0, | |
| "step": 3970 | |
| }, | |
| { | |
| "entropy": 0.7573722243309021, | |
| "epoch": 5.356662180349932, | |
| "grad_norm": 0.5777075886726379, | |
| "learning_rate": 4.826441625679953e-05, | |
| "loss": 0.010990817844867707, | |
| "mean_token_accuracy": 0.995562344789505, | |
| "num_tokens": 82338043.0, | |
| "step": 3980 | |
| }, | |
| { | |
| "entropy": 0.755225020647049, | |
| "epoch": 5.370121130551817, | |
| "grad_norm": 0.5585280060768127, | |
| "learning_rate": 4.8042012858783223e-05, | |
| "loss": 0.011740070581436158, | |
| "mean_token_accuracy": 0.9957562625408173, | |
| "num_tokens": 82545102.0, | |
| "step": 3990 | |
| }, | |
| { | |
| "entropy": 0.7581014811992646, | |
| "epoch": 5.383580080753701, | |
| "grad_norm": 0.4570481777191162, | |
| "learning_rate": 4.781964825306923e-05, | |
| "loss": 0.010656823217868806, | |
| "mean_token_accuracy": 0.996157032251358, | |
| "num_tokens": 82751505.0, | |
| "step": 4000 | |
| }, | |
| { | |
| "entropy": 0.759818023443222, | |
| "epoch": 5.397039030955585, | |
| "grad_norm": 0.4566776156425476, | |
| "learning_rate": 4.7597326845220206e-05, | |
| "loss": 0.011652395129203796, | |
| "mean_token_accuracy": 0.995825469493866, | |
| "num_tokens": 82958553.0, | |
| "step": 4010 | |
| }, | |
| { | |
| "entropy": 0.7625110745429993, | |
| "epoch": 5.410497981157469, | |
| "grad_norm": 0.47552627325057983, | |
| "learning_rate": 4.737505303994292e-05, | |
| "loss": 0.01105176955461502, | |
| "mean_token_accuracy": 0.995843505859375, | |
| "num_tokens": 83165855.0, | |
| "step": 4020 | |
| }, | |
| { | |
| "entropy": 0.7676438748836517, | |
| "epoch": 5.423956931359354, | |
| "grad_norm": 0.5029258131980896, | |
| "learning_rate": 4.7152831241001065e-05, | |
| "loss": 0.012058970332145692, | |
| "mean_token_accuracy": 0.9953496634960175, | |
| "num_tokens": 83372907.0, | |
| "step": 4030 | |
| }, | |
| { | |
| "entropy": 0.7582855522632599, | |
| "epoch": 5.437415881561238, | |
| "grad_norm": 0.40411460399627686, | |
| "learning_rate": 4.693066585112795e-05, | |
| "loss": 0.011585983633995055, | |
| "mean_token_accuracy": 0.995668250322342, | |
| "num_tokens": 83579883.0, | |
| "step": 4040 | |
| }, | |
| { | |
| "entropy": 0.7627740204334259, | |
| "epoch": 5.450874831763122, | |
| "grad_norm": 0.4695113003253937, | |
| "learning_rate": 4.670856127193928e-05, | |
| "loss": 0.012437713891267776, | |
| "mean_token_accuracy": 0.9953029453754425, | |
| "num_tokens": 83786422.0, | |
| "step": 4050 | |
| }, | |
| { | |
| "entropy": 0.7630968987941742, | |
| "epoch": 5.464333781965006, | |
| "grad_norm": 0.6173301339149475, | |
| "learning_rate": 4.648652190384597e-05, | |
| "loss": 0.011899437010288238, | |
| "mean_token_accuracy": 0.9953746914863586, | |
| "num_tokens": 83993873.0, | |
| "step": 4060 | |
| }, | |
| { | |
| "entropy": 0.7567782461643219, | |
| "epoch": 5.477792732166891, | |
| "grad_norm": 0.35925814509391785, | |
| "learning_rate": 4.626455214596695e-05, | |
| "loss": 0.011643938720226288, | |
| "mean_token_accuracy": 0.9955205857753754, | |
| "num_tokens": 84201046.0, | |
| "step": 4070 | |
| }, | |
| { | |
| "entropy": 0.7553957641124726, | |
| "epoch": 5.491251682368775, | |
| "grad_norm": 0.4315947890281677, | |
| "learning_rate": 4.6042656396042e-05, | |
| "loss": 0.011083407700061798, | |
| "mean_token_accuracy": 0.9957548975944519, | |
| "num_tokens": 84408311.0, | |
| "step": 4080 | |
| }, | |
| { | |
| "entropy": 0.7516207814216613, | |
| "epoch": 5.504710632570659, | |
| "grad_norm": 0.5060084462165833, | |
| "learning_rate": 4.5820839050344643e-05, | |
| "loss": 0.01217108517885208, | |
| "mean_token_accuracy": 0.9953884065151215, | |
| "num_tokens": 84615252.0, | |
| "step": 4090 | |
| }, | |
| { | |
| "entropy": 0.7487595736980438, | |
| "epoch": 5.518169582772543, | |
| "grad_norm": 0.35507968068122864, | |
| "learning_rate": 4.559910450359502e-05, | |
| "loss": 0.01100190356373787, | |
| "mean_token_accuracy": 0.995825058221817, | |
| "num_tokens": 84822094.0, | |
| "step": 4100 | |
| }, | |
| { | |
| "entropy": 0.754398238658905, | |
| "epoch": 5.531628532974428, | |
| "grad_norm": 0.4639805555343628, | |
| "learning_rate": 4.5377457148872837e-05, | |
| "loss": 0.012004619836807251, | |
| "mean_token_accuracy": 0.9956164836883545, | |
| "num_tokens": 85028800.0, | |
| "step": 4110 | |
| }, | |
| { | |
| "entropy": 0.7597955822944641, | |
| "epoch": 5.545087483176312, | |
| "grad_norm": 0.52503901720047, | |
| "learning_rate": 4.515590137753032e-05, | |
| "loss": 0.01215251013636589, | |
| "mean_token_accuracy": 0.9956142961978912, | |
| "num_tokens": 85234972.0, | |
| "step": 4120 | |
| }, | |
| { | |
| "entropy": 0.7510636806488037, | |
| "epoch": 5.558546433378196, | |
| "grad_norm": 0.5228842496871948, | |
| "learning_rate": 4.493444157910521e-05, | |
| "loss": 0.011907792836427688, | |
| "mean_token_accuracy": 0.9956765532493591, | |
| "num_tokens": 85442303.0, | |
| "step": 4130 | |
| }, | |
| { | |
| "entropy": 0.7509365022182465, | |
| "epoch": 5.5720053835800805, | |
| "grad_norm": 0.3873786926269531, | |
| "learning_rate": 4.471308214123381e-05, | |
| "loss": 0.010966875404119492, | |
| "mean_token_accuracy": 0.995771324634552, | |
| "num_tokens": 85648692.0, | |
| "step": 4140 | |
| }, | |
| { | |
| "entropy": 0.7490605235099792, | |
| "epoch": 5.585464333781965, | |
| "grad_norm": 0.5178571939468384, | |
| "learning_rate": 4.449182744956403e-05, | |
| "loss": 0.012869048118591308, | |
| "mean_token_accuracy": 0.9949001133441925, | |
| "num_tokens": 85855568.0, | |
| "step": 4150 | |
| }, | |
| { | |
| "entropy": 0.7433833122253418, | |
| "epoch": 5.598923283983849, | |
| "grad_norm": 0.47041696310043335, | |
| "learning_rate": 4.4270681887668544e-05, | |
| "loss": 0.012250985950231552, | |
| "mean_token_accuracy": 0.9952748596668244, | |
| "num_tokens": 86061971.0, | |
| "step": 4160 | |
| }, | |
| { | |
| "entropy": 0.7359922230243683, | |
| "epoch": 5.612382234185733, | |
| "grad_norm": 0.33492347598075867, | |
| "learning_rate": 4.404964983695786e-05, | |
| "loss": 0.010909316688776016, | |
| "mean_token_accuracy": 0.9960612893104553, | |
| "num_tokens": 86269179.0, | |
| "step": 4170 | |
| }, | |
| { | |
| "entropy": 0.7412485539913177, | |
| "epoch": 5.6258411843876175, | |
| "grad_norm": 0.26885855197906494, | |
| "learning_rate": 4.382873567659361e-05, | |
| "loss": 0.010674068331718444, | |
| "mean_token_accuracy": 0.9960609257221222, | |
| "num_tokens": 86476072.0, | |
| "step": 4180 | |
| }, | |
| { | |
| "entropy": 0.7493269741535187, | |
| "epoch": 5.639300134589502, | |
| "grad_norm": 0.4859159588813782, | |
| "learning_rate": 4.3607943783401736e-05, | |
| "loss": 0.012274256348609925, | |
| "mean_token_accuracy": 0.9954603254795075, | |
| "num_tokens": 86682931.0, | |
| "step": 4190 | |
| }, | |
| { | |
| "entropy": 0.7531224548816681, | |
| "epoch": 5.652759084791386, | |
| "grad_norm": 0.45160216093063354, | |
| "learning_rate": 4.3387278531785747e-05, | |
| "loss": 0.01201828122138977, | |
| "mean_token_accuracy": 0.9953709781169892, | |
| "num_tokens": 86889799.0, | |
| "step": 4200 | |
| }, | |
| { | |
| "entropy": 0.7501720905303955, | |
| "epoch": 5.66621803499327, | |
| "grad_norm": 0.6317504048347473, | |
| "learning_rate": 4.3166744293640134e-05, | |
| "loss": 0.011446791887283325, | |
| "mean_token_accuracy": 0.9956945776939392, | |
| "num_tokens": 87096029.0, | |
| "step": 4210 | |
| }, | |
| { | |
| "entropy": 0.7444611549377441, | |
| "epoch": 5.6796769851951545, | |
| "grad_norm": 0.4731798768043518, | |
| "learning_rate": 4.2946345438263665e-05, | |
| "loss": 0.011316908895969391, | |
| "mean_token_accuracy": 0.9955646634101868, | |
| "num_tokens": 87303163.0, | |
| "step": 4220 | |
| }, | |
| { | |
| "entropy": 0.7472650587558747, | |
| "epoch": 5.693135935397039, | |
| "grad_norm": 0.4799041152000427, | |
| "learning_rate": 4.272608633227287e-05, | |
| "loss": 0.012147380411624909, | |
| "mean_token_accuracy": 0.9951766729354858, | |
| "num_tokens": 87509492.0, | |
| "step": 4230 | |
| }, | |
| { | |
| "entropy": 0.7370569348335266, | |
| "epoch": 5.706594885598923, | |
| "grad_norm": 0.36718371510505676, | |
| "learning_rate": 4.250597133951554e-05, | |
| "loss": 0.011406458914279938, | |
| "mean_token_accuracy": 0.9959278583526612, | |
| "num_tokens": 87716755.0, | |
| "step": 4240 | |
| }, | |
| { | |
| "entropy": 0.73809614777565, | |
| "epoch": 5.720053835800807, | |
| "grad_norm": 0.4381415843963623, | |
| "learning_rate": 4.228600482098423e-05, | |
| "loss": 0.011750604957342148, | |
| "mean_token_accuracy": 0.9957403659820556, | |
| "num_tokens": 87923530.0, | |
| "step": 4250 | |
| }, | |
| { | |
| "entropy": 0.7487466990947723, | |
| "epoch": 5.7335127860026915, | |
| "grad_norm": 0.4299047291278839, | |
| "learning_rate": 4.206619113472986e-05, | |
| "loss": 0.01089790165424347, | |
| "mean_token_accuracy": 0.9957152485847474, | |
| "num_tokens": 88130348.0, | |
| "step": 4260 | |
| }, | |
| { | |
| "entropy": 0.7592370331287384, | |
| "epoch": 5.746971736204576, | |
| "grad_norm": 0.502768874168396, | |
| "learning_rate": 4.18465346357754e-05, | |
| "loss": 0.01133182942867279, | |
| "mean_token_accuracy": 0.9958466529846192, | |
| "num_tokens": 88337724.0, | |
| "step": 4270 | |
| }, | |
| { | |
| "entropy": 0.7617475092411041, | |
| "epoch": 5.76043068640646, | |
| "grad_norm": 0.419840544462204, | |
| "learning_rate": 4.16270396760296e-05, | |
| "loss": 0.011695357412099839, | |
| "mean_token_accuracy": 0.99588702917099, | |
| "num_tokens": 88544195.0, | |
| "step": 4280 | |
| }, | |
| { | |
| "entropy": 0.7570286870002747, | |
| "epoch": 5.773889636608344, | |
| "grad_norm": 0.5709792375564575, | |
| "learning_rate": 4.140771060420066e-05, | |
| "loss": 0.01149986982345581, | |
| "mean_token_accuracy": 0.995744913816452, | |
| "num_tokens": 88751100.0, | |
| "step": 4290 | |
| }, | |
| { | |
| "entropy": 0.7453589260578155, | |
| "epoch": 5.787348586810229, | |
| "grad_norm": 0.47392651438713074, | |
| "learning_rate": 4.118855176571021e-05, | |
| "loss": 0.01253439038991928, | |
| "mean_token_accuracy": 0.9950320243835449, | |
| "num_tokens": 88958170.0, | |
| "step": 4300 | |
| }, | |
| { | |
| "entropy": 0.7403925895690918, | |
| "epoch": 5.800807537012113, | |
| "grad_norm": 0.5566080808639526, | |
| "learning_rate": 4.096956750260718e-05, | |
| "loss": 0.013252611458301543, | |
| "mean_token_accuracy": 0.9950306355953217, | |
| "num_tokens": 89164712.0, | |
| "step": 4310 | |
| }, | |
| { | |
| "entropy": 0.7351096451282502, | |
| "epoch": 5.814266487213997, | |
| "grad_norm": 0.4116886854171753, | |
| "learning_rate": 4.07507621534817e-05, | |
| "loss": 0.012794888019561768, | |
| "mean_token_accuracy": 0.9951526165008545, | |
| "num_tokens": 89371398.0, | |
| "step": 4320 | |
| }, | |
| { | |
| "entropy": 0.7350869536399841, | |
| "epoch": 5.827725437415881, | |
| "grad_norm": 0.37677955627441406, | |
| "learning_rate": 4.053214005337924e-05, | |
| "loss": 0.010807374119758606, | |
| "mean_token_accuracy": 0.9960130155086517, | |
| "num_tokens": 89578181.0, | |
| "step": 4330 | |
| }, | |
| { | |
| "entropy": 0.7448731124401092, | |
| "epoch": 5.841184387617766, | |
| "grad_norm": 0.4849918484687805, | |
| "learning_rate": 4.031370553371465e-05, | |
| "loss": 0.011473974585533142, | |
| "mean_token_accuracy": 0.9955580830574036, | |
| "num_tokens": 89785614.0, | |
| "step": 4340 | |
| }, | |
| { | |
| "entropy": 0.7568134427070617, | |
| "epoch": 5.85464333781965, | |
| "grad_norm": 0.4150851368904114, | |
| "learning_rate": 4.0095462922186385e-05, | |
| "loss": 0.01176745593547821, | |
| "mean_token_accuracy": 0.9955409824848175, | |
| "num_tokens": 89991753.0, | |
| "step": 4350 | |
| }, | |
| { | |
| "entropy": 0.7487130522727966, | |
| "epoch": 5.868102288021534, | |
| "grad_norm": 0.4874976873397827, | |
| "learning_rate": 3.9877416542690746e-05, | |
| "loss": 0.011722442507743836, | |
| "mean_token_accuracy": 0.9955667078495025, | |
| "num_tokens": 90198501.0, | |
| "step": 4360 | |
| }, | |
| { | |
| "entropy": 0.7395595133304596, | |
| "epoch": 5.881561238223418, | |
| "grad_norm": 0.42832764983177185, | |
| "learning_rate": 3.9659570715236234e-05, | |
| "loss": 0.010632017254829406, | |
| "mean_token_accuracy": 0.9957972228527069, | |
| "num_tokens": 90405216.0, | |
| "step": 4370 | |
| }, | |
| { | |
| "entropy": 0.7417290508747101, | |
| "epoch": 5.895020188425303, | |
| "grad_norm": 0.4343918263912201, | |
| "learning_rate": 3.944192975585792e-05, | |
| "loss": 0.011097145825624466, | |
| "mean_token_accuracy": 0.9955754935741424, | |
| "num_tokens": 90611675.0, | |
| "step": 4380 | |
| }, | |
| { | |
| "entropy": 0.7389219880104065, | |
| "epoch": 5.908479138627187, | |
| "grad_norm": 0.4636954367160797, | |
| "learning_rate": 3.922449797653198e-05, | |
| "loss": 0.0111973837018013, | |
| "mean_token_accuracy": 0.9958441913127899, | |
| "num_tokens": 90819047.0, | |
| "step": 4390 | |
| }, | |
| { | |
| "entropy": 0.7388913333415985, | |
| "epoch": 5.921938088829071, | |
| "grad_norm": 0.35796335339546204, | |
| "learning_rate": 3.900727968509024e-05, | |
| "loss": 0.009988104552030563, | |
| "mean_token_accuracy": 0.9962919235229493, | |
| "num_tokens": 91025844.0, | |
| "step": 4400 | |
| }, | |
| { | |
| "entropy": 0.7422888994216919, | |
| "epoch": 5.935397039030955, | |
| "grad_norm": 0.39291512966156006, | |
| "learning_rate": 3.879027918513483e-05, | |
| "loss": 0.010695169866085052, | |
| "mean_token_accuracy": 0.9959912061691284, | |
| "num_tokens": 91232013.0, | |
| "step": 4410 | |
| }, | |
| { | |
| "entropy": 0.7449814796447753, | |
| "epoch": 5.94885598923284, | |
| "grad_norm": 0.539179801940918, | |
| "learning_rate": 3.857350077595289e-05, | |
| "loss": 0.011691944301128387, | |
| "mean_token_accuracy": 0.9955081939697266, | |
| "num_tokens": 91438515.0, | |
| "step": 4420 | |
| }, | |
| { | |
| "entropy": 0.7385162234306335, | |
| "epoch": 5.962314939434724, | |
| "grad_norm": 0.7186609506607056, | |
| "learning_rate": 3.835694875243149e-05, | |
| "loss": 0.012110927700996399, | |
| "mean_token_accuracy": 0.9952600479125977, | |
| "num_tokens": 91645188.0, | |
| "step": 4430 | |
| }, | |
| { | |
| "entropy": 0.731717336177826, | |
| "epoch": 5.975773889636608, | |
| "grad_norm": 0.509856104850769, | |
| "learning_rate": 3.814062740497243e-05, | |
| "loss": 0.011971230804920196, | |
| "mean_token_accuracy": 0.9953718304634094, | |
| "num_tokens": 91851890.0, | |
| "step": 4440 | |
| }, | |
| { | |
| "entropy": 0.724138367176056, | |
| "epoch": 5.989232839838492, | |
| "grad_norm": 0.563079297542572, | |
| "learning_rate": 3.7924541019407264e-05, | |
| "loss": 0.012176686525344848, | |
| "mean_token_accuracy": 0.9949949264526368, | |
| "num_tokens": 92059147.0, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_entropy": 0.7367308508059022, | |
| "eval_loss": 0.050371766090393066, | |
| "eval_mean_token_accuracy": 0.9841803448974706, | |
| "eval_num_tokens": 92224773.0, | |
| "eval_runtime": 14.0163, | |
| "eval_samples_per_second": 356.729, | |
| "eval_steps_per_second": 11.201, | |
| "step": 4458 | |
| }, | |
| { | |
| "entropy": 0.7296845495700837, | |
| "epoch": 6.002691790040377, | |
| "grad_norm": 0.4457104206085205, | |
| "learning_rate": 3.7708693876912435e-05, | |
| "loss": 0.01225304752588272, | |
| "mean_token_accuracy": 0.9953745543956757, | |
| "num_tokens": 92266330.0, | |
| "step": 4460 | |
| }, | |
| { | |
| "entropy": 0.7346499502658844, | |
| "epoch": 6.016150740242261, | |
| "grad_norm": 0.36918142437934875, | |
| "learning_rate": 3.74930902539244e-05, | |
| "loss": 0.00721738263964653, | |
| "mean_token_accuracy": 0.9974470973014832, | |
| "num_tokens": 92473315.0, | |
| "step": 4470 | |
| }, | |
| { | |
| "entropy": 0.7537191212177277, | |
| "epoch": 6.029609690444145, | |
| "grad_norm": 0.3166503310203552, | |
| "learning_rate": 3.727773442205493e-05, | |
| "loss": 0.006283954530954361, | |
| "mean_token_accuracy": 0.9978337228298187, | |
| "num_tokens": 92680500.0, | |
| "step": 4480 | |
| }, | |
| { | |
| "entropy": 0.7762713313102723, | |
| "epoch": 6.043068640646029, | |
| "grad_norm": 0.35029998421669006, | |
| "learning_rate": 3.7062630648006485e-05, | |
| "loss": 0.007443505525588989, | |
| "mean_token_accuracy": 0.9972987174987793, | |
| "num_tokens": 92887510.0, | |
| "step": 4490 | |
| }, | |
| { | |
| "entropy": 0.7617170631885528, | |
| "epoch": 6.056527590847914, | |
| "grad_norm": 0.34308943152427673, | |
| "learning_rate": 3.684778319348765e-05, | |
| "loss": 0.006808276474475861, | |
| "mean_token_accuracy": 0.9976418673992157, | |
| "num_tokens": 93094920.0, | |
| "step": 4500 | |
| }, | |
| { | |
| "entropy": 0.7614555537700654, | |
| "epoch": 6.069986541049798, | |
| "grad_norm": 0.5395469069480896, | |
| "learning_rate": 3.663319631512874e-05, | |
| "loss": 0.007348373532295227, | |
| "mean_token_accuracy": 0.9975483357906342, | |
| "num_tokens": 93301300.0, | |
| "step": 4510 | |
| }, | |
| { | |
| "entropy": 0.7552687644958496, | |
| "epoch": 6.083445491251682, | |
| "grad_norm": 0.3406250476837158, | |
| "learning_rate": 3.641887426439743e-05, | |
| "loss": 0.006675070524215699, | |
| "mean_token_accuracy": 0.9976675331592559, | |
| "num_tokens": 93508326.0, | |
| "step": 4520 | |
| }, | |
| { | |
| "entropy": 0.7513856589794159, | |
| "epoch": 6.0969044414535665, | |
| "grad_norm": 0.5376906394958496, | |
| "learning_rate": 3.620482128751456e-05, | |
| "loss": 0.00666118860244751, | |
| "mean_token_accuracy": 0.9976118326187133, | |
| "num_tokens": 93715792.0, | |
| "step": 4530 | |
| }, | |
| { | |
| "entropy": 0.7578739166259766, | |
| "epoch": 6.110363391655451, | |
| "grad_norm": 0.3736390471458435, | |
| "learning_rate": 3.599104162536997e-05, | |
| "loss": 0.006261451542377472, | |
| "mean_token_accuracy": 0.9977061867713928, | |
| "num_tokens": 93923078.0, | |
| "step": 4540 | |
| }, | |
| { | |
| "entropy": 0.7500752210617065, | |
| "epoch": 6.123822341857335, | |
| "grad_norm": 0.5576215386390686, | |
| "learning_rate": 3.577753951343851e-05, | |
| "loss": 0.006978290528059006, | |
| "mean_token_accuracy": 0.9975865662097931, | |
| "num_tokens": 94129100.0, | |
| "step": 4550 | |
| }, | |
| { | |
| "entropy": 0.7302877962589264, | |
| "epoch": 6.137281292059219, | |
| "grad_norm": 0.40667852759361267, | |
| "learning_rate": 3.55643191816961e-05, | |
| "loss": 0.007030657678842545, | |
| "mean_token_accuracy": 0.9972686529159546, | |
| "num_tokens": 94335652.0, | |
| "step": 4560 | |
| }, | |
| { | |
| "entropy": 0.7341212391853332, | |
| "epoch": 6.1507402422611035, | |
| "grad_norm": 0.3302972614765167, | |
| "learning_rate": 3.535138485453595e-05, | |
| "loss": 0.006430496275424957, | |
| "mean_token_accuracy": 0.9978137254714966, | |
| "num_tokens": 94542535.0, | |
| "step": 4570 | |
| }, | |
| { | |
| "entropy": 0.7521607518196106, | |
| "epoch": 6.164199192462988, | |
| "grad_norm": 0.3833800256252289, | |
| "learning_rate": 3.513874075068484e-05, | |
| "loss": 0.006178916990756988, | |
| "mean_token_accuracy": 0.9977231621742249, | |
| "num_tokens": 94748991.0, | |
| "step": 4580 | |
| }, | |
| { | |
| "entropy": 0.7546293139457703, | |
| "epoch": 6.177658142664872, | |
| "grad_norm": 0.39571505784988403, | |
| "learning_rate": 3.492639108311955e-05, | |
| "loss": 0.007638230919837952, | |
| "mean_token_accuracy": 0.9973102450370789, | |
| "num_tokens": 94955693.0, | |
| "step": 4590 | |
| }, | |
| { | |
| "entropy": 0.7400491952896118, | |
| "epoch": 6.191117092866756, | |
| "grad_norm": 0.4599838852882385, | |
| "learning_rate": 3.471434005898339e-05, | |
| "loss": 0.007158774137496948, | |
| "mean_token_accuracy": 0.9974660098552703, | |
| "num_tokens": 95162378.0, | |
| "step": 4600 | |
| }, | |
| { | |
| "entropy": 0.7313100039958954, | |
| "epoch": 6.2045760430686405, | |
| "grad_norm": 0.27486035227775574, | |
| "learning_rate": 3.450259187950283e-05, | |
| "loss": 0.006652024388313293, | |
| "mean_token_accuracy": 0.9974403619766236, | |
| "num_tokens": 95368816.0, | |
| "step": 4610 | |
| }, | |
| { | |
| "entropy": 0.723324716091156, | |
| "epoch": 6.218034993270525, | |
| "grad_norm": 0.3503046929836273, | |
| "learning_rate": 3.429115073990431e-05, | |
| "loss": 0.006369487941265106, | |
| "mean_token_accuracy": 0.9978444695472717, | |
| "num_tokens": 95576191.0, | |
| "step": 4620 | |
| }, | |
| { | |
| "entropy": 0.7397123396396637, | |
| "epoch": 6.231493943472409, | |
| "grad_norm": 0.3686009347438812, | |
| "learning_rate": 3.408002082933107e-05, | |
| "loss": 0.006405235826969146, | |
| "mean_token_accuracy": 0.9976122856140137, | |
| "num_tokens": 95782987.0, | |
| "step": 4630 | |
| }, | |
| { | |
| "entropy": 0.7597997963428498, | |
| "epoch": 6.244952893674293, | |
| "grad_norm": 0.35962435603141785, | |
| "learning_rate": 3.3869206330760187e-05, | |
| "loss": 0.005804166570305825, | |
| "mean_token_accuracy": 0.9979152083396912, | |
| "num_tokens": 95989600.0, | |
| "step": 4640 | |
| }, | |
| { | |
| "entropy": 0.7672134041786194, | |
| "epoch": 6.2584118438761775, | |
| "grad_norm": 0.4252372980117798, | |
| "learning_rate": 3.365871142091968e-05, | |
| "loss": 0.006617816537618637, | |
| "mean_token_accuracy": 0.9977438449859619, | |
| "num_tokens": 96196971.0, | |
| "step": 4650 | |
| }, | |
| { | |
| "entropy": 0.745790833234787, | |
| "epoch": 6.271870794078062, | |
| "grad_norm": 0.4085806608200073, | |
| "learning_rate": 3.3448540270205766e-05, | |
| "loss": 0.006394334137439728, | |
| "mean_token_accuracy": 0.9979225277900696, | |
| "num_tokens": 96403441.0, | |
| "step": 4660 | |
| }, | |
| { | |
| "entropy": 0.7209958374500275, | |
| "epoch": 6.285329744279946, | |
| "grad_norm": 0.327882319688797, | |
| "learning_rate": 3.323869704260025e-05, | |
| "loss": 0.005710349604487419, | |
| "mean_token_accuracy": 0.9980106890201569, | |
| "num_tokens": 96610397.0, | |
| "step": 4670 | |
| }, | |
| { | |
| "entropy": 0.7231827795505523, | |
| "epoch": 6.29878869448183, | |
| "grad_norm": 0.4412100315093994, | |
| "learning_rate": 3.302918589558801e-05, | |
| "loss": 0.006291732937097549, | |
| "mean_token_accuracy": 0.9975874960422516, | |
| "num_tokens": 96817025.0, | |
| "step": 4680 | |
| }, | |
| { | |
| "entropy": 0.7325192034244538, | |
| "epoch": 6.312247644683715, | |
| "grad_norm": 0.40209078788757324, | |
| "learning_rate": 3.282001098007462e-05, | |
| "loss": 0.00627792626619339, | |
| "mean_token_accuracy": 0.9977674365043641, | |
| "num_tokens": 97023802.0, | |
| "step": 4690 | |
| }, | |
| { | |
| "entropy": 0.7360162317752839, | |
| "epoch": 6.325706594885599, | |
| "grad_norm": 0.38745999336242676, | |
| "learning_rate": 3.261117644030412e-05, | |
| "loss": 0.00608489103615284, | |
| "mean_token_accuracy": 0.997675096988678, | |
| "num_tokens": 97230943.0, | |
| "step": 4700 | |
| }, | |
| { | |
| "entropy": 0.7425191223621368, | |
| "epoch": 6.339165545087483, | |
| "grad_norm": 0.39276620745658875, | |
| "learning_rate": 3.240268641377694e-05, | |
| "loss": 0.0066022701561450955, | |
| "mean_token_accuracy": 0.9976878345012665, | |
| "num_tokens": 97437362.0, | |
| "step": 4710 | |
| }, | |
| { | |
| "entropy": 0.7288519084453583, | |
| "epoch": 6.352624495289367, | |
| "grad_norm": 0.3171084225177765, | |
| "learning_rate": 3.2194545031167866e-05, | |
| "loss": 0.00590059943497181, | |
| "mean_token_accuracy": 0.9977839410305023, | |
| "num_tokens": 97644977.0, | |
| "step": 4720 | |
| }, | |
| { | |
| "entropy": 0.7246840715408325, | |
| "epoch": 6.366083445491252, | |
| "grad_norm": 0.5965446829795837, | |
| "learning_rate": 3.1986756416244245e-05, | |
| "loss": 0.0069613344967365265, | |
| "mean_token_accuracy": 0.9974348545074463, | |
| "num_tokens": 97851595.0, | |
| "step": 4730 | |
| }, | |
| { | |
| "entropy": 0.731091046333313, | |
| "epoch": 6.379542395693136, | |
| "grad_norm": 0.4378451108932495, | |
| "learning_rate": 3.177932468578426e-05, | |
| "loss": 0.0070390477776527405, | |
| "mean_token_accuracy": 0.997273427248001, | |
| "num_tokens": 98058641.0, | |
| "step": 4740 | |
| }, | |
| { | |
| "entropy": 0.7363841950893402, | |
| "epoch": 6.39300134589502, | |
| "grad_norm": 0.42163100838661194, | |
| "learning_rate": 3.157225394949542e-05, | |
| "loss": 0.00652310848236084, | |
| "mean_token_accuracy": 0.99771688580513, | |
| "num_tokens": 98265432.0, | |
| "step": 4750 | |
| }, | |
| { | |
| "entropy": 0.748940235376358, | |
| "epoch": 6.406460296096904, | |
| "grad_norm": 0.48964178562164307, | |
| "learning_rate": 3.136554830993304e-05, | |
| "loss": 0.007442094385623932, | |
| "mean_token_accuracy": 0.996977812051773, | |
| "num_tokens": 98472309.0, | |
| "step": 4760 | |
| }, | |
| { | |
| "entropy": 0.7387059688568115, | |
| "epoch": 6.419919246298789, | |
| "grad_norm": 0.4443625211715698, | |
| "learning_rate": 3.115921186241906e-05, | |
| "loss": 0.0067341111600399016, | |
| "mean_token_accuracy": 0.9978115797042847, | |
| "num_tokens": 98679369.0, | |
| "step": 4770 | |
| }, | |
| { | |
| "entropy": 0.7278500914573669, | |
| "epoch": 6.433378196500673, | |
| "grad_norm": 0.31731724739074707, | |
| "learning_rate": 3.0953248694960824e-05, | |
| "loss": 0.006909257918596268, | |
| "mean_token_accuracy": 0.9976158678531647, | |
| "num_tokens": 98886649.0, | |
| "step": 4780 | |
| }, | |
| { | |
| "entropy": 0.7249270141124725, | |
| "epoch": 6.446837146702557, | |
| "grad_norm": 0.5315210223197937, | |
| "learning_rate": 3.0747662888170146e-05, | |
| "loss": 0.006646881997585297, | |
| "mean_token_accuracy": 0.9975297033786774, | |
| "num_tokens": 99093341.0, | |
| "step": 4790 | |
| }, | |
| { | |
| "entropy": 0.7275424122810363, | |
| "epoch": 6.460296096904441, | |
| "grad_norm": 0.36423051357269287, | |
| "learning_rate": 3.054245851518246e-05, | |
| "loss": 0.006122813746333122, | |
| "mean_token_accuracy": 0.9977832078933716, | |
| "num_tokens": 99300096.0, | |
| "step": 4800 | |
| }, | |
| { | |
| "entropy": 0.7336158037185669, | |
| "epoch": 6.473755047106326, | |
| "grad_norm": 0.5945335626602173, | |
| "learning_rate": 3.0337639641576065e-05, | |
| "loss": 0.006734760850667954, | |
| "mean_token_accuracy": 0.9974972426891326, | |
| "num_tokens": 99506798.0, | |
| "step": 4810 | |
| }, | |
| { | |
| "entropy": 0.7330217719078064, | |
| "epoch": 6.48721399730821, | |
| "grad_norm": 0.4753057360649109, | |
| "learning_rate": 3.0133210325291662e-05, | |
| "loss": 0.0071483604609966275, | |
| "mean_token_accuracy": 0.9972701132297516, | |
| "num_tokens": 99713316.0, | |
| "step": 4820 | |
| }, | |
| { | |
| "entropy": 0.7293879866600037, | |
| "epoch": 6.500672947510094, | |
| "grad_norm": 0.44765713810920715, | |
| "learning_rate": 2.9929174616551857e-05, | |
| "loss": 0.0069991335272789005, | |
| "mean_token_accuracy": 0.9972541630268097, | |
| "num_tokens": 99920106.0, | |
| "step": 4830 | |
| }, | |
| { | |
| "entropy": 0.7240224123001099, | |
| "epoch": 6.514131897711978, | |
| "grad_norm": 0.40643468499183655, | |
| "learning_rate": 2.9725536557781008e-05, | |
| "loss": 0.006019005179405212, | |
| "mean_token_accuracy": 0.9977357804775238, | |
| "num_tokens": 100127187.0, | |
| "step": 4840 | |
| }, | |
| { | |
| "entropy": 0.7268623948097229, | |
| "epoch": 6.527590847913863, | |
| "grad_norm": 0.4088582396507263, | |
| "learning_rate": 2.9522300183525097e-05, | |
| "loss": 0.006773443520069122, | |
| "mean_token_accuracy": 0.9972230792045593, | |
| "num_tokens": 100334160.0, | |
| "step": 4850 | |
| }, | |
| { | |
| "entropy": 0.7315291166305542, | |
| "epoch": 6.541049798115747, | |
| "grad_norm": 0.3768236041069031, | |
| "learning_rate": 2.931946952037179e-05, | |
| "loss": 0.006892500817775727, | |
| "mean_token_accuracy": 0.9973698258399963, | |
| "num_tokens": 100541088.0, | |
| "step": 4860 | |
| }, | |
| { | |
| "entropy": 0.7324226260185241, | |
| "epoch": 6.554508748317631, | |
| "grad_norm": 0.5730559825897217, | |
| "learning_rate": 2.9117048586870654e-05, | |
| "loss": 0.007101823389530182, | |
| "mean_token_accuracy": 0.9975831270217895, | |
| "num_tokens": 100748086.0, | |
| "step": 4870 | |
| }, | |
| { | |
| "entropy": 0.7297871172428131, | |
| "epoch": 6.5679676985195155, | |
| "grad_norm": 0.42341160774230957, | |
| "learning_rate": 2.891504139345358e-05, | |
| "loss": 0.0055365487933158875, | |
| "mean_token_accuracy": 0.9979402482509613, | |
| "num_tokens": 100954751.0, | |
| "step": 4880 | |
| }, | |
| { | |
| "entropy": 0.7403721213340759, | |
| "epoch": 6.5814266487214, | |
| "grad_norm": 0.6541618704795837, | |
| "learning_rate": 2.8713451942355285e-05, | |
| "loss": 0.0077784605324268345, | |
| "mean_token_accuracy": 0.9971624433994293, | |
| "num_tokens": 101161323.0, | |
| "step": 4890 | |
| }, | |
| { | |
| "entropy": 0.7294679641723633, | |
| "epoch": 6.594885598923284, | |
| "grad_norm": 0.5061529278755188, | |
| "learning_rate": 2.8512284227534027e-05, | |
| "loss": 0.0068440020084381105, | |
| "mean_token_accuracy": 0.9972440838813782, | |
| "num_tokens": 101369013.0, | |
| "step": 4900 | |
| }, | |
| { | |
| "entropy": 0.7254895687103271, | |
| "epoch": 6.608344549125168, | |
| "grad_norm": 0.6346190571784973, | |
| "learning_rate": 2.8311542234592497e-05, | |
| "loss": 0.006360020488500595, | |
| "mean_token_accuracy": 0.9975525736808777, | |
| "num_tokens": 101575775.0, | |
| "step": 4910 | |
| }, | |
| { | |
| "entropy": 0.7256027460098267, | |
| "epoch": 6.6218034993270525, | |
| "grad_norm": 0.5224611163139343, | |
| "learning_rate": 2.8111229940698842e-05, | |
| "loss": 0.0073788858950138096, | |
| "mean_token_accuracy": 0.9969935595989228, | |
| "num_tokens": 101782675.0, | |
| "step": 4920 | |
| }, | |
| { | |
| "entropy": 0.7316436052322388, | |
| "epoch": 6.635262449528937, | |
| "grad_norm": 0.49549564719200134, | |
| "learning_rate": 2.791135131450785e-05, | |
| "loss": 0.007514142990112304, | |
| "mean_token_accuracy": 0.9972495913505555, | |
| "num_tokens": 101989297.0, | |
| "step": 4930 | |
| }, | |
| { | |
| "entropy": 0.7356618404388428, | |
| "epoch": 6.648721399730821, | |
| "grad_norm": 0.40386277437210083, | |
| "learning_rate": 2.7711910316082357e-05, | |
| "loss": 0.007244438678026199, | |
| "mean_token_accuracy": 0.9973312318325043, | |
| "num_tokens": 102195867.0, | |
| "step": 4940 | |
| }, | |
| { | |
| "entropy": 0.7294074118137359, | |
| "epoch": 6.662180349932705, | |
| "grad_norm": 0.26524385809898376, | |
| "learning_rate": 2.7512910896814747e-05, | |
| "loss": 0.006912172585725784, | |
| "mean_token_accuracy": 0.9975458741188049, | |
| "num_tokens": 102402820.0, | |
| "step": 4950 | |
| }, | |
| { | |
| "entropy": 0.7264546751976013, | |
| "epoch": 6.6756393001345895, | |
| "grad_norm": 0.3604874908924103, | |
| "learning_rate": 2.7314356999348713e-05, | |
| "loss": 0.006820497661828994, | |
| "mean_token_accuracy": 0.9975083887577056, | |
| "num_tokens": 102609492.0, | |
| "step": 4960 | |
| }, | |
| { | |
| "entropy": 0.7235826432704926, | |
| "epoch": 6.689098250336474, | |
| "grad_norm": 0.4252055883407593, | |
| "learning_rate": 2.711625255750111e-05, | |
| "loss": 0.006822900474071502, | |
| "mean_token_accuracy": 0.9974255442619324, | |
| "num_tokens": 102816432.0, | |
| "step": 4970 | |
| }, | |
| { | |
| "entropy": 0.7244568645954133, | |
| "epoch": 6.702557200538358, | |
| "grad_norm": 0.4580247104167938, | |
| "learning_rate": 2.691860149618402e-05, | |
| "loss": 0.00701884925365448, | |
| "mean_token_accuracy": 0.9972208499908447, | |
| "num_tokens": 103023278.0, | |
| "step": 4980 | |
| }, | |
| { | |
| "entropy": 0.727864944934845, | |
| "epoch": 6.716016150740242, | |
| "grad_norm": 0.35556018352508545, | |
| "learning_rate": 2.6721407731327004e-05, | |
| "loss": 0.006804829835891724, | |
| "mean_token_accuracy": 0.9975570499897003, | |
| "num_tokens": 103230198.0, | |
| "step": 4990 | |
| }, | |
| { | |
| "entropy": 0.7289696097373962, | |
| "epoch": 6.7294751009421265, | |
| "grad_norm": 0.357962042093277, | |
| "learning_rate": 2.6524675169799506e-05, | |
| "loss": 0.006180135905742646, | |
| "mean_token_accuracy": 0.9977405965328217, | |
| "num_tokens": 103437417.0, | |
| "step": 5000 | |
| }, | |
| { | |
| "entropy": 0.7292522251605987, | |
| "epoch": 6.742934051144011, | |
| "grad_norm": 0.3891056180000305, | |
| "learning_rate": 2.6328407709333463e-05, | |
| "loss": 0.005779655277729034, | |
| "mean_token_accuracy": 0.9977752268314362, | |
| "num_tokens": 103644773.0, | |
| "step": 5010 | |
| }, | |
| { | |
| "entropy": 0.7364232182502747, | |
| "epoch": 6.756393001345895, | |
| "grad_norm": 0.4316810369491577, | |
| "learning_rate": 2.6132609238446072e-05, | |
| "loss": 0.006378757953643799, | |
| "mean_token_accuracy": 0.9975412786006927, | |
| "num_tokens": 103851437.0, | |
| "step": 5020 | |
| }, | |
| { | |
| "entropy": 0.7294283807277679, | |
| "epoch": 6.769851951547779, | |
| "grad_norm": 0.28501173853874207, | |
| "learning_rate": 2.5937283636362724e-05, | |
| "loss": 0.006514771282672882, | |
| "mean_token_accuracy": 0.9976726651191712, | |
| "num_tokens": 104058632.0, | |
| "step": 5030 | |
| }, | |
| { | |
| "entropy": 0.7193506896495819, | |
| "epoch": 6.783310901749664, | |
| "grad_norm": 0.4643396735191345, | |
| "learning_rate": 2.5742434772940216e-05, | |
| "loss": 0.006748485565185547, | |
| "mean_token_accuracy": 0.9975197494029999, | |
| "num_tokens": 104265547.0, | |
| "step": 5040 | |
| }, | |
| { | |
| "entropy": 0.7154334783554077, | |
| "epoch": 6.796769851951548, | |
| "grad_norm": 0.6031412482261658, | |
| "learning_rate": 2.5548066508590007e-05, | |
| "loss": 0.0062897935509681705, | |
| "mean_token_accuracy": 0.9975806593894958, | |
| "num_tokens": 104472797.0, | |
| "step": 5050 | |
| }, | |
| { | |
| "entropy": 0.7141842901706695, | |
| "epoch": 6.810228802153432, | |
| "grad_norm": 0.3686530292034149, | |
| "learning_rate": 2.535418269420178e-05, | |
| "loss": 0.006743116676807404, | |
| "mean_token_accuracy": 0.9975346326828003, | |
| "num_tokens": 104679303.0, | |
| "step": 5060 | |
| }, | |
| { | |
| "entropy": 0.7162917137145997, | |
| "epoch": 6.823687752355316, | |
| "grad_norm": 0.3937174081802368, | |
| "learning_rate": 2.5160787171067126e-05, | |
| "loss": 0.006931714713573456, | |
| "mean_token_accuracy": 0.9975650846958161, | |
| "num_tokens": 104886129.0, | |
| "step": 5070 | |
| }, | |
| { | |
| "entropy": 0.7184829175472259, | |
| "epoch": 6.837146702557201, | |
| "grad_norm": 0.3974623382091522, | |
| "learning_rate": 2.4967883770803413e-05, | |
| "loss": 0.006391709297895431, | |
| "mean_token_accuracy": 0.9977280080318451, | |
| "num_tokens": 105092511.0, | |
| "step": 5080 | |
| }, | |
| { | |
| "entropy": 0.7110052049160004, | |
| "epoch": 6.850605652759085, | |
| "grad_norm": 0.3725025951862335, | |
| "learning_rate": 2.477547631527799e-05, | |
| "loss": 0.006394396722316742, | |
| "mean_token_accuracy": 0.9976818323135376, | |
| "num_tokens": 105299187.0, | |
| "step": 5090 | |
| }, | |
| { | |
| "entropy": 0.7120427250862121, | |
| "epoch": 6.864064602960969, | |
| "grad_norm": 0.43178483843803406, | |
| "learning_rate": 2.45835686165323e-05, | |
| "loss": 0.006332089006900787, | |
| "mean_token_accuracy": 0.9976500451564789, | |
| "num_tokens": 105505571.0, | |
| "step": 5100 | |
| }, | |
| { | |
| "entropy": 0.7212999403476715, | |
| "epoch": 6.877523553162853, | |
| "grad_norm": 0.4976682960987091, | |
| "learning_rate": 2.4392164476706468e-05, | |
| "loss": 0.005901779979467392, | |
| "mean_token_accuracy": 0.9980143666267395, | |
| "num_tokens": 105712714.0, | |
| "step": 5110 | |
| }, | |
| { | |
| "entropy": 0.7251917839050293, | |
| "epoch": 6.890982503364738, | |
| "grad_norm": 0.37038931250572205, | |
| "learning_rate": 2.4201267687963935e-05, | |
| "loss": 0.006622254848480225, | |
| "mean_token_accuracy": 0.9975569725036622, | |
| "num_tokens": 105919685.0, | |
| "step": 5120 | |
| }, | |
| { | |
| "entropy": 0.7244008183479309, | |
| "epoch": 6.904441453566622, | |
| "grad_norm": 0.4485451877117157, | |
| "learning_rate": 2.4010882032416332e-05, | |
| "loss": 0.00556907095015049, | |
| "mean_token_accuracy": 0.9980982482433319, | |
| "num_tokens": 106126360.0, | |
| "step": 5130 | |
| }, | |
| { | |
| "entropy": 0.7264035522937775, | |
| "epoch": 6.917900403768506, | |
| "grad_norm": 0.3821909427642822, | |
| "learning_rate": 2.3821011282048545e-05, | |
| "loss": 0.005761538445949554, | |
| "mean_token_accuracy": 0.9980070352554321, | |
| "num_tokens": 106332315.0, | |
| "step": 5140 | |
| }, | |
| { | |
| "entropy": 0.7214965403079987, | |
| "epoch": 6.93135935397039, | |
| "grad_norm": 0.5453296899795532, | |
| "learning_rate": 2.3631659198643985e-05, | |
| "loss": 0.006120505183935166, | |
| "mean_token_accuracy": 0.9977015674114227, | |
| "num_tokens": 106539439.0, | |
| "step": 5150 | |
| }, | |
| { | |
| "entropy": 0.7204740345478058, | |
| "epoch": 6.944818304172275, | |
| "grad_norm": 0.5277069807052612, | |
| "learning_rate": 2.344282953371006e-05, | |
| "loss": 0.0063091211020946504, | |
| "mean_token_accuracy": 0.99763303399086, | |
| "num_tokens": 106746217.0, | |
| "step": 5160 | |
| }, | |
| { | |
| "entropy": 0.7176619052886963, | |
| "epoch": 6.958277254374159, | |
| "grad_norm": 0.4055790901184082, | |
| "learning_rate": 2.325452602840385e-05, | |
| "loss": 0.005276233702898025, | |
| "mean_token_accuracy": 0.9980817437171936, | |
| "num_tokens": 106953032.0, | |
| "step": 5170 | |
| }, | |
| { | |
| "entropy": 0.7127950310707092, | |
| "epoch": 6.971736204576043, | |
| "grad_norm": 0.336780309677124, | |
| "learning_rate": 2.306675241345797e-05, | |
| "loss": 0.005725700408220291, | |
| "mean_token_accuracy": 0.9980043768882751, | |
| "num_tokens": 107160130.0, | |
| "step": 5180 | |
| }, | |
| { | |
| "entropy": 0.715798842906952, | |
| "epoch": 6.985195154777927, | |
| "grad_norm": 0.38042059540748596, | |
| "learning_rate": 2.287951240910668e-05, | |
| "loss": 0.0058772068470716475, | |
| "mean_token_accuracy": 0.9980284452438355, | |
| "num_tokens": 107367185.0, | |
| "step": 5190 | |
| }, | |
| { | |
| "entropy": 0.7066363096237183, | |
| "epoch": 6.998654104979812, | |
| "grad_norm": 0.44882187247276306, | |
| "learning_rate": 2.269280972501217e-05, | |
| "loss": 0.005587458610534668, | |
| "mean_token_accuracy": 0.9979583859443665, | |
| "num_tokens": 107574860.0, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_entropy": 0.7108410179235374, | |
| "eval_loss": 0.05958922207355499, | |
| "eval_mean_token_accuracy": 0.9847923464076535, | |
| "eval_num_tokens": 107595742.0, | |
| "eval_runtime": 13.9793, | |
| "eval_samples_per_second": 357.671, | |
| "eval_steps_per_second": 11.231, | |
| "step": 5201 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 7430, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "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": 5.280718172519924e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |