| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 100, | |
| "global_step": 2682, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "entropy": 1.93066748380661, | |
| "epoch": 0.0037309952429810654, | |
| "grad_norm": 14.3125, | |
| "learning_rate": 9.876543209876544e-07, | |
| "loss": 2.437, | |
| "mean_token_accuracy": 0.4887664679437876, | |
| "num_tokens": 529463.0, | |
| "step": 5 | |
| }, | |
| { | |
| "entropy": 1.9279134914278984, | |
| "epoch": 0.007461990485962131, | |
| "grad_norm": 15.9375, | |
| "learning_rate": 2.222222222222222e-06, | |
| "loss": 2.421, | |
| "mean_token_accuracy": 0.4953322228044271, | |
| "num_tokens": 1062929.0, | |
| "step": 10 | |
| }, | |
| { | |
| "entropy": 1.9278883010149002, | |
| "epoch": 0.011192985728943195, | |
| "grad_norm": 15.4375, | |
| "learning_rate": 3.4567901234567904e-06, | |
| "loss": 2.4307, | |
| "mean_token_accuracy": 0.49091244526207445, | |
| "num_tokens": 1593737.0, | |
| "step": 15 | |
| }, | |
| { | |
| "entropy": 1.9264666512608528, | |
| "epoch": 0.014923980971924261, | |
| "grad_norm": 14.3125, | |
| "learning_rate": 4.691358024691358e-06, | |
| "loss": 2.3686, | |
| "mean_token_accuracy": 0.5026748184114694, | |
| "num_tokens": 2125554.0, | |
| "step": 20 | |
| }, | |
| { | |
| "entropy": 1.915960419178009, | |
| "epoch": 0.018654976214905326, | |
| "grad_norm": 9.5625, | |
| "learning_rate": 5.925925925925926e-06, | |
| "loss": 2.347, | |
| "mean_token_accuracy": 0.49995064437389375, | |
| "num_tokens": 2657455.0, | |
| "step": 25 | |
| }, | |
| { | |
| "entropy": 1.9118589267134667, | |
| "epoch": 0.02238597145788639, | |
| "grad_norm": 10.0625, | |
| "learning_rate": 7.160493827160494e-06, | |
| "loss": 2.2538, | |
| "mean_token_accuracy": 0.5263953868299722, | |
| "num_tokens": 3187189.0, | |
| "step": 30 | |
| }, | |
| { | |
| "entropy": 1.899963890016079, | |
| "epoch": 0.026116966700867456, | |
| "grad_norm": 9.3125, | |
| "learning_rate": 8.395061728395062e-06, | |
| "loss": 2.1564, | |
| "mean_token_accuracy": 0.5407103352248669, | |
| "num_tokens": 3718429.0, | |
| "step": 35 | |
| }, | |
| { | |
| "entropy": 1.911753496527672, | |
| "epoch": 0.029847961943848523, | |
| "grad_norm": 7.9375, | |
| "learning_rate": 9.62962962962963e-06, | |
| "loss": 2.095, | |
| "mean_token_accuracy": 0.5577171023935079, | |
| "num_tokens": 4251155.0, | |
| "step": 40 | |
| }, | |
| { | |
| "entropy": 1.9223718717694283, | |
| "epoch": 0.033578957186829586, | |
| "grad_norm": 6.96875, | |
| "learning_rate": 1.0864197530864198e-05, | |
| "loss": 2.0702, | |
| "mean_token_accuracy": 0.5552546553313732, | |
| "num_tokens": 4781447.0, | |
| "step": 45 | |
| }, | |
| { | |
| "entropy": 1.9131259977817536, | |
| "epoch": 0.03730995242981065, | |
| "grad_norm": 6.1875, | |
| "learning_rate": 1.2098765432098767e-05, | |
| "loss": 1.934, | |
| "mean_token_accuracy": 0.5727813556790352, | |
| "num_tokens": 5314277.0, | |
| "step": 50 | |
| }, | |
| { | |
| "entropy": 1.9110908284783363, | |
| "epoch": 0.04104094767279172, | |
| "grad_norm": 5.40625, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 1.8792, | |
| "mean_token_accuracy": 0.594604616984725, | |
| "num_tokens": 5845509.0, | |
| "step": 55 | |
| }, | |
| { | |
| "entropy": 1.9029613688588143, | |
| "epoch": 0.04477194291577278, | |
| "grad_norm": 5.21875, | |
| "learning_rate": 1.4567901234567903e-05, | |
| "loss": 1.7805, | |
| "mean_token_accuracy": 0.630406080186367, | |
| "num_tokens": 6376657.0, | |
| "step": 60 | |
| }, | |
| { | |
| "entropy": 1.8792628690600395, | |
| "epoch": 0.048502938158753846, | |
| "grad_norm": 3.84375, | |
| "learning_rate": 1.580246913580247e-05, | |
| "loss": 1.6705, | |
| "mean_token_accuracy": 0.6583383537828922, | |
| "num_tokens": 6909470.0, | |
| "step": 65 | |
| }, | |
| { | |
| "entropy": 1.8848115488886834, | |
| "epoch": 0.05223393340173491, | |
| "grad_norm": 4.6875, | |
| "learning_rate": 1.7037037037037038e-05, | |
| "loss": 1.5614, | |
| "mean_token_accuracy": 0.6829224102199077, | |
| "num_tokens": 7440943.0, | |
| "step": 70 | |
| }, | |
| { | |
| "entropy": 1.9064736932516098, | |
| "epoch": 0.05596492864471598, | |
| "grad_norm": 3.8125, | |
| "learning_rate": 1.8271604938271607e-05, | |
| "loss": 1.4162, | |
| "mean_token_accuracy": 0.7170818209648132, | |
| "num_tokens": 7973046.0, | |
| "step": 75 | |
| }, | |
| { | |
| "entropy": 1.9023971110582352, | |
| "epoch": 0.059695923887697046, | |
| "grad_norm": 3.203125, | |
| "learning_rate": 1.9506172839506175e-05, | |
| "loss": 1.4074, | |
| "mean_token_accuracy": 0.7140415258705616, | |
| "num_tokens": 8504722.0, | |
| "step": 80 | |
| }, | |
| { | |
| "entropy": 1.889440931379795, | |
| "epoch": 0.0634269191306781, | |
| "grad_norm": 3.109375, | |
| "learning_rate": 1.999994091549669e-05, | |
| "loss": 1.4883, | |
| "mean_token_accuracy": 0.7016305826604367, | |
| "num_tokens": 9033389.0, | |
| "step": 85 | |
| }, | |
| { | |
| "entropy": 1.871435184776783, | |
| "epoch": 0.06715791437365917, | |
| "grad_norm": 3.5625, | |
| "learning_rate": 1.999957984634139e-05, | |
| "loss": 1.3443, | |
| "mean_token_accuracy": 0.7220834337174893, | |
| "num_tokens": 9564491.0, | |
| "step": 90 | |
| }, | |
| { | |
| "entropy": 1.8715314790606499, | |
| "epoch": 0.07088890961664024, | |
| "grad_norm": 2.984375, | |
| "learning_rate": 1.9998890545907742e-05, | |
| "loss": 1.3409, | |
| "mean_token_accuracy": 0.7232061706483364, | |
| "num_tokens": 10094169.0, | |
| "step": 95 | |
| }, | |
| { | |
| "entropy": 1.8687299489974976, | |
| "epoch": 0.0746199048596213, | |
| "grad_norm": 3.125, | |
| "learning_rate": 1.9997873039335807e-05, | |
| "loss": 1.3168, | |
| "mean_token_accuracy": 0.721094774454832, | |
| "num_tokens": 10626035.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0746199048596213, | |
| "eval_entropy": 1.869174944090953, | |
| "eval_loss": 1.0890228748321533, | |
| "eval_mean_token_accuracy": 0.7311080878231383, | |
| "eval_num_tokens": 10626035.0, | |
| "eval_runtime": 416.9338, | |
| "eval_samples_per_second": 2.079, | |
| "eval_steps_per_second": 0.52, | |
| "step": 100 | |
| }, | |
| { | |
| "entropy": 1.8742459282279014, | |
| "epoch": 0.07835090010260237, | |
| "grad_norm": 2.625, | |
| "learning_rate": 1.9996527363735932e-05, | |
| "loss": 1.332, | |
| "mean_token_accuracy": 0.7202699460089207, | |
| "num_tokens": 11157038.0, | |
| "step": 105 | |
| }, | |
| { | |
| "entropy": 1.876672126352787, | |
| "epoch": 0.08208189534558344, | |
| "grad_norm": 3.1875, | |
| "learning_rate": 1.999485356818738e-05, | |
| "loss": 1.2506, | |
| "mean_token_accuracy": 0.7332465507090091, | |
| "num_tokens": 11689056.0, | |
| "step": 110 | |
| }, | |
| { | |
| "entropy": 1.8850012466311454, | |
| "epoch": 0.0858128905885645, | |
| "grad_norm": 2.890625, | |
| "learning_rate": 1.9992851713736567e-05, | |
| "loss": 1.2925, | |
| "mean_token_accuracy": 0.7265870451927186, | |
| "num_tokens": 12219351.0, | |
| "step": 115 | |
| }, | |
| { | |
| "entropy": 1.8786048024892807, | |
| "epoch": 0.08954388583154556, | |
| "grad_norm": 2.65625, | |
| "learning_rate": 1.999052187339482e-05, | |
| "loss": 1.3057, | |
| "mean_token_accuracy": 0.7244717724621296, | |
| "num_tokens": 12753651.0, | |
| "step": 120 | |
| }, | |
| { | |
| "entropy": 1.885955972969532, | |
| "epoch": 0.09327488107452662, | |
| "grad_norm": 3.28125, | |
| "learning_rate": 1.9987864132135707e-05, | |
| "loss": 1.2657, | |
| "mean_token_accuracy": 0.7337329223752022, | |
| "num_tokens": 13285085.0, | |
| "step": 125 | |
| }, | |
| { | |
| "entropy": 1.8783888518810272, | |
| "epoch": 0.09700587631750769, | |
| "grad_norm": 3.390625, | |
| "learning_rate": 1.998487858689196e-05, | |
| "loss": 1.2291, | |
| "mean_token_accuracy": 0.7372383318841458, | |
| "num_tokens": 13814797.0, | |
| "step": 130 | |
| }, | |
| { | |
| "entropy": 1.8861249819397927, | |
| "epoch": 0.10073687156048876, | |
| "grad_norm": 2.4375, | |
| "learning_rate": 1.998156534655192e-05, | |
| "loss": 1.2551, | |
| "mean_token_accuracy": 0.735904411226511, | |
| "num_tokens": 14345582.0, | |
| "step": 135 | |
| }, | |
| { | |
| "entropy": 1.8703672036528587, | |
| "epoch": 0.10446786680346982, | |
| "grad_norm": 3.109375, | |
| "learning_rate": 1.9977924531955573e-05, | |
| "loss": 1.2374, | |
| "mean_token_accuracy": 0.7376377083361149, | |
| "num_tokens": 14877910.0, | |
| "step": 140 | |
| }, | |
| { | |
| "entropy": 1.882800543308258, | |
| "epoch": 0.10819886204645089, | |
| "grad_norm": 2.71875, | |
| "learning_rate": 1.9973956275890142e-05, | |
| "loss": 1.207, | |
| "mean_token_accuracy": 0.7382527463138103, | |
| "num_tokens": 15408599.0, | |
| "step": 145 | |
| }, | |
| { | |
| "entropy": 1.8789533048868179, | |
| "epoch": 0.11192985728943196, | |
| "grad_norm": 2.609375, | |
| "learning_rate": 1.996966072308525e-05, | |
| "loss": 1.3252, | |
| "mean_token_accuracy": 0.7186619438230991, | |
| "num_tokens": 15940048.0, | |
| "step": 150 | |
| }, | |
| { | |
| "entropy": 1.8727819621562958, | |
| "epoch": 0.11566085253241302, | |
| "grad_norm": 2.78125, | |
| "learning_rate": 1.996503803020763e-05, | |
| "loss": 1.1866, | |
| "mean_token_accuracy": 0.7416010297834873, | |
| "num_tokens": 16472753.0, | |
| "step": 155 | |
| }, | |
| { | |
| "entropy": 1.869297370314598, | |
| "epoch": 0.11939184777539409, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 1.996008836585542e-05, | |
| "loss": 1.1632, | |
| "mean_token_accuracy": 0.7470499858260155, | |
| "num_tokens": 17000919.0, | |
| "step": 160 | |
| }, | |
| { | |
| "entropy": 1.8754076406359672, | |
| "epoch": 0.12312284301837516, | |
| "grad_norm": 2.890625, | |
| "learning_rate": 1.9954811910552006e-05, | |
| "loss": 1.1094, | |
| "mean_token_accuracy": 0.7585403077304363, | |
| "num_tokens": 17530757.0, | |
| "step": 165 | |
| }, | |
| { | |
| "entropy": 1.8743575155735015, | |
| "epoch": 0.1268538382613562, | |
| "grad_norm": 2.921875, | |
| "learning_rate": 1.994920885673945e-05, | |
| "loss": 1.1752, | |
| "mean_token_accuracy": 0.7442750185728073, | |
| "num_tokens": 18063683.0, | |
| "step": 170 | |
| }, | |
| { | |
| "entropy": 1.8884308516979218, | |
| "epoch": 0.13058483350433728, | |
| "grad_norm": 2.96875, | |
| "learning_rate": 1.9943279408771458e-05, | |
| "loss": 1.1346, | |
| "mean_token_accuracy": 0.7534236386418343, | |
| "num_tokens": 18594235.0, | |
| "step": 175 | |
| }, | |
| { | |
| "entropy": 1.885941931605339, | |
| "epoch": 0.13431582874731834, | |
| "grad_norm": 2.765625, | |
| "learning_rate": 1.9937023782905938e-05, | |
| "loss": 1.1172, | |
| "mean_token_accuracy": 0.7521387666463852, | |
| "num_tokens": 19125078.0, | |
| "step": 180 | |
| }, | |
| { | |
| "entropy": 1.8702793419361115, | |
| "epoch": 0.1380468239902994, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 1.9930442207297097e-05, | |
| "loss": 1.1865, | |
| "mean_token_accuracy": 0.7442984923720359, | |
| "num_tokens": 19657833.0, | |
| "step": 185 | |
| }, | |
| { | |
| "entropy": 1.8780140653252602, | |
| "epoch": 0.14177781923328048, | |
| "grad_norm": 3.0625, | |
| "learning_rate": 1.992353492198715e-05, | |
| "loss": 1.098, | |
| "mean_token_accuracy": 0.7611210979521275, | |
| "num_tokens": 20190362.0, | |
| "step": 190 | |
| }, | |
| { | |
| "entropy": 1.8812837466597556, | |
| "epoch": 0.14550881447626154, | |
| "grad_norm": 2.640625, | |
| "learning_rate": 1.9916302178897526e-05, | |
| "loss": 1.152, | |
| "mean_token_accuracy": 0.751427735388279, | |
| "num_tokens": 20718896.0, | |
| "step": 195 | |
| }, | |
| { | |
| "entropy": 1.881430271267891, | |
| "epoch": 0.1492398097192426, | |
| "grad_norm": 2.65625, | |
| "learning_rate": 1.9908744241819712e-05, | |
| "loss": 1.1011, | |
| "mean_token_accuracy": 0.7548866882920265, | |
| "num_tokens": 21252633.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.1492398097192426, | |
| "eval_entropy": 1.8965141059066843, | |
| "eval_loss": 0.9376018047332764, | |
| "eval_mean_token_accuracy": 0.7604197722426208, | |
| "eval_num_tokens": 21252633.0, | |
| "eval_runtime": 416.2999, | |
| "eval_samples_per_second": 2.083, | |
| "eval_steps_per_second": 0.521, | |
| "step": 200 | |
| }, | |
| { | |
| "entropy": 1.901954147219658, | |
| "epoch": 0.15297080496222368, | |
| "grad_norm": 2.59375, | |
| "learning_rate": 1.990086138640561e-05, | |
| "loss": 1.1625, | |
| "mean_token_accuracy": 0.7511769436299801, | |
| "num_tokens": 21780658.0, | |
| "step": 205 | |
| }, | |
| { | |
| "entropy": 1.8937502846121788, | |
| "epoch": 0.15670180020520474, | |
| "grad_norm": 2.3125, | |
| "learning_rate": 1.98926539001575e-05, | |
| "loss": 1.1358, | |
| "mean_token_accuracy": 0.750651653856039, | |
| "num_tokens": 22311279.0, | |
| "step": 210 | |
| }, | |
| { | |
| "entropy": 1.900780713558197, | |
| "epoch": 0.1604327954481858, | |
| "grad_norm": 2.484375, | |
| "learning_rate": 1.988412208241755e-05, | |
| "loss": 1.1354, | |
| "mean_token_accuracy": 0.753037316352129, | |
| "num_tokens": 22842732.0, | |
| "step": 215 | |
| }, | |
| { | |
| "entropy": 1.900828868150711, | |
| "epoch": 0.16416379069116688, | |
| "grad_norm": 2.65625, | |
| "learning_rate": 1.987526624435689e-05, | |
| "loss": 1.1153, | |
| "mean_token_accuracy": 0.7550405651330948, | |
| "num_tokens": 23370062.0, | |
| "step": 220 | |
| }, | |
| { | |
| "entropy": 1.8861738339066505, | |
| "epoch": 0.16789478593414794, | |
| "grad_norm": 2.71875, | |
| "learning_rate": 1.9866086708964264e-05, | |
| "loss": 1.0807, | |
| "mean_token_accuracy": 0.7639111615717411, | |
| "num_tokens": 23899529.0, | |
| "step": 225 | |
| }, | |
| { | |
| "entropy": 1.8919328197836875, | |
| "epoch": 0.171625781177129, | |
| "grad_norm": 2.640625, | |
| "learning_rate": 1.985658381103427e-05, | |
| "loss": 1.1309, | |
| "mean_token_accuracy": 0.7507242120802402, | |
| "num_tokens": 24432664.0, | |
| "step": 230 | |
| }, | |
| { | |
| "entropy": 1.8881874978542328, | |
| "epoch": 0.17535677642011008, | |
| "grad_norm": 2.6875, | |
| "learning_rate": 1.984675789715512e-05, | |
| "loss": 1.0927, | |
| "mean_token_accuracy": 0.7648542866110801, | |
| "num_tokens": 24962958.0, | |
| "step": 235 | |
| }, | |
| { | |
| "entropy": 1.888606432080269, | |
| "epoch": 0.17908777166309112, | |
| "grad_norm": 2.265625, | |
| "learning_rate": 1.9836609325696017e-05, | |
| "loss": 1.2134, | |
| "mean_token_accuracy": 0.7300407648086548, | |
| "num_tokens": 25496026.0, | |
| "step": 240 | |
| }, | |
| { | |
| "entropy": 1.8738144993782044, | |
| "epoch": 0.18281876690607218, | |
| "grad_norm": 2.75, | |
| "learning_rate": 1.9826138466794088e-05, | |
| "loss": 1.1858, | |
| "mean_token_accuracy": 0.7387278139591217, | |
| "num_tokens": 26029309.0, | |
| "step": 245 | |
| }, | |
| { | |
| "entropy": 1.8657475382089614, | |
| "epoch": 0.18654976214905325, | |
| "grad_norm": 2.3125, | |
| "learning_rate": 1.981534570234087e-05, | |
| "loss": 1.1096, | |
| "mean_token_accuracy": 0.7601700283586978, | |
| "num_tokens": 26561603.0, | |
| "step": 250 | |
| }, | |
| { | |
| "entropy": 1.8530463799834251, | |
| "epoch": 0.19028075739203432, | |
| "grad_norm": 2.390625, | |
| "learning_rate": 1.9804231425968394e-05, | |
| "loss": 1.0604, | |
| "mean_token_accuracy": 0.7672378472983837, | |
| "num_tokens": 27095577.0, | |
| "step": 255 | |
| }, | |
| { | |
| "entropy": 1.8480310454964637, | |
| "epoch": 0.19401175263501538, | |
| "grad_norm": 2.96875, | |
| "learning_rate": 1.9792796043034817e-05, | |
| "loss": 1.0706, | |
| "mean_token_accuracy": 0.7706682577729225, | |
| "num_tokens": 27626494.0, | |
| "step": 260 | |
| }, | |
| { | |
| "entropy": 1.8671077743172646, | |
| "epoch": 0.19774274787799645, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 1.9781039970609656e-05, | |
| "loss": 1.0765, | |
| "mean_token_accuracy": 0.7629323773086071, | |
| "num_tokens": 28157811.0, | |
| "step": 265 | |
| }, | |
| { | |
| "entropy": 1.853178422152996, | |
| "epoch": 0.20147374312097752, | |
| "grad_norm": 2.46875, | |
| "learning_rate": 1.9768963637458553e-05, | |
| "loss": 1.1053, | |
| "mean_token_accuracy": 0.7563259281218052, | |
| "num_tokens": 28689739.0, | |
| "step": 270 | |
| }, | |
| { | |
| "entropy": 1.8592572018504143, | |
| "epoch": 0.20520473836395858, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 1.9756567484027657e-05, | |
| "loss": 1.064, | |
| "mean_token_accuracy": 0.7610228173434734, | |
| "num_tokens": 29220279.0, | |
| "step": 275 | |
| }, | |
| { | |
| "entropy": 1.868624246120453, | |
| "epoch": 0.20893573360693965, | |
| "grad_norm": 2.5, | |
| "learning_rate": 1.9743851962427547e-05, | |
| "loss": 1.1369, | |
| "mean_token_accuracy": 0.7518735721707344, | |
| "num_tokens": 29750745.0, | |
| "step": 280 | |
| }, | |
| { | |
| "entropy": 1.8660186305642128, | |
| "epoch": 0.21266672884992072, | |
| "grad_norm": 2.5625, | |
| "learning_rate": 1.9730817536416757e-05, | |
| "loss": 1.0856, | |
| "mean_token_accuracy": 0.7596553325653076, | |
| "num_tokens": 30282712.0, | |
| "step": 285 | |
| }, | |
| { | |
| "entropy": 1.8520298555493355, | |
| "epoch": 0.21639772409290178, | |
| "grad_norm": 2.625, | |
| "learning_rate": 1.9717464681384847e-05, | |
| "loss": 1.03, | |
| "mean_token_accuracy": 0.7732533916831017, | |
| "num_tokens": 30814113.0, | |
| "step": 290 | |
| }, | |
| { | |
| "entropy": 1.848675537109375, | |
| "epoch": 0.22012871933588285, | |
| "grad_norm": 2.765625, | |
| "learning_rate": 1.970379388433507e-05, | |
| "loss": 1.1311, | |
| "mean_token_accuracy": 0.7620892561972141, | |
| "num_tokens": 31344383.0, | |
| "step": 295 | |
| }, | |
| { | |
| "entropy": 1.8459958881139755, | |
| "epoch": 0.22385971457886392, | |
| "grad_norm": 2.625, | |
| "learning_rate": 1.9689805643866612e-05, | |
| "loss": 1.1939, | |
| "mean_token_accuracy": 0.738617904484272, | |
| "num_tokens": 31876803.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.22385971457886392, | |
| "eval_entropy": 1.8536106128297094, | |
| "eval_loss": 0.8944675922393799, | |
| "eval_mean_token_accuracy": 0.7675316457374854, | |
| "eval_num_tokens": 31876803.0, | |
| "eval_runtime": 419.8489, | |
| "eval_samples_per_second": 2.065, | |
| "eval_steps_per_second": 0.517, | |
| "step": 300 | |
| }, | |
| { | |
| "entropy": 1.8487590283155442, | |
| "epoch": 0.22759070982184498, | |
| "grad_norm": 2.65625, | |
| "learning_rate": 1.9675500470156413e-05, | |
| "loss": 1.0223, | |
| "mean_token_accuracy": 0.7746541768312454, | |
| "num_tokens": 32407779.0, | |
| "step": 305 | |
| }, | |
| { | |
| "entropy": 1.8505715727806091, | |
| "epoch": 0.23132170506482605, | |
| "grad_norm": 2.609375, | |
| "learning_rate": 1.9660878884940538e-05, | |
| "loss": 1.064, | |
| "mean_token_accuracy": 0.7622771561145782, | |
| "num_tokens": 32939220.0, | |
| "step": 310 | |
| }, | |
| { | |
| "entropy": 1.8618406757712365, | |
| "epoch": 0.23505270030780712, | |
| "grad_norm": 2.875, | |
| "learning_rate": 1.9645941421495175e-05, | |
| "loss": 1.0937, | |
| "mean_token_accuracy": 0.7551429606974125, | |
| "num_tokens": 33470031.0, | |
| "step": 315 | |
| }, | |
| { | |
| "entropy": 1.8671145975589751, | |
| "epoch": 0.23878369555078818, | |
| "grad_norm": 2.59375, | |
| "learning_rate": 1.9630688624617175e-05, | |
| "loss": 1.0394, | |
| "mean_token_accuracy": 0.7662747830152512, | |
| "num_tokens": 34002483.0, | |
| "step": 320 | |
| }, | |
| { | |
| "entropy": 1.8697764590382575, | |
| "epoch": 0.24251469079376925, | |
| "grad_norm": 2.609375, | |
| "learning_rate": 1.9615121050604166e-05, | |
| "loss": 1.0503, | |
| "mean_token_accuracy": 0.7624305739998818, | |
| "num_tokens": 34534879.0, | |
| "step": 325 | |
| }, | |
| { | |
| "entropy": 1.8799255907535553, | |
| "epoch": 0.24624568603675032, | |
| "grad_norm": 2.390625, | |
| "learning_rate": 1.9599239267234304e-05, | |
| "loss": 1.028, | |
| "mean_token_accuracy": 0.7683257654309272, | |
| "num_tokens": 35065564.0, | |
| "step": 330 | |
| }, | |
| { | |
| "entropy": 1.873243047297001, | |
| "epoch": 0.24997668127973136, | |
| "grad_norm": 2.484375, | |
| "learning_rate": 1.9583043853745514e-05, | |
| "loss": 1.1061, | |
| "mean_token_accuracy": 0.7559119880199432, | |
| "num_tokens": 35596284.0, | |
| "step": 335 | |
| }, | |
| { | |
| "entropy": 1.8775247171521188, | |
| "epoch": 0.2537076765227124, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 1.9566535400814407e-05, | |
| "loss": 1.1048, | |
| "mean_token_accuracy": 0.7629238598048687, | |
| "num_tokens": 36130255.0, | |
| "step": 340 | |
| }, | |
| { | |
| "entropy": 1.860211183130741, | |
| "epoch": 0.2574386717656935, | |
| "grad_norm": 3.15625, | |
| "learning_rate": 1.954971451053471e-05, | |
| "loss": 1.0581, | |
| "mean_token_accuracy": 0.7671318039298057, | |
| "num_tokens": 36662579.0, | |
| "step": 345 | |
| }, | |
| { | |
| "entropy": 1.8578041836619377, | |
| "epoch": 0.26116966700867456, | |
| "grad_norm": 2.421875, | |
| "learning_rate": 1.9532581796395327e-05, | |
| "loss": 1.1024, | |
| "mean_token_accuracy": 0.7555016644299031, | |
| "num_tokens": 37194467.0, | |
| "step": 350 | |
| }, | |
| { | |
| "entropy": 1.866262961924076, | |
| "epoch": 0.26490066225165565, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 1.951513788325794e-05, | |
| "loss": 1.0253, | |
| "mean_token_accuracy": 0.7781079560518265, | |
| "num_tokens": 37723064.0, | |
| "step": 355 | |
| }, | |
| { | |
| "entropy": 1.856664003431797, | |
| "epoch": 0.2686316574946367, | |
| "grad_norm": 2.890625, | |
| "learning_rate": 1.9497383407334245e-05, | |
| "loss": 1.0596, | |
| "mean_token_accuracy": 0.7623144149780273, | |
| "num_tokens": 38256284.0, | |
| "step": 360 | |
| }, | |
| { | |
| "entropy": 1.8678738117218017, | |
| "epoch": 0.2723626527376178, | |
| "grad_norm": 2.40625, | |
| "learning_rate": 1.9479319016162727e-05, | |
| "loss": 1.0514, | |
| "mean_token_accuracy": 0.764145913720131, | |
| "num_tokens": 38787832.0, | |
| "step": 365 | |
| }, | |
| { | |
| "entropy": 1.8648770898580551, | |
| "epoch": 0.2760936479805988, | |
| "grad_norm": 2.5, | |
| "learning_rate": 1.9460945368585057e-05, | |
| "loss": 1.0654, | |
| "mean_token_accuracy": 0.7684322811663151, | |
| "num_tokens": 39319841.0, | |
| "step": 370 | |
| }, | |
| { | |
| "entropy": 1.8789657562971116, | |
| "epoch": 0.2798246432235799, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 1.9442263134722055e-05, | |
| "loss": 1.0287, | |
| "mean_token_accuracy": 0.7699924275279045, | |
| "num_tokens": 39849403.0, | |
| "step": 375 | |
| }, | |
| { | |
| "entropy": 1.8746845886111259, | |
| "epoch": 0.28355563846656096, | |
| "grad_norm": 2.765625, | |
| "learning_rate": 1.9423272995949248e-05, | |
| "loss": 1.0038, | |
| "mean_token_accuracy": 0.7791954837739468, | |
| "num_tokens": 40380746.0, | |
| "step": 380 | |
| }, | |
| { | |
| "entropy": 1.8678623661398888, | |
| "epoch": 0.287286633709542, | |
| "grad_norm": 2.578125, | |
| "learning_rate": 1.9403975644872035e-05, | |
| "loss": 1.0835, | |
| "mean_token_accuracy": 0.759261854737997, | |
| "num_tokens": 40911733.0, | |
| "step": 385 | |
| }, | |
| { | |
| "entropy": 1.8729774489998818, | |
| "epoch": 0.2910176289525231, | |
| "grad_norm": 2.390625, | |
| "learning_rate": 1.9384371785300408e-05, | |
| "loss": 1.0718, | |
| "mean_token_accuracy": 0.7628073863685131, | |
| "num_tokens": 41443082.0, | |
| "step": 390 | |
| }, | |
| { | |
| "entropy": 1.8807472854852676, | |
| "epoch": 0.2947486241955041, | |
| "grad_norm": 2.609375, | |
| "learning_rate": 1.936446213222328e-05, | |
| "loss": 1.1063, | |
| "mean_token_accuracy": 0.7536667741835117, | |
| "num_tokens": 41975804.0, | |
| "step": 395 | |
| }, | |
| { | |
| "entropy": 1.8795248806476592, | |
| "epoch": 0.2984796194384852, | |
| "grad_norm": 2.703125, | |
| "learning_rate": 1.934424741178243e-05, | |
| "loss": 1.0782, | |
| "mean_token_accuracy": 0.7614248670637608, | |
| "num_tokens": 42506840.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.2984796194384852, | |
| "eval_entropy": 1.8717721261187084, | |
| "eval_loss": 0.8698498010635376, | |
| "eval_mean_token_accuracy": 0.7723283369420311, | |
| "eval_num_tokens": 42506840.0, | |
| "eval_runtime": 421.506, | |
| "eval_samples_per_second": 2.057, | |
| "eval_steps_per_second": 0.515, | |
| "step": 400 | |
| }, | |
| { | |
| "entropy": 1.8597126081585884, | |
| "epoch": 0.30221061468146626, | |
| "grad_norm": 2.515625, | |
| "learning_rate": 1.932372836124601e-05, | |
| "loss": 1.0929, | |
| "mean_token_accuracy": 0.7585588760674, | |
| "num_tokens": 43037896.0, | |
| "step": 405 | |
| }, | |
| { | |
| "entropy": 1.8776621356606484, | |
| "epoch": 0.30594160992444736, | |
| "grad_norm": 2.515625, | |
| "learning_rate": 1.9302905728981628e-05, | |
| "loss": 1.0856, | |
| "mean_token_accuracy": 0.7586130477488041, | |
| "num_tokens": 43568194.0, | |
| "step": 410 | |
| }, | |
| { | |
| "entropy": 1.8922527134418488, | |
| "epoch": 0.3096726051674284, | |
| "grad_norm": 2.546875, | |
| "learning_rate": 1.9281780274429108e-05, | |
| "loss": 1.1148, | |
| "mean_token_accuracy": 0.7570016115903855, | |
| "num_tokens": 44097543.0, | |
| "step": 415 | |
| }, | |
| { | |
| "entropy": 1.8982042223215103, | |
| "epoch": 0.3134036004104095, | |
| "grad_norm": 2.640625, | |
| "learning_rate": 1.9260352768072737e-05, | |
| "loss": 1.0039, | |
| "mean_token_accuracy": 0.7770169205963612, | |
| "num_tokens": 44628497.0, | |
| "step": 420 | |
| }, | |
| { | |
| "entropy": 1.8883474573493004, | |
| "epoch": 0.3171345956533905, | |
| "grad_norm": 2.671875, | |
| "learning_rate": 1.9238623991413212e-05, | |
| "loss": 1.0516, | |
| "mean_token_accuracy": 0.7661412447690964, | |
| "num_tokens": 45161594.0, | |
| "step": 425 | |
| }, | |
| { | |
| "entropy": 1.8868870452046393, | |
| "epoch": 0.3208655908963716, | |
| "grad_norm": 2.578125, | |
| "learning_rate": 1.9216594736939086e-05, | |
| "loss": 1.0684, | |
| "mean_token_accuracy": 0.7590530589222908, | |
| "num_tokens": 45691957.0, | |
| "step": 430 | |
| }, | |
| { | |
| "entropy": 1.8828503325581551, | |
| "epoch": 0.32459658613935266, | |
| "grad_norm": 2.828125, | |
| "learning_rate": 1.9194265808097913e-05, | |
| "loss": 1.044, | |
| "mean_token_accuracy": 0.7744015090167522, | |
| "num_tokens": 46222540.0, | |
| "step": 435 | |
| }, | |
| { | |
| "entropy": 1.8643267348408699, | |
| "epoch": 0.32832758138233376, | |
| "grad_norm": 2.671875, | |
| "learning_rate": 1.9171638019266915e-05, | |
| "loss": 1.0212, | |
| "mean_token_accuracy": 0.768348614871502, | |
| "num_tokens": 46756535.0, | |
| "step": 440 | |
| }, | |
| { | |
| "entropy": 1.8655900582671165, | |
| "epoch": 0.3320585766253148, | |
| "grad_norm": 2.265625, | |
| "learning_rate": 1.91487121957233e-05, | |
| "loss": 1.0475, | |
| "mean_token_accuracy": 0.772677880525589, | |
| "num_tokens": 47288448.0, | |
| "step": 445 | |
| }, | |
| { | |
| "entropy": 1.8565448239445685, | |
| "epoch": 0.3357895718682959, | |
| "grad_norm": 2.25, | |
| "learning_rate": 1.9125489173614132e-05, | |
| "loss": 1.0702, | |
| "mean_token_accuracy": 0.7584976136684418, | |
| "num_tokens": 47818809.0, | |
| "step": 450 | |
| }, | |
| { | |
| "entropy": 1.8645773649215698, | |
| "epoch": 0.3395205671112769, | |
| "grad_norm": 3.21875, | |
| "learning_rate": 1.9101969799925877e-05, | |
| "loss": 0.9895, | |
| "mean_token_accuracy": 0.7730739787220955, | |
| "num_tokens": 48349840.0, | |
| "step": 455 | |
| }, | |
| { | |
| "entropy": 1.8840496107935905, | |
| "epoch": 0.343251562354258, | |
| "grad_norm": 2.65625, | |
| "learning_rate": 1.907815493245347e-05, | |
| "loss": 1.026, | |
| "mean_token_accuracy": 0.7796110861003399, | |
| "num_tokens": 48880975.0, | |
| "step": 460 | |
| }, | |
| { | |
| "entropy": 1.8931686580181122, | |
| "epoch": 0.34698255759723906, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 1.905404543976906e-05, | |
| "loss": 1.0454, | |
| "mean_token_accuracy": 0.7702999524772167, | |
| "num_tokens": 49411651.0, | |
| "step": 465 | |
| }, | |
| { | |
| "entropy": 1.8839797154068947, | |
| "epoch": 0.35071355284022016, | |
| "grad_norm": 2.546875, | |
| "learning_rate": 1.9029642201190328e-05, | |
| "loss": 1.0322, | |
| "mean_token_accuracy": 0.7673676989972591, | |
| "num_tokens": 49942631.0, | |
| "step": 470 | |
| }, | |
| { | |
| "entropy": 1.8662499740719796, | |
| "epoch": 0.3544445480832012, | |
| "grad_norm": 2.625, | |
| "learning_rate": 1.9004946106748392e-05, | |
| "loss": 1.0455, | |
| "mean_token_accuracy": 0.7651143468916416, | |
| "num_tokens": 50475396.0, | |
| "step": 475 | |
| }, | |
| { | |
| "entropy": 1.861226101219654, | |
| "epoch": 0.35817554332618223, | |
| "grad_norm": 2.578125, | |
| "learning_rate": 1.8979958057155377e-05, | |
| "loss": 0.9745, | |
| "mean_token_accuracy": 0.777230667322874, | |
| "num_tokens": 51008321.0, | |
| "step": 480 | |
| }, | |
| { | |
| "entropy": 1.876523844897747, | |
| "epoch": 0.3619065385691633, | |
| "grad_norm": 2.359375, | |
| "learning_rate": 1.8954678963771543e-05, | |
| "loss": 1.0391, | |
| "mean_token_accuracy": 0.7686795577406883, | |
| "num_tokens": 51540064.0, | |
| "step": 485 | |
| }, | |
| { | |
| "entropy": 1.8753577783703803, | |
| "epoch": 0.36563753381214437, | |
| "grad_norm": 2.4375, | |
| "learning_rate": 1.892910974857206e-05, | |
| "loss": 0.9281, | |
| "mean_token_accuracy": 0.787179034948349, | |
| "num_tokens": 52071265.0, | |
| "step": 490 | |
| }, | |
| { | |
| "entropy": 1.8801261857151985, | |
| "epoch": 0.36936852905512546, | |
| "grad_norm": 2.75, | |
| "learning_rate": 1.8903251344113378e-05, | |
| "loss": 1.0486, | |
| "mean_token_accuracy": 0.7643107511103153, | |
| "num_tokens": 52602478.0, | |
| "step": 495 | |
| }, | |
| { | |
| "entropy": 1.8888003394007682, | |
| "epoch": 0.3730995242981065, | |
| "grad_norm": 2.46875, | |
| "learning_rate": 1.8877104693499196e-05, | |
| "loss": 1.0622, | |
| "mean_token_accuracy": 0.7684491701424122, | |
| "num_tokens": 53133417.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.3730995242981065, | |
| "eval_entropy": 1.895705726838881, | |
| "eval_loss": 0.8520886301994324, | |
| "eval_mean_token_accuracy": 0.77683642795009, | |
| "eval_num_tokens": 53133417.0, | |
| "eval_runtime": 430.7614, | |
| "eval_samples_per_second": 2.013, | |
| "eval_steps_per_second": 0.504, | |
| "step": 500 | |
| }, | |
| { | |
| "entropy": 1.8893942952156066, | |
| "epoch": 0.3768305195410876, | |
| "grad_norm": 2.640625, | |
| "learning_rate": 1.885067075034611e-05, | |
| "loss": 1.0565, | |
| "mean_token_accuracy": 0.7684147022664547, | |
| "num_tokens": 53664950.0, | |
| "step": 505 | |
| }, | |
| { | |
| "entropy": 1.879076398909092, | |
| "epoch": 0.38056151478406863, | |
| "grad_norm": 2.671875, | |
| "learning_rate": 1.8823950478748776e-05, | |
| "loss": 0.9903, | |
| "mean_token_accuracy": 0.7752767533063889, | |
| "num_tokens": 54193587.0, | |
| "step": 510 | |
| }, | |
| { | |
| "entropy": 1.8704274088144301, | |
| "epoch": 0.3842925100270497, | |
| "grad_norm": 2.859375, | |
| "learning_rate": 1.8796944853244792e-05, | |
| "loss": 1.0437, | |
| "mean_token_accuracy": 0.7737653762102127, | |
| "num_tokens": 54725214.0, | |
| "step": 515 | |
| }, | |
| { | |
| "entropy": 1.8798809126019478, | |
| "epoch": 0.38802350527003077, | |
| "grad_norm": 2.796875, | |
| "learning_rate": 1.876965485877914e-05, | |
| "loss": 1.0818, | |
| "mean_token_accuracy": 0.7597776927053929, | |
| "num_tokens": 55257440.0, | |
| "step": 520 | |
| }, | |
| { | |
| "entropy": 1.8531851500272751, | |
| "epoch": 0.39175450051301186, | |
| "grad_norm": 2.90625, | |
| "learning_rate": 1.8742081490668262e-05, | |
| "loss": 0.9992, | |
| "mean_token_accuracy": 0.770975799113512, | |
| "num_tokens": 55789441.0, | |
| "step": 525 | |
| }, | |
| { | |
| "entropy": 1.8578070297837257, | |
| "epoch": 0.3954854957559929, | |
| "grad_norm": 2.703125, | |
| "learning_rate": 1.871422575456375e-05, | |
| "loss": 1.0776, | |
| "mean_token_accuracy": 0.7619852371513843, | |
| "num_tokens": 56320165.0, | |
| "step": 530 | |
| }, | |
| { | |
| "entropy": 1.8590588822960854, | |
| "epoch": 0.399216490998974, | |
| "grad_norm": 2.890625, | |
| "learning_rate": 1.8686088666415688e-05, | |
| "loss": 1.0425, | |
| "mean_token_accuracy": 0.7635523222386837, | |
| "num_tokens": 56853151.0, | |
| "step": 535 | |
| }, | |
| { | |
| "entropy": 1.853328062593937, | |
| "epoch": 0.40294748624195503, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 1.8657671252435588e-05, | |
| "loss": 0.9841, | |
| "mean_token_accuracy": 0.7831168882548809, | |
| "num_tokens": 57384404.0, | |
| "step": 540 | |
| }, | |
| { | |
| "entropy": 1.8588544443249702, | |
| "epoch": 0.4066784814849361, | |
| "grad_norm": 3.890625, | |
| "learning_rate": 1.8628974549058953e-05, | |
| "loss": 0.968, | |
| "mean_token_accuracy": 0.7785750322043896, | |
| "num_tokens": 57918551.0, | |
| "step": 545 | |
| }, | |
| { | |
| "entropy": 1.849987468123436, | |
| "epoch": 0.41040947672791717, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 1.8599999602907493e-05, | |
| "loss": 1.0544, | |
| "mean_token_accuracy": 0.7708779990673065, | |
| "num_tokens": 58451041.0, | |
| "step": 550 | |
| }, | |
| { | |
| "entropy": 1.8577365413308145, | |
| "epoch": 0.41414047197089826, | |
| "grad_norm": 2.859375, | |
| "learning_rate": 1.857074747075095e-05, | |
| "loss": 0.9909, | |
| "mean_token_accuracy": 0.7778203032910824, | |
| "num_tokens": 58985420.0, | |
| "step": 555 | |
| }, | |
| { | |
| "entropy": 1.8802942395210267, | |
| "epoch": 0.4178714672138793, | |
| "grad_norm": 2.859375, | |
| "learning_rate": 1.8541219219468534e-05, | |
| "loss": 1.0193, | |
| "mean_token_accuracy": 0.7772314816713333, | |
| "num_tokens": 59516362.0, | |
| "step": 560 | |
| }, | |
| { | |
| "entropy": 1.8853446871042252, | |
| "epoch": 0.4216024624568604, | |
| "grad_norm": 2.375, | |
| "learning_rate": 1.8511415926010043e-05, | |
| "loss": 1.0619, | |
| "mean_token_accuracy": 0.7719809092581272, | |
| "num_tokens": 60046588.0, | |
| "step": 565 | |
| }, | |
| { | |
| "entropy": 1.8890699461102485, | |
| "epoch": 0.42533345769984143, | |
| "grad_norm": 2.421875, | |
| "learning_rate": 1.8481338677356574e-05, | |
| "loss": 1.0658, | |
| "mean_token_accuracy": 0.7626231409609318, | |
| "num_tokens": 60577014.0, | |
| "step": 570 | |
| }, | |
| { | |
| "entropy": 1.8884864136576653, | |
| "epoch": 0.42906445294282247, | |
| "grad_norm": 2.40625, | |
| "learning_rate": 1.8450988570480865e-05, | |
| "loss": 1.0268, | |
| "mean_token_accuracy": 0.7732196651399136, | |
| "num_tokens": 61109729.0, | |
| "step": 575 | |
| }, | |
| { | |
| "entropy": 1.8984817937016487, | |
| "epoch": 0.43279544818580357, | |
| "grad_norm": 2.5625, | |
| "learning_rate": 1.8420366712307293e-05, | |
| "loss": 1.0837, | |
| "mean_token_accuracy": 0.760554713755846, | |
| "num_tokens": 61640531.0, | |
| "step": 580 | |
| }, | |
| { | |
| "entropy": 1.8876586690545083, | |
| "epoch": 0.4365264434287846, | |
| "grad_norm": 2.671875, | |
| "learning_rate": 1.838947421967152e-05, | |
| "loss": 1.0442, | |
| "mean_token_accuracy": 0.763022082298994, | |
| "num_tokens": 62169871.0, | |
| "step": 585 | |
| }, | |
| { | |
| "entropy": 1.8796870589256287, | |
| "epoch": 0.4402574386717657, | |
| "grad_norm": 2.453125, | |
| "learning_rate": 1.8358312219279733e-05, | |
| "loss": 0.9773, | |
| "mean_token_accuracy": 0.7882885307073593, | |
| "num_tokens": 62700745.0, | |
| "step": 590 | |
| }, | |
| { | |
| "entropy": 1.8949595779180526, | |
| "epoch": 0.44398843391474674, | |
| "grad_norm": 2.65625, | |
| "learning_rate": 1.832688184766758e-05, | |
| "loss": 1.0091, | |
| "mean_token_accuracy": 0.7738702580332756, | |
| "num_tokens": 63230735.0, | |
| "step": 595 | |
| }, | |
| { | |
| "entropy": 1.8843660712242127, | |
| "epoch": 0.44771942915772783, | |
| "grad_norm": 2.640625, | |
| "learning_rate": 1.8295184251158683e-05, | |
| "loss": 1.0339, | |
| "mean_token_accuracy": 0.7698764786124229, | |
| "num_tokens": 63762011.0, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.44771942915772783, | |
| "eval_entropy": 1.8978905815133302, | |
| "eval_loss": 0.8385350704193115, | |
| "eval_mean_token_accuracy": 0.7798161514893106, | |
| "eval_num_tokens": 63762011.0, | |
| "eval_runtime": 421.7508, | |
| "eval_samples_per_second": 2.056, | |
| "eval_steps_per_second": 0.515, | |
| "step": 600 | |
| }, | |
| { | |
| "entropy": 1.8987897396087647, | |
| "epoch": 0.45145042440070887, | |
| "grad_norm": 2.390625, | |
| "learning_rate": 1.826322058582287e-05, | |
| "loss": 0.9574, | |
| "mean_token_accuracy": 0.7808470018208027, | |
| "num_tokens": 64293628.0, | |
| "step": 605 | |
| }, | |
| { | |
| "entropy": 1.9083756417036057, | |
| "epoch": 0.45518141964368997, | |
| "grad_norm": 2.765625, | |
| "learning_rate": 1.8230992017433964e-05, | |
| "loss": 1.0223, | |
| "mean_token_accuracy": 0.7760558076202869, | |
| "num_tokens": 64823314.0, | |
| "step": 610 | |
| }, | |
| { | |
| "entropy": 1.8789043992757797, | |
| "epoch": 0.458912414886671, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 1.8198499721427315e-05, | |
| "loss": 1.0547, | |
| "mean_token_accuracy": 0.7682580567896367, | |
| "num_tokens": 65354447.0, | |
| "step": 615 | |
| }, | |
| { | |
| "entropy": 1.88258585780859, | |
| "epoch": 0.4626434101296521, | |
| "grad_norm": 3.046875, | |
| "learning_rate": 1.8165744882856896e-05, | |
| "loss": 0.9368, | |
| "mean_token_accuracy": 0.7864787146449089, | |
| "num_tokens": 65883446.0, | |
| "step": 620 | |
| }, | |
| { | |
| "entropy": 1.8828800201416016, | |
| "epoch": 0.46637440537263314, | |
| "grad_norm": 2.59375, | |
| "learning_rate": 1.813272869635209e-05, | |
| "loss": 0.9939, | |
| "mean_token_accuracy": 0.7787854075431824, | |
| "num_tokens": 66413154.0, | |
| "step": 625 | |
| }, | |
| { | |
| "entropy": 1.8896025449037552, | |
| "epoch": 0.47010540061561423, | |
| "grad_norm": 2.453125, | |
| "learning_rate": 1.8099452366074125e-05, | |
| "loss": 1.0421, | |
| "mean_token_accuracy": 0.7667336985468864, | |
| "num_tokens": 66944797.0, | |
| "step": 630 | |
| }, | |
| { | |
| "entropy": 1.9044037982821465, | |
| "epoch": 0.47383639585859527, | |
| "grad_norm": 2.609375, | |
| "learning_rate": 1.8065917105672147e-05, | |
| "loss": 1.03, | |
| "mean_token_accuracy": 0.7720849968492984, | |
| "num_tokens": 67475154.0, | |
| "step": 635 | |
| }, | |
| { | |
| "entropy": 1.9032243177294732, | |
| "epoch": 0.47756739110157637, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 1.8032124138238964e-05, | |
| "loss": 1.0904, | |
| "mean_token_accuracy": 0.7631759561598301, | |
| "num_tokens": 68005497.0, | |
| "step": 640 | |
| }, | |
| { | |
| "entropy": 1.9050288692116737, | |
| "epoch": 0.4812983863445574, | |
| "grad_norm": 2.5625, | |
| "learning_rate": 1.7998074696266438e-05, | |
| "loss": 1.0385, | |
| "mean_token_accuracy": 0.7717444844543934, | |
| "num_tokens": 68538652.0, | |
| "step": 645 | |
| }, | |
| { | |
| "entropy": 1.9110868632793427, | |
| "epoch": 0.4850293815875385, | |
| "grad_norm": 2.515625, | |
| "learning_rate": 1.7963770021600533e-05, | |
| "loss": 1.0514, | |
| "mean_token_accuracy": 0.7663141049444675, | |
| "num_tokens": 69067407.0, | |
| "step": 650 | |
| }, | |
| { | |
| "entropy": 1.9152159363031387, | |
| "epoch": 0.48876037683051954, | |
| "grad_norm": 2.75, | |
| "learning_rate": 1.7929211365396005e-05, | |
| "loss": 1.0354, | |
| "mean_token_accuracy": 0.7692722842097283, | |
| "num_tokens": 69595794.0, | |
| "step": 655 | |
| }, | |
| { | |
| "entropy": 1.9117783293128014, | |
| "epoch": 0.49249137207350063, | |
| "grad_norm": 2.640625, | |
| "learning_rate": 1.7894399988070804e-05, | |
| "loss": 0.9893, | |
| "mean_token_accuracy": 0.7810171820223332, | |
| "num_tokens": 70124120.0, | |
| "step": 660 | |
| }, | |
| { | |
| "entropy": 1.898228144645691, | |
| "epoch": 0.49622236731648167, | |
| "grad_norm": 2.453125, | |
| "learning_rate": 1.785933715926007e-05, | |
| "loss": 1.0349, | |
| "mean_token_accuracy": 0.7741277053952217, | |
| "num_tokens": 70658383.0, | |
| "step": 665 | |
| }, | |
| { | |
| "entropy": 1.892415849864483, | |
| "epoch": 0.4999533625594627, | |
| "grad_norm": 2.640625, | |
| "learning_rate": 1.7824024157769857e-05, | |
| "loss": 1.0535, | |
| "mean_token_accuracy": 0.7646197609603405, | |
| "num_tokens": 71190508.0, | |
| "step": 670 | |
| }, | |
| { | |
| "entropy": 1.8964731127023697, | |
| "epoch": 0.5036843578024438, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 1.7788462271530465e-05, | |
| "loss": 0.9729, | |
| "mean_token_accuracy": 0.7833174630999565, | |
| "num_tokens": 71723784.0, | |
| "step": 675 | |
| }, | |
| { | |
| "entropy": 1.8879738718271255, | |
| "epoch": 0.5074153530454248, | |
| "grad_norm": 2.515625, | |
| "learning_rate": 1.7752652797549488e-05, | |
| "loss": 1.0651, | |
| "mean_token_accuracy": 0.7697323687374592, | |
| "num_tokens": 72256599.0, | |
| "step": 680 | |
| }, | |
| { | |
| "entropy": 1.880824202299118, | |
| "epoch": 0.5111463482884059, | |
| "grad_norm": 2.4375, | |
| "learning_rate": 1.77165970418645e-05, | |
| "loss": 1.013, | |
| "mean_token_accuracy": 0.7752033665776252, | |
| "num_tokens": 72791530.0, | |
| "step": 685 | |
| }, | |
| { | |
| "entropy": 1.9036763146519662, | |
| "epoch": 0.514877343531387, | |
| "grad_norm": 2.9375, | |
| "learning_rate": 1.7680296319495417e-05, | |
| "loss": 1.0175, | |
| "mean_token_accuracy": 0.768329168856144, | |
| "num_tokens": 73321750.0, | |
| "step": 690 | |
| }, | |
| { | |
| "entropy": 1.8978674352169036, | |
| "epoch": 0.5186083387743681, | |
| "grad_norm": 2.71875, | |
| "learning_rate": 1.764375195439655e-05, | |
| "loss": 0.9838, | |
| "mean_token_accuracy": 0.776180149614811, | |
| "num_tokens": 73851824.0, | |
| "step": 695 | |
| }, | |
| { | |
| "entropy": 1.8836245954036712, | |
| "epoch": 0.5223393340173491, | |
| "grad_norm": 3.03125, | |
| "learning_rate": 1.7606965279408306e-05, | |
| "loss": 0.9327, | |
| "mean_token_accuracy": 0.7869227968156338, | |
| "num_tokens": 74383284.0, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.5223393340173491, | |
| "eval_entropy": 1.8904020984051964, | |
| "eval_loss": 0.8297026753425598, | |
| "eval_mean_token_accuracy": 0.7804744441388389, | |
| "eval_num_tokens": 74383284.0, | |
| "eval_runtime": 413.2232, | |
| "eval_samples_per_second": 2.098, | |
| "eval_steps_per_second": 0.525, | |
| "step": 700 | |
| }, | |
| { | |
| "entropy": 1.8916564375162124, | |
| "epoch": 0.5260703292603301, | |
| "grad_norm": 2.90625, | |
| "learning_rate": 1.756993763620859e-05, | |
| "loss": 1.0128, | |
| "mean_token_accuracy": 0.7728722743690014, | |
| "num_tokens": 74914750.0, | |
| "step": 705 | |
| }, | |
| { | |
| "entropy": 1.8978112503886222, | |
| "epoch": 0.5298013245033113, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 1.7532670375263836e-05, | |
| "loss": 1.0299, | |
| "mean_token_accuracy": 0.7684225983917713, | |
| "num_tokens": 75446535.0, | |
| "step": 710 | |
| }, | |
| { | |
| "entropy": 1.8988500460982323, | |
| "epoch": 0.5335323197462923, | |
| "grad_norm": 2.75, | |
| "learning_rate": 1.7495164855779812e-05, | |
| "loss": 0.9841, | |
| "mean_token_accuracy": 0.7884247310459613, | |
| "num_tokens": 75978225.0, | |
| "step": 715 | |
| }, | |
| { | |
| "entropy": 1.903371374309063, | |
| "epoch": 0.5372633149892734, | |
| "grad_norm": 2.390625, | |
| "learning_rate": 1.7457422445651996e-05, | |
| "loss": 1.0304, | |
| "mean_token_accuracy": 0.7681498162448406, | |
| "num_tokens": 76514443.0, | |
| "step": 720 | |
| }, | |
| { | |
| "entropy": 1.9176162853837013, | |
| "epoch": 0.5409943102322544, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 1.7419444521415706e-05, | |
| "loss": 0.9887, | |
| "mean_token_accuracy": 0.778039886802435, | |
| "num_tokens": 77045887.0, | |
| "step": 725 | |
| }, | |
| { | |
| "entropy": 1.9141801953315736, | |
| "epoch": 0.5447253054752356, | |
| "grad_norm": 2.703125, | |
| "learning_rate": 1.7381232468195896e-05, | |
| "loss": 0.953, | |
| "mean_token_accuracy": 0.7912342786788941, | |
| "num_tokens": 77579089.0, | |
| "step": 730 | |
| }, | |
| { | |
| "entropy": 1.9069402724504472, | |
| "epoch": 0.5484563007182166, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 1.7342787679656635e-05, | |
| "loss": 1.0026, | |
| "mean_token_accuracy": 0.7827796794474124, | |
| "num_tokens": 78108383.0, | |
| "step": 735 | |
| }, | |
| { | |
| "entropy": 1.9042499542236329, | |
| "epoch": 0.5521872959611976, | |
| "grad_norm": 2.953125, | |
| "learning_rate": 1.730411155795028e-05, | |
| "loss": 1.0295, | |
| "mean_token_accuracy": 0.7759525053203106, | |
| "num_tokens": 78638979.0, | |
| "step": 740 | |
| }, | |
| { | |
| "entropy": 1.9021551787853241, | |
| "epoch": 0.5559182912041787, | |
| "grad_norm": 2.4375, | |
| "learning_rate": 1.726520551366634e-05, | |
| "loss": 1.013, | |
| "mean_token_accuracy": 0.7834214746952057, | |
| "num_tokens": 79170107.0, | |
| "step": 745 | |
| }, | |
| { | |
| "entropy": 1.886176513135433, | |
| "epoch": 0.5596492864471598, | |
| "grad_norm": 2.90625, | |
| "learning_rate": 1.7226070965780016e-05, | |
| "loss": 0.9796, | |
| "mean_token_accuracy": 0.7753789328038693, | |
| "num_tokens": 79700908.0, | |
| "step": 750 | |
| }, | |
| { | |
| "entropy": 1.9083970338106155, | |
| "epoch": 0.5633802816901409, | |
| "grad_norm": 2.9375, | |
| "learning_rate": 1.7186709341600453e-05, | |
| "loss": 0.9348, | |
| "mean_token_accuracy": 0.7793697625398636, | |
| "num_tokens": 80230760.0, | |
| "step": 755 | |
| }, | |
| { | |
| "entropy": 1.8939674898982048, | |
| "epoch": 0.5671112769331219, | |
| "grad_norm": 2.71875, | |
| "learning_rate": 1.7147122076718702e-05, | |
| "loss": 0.9813, | |
| "mean_token_accuracy": 0.7803831771016121, | |
| "num_tokens": 80760531.0, | |
| "step": 760 | |
| }, | |
| { | |
| "entropy": 1.9014861181378364, | |
| "epoch": 0.570842272176103, | |
| "grad_norm": 2.59375, | |
| "learning_rate": 1.710731061495534e-05, | |
| "loss": 1.0185, | |
| "mean_token_accuracy": 0.7759978130459786, | |
| "num_tokens": 81291358.0, | |
| "step": 765 | |
| }, | |
| { | |
| "entropy": 1.89882051050663, | |
| "epoch": 0.574573267419084, | |
| "grad_norm": 2.9375, | |
| "learning_rate": 1.7067276408307813e-05, | |
| "loss": 0.9795, | |
| "mean_token_accuracy": 0.7780521295964717, | |
| "num_tokens": 81822399.0, | |
| "step": 770 | |
| }, | |
| { | |
| "entropy": 1.9006829962134362, | |
| "epoch": 0.5783042626620651, | |
| "grad_norm": 2.8125, | |
| "learning_rate": 1.702702091689749e-05, | |
| "loss": 0.9759, | |
| "mean_token_accuracy": 0.7813475333154202, | |
| "num_tokens": 82353944.0, | |
| "step": 775 | |
| }, | |
| { | |
| "entropy": 1.8907926201820373, | |
| "epoch": 0.5820352579050462, | |
| "grad_norm": 2.46875, | |
| "learning_rate": 1.6986545608916398e-05, | |
| "loss": 1.0128, | |
| "mean_token_accuracy": 0.7728120058774948, | |
| "num_tokens": 82884998.0, | |
| "step": 780 | |
| }, | |
| { | |
| "entropy": 1.9046567052602768, | |
| "epoch": 0.5857662531480272, | |
| "grad_norm": 3.609375, | |
| "learning_rate": 1.6945851960573688e-05, | |
| "loss": 0.9869, | |
| "mean_token_accuracy": 0.7850996717810631, | |
| "num_tokens": 83413705.0, | |
| "step": 785 | |
| }, | |
| { | |
| "entropy": 1.8946405827999115, | |
| "epoch": 0.5894972483910083, | |
| "grad_norm": 2.5, | |
| "learning_rate": 1.690494145604178e-05, | |
| "loss": 1.0068, | |
| "mean_token_accuracy": 0.7735021203756333, | |
| "num_tokens": 83945754.0, | |
| "step": 790 | |
| }, | |
| { | |
| "entropy": 1.8882904008030892, | |
| "epoch": 0.5932282436339894, | |
| "grad_norm": 2.703125, | |
| "learning_rate": 1.6863815587402238e-05, | |
| "loss": 0.9559, | |
| "mean_token_accuracy": 0.7860287889838219, | |
| "num_tokens": 84476584.0, | |
| "step": 795 | |
| }, | |
| { | |
| "entropy": 1.8921405717730522, | |
| "epoch": 0.5969592388769704, | |
| "grad_norm": 2.65625, | |
| "learning_rate": 1.682247585459136e-05, | |
| "loss": 0.9545, | |
| "mean_token_accuracy": 0.7818309612572193, | |
| "num_tokens": 85009333.0, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.5969592388769704, | |
| "eval_entropy": 1.9031854873428697, | |
| "eval_loss": 0.8225738406181335, | |
| "eval_mean_token_accuracy": 0.7820164143764479, | |
| "eval_num_tokens": 85009333.0, | |
| "eval_runtime": 414.4529, | |
| "eval_samples_per_second": 2.092, | |
| "eval_steps_per_second": 0.524, | |
| "step": 800 | |
| }, | |
| { | |
| "entropy": 1.8995822116732597, | |
| "epoch": 0.6006902341199515, | |
| "grad_norm": 2.890625, | |
| "learning_rate": 1.6780923765345456e-05, | |
| "loss": 0.9868, | |
| "mean_token_accuracy": 0.7774978131055832, | |
| "num_tokens": 85539990.0, | |
| "step": 805 | |
| }, | |
| { | |
| "entropy": 1.8972021773457528, | |
| "epoch": 0.6044212293629325, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 1.6739160835145874e-05, | |
| "loss": 1.0258, | |
| "mean_token_accuracy": 0.7669338978826999, | |
| "num_tokens": 86071665.0, | |
| "step": 810 | |
| }, | |
| { | |
| "entropy": 1.8983050301671027, | |
| "epoch": 0.6081522246059137, | |
| "grad_norm": 2.6875, | |
| "learning_rate": 1.669718858716372e-05, | |
| "loss": 0.9648, | |
| "mean_token_accuracy": 0.7823536217212677, | |
| "num_tokens": 86603171.0, | |
| "step": 815 | |
| }, | |
| { | |
| "entropy": 1.8986048236489297, | |
| "epoch": 0.6118832198488947, | |
| "grad_norm": 2.5, | |
| "learning_rate": 1.6655008552204296e-05, | |
| "loss": 1.0247, | |
| "mean_token_accuracy": 0.7682311937212944, | |
| "num_tokens": 87133722.0, | |
| "step": 820 | |
| }, | |
| { | |
| "entropy": 1.9042039334774017, | |
| "epoch": 0.6156142150918757, | |
| "grad_norm": 2.6875, | |
| "learning_rate": 1.661262226865129e-05, | |
| "loss": 0.9211, | |
| "mean_token_accuracy": 0.7911783196032047, | |
| "num_tokens": 87664262.0, | |
| "step": 825 | |
| }, | |
| { | |
| "entropy": 1.896624006330967, | |
| "epoch": 0.6193452103348568, | |
| "grad_norm": 2.75, | |
| "learning_rate": 1.657003128241065e-05, | |
| "loss": 1.0694, | |
| "mean_token_accuracy": 0.7654512405395508, | |
| "num_tokens": 88197100.0, | |
| "step": 830 | |
| }, | |
| { | |
| "entropy": 1.9086493596434593, | |
| "epoch": 0.6230762055778379, | |
| "grad_norm": 2.5, | |
| "learning_rate": 1.6527237146854216e-05, | |
| "loss": 1.0434, | |
| "mean_token_accuracy": 0.7728351354598999, | |
| "num_tokens": 88729818.0, | |
| "step": 835 | |
| }, | |
| { | |
| "entropy": 1.9073491543531418, | |
| "epoch": 0.626807200820819, | |
| "grad_norm": 3.015625, | |
| "learning_rate": 1.648424142276305e-05, | |
| "loss": 0.9657, | |
| "mean_token_accuracy": 0.7809720672667027, | |
| "num_tokens": 89261237.0, | |
| "step": 840 | |
| }, | |
| { | |
| "entropy": 1.9095076739788055, | |
| "epoch": 0.6305381960638, | |
| "grad_norm": 2.703125, | |
| "learning_rate": 1.6441045678270523e-05, | |
| "loss": 0.9939, | |
| "mean_token_accuracy": 0.7778474785387516, | |
| "num_tokens": 89792709.0, | |
| "step": 845 | |
| }, | |
| { | |
| "entropy": 1.9190806448459625, | |
| "epoch": 0.634269191306781, | |
| "grad_norm": 2.703125, | |
| "learning_rate": 1.6397651488805123e-05, | |
| "loss": 1.0188, | |
| "mean_token_accuracy": 0.7764581590890884, | |
| "num_tokens": 90325632.0, | |
| "step": 850 | |
| }, | |
| { | |
| "entropy": 1.9133808985352516, | |
| "epoch": 0.6380001865497621, | |
| "grad_norm": 2.578125, | |
| "learning_rate": 1.635406043703298e-05, | |
| "loss": 1.0084, | |
| "mean_token_accuracy": 0.7716027073562145, | |
| "num_tokens": 90856786.0, | |
| "step": 855 | |
| }, | |
| { | |
| "entropy": 1.9075268417596818, | |
| "epoch": 0.6417311817927432, | |
| "grad_norm": 2.59375, | |
| "learning_rate": 1.6310274112800168e-05, | |
| "loss": 0.9919, | |
| "mean_token_accuracy": 0.7748941496014595, | |
| "num_tokens": 91388721.0, | |
| "step": 860 | |
| }, | |
| { | |
| "entropy": 1.918405619263649, | |
| "epoch": 0.6454621770357243, | |
| "grad_norm": 2.609375, | |
| "learning_rate": 1.6266294113074705e-05, | |
| "loss": 1.0701, | |
| "mean_token_accuracy": 0.7638019427657128, | |
| "num_tokens": 91920341.0, | |
| "step": 865 | |
| }, | |
| { | |
| "entropy": 1.9207670271396637, | |
| "epoch": 0.6491931722787053, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 1.622212204188831e-05, | |
| "loss": 1.0503, | |
| "mean_token_accuracy": 0.7648871757090092, | |
| "num_tokens": 92451835.0, | |
| "step": 870 | |
| }, | |
| { | |
| "entropy": 1.907970777153969, | |
| "epoch": 0.6529241675216864, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 1.6177759510277896e-05, | |
| "loss": 1.0486, | |
| "mean_token_accuracy": 0.7644262924790383, | |
| "num_tokens": 92983993.0, | |
| "step": 875 | |
| }, | |
| { | |
| "entropy": 1.906702682375908, | |
| "epoch": 0.6566551627646675, | |
| "grad_norm": 2.625, | |
| "learning_rate": 1.6133208136226837e-05, | |
| "loss": 0.9787, | |
| "mean_token_accuracy": 0.7803527511656284, | |
| "num_tokens": 93515391.0, | |
| "step": 880 | |
| }, | |
| { | |
| "entropy": 1.9120250821113587, | |
| "epoch": 0.6603861580076485, | |
| "grad_norm": 2.765625, | |
| "learning_rate": 1.6088469544605917e-05, | |
| "loss": 1.0555, | |
| "mean_token_accuracy": 0.7651013791561126, | |
| "num_tokens": 94046135.0, | |
| "step": 885 | |
| }, | |
| { | |
| "entropy": 1.903009794652462, | |
| "epoch": 0.6641171532506296, | |
| "grad_norm": 3.84375, | |
| "learning_rate": 1.6043545367114108e-05, | |
| "loss": 1.0049, | |
| "mean_token_accuracy": 0.7814605854451656, | |
| "num_tokens": 94579367.0, | |
| "step": 890 | |
| }, | |
| { | |
| "entropy": 1.9165362551808358, | |
| "epoch": 0.6678481484936106, | |
| "grad_norm": 2.515625, | |
| "learning_rate": 1.599843724221903e-05, | |
| "loss": 1.0443, | |
| "mean_token_accuracy": 0.7678561337292195, | |
| "num_tokens": 95108280.0, | |
| "step": 895 | |
| }, | |
| { | |
| "entropy": 1.8937674418091774, | |
| "epoch": 0.6715791437365918, | |
| "grad_norm": 3.296875, | |
| "learning_rate": 1.595314681509721e-05, | |
| "loss": 0.9987, | |
| "mean_token_accuracy": 0.780899266153574, | |
| "num_tokens": 95640164.0, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.6715791437365918, | |
| "eval_entropy": 1.911442369359979, | |
| "eval_loss": 0.8153104186058044, | |
| "eval_mean_token_accuracy": 0.7842850034138025, | |
| "eval_num_tokens": 95640164.0, | |
| "eval_runtime": 407.5269, | |
| "eval_samples_per_second": 2.127, | |
| "eval_steps_per_second": 0.532, | |
| "step": 900 | |
| }, | |
| { | |
| "entropy": 1.9134518131613731, | |
| "epoch": 0.6753101389795728, | |
| "grad_norm": 2.671875, | |
| "learning_rate": 1.590767573757407e-05, | |
| "loss": 1.0539, | |
| "mean_token_accuracy": 0.7672203324735165, | |
| "num_tokens": 96174673.0, | |
| "step": 905 | |
| }, | |
| { | |
| "entropy": 1.9068228647112846, | |
| "epoch": 0.6790411342225539, | |
| "grad_norm": 2.96875, | |
| "learning_rate": 1.5862025668063684e-05, | |
| "loss": 0.9293, | |
| "mean_token_accuracy": 0.797333613038063, | |
| "num_tokens": 96705226.0, | |
| "step": 910 | |
| }, | |
| { | |
| "entropy": 1.9047024309635163, | |
| "epoch": 0.6827721294655349, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 1.5816198271508304e-05, | |
| "loss": 0.9766, | |
| "mean_token_accuracy": 0.7800018131732941, | |
| "num_tokens": 97237322.0, | |
| "step": 915 | |
| }, | |
| { | |
| "entropy": 1.8980093270540237, | |
| "epoch": 0.686503124708516, | |
| "grad_norm": 2.515625, | |
| "learning_rate": 1.5770195219317616e-05, | |
| "loss": 1.0123, | |
| "mean_token_accuracy": 0.7715090371668338, | |
| "num_tokens": 97769225.0, | |
| "step": 920 | |
| }, | |
| { | |
| "entropy": 1.8994540840387344, | |
| "epoch": 0.6902341199514971, | |
| "grad_norm": 3.046875, | |
| "learning_rate": 1.5724018189307794e-05, | |
| "loss": 0.9984, | |
| "mean_token_accuracy": 0.7745929844677448, | |
| "num_tokens": 98303973.0, | |
| "step": 925 | |
| }, | |
| { | |
| "entropy": 1.8997361719608308, | |
| "epoch": 0.6939651151944781, | |
| "grad_norm": 2.796875, | |
| "learning_rate": 1.5677668865640303e-05, | |
| "loss": 1.0065, | |
| "mean_token_accuracy": 0.7724752642214299, | |
| "num_tokens": 98834383.0, | |
| "step": 930 | |
| }, | |
| { | |
| "entropy": 1.906589935719967, | |
| "epoch": 0.6976961104374592, | |
| "grad_norm": 2.625, | |
| "learning_rate": 1.5631148938760478e-05, | |
| "loss": 0.9321, | |
| "mean_token_accuracy": 0.7906432278454304, | |
| "num_tokens": 99366644.0, | |
| "step": 935 | |
| }, | |
| { | |
| "entropy": 1.9116594985127449, | |
| "epoch": 0.7014271056804403, | |
| "grad_norm": 2.765625, | |
| "learning_rate": 1.558446010533587e-05, | |
| "loss": 0.9932, | |
| "mean_token_accuracy": 0.7812504962086677, | |
| "num_tokens": 99899469.0, | |
| "step": 940 | |
| }, | |
| { | |
| "entropy": 1.908557726442814, | |
| "epoch": 0.7051581009234213, | |
| "grad_norm": 2.9375, | |
| "learning_rate": 1.553760406819435e-05, | |
| "loss": 0.9354, | |
| "mean_token_accuracy": 0.7859705902636052, | |
| "num_tokens": 100432079.0, | |
| "step": 945 | |
| }, | |
| { | |
| "entropy": 1.911416806280613, | |
| "epoch": 0.7088890961664024, | |
| "grad_norm": 2.59375, | |
| "learning_rate": 1.549058253626204e-05, | |
| "loss": 0.9158, | |
| "mean_token_accuracy": 0.7985282003879547, | |
| "num_tokens": 100964903.0, | |
| "step": 950 | |
| }, | |
| { | |
| "entropy": 1.9102476298809052, | |
| "epoch": 0.7126200914093834, | |
| "grad_norm": 2.59375, | |
| "learning_rate": 1.544339722450094e-05, | |
| "loss": 0.9396, | |
| "mean_token_accuracy": 0.7870368644595146, | |
| "num_tokens": 101495644.0, | |
| "step": 955 | |
| }, | |
| { | |
| "entropy": 1.9011426746845246, | |
| "epoch": 0.7163510866523645, | |
| "grad_norm": 2.578125, | |
| "learning_rate": 1.5396049853846416e-05, | |
| "loss": 0.9782, | |
| "mean_token_accuracy": 0.776444636285305, | |
| "num_tokens": 102027056.0, | |
| "step": 960 | |
| }, | |
| { | |
| "entropy": 1.9028504237532615, | |
| "epoch": 0.7200820818953456, | |
| "grad_norm": 2.78125, | |
| "learning_rate": 1.5348542151144412e-05, | |
| "loss": 1.0195, | |
| "mean_token_accuracy": 0.7756047353148461, | |
| "num_tokens": 102558960.0, | |
| "step": 965 | |
| }, | |
| { | |
| "entropy": 1.913777655363083, | |
| "epoch": 0.7238130771383267, | |
| "grad_norm": 2.578125, | |
| "learning_rate": 1.530087584908849e-05, | |
| "loss": 0.9679, | |
| "mean_token_accuracy": 0.783194737881422, | |
| "num_tokens": 103090509.0, | |
| "step": 970 | |
| }, | |
| { | |
| "entropy": 1.9065766379237175, | |
| "epoch": 0.7275440723813077, | |
| "grad_norm": 2.953125, | |
| "learning_rate": 1.5253052686156606e-05, | |
| "loss": 0.9767, | |
| "mean_token_accuracy": 0.7749697960913181, | |
| "num_tokens": 103623149.0, | |
| "step": 975 | |
| }, | |
| { | |
| "entropy": 1.9180918678641319, | |
| "epoch": 0.7312750676242887, | |
| "grad_norm": 2.640625, | |
| "learning_rate": 1.5205074406547737e-05, | |
| "loss": 0.9984, | |
| "mean_token_accuracy": 0.7796571411192417, | |
| "num_tokens": 104151367.0, | |
| "step": 980 | |
| }, | |
| { | |
| "entropy": 1.9228741899132729, | |
| "epoch": 0.7350060628672699, | |
| "grad_norm": 2.703125, | |
| "learning_rate": 1.5156942760118243e-05, | |
| "loss": 0.9168, | |
| "mean_token_accuracy": 0.7995883099734783, | |
| "num_tokens": 104680461.0, | |
| "step": 985 | |
| }, | |
| { | |
| "entropy": 1.923213917016983, | |
| "epoch": 0.7387370581102509, | |
| "grad_norm": 2.4375, | |
| "learning_rate": 1.5108659502318057e-05, | |
| "loss": 0.983, | |
| "mean_token_accuracy": 0.7768499352037906, | |
| "num_tokens": 105211200.0, | |
| "step": 990 | |
| }, | |
| { | |
| "entropy": 1.9263088315725327, | |
| "epoch": 0.742468053353232, | |
| "grad_norm": 2.703125, | |
| "learning_rate": 1.506022639412666e-05, | |
| "loss": 0.9758, | |
| "mean_token_accuracy": 0.7826492115855217, | |
| "num_tokens": 105743445.0, | |
| "step": 995 | |
| }, | |
| { | |
| "entropy": 1.927260972559452, | |
| "epoch": 0.746199048596213, | |
| "grad_norm": 3.171875, | |
| "learning_rate": 1.5011645201988847e-05, | |
| "loss": 0.9638, | |
| "mean_token_accuracy": 0.7851476401090622, | |
| "num_tokens": 106276369.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.746199048596213, | |
| "eval_entropy": 1.93777990505992, | |
| "eval_loss": 0.810206949710846, | |
| "eval_mean_token_accuracy": 0.7849089860366786, | |
| "eval_num_tokens": 106276369.0, | |
| "eval_runtime": 413.4859, | |
| "eval_samples_per_second": 2.097, | |
| "eval_steps_per_second": 0.525, | |
| "step": 1000 | |
| }, | |
| { | |
| "entropy": 1.924168910086155, | |
| "epoch": 0.7499300438391941, | |
| "grad_norm": 2.703125, | |
| "learning_rate": 1.4962917697750312e-05, | |
| "loss": 1.0092, | |
| "mean_token_accuracy": 0.7759475007653236, | |
| "num_tokens": 106806838.0, | |
| "step": 1005 | |
| }, | |
| { | |
| "entropy": 1.926104436814785, | |
| "epoch": 0.7536610390821752, | |
| "grad_norm": 2.75, | |
| "learning_rate": 1.4914045658593029e-05, | |
| "loss": 1.008, | |
| "mean_token_accuracy": 0.7736393176019192, | |
| "num_tokens": 107339166.0, | |
| "step": 1010 | |
| }, | |
| { | |
| "entropy": 1.927248127758503, | |
| "epoch": 0.7573920343251562, | |
| "grad_norm": 2.59375, | |
| "learning_rate": 1.4865030866970408e-05, | |
| "loss": 0.9093, | |
| "mean_token_accuracy": 0.7949215397238731, | |
| "num_tokens": 107870267.0, | |
| "step": 1015 | |
| }, | |
| { | |
| "entropy": 1.915828388929367, | |
| "epoch": 0.7611230295681373, | |
| "grad_norm": 2.640625, | |
| "learning_rate": 1.4815875110542326e-05, | |
| "loss": 0.9008, | |
| "mean_token_accuracy": 0.7937774039804936, | |
| "num_tokens": 108400513.0, | |
| "step": 1020 | |
| }, | |
| { | |
| "entropy": 1.9184807062149047, | |
| "epoch": 0.7648540248111184, | |
| "grad_norm": 2.640625, | |
| "learning_rate": 1.4766580182109889e-05, | |
| "loss": 1.0036, | |
| "mean_token_accuracy": 0.7738492339849472, | |
| "num_tokens": 108932594.0, | |
| "step": 1025 | |
| }, | |
| { | |
| "entropy": 1.9205460771918297, | |
| "epoch": 0.7685850200540995, | |
| "grad_norm": 2.671875, | |
| "learning_rate": 1.4717147879550078e-05, | |
| "loss": 0.9702, | |
| "mean_token_accuracy": 0.7899442717432976, | |
| "num_tokens": 109462921.0, | |
| "step": 1030 | |
| }, | |
| { | |
| "entropy": 1.9184999212622642, | |
| "epoch": 0.7723160152970805, | |
| "grad_norm": 2.890625, | |
| "learning_rate": 1.4667580005750146e-05, | |
| "loss": 0.9383, | |
| "mean_token_accuracy": 0.7896254241466523, | |
| "num_tokens": 109994997.0, | |
| "step": 1035 | |
| }, | |
| { | |
| "entropy": 1.9122421011328696, | |
| "epoch": 0.7760470105400615, | |
| "grad_norm": 2.65625, | |
| "learning_rate": 1.4617878368541895e-05, | |
| "loss": 0.9512, | |
| "mean_token_accuracy": 0.7840572439134121, | |
| "num_tokens": 110525919.0, | |
| "step": 1040 | |
| }, | |
| { | |
| "entropy": 1.913463969528675, | |
| "epoch": 0.7797780057830426, | |
| "grad_norm": 2.828125, | |
| "learning_rate": 1.456804478063571e-05, | |
| "loss": 1.0129, | |
| "mean_token_accuracy": 0.7674046225845814, | |
| "num_tokens": 111055974.0, | |
| "step": 1045 | |
| }, | |
| { | |
| "entropy": 1.9107275918126105, | |
| "epoch": 0.7835090010260237, | |
| "grad_norm": 2.515625, | |
| "learning_rate": 1.4518081059554477e-05, | |
| "loss": 0.9937, | |
| "mean_token_accuracy": 0.777343125641346, | |
| "num_tokens": 111585284.0, | |
| "step": 1050 | |
| }, | |
| { | |
| "entropy": 1.917552863061428, | |
| "epoch": 0.7872399962690048, | |
| "grad_norm": 2.75, | |
| "learning_rate": 1.4467989027567263e-05, | |
| "loss": 0.9839, | |
| "mean_token_accuracy": 0.7785539641976357, | |
| "num_tokens": 112116183.0, | |
| "step": 1055 | |
| }, | |
| { | |
| "entropy": 1.9054254487156868, | |
| "epoch": 0.7909709915119858, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 1.4417770511622887e-05, | |
| "loss": 0.9861, | |
| "mean_token_accuracy": 0.7839046396315098, | |
| "num_tokens": 112646135.0, | |
| "step": 1060 | |
| }, | |
| { | |
| "entropy": 1.8971596196293832, | |
| "epoch": 0.7947019867549668, | |
| "grad_norm": 2.765625, | |
| "learning_rate": 1.4367427343283254e-05, | |
| "loss": 0.9637, | |
| "mean_token_accuracy": 0.7812280923128128, | |
| "num_tokens": 113176362.0, | |
| "step": 1065 | |
| }, | |
| { | |
| "entropy": 1.9003028556704522, | |
| "epoch": 0.798432981997948, | |
| "grad_norm": 2.859375, | |
| "learning_rate": 1.4316961358656584e-05, | |
| "loss": 0.9873, | |
| "mean_token_accuracy": 0.7795728340744972, | |
| "num_tokens": 113708268.0, | |
| "step": 1070 | |
| }, | |
| { | |
| "entropy": 1.896422977745533, | |
| "epoch": 0.802163977240929, | |
| "grad_norm": 2.75, | |
| "learning_rate": 1.4266374398330433e-05, | |
| "loss": 1.0349, | |
| "mean_token_accuracy": 0.7646013095974922, | |
| "num_tokens": 114240150.0, | |
| "step": 1075 | |
| }, | |
| { | |
| "entropy": 1.899100808799267, | |
| "epoch": 0.8058949724839101, | |
| "grad_norm": 2.765625, | |
| "learning_rate": 1.4215668307304557e-05, | |
| "loss": 0.9489, | |
| "mean_token_accuracy": 0.7867104850709439, | |
| "num_tokens": 114771681.0, | |
| "step": 1080 | |
| }, | |
| { | |
| "entropy": 1.9089683890342712, | |
| "epoch": 0.8096259677268911, | |
| "grad_norm": 2.59375, | |
| "learning_rate": 1.4164844934923631e-05, | |
| "loss": 1.0208, | |
| "mean_token_accuracy": 0.7843053504824639, | |
| "num_tokens": 115303073.0, | |
| "step": 1085 | |
| }, | |
| { | |
| "entropy": 1.9021274089813232, | |
| "epoch": 0.8133569629698723, | |
| "grad_norm": 2.875, | |
| "learning_rate": 1.4113906134809805e-05, | |
| "loss": 0.9929, | |
| "mean_token_accuracy": 0.7804038859903812, | |
| "num_tokens": 115837335.0, | |
| "step": 1090 | |
| }, | |
| { | |
| "entropy": 1.9116863787174225, | |
| "epoch": 0.8170879582128533, | |
| "grad_norm": 2.59375, | |
| "learning_rate": 1.406285376479508e-05, | |
| "loss": 0.9766, | |
| "mean_token_accuracy": 0.7845917344093323, | |
| "num_tokens": 116369639.0, | |
| "step": 1095 | |
| }, | |
| { | |
| "entropy": 1.8996223762631417, | |
| "epoch": 0.8208189534558343, | |
| "grad_norm": 2.6875, | |
| "learning_rate": 1.4011689686853562e-05, | |
| "loss": 1.065, | |
| "mean_token_accuracy": 0.7678873062133789, | |
| "num_tokens": 116901018.0, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.8208189534558343, | |
| "eval_entropy": 1.9164034864320183, | |
| "eval_loss": 0.8076829314231873, | |
| "eval_mean_token_accuracy": 0.7854106917908664, | |
| "eval_num_tokens": 116901018.0, | |
| "eval_runtime": 410.9839, | |
| "eval_samples_per_second": 2.11, | |
| "eval_steps_per_second": 0.528, | |
| "step": 1100 | |
| }, | |
| { | |
| "entropy": 1.912019345164299, | |
| "epoch": 0.8245499486988154, | |
| "grad_norm": 2.703125, | |
| "learning_rate": 1.3960415767033566e-05, | |
| "loss": 1.0343, | |
| "mean_token_accuracy": 0.7703364498913288, | |
| "num_tokens": 117434104.0, | |
| "step": 1105 | |
| }, | |
| { | |
| "entropy": 1.9091193810105325, | |
| "epoch": 0.8282809439417965, | |
| "grad_norm": 2.703125, | |
| "learning_rate": 1.3909033875389522e-05, | |
| "loss": 0.9879, | |
| "mean_token_accuracy": 0.7769205167889595, | |
| "num_tokens": 117964339.0, | |
| "step": 1110 | |
| }, | |
| { | |
| "entropy": 1.9093813717365264, | |
| "epoch": 0.8320119391847776, | |
| "grad_norm": 2.578125, | |
| "learning_rate": 1.3857545885913806e-05, | |
| "loss": 1.0359, | |
| "mean_token_accuracy": 0.7665309607982635, | |
| "num_tokens": 118493981.0, | |
| "step": 1115 | |
| }, | |
| { | |
| "entropy": 1.9185933470726013, | |
| "epoch": 0.8357429344277586, | |
| "grad_norm": 2.984375, | |
| "learning_rate": 1.3805953676468372e-05, | |
| "loss": 1.0506, | |
| "mean_token_accuracy": 0.762969171255827, | |
| "num_tokens": 119026536.0, | |
| "step": 1120 | |
| }, | |
| { | |
| "entropy": 1.9164486616849898, | |
| "epoch": 0.8394739296707396, | |
| "grad_norm": 3.0625, | |
| "learning_rate": 1.3754259128716266e-05, | |
| "loss": 0.9963, | |
| "mean_token_accuracy": 0.7848824128508568, | |
| "num_tokens": 119557686.0, | |
| "step": 1125 | |
| }, | |
| { | |
| "entropy": 1.9078744739294051, | |
| "epoch": 0.8432049249137208, | |
| "grad_norm": 2.625, | |
| "learning_rate": 1.370246412805301e-05, | |
| "loss": 0.9685, | |
| "mean_token_accuracy": 0.7828864552080631, | |
| "num_tokens": 120087050.0, | |
| "step": 1130 | |
| }, | |
| { | |
| "entropy": 1.9092570304870606, | |
| "epoch": 0.8469359201567018, | |
| "grad_norm": 2.65625, | |
| "learning_rate": 1.3650570563537824e-05, | |
| "loss": 0.9468, | |
| "mean_token_accuracy": 0.7840012639760972, | |
| "num_tokens": 120618701.0, | |
| "step": 1135 | |
| }, | |
| { | |
| "entropy": 1.90948646068573, | |
| "epoch": 0.8506669153996829, | |
| "grad_norm": 2.78125, | |
| "learning_rate": 1.3598580327824726e-05, | |
| "loss": 0.974, | |
| "mean_token_accuracy": 0.7765664204955101, | |
| "num_tokens": 121152315.0, | |
| "step": 1140 | |
| }, | |
| { | |
| "entropy": 1.913860061764717, | |
| "epoch": 0.8543979106426639, | |
| "grad_norm": 2.515625, | |
| "learning_rate": 1.3546495317093527e-05, | |
| "loss": 0.9608, | |
| "mean_token_accuracy": 0.784039318561554, | |
| "num_tokens": 121684014.0, | |
| "step": 1145 | |
| }, | |
| { | |
| "entropy": 1.908640170097351, | |
| "epoch": 0.8581289058856449, | |
| "grad_norm": 2.5, | |
| "learning_rate": 1.3494317430980642e-05, | |
| "loss": 0.9537, | |
| "mean_token_accuracy": 0.7842854559421539, | |
| "num_tokens": 122217932.0, | |
| "step": 1150 | |
| }, | |
| { | |
| "entropy": 1.9161628365516663, | |
| "epoch": 0.8618599011286261, | |
| "grad_norm": 2.609375, | |
| "learning_rate": 1.3442048572509827e-05, | |
| "loss": 0.9725, | |
| "mean_token_accuracy": 0.7805037409067154, | |
| "num_tokens": 122749728.0, | |
| "step": 1155 | |
| }, | |
| { | |
| "entropy": 1.9111833572387695, | |
| "epoch": 0.8655908963716071, | |
| "grad_norm": 2.6875, | |
| "learning_rate": 1.3389690648022777e-05, | |
| "loss": 0.8939, | |
| "mean_token_accuracy": 0.7963828206062317, | |
| "num_tokens": 123281364.0, | |
| "step": 1160 | |
| }, | |
| { | |
| "entropy": 1.9157856091856957, | |
| "epoch": 0.8693218916145882, | |
| "grad_norm": 2.640625, | |
| "learning_rate": 1.3337245567109578e-05, | |
| "loss": 1.006, | |
| "mean_token_accuracy": 0.7796331122517586, | |
| "num_tokens": 123812659.0, | |
| "step": 1165 | |
| }, | |
| { | |
| "entropy": 1.92343310713768, | |
| "epoch": 0.8730528868575692, | |
| "grad_norm": 2.8125, | |
| "learning_rate": 1.3284715242539073e-05, | |
| "loss": 0.8891, | |
| "mean_token_accuracy": 0.789270393550396, | |
| "num_tokens": 124341405.0, | |
| "step": 1170 | |
| }, | |
| { | |
| "entropy": 1.9144797176122665, | |
| "epoch": 0.8767838821005504, | |
| "grad_norm": 2.828125, | |
| "learning_rate": 1.3232101590189104e-05, | |
| "loss": 0.9934, | |
| "mean_token_accuracy": 0.7757502853870392, | |
| "num_tokens": 124872130.0, | |
| "step": 1175 | |
| }, | |
| { | |
| "entropy": 1.921220065653324, | |
| "epoch": 0.8805148773435314, | |
| "grad_norm": 2.578125, | |
| "learning_rate": 1.317940652897663e-05, | |
| "loss": 0.9992, | |
| "mean_token_accuracy": 0.7749721556901932, | |
| "num_tokens": 125402195.0, | |
| "step": 1180 | |
| }, | |
| { | |
| "entropy": 1.9140778228640556, | |
| "epoch": 0.8842458725865124, | |
| "grad_norm": 2.609375, | |
| "learning_rate": 1.3126631980787729e-05, | |
| "loss": 0.9669, | |
| "mean_token_accuracy": 0.781208099424839, | |
| "num_tokens": 125933557.0, | |
| "step": 1185 | |
| }, | |
| { | |
| "entropy": 1.9249017596244813, | |
| "epoch": 0.8879768678294935, | |
| "grad_norm": 2.546875, | |
| "learning_rate": 1.3073779870407539e-05, | |
| "loss": 0.9694, | |
| "mean_token_accuracy": 0.7858038902282715, | |
| "num_tokens": 126465874.0, | |
| "step": 1190 | |
| }, | |
| { | |
| "entropy": 1.9239431992173195, | |
| "epoch": 0.8917078630724746, | |
| "grad_norm": 2.625, | |
| "learning_rate": 1.3020852125450009e-05, | |
| "loss": 0.9928, | |
| "mean_token_accuracy": 0.7798442251980304, | |
| "num_tokens": 126995887.0, | |
| "step": 1195 | |
| }, | |
| { | |
| "entropy": 1.9185133665800094, | |
| "epoch": 0.8954388583154557, | |
| "grad_norm": 2.6875, | |
| "learning_rate": 1.296785067628764e-05, | |
| "loss": 0.9198, | |
| "mean_token_accuracy": 0.7875108510255814, | |
| "num_tokens": 127526712.0, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.8954388583154557, | |
| "eval_entropy": 1.9207860181957894, | |
| "eval_loss": 0.8042152523994446, | |
| "eval_mean_token_accuracy": 0.7863888339512909, | |
| "eval_num_tokens": 127526712.0, | |
| "eval_runtime": 409.4078, | |
| "eval_samples_per_second": 2.118, | |
| "eval_steps_per_second": 0.53, | |
| "step": 1200 | |
| }, | |
| { | |
| "entropy": 1.9089737579226493, | |
| "epoch": 0.8991698535584367, | |
| "grad_norm": 2.609375, | |
| "learning_rate": 1.2914777455981055e-05, | |
| "loss": 0.9846, | |
| "mean_token_accuracy": 0.7735326617956162, | |
| "num_tokens": 128061650.0, | |
| "step": 1205 | |
| }, | |
| { | |
| "entropy": 1.9178216248750686, | |
| "epoch": 0.9029008488014177, | |
| "grad_norm": 2.953125, | |
| "learning_rate": 1.2861634400208494e-05, | |
| "loss": 0.9333, | |
| "mean_token_accuracy": 0.7947493709623814, | |
| "num_tokens": 128594317.0, | |
| "step": 1210 | |
| }, | |
| { | |
| "entropy": 1.9146702647209168, | |
| "epoch": 0.9066318440443989, | |
| "grad_norm": 2.8125, | |
| "learning_rate": 1.2808423447195238e-05, | |
| "loss": 1.021, | |
| "mean_token_accuracy": 0.7814876094460488, | |
| "num_tokens": 129127989.0, | |
| "step": 1215 | |
| }, | |
| { | |
| "entropy": 1.917625893652439, | |
| "epoch": 0.9103628392873799, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 1.27551465376429e-05, | |
| "loss": 0.9356, | |
| "mean_token_accuracy": 0.7922505825757981, | |
| "num_tokens": 129658129.0, | |
| "step": 1220 | |
| }, | |
| { | |
| "entropy": 1.9145172625780105, | |
| "epoch": 0.914093834530361, | |
| "grad_norm": 2.875, | |
| "learning_rate": 1.2701805614658646e-05, | |
| "loss": 0.9872, | |
| "mean_token_accuracy": 0.775139132887125, | |
| "num_tokens": 130190875.0, | |
| "step": 1225 | |
| }, | |
| { | |
| "entropy": 1.9233573004603386, | |
| "epoch": 0.917824829773342, | |
| "grad_norm": 2.984375, | |
| "learning_rate": 1.264840262368434e-05, | |
| "loss": 1.0117, | |
| "mean_token_accuracy": 0.7777254186570645, | |
| "num_tokens": 130723320.0, | |
| "step": 1230 | |
| }, | |
| { | |
| "entropy": 1.9207363352179527, | |
| "epoch": 0.921555825016323, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 1.2594939512425575e-05, | |
| "loss": 0.9916, | |
| "mean_token_accuracy": 0.7813470110297203, | |
| "num_tokens": 131254800.0, | |
| "step": 1235 | |
| }, | |
| { | |
| "entropy": 1.9260804876685143, | |
| "epoch": 0.9252868202593042, | |
| "grad_norm": 2.96875, | |
| "learning_rate": 1.2541418230780636e-05, | |
| "loss": 0.9056, | |
| "mean_token_accuracy": 0.790333466976881, | |
| "num_tokens": 131784122.0, | |
| "step": 1240 | |
| }, | |
| { | |
| "entropy": 1.9206727132201196, | |
| "epoch": 0.9290178155022852, | |
| "grad_norm": 2.875, | |
| "learning_rate": 1.2487840730769393e-05, | |
| "loss": 1.001, | |
| "mean_token_accuracy": 0.7754542909562587, | |
| "num_tokens": 132315594.0, | |
| "step": 1245 | |
| }, | |
| { | |
| "entropy": 1.931351412832737, | |
| "epoch": 0.9327488107452663, | |
| "grad_norm": 2.96875, | |
| "learning_rate": 1.2434208966462113e-05, | |
| "loss": 0.9194, | |
| "mean_token_accuracy": 0.7928143329918385, | |
| "num_tokens": 132845920.0, | |
| "step": 1250 | |
| }, | |
| { | |
| "entropy": 1.9268579319119454, | |
| "epoch": 0.9364798059882473, | |
| "grad_norm": 3.171875, | |
| "learning_rate": 1.238052489390817e-05, | |
| "loss": 1.0312, | |
| "mean_token_accuracy": 0.7688205942511559, | |
| "num_tokens": 133376732.0, | |
| "step": 1255 | |
| }, | |
| { | |
| "entropy": 1.9306054621934892, | |
| "epoch": 0.9402108012312285, | |
| "grad_norm": 2.796875, | |
| "learning_rate": 1.2326790471064715e-05, | |
| "loss": 0.984, | |
| "mean_token_accuracy": 0.7766520656645298, | |
| "num_tokens": 133907577.0, | |
| "step": 1260 | |
| }, | |
| { | |
| "entropy": 1.9358166873455047, | |
| "epoch": 0.9439417964742095, | |
| "grad_norm": 2.859375, | |
| "learning_rate": 1.2273007657725278e-05, | |
| "loss": 0.9288, | |
| "mean_token_accuracy": 0.7995492741465569, | |
| "num_tokens": 134439785.0, | |
| "step": 1265 | |
| }, | |
| { | |
| "entropy": 1.9333247378468514, | |
| "epoch": 0.9476727917171905, | |
| "grad_norm": 2.6875, | |
| "learning_rate": 1.2219178415448271e-05, | |
| "loss": 0.9917, | |
| "mean_token_accuracy": 0.7727632015943527, | |
| "num_tokens": 134969134.0, | |
| "step": 1270 | |
| }, | |
| { | |
| "entropy": 1.9407745644450187, | |
| "epoch": 0.9514037869601716, | |
| "grad_norm": 2.71875, | |
| "learning_rate": 1.216530470748546e-05, | |
| "loss": 0.9204, | |
| "mean_token_accuracy": 0.7908377006649971, | |
| "num_tokens": 135497613.0, | |
| "step": 1275 | |
| }, | |
| { | |
| "entropy": 1.9259536176919938, | |
| "epoch": 0.9551347822031527, | |
| "grad_norm": 2.9375, | |
| "learning_rate": 1.2111388498710347e-05, | |
| "loss": 0.9738, | |
| "mean_token_accuracy": 0.7784877195954323, | |
| "num_tokens": 136028881.0, | |
| "step": 1280 | |
| }, | |
| { | |
| "entropy": 1.925316996872425, | |
| "epoch": 0.9588657774461338, | |
| "grad_norm": 2.8125, | |
| "learning_rate": 1.2057431755546535e-05, | |
| "loss": 1.01, | |
| "mean_token_accuracy": 0.7734282180666924, | |
| "num_tokens": 136560459.0, | |
| "step": 1285 | |
| }, | |
| { | |
| "entropy": 1.9157800003886223, | |
| "epoch": 0.9625967726891148, | |
| "grad_norm": 2.546875, | |
| "learning_rate": 1.2003436445895973e-05, | |
| "loss": 0.9531, | |
| "mean_token_accuracy": 0.7834272600710392, | |
| "num_tokens": 137092130.0, | |
| "step": 1290 | |
| }, | |
| { | |
| "entropy": 1.90481239259243, | |
| "epoch": 0.9663277679320958, | |
| "grad_norm": 2.421875, | |
| "learning_rate": 1.194940453906721e-05, | |
| "loss": 0.9573, | |
| "mean_token_accuracy": 0.786161408573389, | |
| "num_tokens": 137623136.0, | |
| "step": 1295 | |
| }, | |
| { | |
| "entropy": 1.8986893266439437, | |
| "epoch": 0.970058763175077, | |
| "grad_norm": 2.765625, | |
| "learning_rate": 1.189533800570356e-05, | |
| "loss": 1.0726, | |
| "mean_token_accuracy": 0.764766127616167, | |
| "num_tokens": 138155488.0, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.970058763175077, | |
| "eval_entropy": 1.9125681104747931, | |
| "eval_loss": 0.8023692965507507, | |
| "eval_mean_token_accuracy": 0.7871058926604311, | |
| "eval_num_tokens": 138155488.0, | |
| "eval_runtime": 411.7048, | |
| "eval_samples_per_second": 2.106, | |
| "eval_steps_per_second": 0.527, | |
| "step": 1300 | |
| }, | |
| { | |
| "entropy": 1.909130072593689, | |
| "epoch": 0.973789758418058, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 1.1841238817711226e-05, | |
| "loss": 1.0111, | |
| "mean_token_accuracy": 0.7737887717783452, | |
| "num_tokens": 138685815.0, | |
| "step": 1305 | |
| }, | |
| { | |
| "entropy": 1.914137528836727, | |
| "epoch": 0.9775207536610391, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 1.1787108948187395e-05, | |
| "loss": 0.9504, | |
| "mean_token_accuracy": 0.7876806251704693, | |
| "num_tokens": 139214572.0, | |
| "step": 1310 | |
| }, | |
| { | |
| "entropy": 1.923145028948784, | |
| "epoch": 0.9812517489040201, | |
| "grad_norm": 2.546875, | |
| "learning_rate": 1.1732950371348262e-05, | |
| "loss": 0.9302, | |
| "mean_token_accuracy": 0.7920562744140625, | |
| "num_tokens": 139743508.0, | |
| "step": 1315 | |
| }, | |
| { | |
| "entropy": 1.916971817612648, | |
| "epoch": 0.9849827441470013, | |
| "grad_norm": 2.703125, | |
| "learning_rate": 1.1678765062457023e-05, | |
| "loss": 0.9254, | |
| "mean_token_accuracy": 0.7934870257973671, | |
| "num_tokens": 140274750.0, | |
| "step": 1320 | |
| }, | |
| { | |
| "entropy": 1.9185368612408638, | |
| "epoch": 0.9887137393899823, | |
| "grad_norm": 2.703125, | |
| "learning_rate": 1.1624554997751853e-05, | |
| "loss": 0.8702, | |
| "mean_token_accuracy": 0.7973764210939407, | |
| "num_tokens": 140807008.0, | |
| "step": 1325 | |
| }, | |
| { | |
| "entropy": 1.9259465247392655, | |
| "epoch": 0.9924447346329633, | |
| "grad_norm": 2.78125, | |
| "learning_rate": 1.157032215437381e-05, | |
| "loss": 0.9814, | |
| "mean_token_accuracy": 0.7817091770470143, | |
| "num_tokens": 141336497.0, | |
| "step": 1330 | |
| }, | |
| { | |
| "entropy": 1.9247869119048118, | |
| "epoch": 0.9961757298759444, | |
| "grad_norm": 2.96875, | |
| "learning_rate": 1.1516068510294735e-05, | |
| "loss": 0.9902, | |
| "mean_token_accuracy": 0.7780245266854763, | |
| "num_tokens": 141867864.0, | |
| "step": 1335 | |
| }, | |
| { | |
| "entropy": 1.9211131125688552, | |
| "epoch": 0.9999067251189254, | |
| "grad_norm": 2.875, | |
| "learning_rate": 1.1461796044245108e-05, | |
| "loss": 0.9372, | |
| "mean_token_accuracy": 0.7970803648233413, | |
| "num_tokens": 142401439.0, | |
| "step": 1340 | |
| }, | |
| { | |
| "entropy": 1.9021222645586187, | |
| "epoch": 1.0029847961943847, | |
| "grad_norm": 2.765625, | |
| "learning_rate": 1.1407506735641882e-05, | |
| "loss": 1.0408, | |
| "mean_token_accuracy": 0.7564558558391802, | |
| "num_tokens": 142842106.0, | |
| "step": 1345 | |
| }, | |
| { | |
| "entropy": 1.91049023270607, | |
| "epoch": 1.006715791437366, | |
| "grad_norm": 2.453125, | |
| "learning_rate": 1.1353202564516287e-05, | |
| "loss": 0.9824, | |
| "mean_token_accuracy": 0.7773703202605248, | |
| "num_tokens": 143375469.0, | |
| "step": 1350 | |
| }, | |
| { | |
| "entropy": 1.9135325998067856, | |
| "epoch": 1.010446786680347, | |
| "grad_norm": 3.578125, | |
| "learning_rate": 1.1298885511441618e-05, | |
| "loss": 0.9687, | |
| "mean_token_accuracy": 0.7757138065993786, | |
| "num_tokens": 143908345.0, | |
| "step": 1355 | |
| }, | |
| { | |
| "entropy": 1.9061910092830658, | |
| "epoch": 1.014177781923328, | |
| "grad_norm": 2.765625, | |
| "learning_rate": 1.1244557557461002e-05, | |
| "loss": 0.9514, | |
| "mean_token_accuracy": 0.7835961289703846, | |
| "num_tokens": 144437756.0, | |
| "step": 1360 | |
| }, | |
| { | |
| "entropy": 1.9110153183341025, | |
| "epoch": 1.0179087771663091, | |
| "grad_norm": 2.796875, | |
| "learning_rate": 1.1190220684015129e-05, | |
| "loss": 0.9301, | |
| "mean_token_accuracy": 0.7900028511881828, | |
| "num_tokens": 144966417.0, | |
| "step": 1365 | |
| }, | |
| { | |
| "entropy": 1.9046073108911514, | |
| "epoch": 1.0216397724092903, | |
| "grad_norm": 2.71875, | |
| "learning_rate": 1.1135876872870018e-05, | |
| "loss": 0.9883, | |
| "mean_token_accuracy": 0.7769135765731334, | |
| "num_tokens": 145499906.0, | |
| "step": 1370 | |
| }, | |
| { | |
| "entropy": 1.9097348660230637, | |
| "epoch": 1.0253707676522712, | |
| "grad_norm": 2.609375, | |
| "learning_rate": 1.1081528106044704e-05, | |
| "loss": 1.0131, | |
| "mean_token_accuracy": 0.7666771307587623, | |
| "num_tokens": 146031293.0, | |
| "step": 1375 | |
| }, | |
| { | |
| "entropy": 1.9049879655241966, | |
| "epoch": 1.0291017628952523, | |
| "grad_norm": 2.8125, | |
| "learning_rate": 1.1027176365738965e-05, | |
| "loss": 1.025, | |
| "mean_token_accuracy": 0.7679546378552914, | |
| "num_tokens": 146564883.0, | |
| "step": 1380 | |
| }, | |
| { | |
| "entropy": 1.9138263523578645, | |
| "epoch": 1.0328327581382333, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 1.0972823634261038e-05, | |
| "loss": 0.9745, | |
| "mean_token_accuracy": 0.784792798012495, | |
| "num_tokens": 147097765.0, | |
| "step": 1385 | |
| }, | |
| { | |
| "entropy": 1.9188172191381454, | |
| "epoch": 1.0365637533812144, | |
| "grad_norm": 2.875, | |
| "learning_rate": 1.0918471893955303e-05, | |
| "loss": 1.0081, | |
| "mean_token_accuracy": 0.7770697064697742, | |
| "num_tokens": 147628650.0, | |
| "step": 1390 | |
| }, | |
| { | |
| "entropy": 1.9182799458503723, | |
| "epoch": 1.0402947486241956, | |
| "grad_norm": 2.515625, | |
| "learning_rate": 1.0864123127129987e-05, | |
| "loss": 0.9117, | |
| "mean_token_accuracy": 0.8060022041201591, | |
| "num_tokens": 148159888.0, | |
| "step": 1395 | |
| }, | |
| { | |
| "entropy": 1.9043408751487731, | |
| "epoch": 1.0440257438671765, | |
| "grad_norm": 2.859375, | |
| "learning_rate": 1.0809779315984874e-05, | |
| "loss": 0.9451, | |
| "mean_token_accuracy": 0.7813556417822838, | |
| "num_tokens": 148691293.0, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.0440257438671765, | |
| "eval_entropy": 1.914900781372176, | |
| "eval_loss": 0.8001424670219421, | |
| "eval_mean_token_accuracy": 0.7873817116434124, | |
| "eval_num_tokens": 148691293.0, | |
| "eval_runtime": 408.5753, | |
| "eval_samples_per_second": 2.122, | |
| "eval_steps_per_second": 0.531, | |
| "step": 1400 | |
| }, | |
| { | |
| "entropy": 1.906543317437172, | |
| "epoch": 1.0477567391101577, | |
| "grad_norm": 2.828125, | |
| "learning_rate": 1.0755442442539004e-05, | |
| "loss": 0.9118, | |
| "mean_token_accuracy": 0.7968203231692315, | |
| "num_tokens": 149221200.0, | |
| "step": 1405 | |
| }, | |
| { | |
| "entropy": 1.8938933908939362, | |
| "epoch": 1.0514877343531388, | |
| "grad_norm": 2.75, | |
| "learning_rate": 1.0701114488558387e-05, | |
| "loss": 0.9224, | |
| "mean_token_accuracy": 0.7925568759441376, | |
| "num_tokens": 149754700.0, | |
| "step": 1410 | |
| }, | |
| { | |
| "entropy": 1.9065657809376717, | |
| "epoch": 1.0552187295961197, | |
| "grad_norm": 2.609375, | |
| "learning_rate": 1.0646797435483716e-05, | |
| "loss": 0.9389, | |
| "mean_token_accuracy": 0.7918999843299389, | |
| "num_tokens": 150284180.0, | |
| "step": 1415 | |
| }, | |
| { | |
| "entropy": 1.9041003629565239, | |
| "epoch": 1.0589497248391009, | |
| "grad_norm": 3.09375, | |
| "learning_rate": 1.0592493264358122e-05, | |
| "loss": 0.9762, | |
| "mean_token_accuracy": 0.7818893454968929, | |
| "num_tokens": 150815166.0, | |
| "step": 1420 | |
| }, | |
| { | |
| "entropy": 1.8972408846020699, | |
| "epoch": 1.0626807200820818, | |
| "grad_norm": 2.8125, | |
| "learning_rate": 1.0538203955754893e-05, | |
| "loss": 1.0264, | |
| "mean_token_accuracy": 0.7636294946074486, | |
| "num_tokens": 151348074.0, | |
| "step": 1425 | |
| }, | |
| { | |
| "entropy": 1.9111024513840675, | |
| "epoch": 1.066411715325063, | |
| "grad_norm": 2.75, | |
| "learning_rate": 1.0483931489705267e-05, | |
| "loss": 0.9958, | |
| "mean_token_accuracy": 0.7807611756026744, | |
| "num_tokens": 151878240.0, | |
| "step": 1430 | |
| }, | |
| { | |
| "entropy": 1.8972911700606345, | |
| "epoch": 1.070142710568044, | |
| "grad_norm": 2.765625, | |
| "learning_rate": 1.0429677845626191e-05, | |
| "loss": 0.92, | |
| "mean_token_accuracy": 0.7862489655613899, | |
| "num_tokens": 152411551.0, | |
| "step": 1435 | |
| }, | |
| { | |
| "entropy": 1.8995465740561486, | |
| "epoch": 1.073873705811025, | |
| "grad_norm": 2.609375, | |
| "learning_rate": 1.0375445002248153e-05, | |
| "loss": 0.9829, | |
| "mean_token_accuracy": 0.779705585539341, | |
| "num_tokens": 152944517.0, | |
| "step": 1440 | |
| }, | |
| { | |
| "entropy": 1.9031965538859368, | |
| "epoch": 1.0776047010540062, | |
| "grad_norm": 2.578125, | |
| "learning_rate": 1.0321234937542982e-05, | |
| "loss": 0.9502, | |
| "mean_token_accuracy": 0.7840150997042656, | |
| "num_tokens": 153477408.0, | |
| "step": 1445 | |
| }, | |
| { | |
| "entropy": 1.900654748082161, | |
| "epoch": 1.0813356962969873, | |
| "grad_norm": 2.71875, | |
| "learning_rate": 1.0267049628651744e-05, | |
| "loss": 0.9186, | |
| "mean_token_accuracy": 0.7939566880464554, | |
| "num_tokens": 154009646.0, | |
| "step": 1450 | |
| }, | |
| { | |
| "entropy": 1.9173641785979272, | |
| "epoch": 1.0850666915399683, | |
| "grad_norm": 2.921875, | |
| "learning_rate": 1.0212891051812606e-05, | |
| "loss": 0.9827, | |
| "mean_token_accuracy": 0.7764195807278156, | |
| "num_tokens": 154538093.0, | |
| "step": 1455 | |
| }, | |
| { | |
| "entropy": 1.9076469540596008, | |
| "epoch": 1.0887976867829494, | |
| "grad_norm": 2.71875, | |
| "learning_rate": 1.0158761182288776e-05, | |
| "loss": 0.9337, | |
| "mean_token_accuracy": 0.7856325849890708, | |
| "num_tokens": 155069159.0, | |
| "step": 1460 | |
| }, | |
| { | |
| "entropy": 1.9166174724698066, | |
| "epoch": 1.0925286820259303, | |
| "grad_norm": 2.671875, | |
| "learning_rate": 1.0104661994296445e-05, | |
| "loss": 0.9603, | |
| "mean_token_accuracy": 0.7911513254046441, | |
| "num_tokens": 155599420.0, | |
| "step": 1465 | |
| }, | |
| { | |
| "entropy": 1.9228487834334373, | |
| "epoch": 1.0962596772689115, | |
| "grad_norm": 2.75, | |
| "learning_rate": 1.0050595460932795e-05, | |
| "loss": 0.9645, | |
| "mean_token_accuracy": 0.7795494057238102, | |
| "num_tokens": 156130263.0, | |
| "step": 1470 | |
| }, | |
| { | |
| "entropy": 1.8965369552373885, | |
| "epoch": 1.0999906725118926, | |
| "grad_norm": 2.546875, | |
| "learning_rate": 9.99656355410403e-06, | |
| "loss": 1.0223, | |
| "mean_token_accuracy": 0.7734660752117634, | |
| "num_tokens": 156663734.0, | |
| "step": 1475 | |
| }, | |
| { | |
| "entropy": 1.9180607333779336, | |
| "epoch": 1.1037216677548736, | |
| "grad_norm": 2.75, | |
| "learning_rate": 9.942568244453469e-06, | |
| "loss": 0.9277, | |
| "mean_token_accuracy": 0.7880247853696346, | |
| "num_tokens": 157194630.0, | |
| "step": 1480 | |
| }, | |
| { | |
| "entropy": 1.91579008102417, | |
| "epoch": 1.1074526629978547, | |
| "grad_norm": 2.46875, | |
| "learning_rate": 9.88861150128965e-06, | |
| "loss": 0.9902, | |
| "mean_token_accuracy": 0.7840256102383136, | |
| "num_tokens": 157725220.0, | |
| "step": 1485 | |
| }, | |
| { | |
| "entropy": 1.918996299803257, | |
| "epoch": 1.1111836582408356, | |
| "grad_norm": 2.765625, | |
| "learning_rate": 9.834695292514545e-06, | |
| "loss": 0.8728, | |
| "mean_token_accuracy": 0.802612192928791, | |
| "num_tokens": 158254991.0, | |
| "step": 1490 | |
| }, | |
| { | |
| "entropy": 1.921280962228775, | |
| "epoch": 1.1149146534838168, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 9.78082158455173e-06, | |
| "loss": 0.9266, | |
| "mean_token_accuracy": 0.7892040610313416, | |
| "num_tokens": 158785345.0, | |
| "step": 1495 | |
| }, | |
| { | |
| "entropy": 1.9033719599246979, | |
| "epoch": 1.118645648726798, | |
| "grad_norm": 2.71875, | |
| "learning_rate": 9.726992342274726e-06, | |
| "loss": 1.0086, | |
| "mean_token_accuracy": 0.7704753667116165, | |
| "num_tokens": 159318008.0, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.118645648726798, | |
| "eval_entropy": 1.9108136875838178, | |
| "eval_loss": 0.7981786131858826, | |
| "eval_mean_token_accuracy": 0.7881955545618787, | |
| "eval_num_tokens": 159318008.0, | |
| "eval_runtime": 421.7688, | |
| "eval_samples_per_second": 2.056, | |
| "eval_steps_per_second": 0.514, | |
| "step": 1500 | |
| }, | |
| { | |
| "entropy": 1.9149455368518828, | |
| "epoch": 1.1223766439697789, | |
| "grad_norm": 2.921875, | |
| "learning_rate": 9.673209528935288e-06, | |
| "loss": 0.9201, | |
| "mean_token_accuracy": 0.7925434753298759, | |
| "num_tokens": 159850478.0, | |
| "step": 1505 | |
| }, | |
| { | |
| "entropy": 1.8980061173439027, | |
| "epoch": 1.12610763921276, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 9.619475106091832e-06, | |
| "loss": 0.9597, | |
| "mean_token_accuracy": 0.7821764424443245, | |
| "num_tokens": 160381164.0, | |
| "step": 1510 | |
| }, | |
| { | |
| "entropy": 1.901640383899212, | |
| "epoch": 1.1298386344557412, | |
| "grad_norm": 3.359375, | |
| "learning_rate": 9.565791033537888e-06, | |
| "loss": 0.9118, | |
| "mean_token_accuracy": 0.7857741206884384, | |
| "num_tokens": 160914862.0, | |
| "step": 1515 | |
| }, | |
| { | |
| "entropy": 1.895643164217472, | |
| "epoch": 1.133569629698722, | |
| "grad_norm": 2.90625, | |
| "learning_rate": 9.512159269230608e-06, | |
| "loss": 0.9746, | |
| "mean_token_accuracy": 0.7788461379706859, | |
| "num_tokens": 161447626.0, | |
| "step": 1520 | |
| }, | |
| { | |
| "entropy": 1.907567872107029, | |
| "epoch": 1.1373006249417033, | |
| "grad_norm": 2.765625, | |
| "learning_rate": 9.458581769219369e-06, | |
| "loss": 0.9623, | |
| "mean_token_accuracy": 0.7834442459046841, | |
| "num_tokens": 161979709.0, | |
| "step": 1525 | |
| }, | |
| { | |
| "entropy": 1.913025863468647, | |
| "epoch": 1.1410316201846842, | |
| "grad_norm": 2.765625, | |
| "learning_rate": 9.40506048757443e-06, | |
| "loss": 0.9361, | |
| "mean_token_accuracy": 0.7849182806909084, | |
| "num_tokens": 162509479.0, | |
| "step": 1530 | |
| }, | |
| { | |
| "entropy": 1.9022073447704315, | |
| "epoch": 1.1447626154276653, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 9.351597376315661e-06, | |
| "loss": 0.963, | |
| "mean_token_accuracy": 0.7830614671111107, | |
| "num_tokens": 163041559.0, | |
| "step": 1535 | |
| }, | |
| { | |
| "entropy": 1.9128715977072717, | |
| "epoch": 1.1484936106706465, | |
| "grad_norm": 3.171875, | |
| "learning_rate": 9.298194385341355e-06, | |
| "loss": 0.9564, | |
| "mean_token_accuracy": 0.7814685918390751, | |
| "num_tokens": 163572658.0, | |
| "step": 1540 | |
| }, | |
| { | |
| "entropy": 1.914643220603466, | |
| "epoch": 1.1522246059136274, | |
| "grad_norm": 3.296875, | |
| "learning_rate": 9.244853462357103e-06, | |
| "loss": 0.9746, | |
| "mean_token_accuracy": 0.7881543360650539, | |
| "num_tokens": 164105639.0, | |
| "step": 1545 | |
| }, | |
| { | |
| "entropy": 1.9207996159791947, | |
| "epoch": 1.1559556011566086, | |
| "grad_norm": 2.875, | |
| "learning_rate": 9.191576552804767e-06, | |
| "loss": 0.9381, | |
| "mean_token_accuracy": 0.7910158529877662, | |
| "num_tokens": 164638056.0, | |
| "step": 1550 | |
| }, | |
| { | |
| "entropy": 1.9149420797824859, | |
| "epoch": 1.1596865963995895, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 9.13836559979151e-06, | |
| "loss": 0.9308, | |
| "mean_token_accuracy": 0.7858420059084892, | |
| "num_tokens": 165170709.0, | |
| "step": 1555 | |
| }, | |
| { | |
| "entropy": 1.9160060003399848, | |
| "epoch": 1.1634175916425706, | |
| "grad_norm": 2.671875, | |
| "learning_rate": 9.08522254401895e-06, | |
| "loss": 0.9486, | |
| "mean_token_accuracy": 0.7823890775442124, | |
| "num_tokens": 165701451.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "entropy": 1.916386367380619, | |
| "epoch": 1.1671485868855518, | |
| "grad_norm": 3.1875, | |
| "learning_rate": 9.032149323712359e-06, | |
| "loss": 1.0188, | |
| "mean_token_accuracy": 0.7758285783231258, | |
| "num_tokens": 166233264.0, | |
| "step": 1565 | |
| }, | |
| { | |
| "entropy": 1.9224628746509551, | |
| "epoch": 1.1708795821285327, | |
| "grad_norm": 2.859375, | |
| "learning_rate": 8.979147874549989e-06, | |
| "loss": 1.0125, | |
| "mean_token_accuracy": 0.7762011967599391, | |
| "num_tokens": 166764218.0, | |
| "step": 1570 | |
| }, | |
| { | |
| "entropy": 1.9250923693180084, | |
| "epoch": 1.1746105773715139, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 8.926220129592464e-06, | |
| "loss": 0.9431, | |
| "mean_token_accuracy": 0.7869702532887459, | |
| "num_tokens": 167294808.0, | |
| "step": 1575 | |
| }, | |
| { | |
| "entropy": 1.9111168920993804, | |
| "epoch": 1.178341572614495, | |
| "grad_norm": 2.75, | |
| "learning_rate": 8.873368019212274e-06, | |
| "loss": 0.9434, | |
| "mean_token_accuracy": 0.789091457426548, | |
| "num_tokens": 167826649.0, | |
| "step": 1580 | |
| }, | |
| { | |
| "entropy": 1.9143835335969925, | |
| "epoch": 1.182072567857476, | |
| "grad_norm": 2.859375, | |
| "learning_rate": 8.820593471023376e-06, | |
| "loss": 0.8946, | |
| "mean_token_accuracy": 0.7969313278794289, | |
| "num_tokens": 168358668.0, | |
| "step": 1585 | |
| }, | |
| { | |
| "entropy": 1.9125552743673324, | |
| "epoch": 1.185803563100457, | |
| "grad_norm": 2.75, | |
| "learning_rate": 8.7678984098109e-06, | |
| "loss": 0.9983, | |
| "mean_token_accuracy": 0.769627034664154, | |
| "num_tokens": 168891441.0, | |
| "step": 1590 | |
| }, | |
| { | |
| "entropy": 1.9116299599409103, | |
| "epoch": 1.189534558343438, | |
| "grad_norm": 2.96875, | |
| "learning_rate": 8.715284757460931e-06, | |
| "loss": 0.9524, | |
| "mean_token_accuracy": 0.7888155646622181, | |
| "num_tokens": 169421986.0, | |
| "step": 1595 | |
| }, | |
| { | |
| "entropy": 1.919787773489952, | |
| "epoch": 1.1932655535864192, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 8.662754432890425e-06, | |
| "loss": 0.9749, | |
| "mean_token_accuracy": 0.7735044836997986, | |
| "num_tokens": 169954027.0, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.1932655535864192, | |
| "eval_entropy": 1.9173187561298846, | |
| "eval_loss": 0.7971454858779907, | |
| "eval_mean_token_accuracy": 0.7884338443180383, | |
| "eval_num_tokens": 169954027.0, | |
| "eval_runtime": 410.1401, | |
| "eval_samples_per_second": 2.114, | |
| "eval_steps_per_second": 0.529, | |
| "step": 1600 | |
| }, | |
| { | |
| "entropy": 1.9170388147234916, | |
| "epoch": 1.1969965488294003, | |
| "grad_norm": 2.796875, | |
| "learning_rate": 8.610309351977229e-06, | |
| "loss": 0.9239, | |
| "mean_token_accuracy": 0.7988493584096432, | |
| "num_tokens": 170485056.0, | |
| "step": 1605 | |
| }, | |
| { | |
| "entropy": 1.9125929340720176, | |
| "epoch": 1.2007275440723812, | |
| "grad_norm": 2.515625, | |
| "learning_rate": 8.557951427490179e-06, | |
| "loss": 0.9515, | |
| "mean_token_accuracy": 0.783885195851326, | |
| "num_tokens": 171014926.0, | |
| "step": 1610 | |
| }, | |
| { | |
| "entropy": 1.9132960721850396, | |
| "epoch": 1.2044585393153624, | |
| "grad_norm": 2.71875, | |
| "learning_rate": 8.505682569019364e-06, | |
| "loss": 0.9995, | |
| "mean_token_accuracy": 0.773869439214468, | |
| "num_tokens": 171545131.0, | |
| "step": 1615 | |
| }, | |
| { | |
| "entropy": 1.9141040802001954, | |
| "epoch": 1.2081895345583433, | |
| "grad_norm": 2.75, | |
| "learning_rate": 8.453504682906475e-06, | |
| "loss": 0.9394, | |
| "mean_token_accuracy": 0.7839238695800305, | |
| "num_tokens": 172077112.0, | |
| "step": 1620 | |
| }, | |
| { | |
| "entropy": 1.9142849922180176, | |
| "epoch": 1.2119205298013245, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 8.401419672175275e-06, | |
| "loss": 0.9279, | |
| "mean_token_accuracy": 0.7974015466868878, | |
| "num_tokens": 172608007.0, | |
| "step": 1625 | |
| }, | |
| { | |
| "entropy": 1.9144698426127433, | |
| "epoch": 1.2156515250443056, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 8.349429436462177e-06, | |
| "loss": 0.9012, | |
| "mean_token_accuracy": 0.7962669752538204, | |
| "num_tokens": 173140132.0, | |
| "step": 1630 | |
| }, | |
| { | |
| "entropy": 1.9135999783873558, | |
| "epoch": 1.2193825202872866, | |
| "grad_norm": 2.921875, | |
| "learning_rate": 8.29753587194699e-06, | |
| "loss": 1.0005, | |
| "mean_token_accuracy": 0.7792818926274776, | |
| "num_tokens": 173671827.0, | |
| "step": 1635 | |
| }, | |
| { | |
| "entropy": 1.9121680706739426, | |
| "epoch": 1.2231135155302677, | |
| "grad_norm": 2.9375, | |
| "learning_rate": 8.245740871283738e-06, | |
| "loss": 0.9935, | |
| "mean_token_accuracy": 0.777762345224619, | |
| "num_tokens": 174204179.0, | |
| "step": 1640 | |
| }, | |
| { | |
| "entropy": 1.9009287789463998, | |
| "epoch": 1.2268445107732489, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 8.194046323531635e-06, | |
| "loss": 1.035, | |
| "mean_token_accuracy": 0.7625086784362793, | |
| "num_tokens": 174736876.0, | |
| "step": 1645 | |
| }, | |
| { | |
| "entropy": 1.9046483889222146, | |
| "epoch": 1.2305755060162298, | |
| "grad_norm": 2.796875, | |
| "learning_rate": 8.142454114086198e-06, | |
| "loss": 0.975, | |
| "mean_token_accuracy": 0.7746729388833046, | |
| "num_tokens": 175268815.0, | |
| "step": 1650 | |
| }, | |
| { | |
| "entropy": 1.9050630331039429, | |
| "epoch": 1.234306501259211, | |
| "grad_norm": 2.5625, | |
| "learning_rate": 8.090966124610479e-06, | |
| "loss": 0.9344, | |
| "mean_token_accuracy": 0.7914486967027188, | |
| "num_tokens": 175801245.0, | |
| "step": 1655 | |
| }, | |
| { | |
| "entropy": 1.9112103179097175, | |
| "epoch": 1.238037496502192, | |
| "grad_norm": 2.78125, | |
| "learning_rate": 8.039584232966437e-06, | |
| "loss": 0.98, | |
| "mean_token_accuracy": 0.7776268184185028, | |
| "num_tokens": 176331996.0, | |
| "step": 1660 | |
| }, | |
| { | |
| "entropy": 1.9143457114696503, | |
| "epoch": 1.241768491745173, | |
| "grad_norm": 3.0, | |
| "learning_rate": 7.988310313146439e-06, | |
| "loss": 0.936, | |
| "mean_token_accuracy": 0.7907832115888596, | |
| "num_tokens": 176865230.0, | |
| "step": 1665 | |
| }, | |
| { | |
| "entropy": 1.9180011659860612, | |
| "epoch": 1.2454994869881542, | |
| "grad_norm": 2.453125, | |
| "learning_rate": 7.937146235204927e-06, | |
| "loss": 1.0015, | |
| "mean_token_accuracy": 0.7779019854962825, | |
| "num_tokens": 177393698.0, | |
| "step": 1670 | |
| }, | |
| { | |
| "entropy": 1.9097063705325126, | |
| "epoch": 1.249230482231135, | |
| "grad_norm": 2.484375, | |
| "learning_rate": 7.886093865190201e-06, | |
| "loss": 1.0247, | |
| "mean_token_accuracy": 0.7732160426676273, | |
| "num_tokens": 177925791.0, | |
| "step": 1675 | |
| }, | |
| { | |
| "entropy": 1.907798358798027, | |
| "epoch": 1.2529614774741162, | |
| "grad_norm": 2.625, | |
| "learning_rate": 7.83515506507637e-06, | |
| "loss": 1.018, | |
| "mean_token_accuracy": 0.7696801349520683, | |
| "num_tokens": 178457035.0, | |
| "step": 1680 | |
| }, | |
| { | |
| "entropy": 1.9117656916379928, | |
| "epoch": 1.2566924727170972, | |
| "grad_norm": 2.921875, | |
| "learning_rate": 7.784331692695447e-06, | |
| "loss": 0.9456, | |
| "mean_token_accuracy": 0.7896642990410327, | |
| "num_tokens": 178987947.0, | |
| "step": 1685 | |
| }, | |
| { | |
| "entropy": 1.9108289450407028, | |
| "epoch": 1.2604234679600783, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 7.73362560166957e-06, | |
| "loss": 0.9616, | |
| "mean_token_accuracy": 0.7905923403799534, | |
| "num_tokens": 179520270.0, | |
| "step": 1690 | |
| }, | |
| { | |
| "entropy": 1.9133642435073852, | |
| "epoch": 1.2641544632030595, | |
| "grad_norm": 2.75, | |
| "learning_rate": 7.683038641343418e-06, | |
| "loss": 0.975, | |
| "mean_token_accuracy": 0.7816100649535656, | |
| "num_tokens": 180050074.0, | |
| "step": 1695 | |
| }, | |
| { | |
| "entropy": 1.918484927713871, | |
| "epoch": 1.2678854584460404, | |
| "grad_norm": 3.109375, | |
| "learning_rate": 7.63257265671675e-06, | |
| "loss": 0.9223, | |
| "mean_token_accuracy": 0.8018887743353844, | |
| "num_tokens": 180583004.0, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.2678854584460404, | |
| "eval_entropy": 1.9196278774243896, | |
| "eval_loss": 0.7961597442626953, | |
| "eval_mean_token_accuracy": 0.78862205683361, | |
| "eval_num_tokens": 180583004.0, | |
| "eval_runtime": 410.4519, | |
| "eval_samples_per_second": 2.112, | |
| "eval_steps_per_second": 0.529, | |
| "step": 1700 | |
| }, | |
| { | |
| "entropy": 1.9090944886207581, | |
| "epoch": 1.2716164536890215, | |
| "grad_norm": 2.96875, | |
| "learning_rate": 7.582229488377117e-06, | |
| "loss": 0.9635, | |
| "mean_token_accuracy": 0.7776286259293557, | |
| "num_tokens": 181116350.0, | |
| "step": 1705 | |
| }, | |
| { | |
| "entropy": 1.915034532546997, | |
| "epoch": 1.2753474489320027, | |
| "grad_norm": 2.625, | |
| "learning_rate": 7.5320109724327394e-06, | |
| "loss": 0.9893, | |
| "mean_token_accuracy": 0.7796139396727085, | |
| "num_tokens": 181647859.0, | |
| "step": 1710 | |
| }, | |
| { | |
| "entropy": 1.9097247406840325, | |
| "epoch": 1.2790784441749836, | |
| "grad_norm": 2.671875, | |
| "learning_rate": 7.4819189404455275e-06, | |
| "loss": 0.9614, | |
| "mean_token_accuracy": 0.778455737233162, | |
| "num_tokens": 182176933.0, | |
| "step": 1715 | |
| }, | |
| { | |
| "entropy": 1.9054157629609108, | |
| "epoch": 1.2828094394179648, | |
| "grad_norm": 2.796875, | |
| "learning_rate": 7.431955219364293e-06, | |
| "loss": 0.9687, | |
| "mean_token_accuracy": 0.7882591933012009, | |
| "num_tokens": 182706541.0, | |
| "step": 1720 | |
| }, | |
| { | |
| "entropy": 1.9075705125927924, | |
| "epoch": 1.286540434660946, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 7.38212163145811e-06, | |
| "loss": 0.9315, | |
| "mean_token_accuracy": 0.7873170509934425, | |
| "num_tokens": 183239225.0, | |
| "step": 1725 | |
| }, | |
| { | |
| "entropy": 1.9072406858205795, | |
| "epoch": 1.2902714299039268, | |
| "grad_norm": 2.75, | |
| "learning_rate": 7.33241999424986e-06, | |
| "loss": 0.8958, | |
| "mean_token_accuracy": 0.7974990576505661, | |
| "num_tokens": 183770965.0, | |
| "step": 1730 | |
| }, | |
| { | |
| "entropy": 1.9208739027380943, | |
| "epoch": 1.294002425146908, | |
| "grad_norm": 2.828125, | |
| "learning_rate": 7.282852120449926e-06, | |
| "loss": 0.9611, | |
| "mean_token_accuracy": 0.7872603751718998, | |
| "num_tokens": 184304098.0, | |
| "step": 1735 | |
| }, | |
| { | |
| "entropy": 1.912934736907482, | |
| "epoch": 1.297733420389889, | |
| "grad_norm": 2.90625, | |
| "learning_rate": 7.2334198178901125e-06, | |
| "loss": 1.0037, | |
| "mean_token_accuracy": 0.7736862108111382, | |
| "num_tokens": 184835401.0, | |
| "step": 1740 | |
| }, | |
| { | |
| "entropy": 1.9067255914211274, | |
| "epoch": 1.30146441563287, | |
| "grad_norm": 2.984375, | |
| "learning_rate": 7.184124889457678e-06, | |
| "loss": 0.9615, | |
| "mean_token_accuracy": 0.7750180624425411, | |
| "num_tokens": 185366030.0, | |
| "step": 1745 | |
| }, | |
| { | |
| "entropy": 1.915813611447811, | |
| "epoch": 1.305195410875851, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 7.134969133029597e-06, | |
| "loss": 0.9655, | |
| "mean_token_accuracy": 0.7763230137526989, | |
| "num_tokens": 185898027.0, | |
| "step": 1750 | |
| }, | |
| { | |
| "entropy": 1.9158352181315421, | |
| "epoch": 1.3089264061188322, | |
| "grad_norm": 2.9375, | |
| "learning_rate": 7.085954341406977e-06, | |
| "loss": 0.9449, | |
| "mean_token_accuracy": 0.7908552013337612, | |
| "num_tokens": 186433530.0, | |
| "step": 1755 | |
| }, | |
| { | |
| "entropy": 1.9180777758359908, | |
| "epoch": 1.3126574013618133, | |
| "grad_norm": 3.390625, | |
| "learning_rate": 7.0370823022496895e-06, | |
| "loss": 0.9632, | |
| "mean_token_accuracy": 0.7842883773148059, | |
| "num_tokens": 186965777.0, | |
| "step": 1760 | |
| }, | |
| { | |
| "entropy": 1.9151813015341759, | |
| "epoch": 1.3163883966047942, | |
| "grad_norm": 3.4375, | |
| "learning_rate": 6.988354798011157e-06, | |
| "loss": 1.0085, | |
| "mean_token_accuracy": 0.7796649239957333, | |
| "num_tokens": 187496044.0, | |
| "step": 1765 | |
| }, | |
| { | |
| "entropy": 1.9258656322956085, | |
| "epoch": 1.3201193918477754, | |
| "grad_norm": 2.625, | |
| "learning_rate": 6.939773605873343e-06, | |
| "loss": 0.9668, | |
| "mean_token_accuracy": 0.7782830119132995, | |
| "num_tokens": 188027696.0, | |
| "step": 1770 | |
| }, | |
| { | |
| "entropy": 1.9207917422056198, | |
| "epoch": 1.3238503870907565, | |
| "grad_norm": 2.703125, | |
| "learning_rate": 6.891340497681943e-06, | |
| "loss": 0.9789, | |
| "mean_token_accuracy": 0.7820106342434883, | |
| "num_tokens": 188557431.0, | |
| "step": 1775 | |
| }, | |
| { | |
| "entropy": 1.9169728681445122, | |
| "epoch": 1.3275813823337375, | |
| "grad_norm": 3.03125, | |
| "learning_rate": 6.843057239881761e-06, | |
| "loss": 0.9628, | |
| "mean_token_accuracy": 0.7850354023277759, | |
| "num_tokens": 189086807.0, | |
| "step": 1780 | |
| }, | |
| { | |
| "entropy": 1.9095087736845016, | |
| "epoch": 1.3313123775767186, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 6.794925593452266e-06, | |
| "loss": 0.9283, | |
| "mean_token_accuracy": 0.7953442484140396, | |
| "num_tokens": 189619674.0, | |
| "step": 1785 | |
| }, | |
| { | |
| "entropy": 1.911048673093319, | |
| "epoch": 1.3350433728196998, | |
| "grad_norm": 2.90625, | |
| "learning_rate": 6.746947313843397e-06, | |
| "loss": 0.8736, | |
| "mean_token_accuracy": 0.798565112799406, | |
| "num_tokens": 190149129.0, | |
| "step": 1790 | |
| }, | |
| { | |
| "entropy": 1.9093924537301064, | |
| "epoch": 1.3387743680626807, | |
| "grad_norm": 2.796875, | |
| "learning_rate": 6.699124150911515e-06, | |
| "loss": 1.0138, | |
| "mean_token_accuracy": 0.7696616865694523, | |
| "num_tokens": 190679470.0, | |
| "step": 1795 | |
| }, | |
| { | |
| "entropy": 1.9110808402299881, | |
| "epoch": 1.3425053633056618, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 6.651457848855589e-06, | |
| "loss": 0.9741, | |
| "mean_token_accuracy": 0.7712423533201218, | |
| "num_tokens": 191209208.0, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.3425053633056618, | |
| "eval_entropy": 1.9213085690951017, | |
| "eval_loss": 0.7952644228935242, | |
| "eval_mean_token_accuracy": 0.7886214846839553, | |
| "eval_num_tokens": 191209208.0, | |
| "eval_runtime": 417.0124, | |
| "eval_samples_per_second": 2.079, | |
| "eval_steps_per_second": 0.52, | |
| "step": 1800 | |
| }, | |
| { | |
| "entropy": 1.9260811403393745, | |
| "epoch": 1.346236358548643, | |
| "grad_norm": 2.625, | |
| "learning_rate": 6.603950146153588e-06, | |
| "loss": 0.9596, | |
| "mean_token_accuracy": 0.7831857018172741, | |
| "num_tokens": 191739157.0, | |
| "step": 1805 | |
| }, | |
| { | |
| "entropy": 1.9144031763076783, | |
| "epoch": 1.349967353791624, | |
| "grad_norm": 2.890625, | |
| "learning_rate": 6.5566027754990655e-06, | |
| "loss": 0.9274, | |
| "mean_token_accuracy": 0.7880234897136689, | |
| "num_tokens": 192268705.0, | |
| "step": 1810 | |
| }, | |
| { | |
| "entropy": 1.909570923447609, | |
| "epoch": 1.353698349034605, | |
| "grad_norm": 2.546875, | |
| "learning_rate": 6.509417463737966e-06, | |
| "loss": 0.8996, | |
| "mean_token_accuracy": 0.790591161698103, | |
| "num_tokens": 192801572.0, | |
| "step": 1815 | |
| }, | |
| { | |
| "entropy": 1.9133508145809173, | |
| "epoch": 1.357429344277586, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 6.462395931805653e-06, | |
| "loss": 0.9941, | |
| "mean_token_accuracy": 0.7782829597592353, | |
| "num_tokens": 193334058.0, | |
| "step": 1820 | |
| }, | |
| { | |
| "entropy": 1.9052420556545258, | |
| "epoch": 1.3611603395205671, | |
| "grad_norm": 2.9375, | |
| "learning_rate": 6.4155398946641356e-06, | |
| "loss": 1.0017, | |
| "mean_token_accuracy": 0.7746684297919273, | |
| "num_tokens": 193865850.0, | |
| "step": 1825 | |
| }, | |
| { | |
| "entropy": 1.913660430908203, | |
| "epoch": 1.364891334763548, | |
| "grad_norm": 2.9375, | |
| "learning_rate": 6.368851061239525e-06, | |
| "loss": 1.0345, | |
| "mean_token_accuracy": 0.7757304526865483, | |
| "num_tokens": 194395523.0, | |
| "step": 1830 | |
| }, | |
| { | |
| "entropy": 1.9195617333054542, | |
| "epoch": 1.3686223300065292, | |
| "grad_norm": 3.109375, | |
| "learning_rate": 6.3223311343596986e-06, | |
| "loss": 0.9157, | |
| "mean_token_accuracy": 0.7950341895222663, | |
| "num_tokens": 194927027.0, | |
| "step": 1835 | |
| }, | |
| { | |
| "entropy": 1.9108835265040398, | |
| "epoch": 1.3723533252495104, | |
| "grad_norm": 2.890625, | |
| "learning_rate": 6.275981810692211e-06, | |
| "loss": 0.962, | |
| "mean_token_accuracy": 0.7879531472921372, | |
| "num_tokens": 195460614.0, | |
| "step": 1840 | |
| }, | |
| { | |
| "entropy": 1.9083492949604988, | |
| "epoch": 1.3760843204924913, | |
| "grad_norm": 2.890625, | |
| "learning_rate": 6.229804780682385e-06, | |
| "loss": 0.9744, | |
| "mean_token_accuracy": 0.7809002794325351, | |
| "num_tokens": 195993086.0, | |
| "step": 1845 | |
| }, | |
| { | |
| "entropy": 1.9126764357089996, | |
| "epoch": 1.3798153157354724, | |
| "grad_norm": 2.78125, | |
| "learning_rate": 6.183801728491699e-06, | |
| "loss": 0.9072, | |
| "mean_token_accuracy": 0.7959237761795521, | |
| "num_tokens": 196523248.0, | |
| "step": 1850 | |
| }, | |
| { | |
| "entropy": 1.9173283711075784, | |
| "epoch": 1.3835463109784536, | |
| "grad_norm": 2.921875, | |
| "learning_rate": 6.137974331936318e-06, | |
| "loss": 0.9121, | |
| "mean_token_accuracy": 0.7949255533516407, | |
| "num_tokens": 197055644.0, | |
| "step": 1855 | |
| }, | |
| { | |
| "entropy": 1.9184476286172867, | |
| "epoch": 1.3872773062214345, | |
| "grad_norm": 2.796875, | |
| "learning_rate": 6.092324262425934e-06, | |
| "loss": 0.9758, | |
| "mean_token_accuracy": 0.787192802876234, | |
| "num_tokens": 197586729.0, | |
| "step": 1860 | |
| }, | |
| { | |
| "entropy": 1.9162007600069046, | |
| "epoch": 1.3910083014644157, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 6.046853184902793e-06, | |
| "loss": 0.9327, | |
| "mean_token_accuracy": 0.7840571783483028, | |
| "num_tokens": 198120218.0, | |
| "step": 1865 | |
| }, | |
| { | |
| "entropy": 1.9201767519116402, | |
| "epoch": 1.3947392967073968, | |
| "grad_norm": 2.703125, | |
| "learning_rate": 6.001562757780975e-06, | |
| "loss": 0.9963, | |
| "mean_token_accuracy": 0.7816694289445877, | |
| "num_tokens": 198653192.0, | |
| "step": 1870 | |
| }, | |
| { | |
| "entropy": 1.91514031291008, | |
| "epoch": 1.3984702919503778, | |
| "grad_norm": 2.765625, | |
| "learning_rate": 5.956454632885894e-06, | |
| "loss": 0.9816, | |
| "mean_token_accuracy": 0.7758061110973358, | |
| "num_tokens": 199183589.0, | |
| "step": 1875 | |
| }, | |
| { | |
| "entropy": 1.913975764811039, | |
| "epoch": 1.402201287193359, | |
| "grad_norm": 2.765625, | |
| "learning_rate": 5.911530455394086e-06, | |
| "loss": 1.0108, | |
| "mean_token_accuracy": 0.7735319837927819, | |
| "num_tokens": 199713315.0, | |
| "step": 1880 | |
| }, | |
| { | |
| "entropy": 1.9288661509752274, | |
| "epoch": 1.4059322824363398, | |
| "grad_norm": 2.703125, | |
| "learning_rate": 5.866791863773168e-06, | |
| "loss": 0.8622, | |
| "mean_token_accuracy": 0.8103111371397972, | |
| "num_tokens": 200243645.0, | |
| "step": 1885 | |
| }, | |
| { | |
| "entropy": 1.926280289888382, | |
| "epoch": 1.409663277679321, | |
| "grad_norm": 3.0625, | |
| "learning_rate": 5.822240489722104e-06, | |
| "loss": 0.8932, | |
| "mean_token_accuracy": 0.8012527912855149, | |
| "num_tokens": 200773847.0, | |
| "step": 1890 | |
| }, | |
| { | |
| "entropy": 1.9145182326436043, | |
| "epoch": 1.413394272922302, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 5.777877958111694e-06, | |
| "loss": 0.9799, | |
| "mean_token_accuracy": 0.778388562053442, | |
| "num_tokens": 201308141.0, | |
| "step": 1895 | |
| }, | |
| { | |
| "entropy": 1.9145977690815925, | |
| "epoch": 1.417125268165283, | |
| "grad_norm": 2.6875, | |
| "learning_rate": 5.733705886925296e-06, | |
| "loss": 0.9105, | |
| "mean_token_accuracy": 0.7903211638331413, | |
| "num_tokens": 201839018.0, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.417125268165283, | |
| "eval_entropy": 1.9226924159010435, | |
| "eval_loss": 0.7947914004325867, | |
| "eval_mean_token_accuracy": 0.7886583176076687, | |
| "eval_num_tokens": 201839018.0, | |
| "eval_runtime": 415.0444, | |
| "eval_samples_per_second": 2.089, | |
| "eval_steps_per_second": 0.523, | |
| "step": 1900 | |
| }, | |
| { | |
| "entropy": 1.9117732971906662, | |
| "epoch": 1.4208562634082642, | |
| "grad_norm": 2.453125, | |
| "learning_rate": 5.689725887199833e-06, | |
| "loss": 0.9656, | |
| "mean_token_accuracy": 0.787474986165762, | |
| "num_tokens": 202368336.0, | |
| "step": 1905 | |
| }, | |
| { | |
| "entropy": 1.919792464375496, | |
| "epoch": 1.4245872586512451, | |
| "grad_norm": 2.859375, | |
| "learning_rate": 5.645939562967026e-06, | |
| "loss": 0.9176, | |
| "mean_token_accuracy": 0.7953712411224843, | |
| "num_tokens": 202899920.0, | |
| "step": 1910 | |
| }, | |
| { | |
| "entropy": 1.9164147719740867, | |
| "epoch": 1.4283182538942263, | |
| "grad_norm": 2.984375, | |
| "learning_rate": 5.602348511194882e-06, | |
| "loss": 0.9731, | |
| "mean_token_accuracy": 0.783729862421751, | |
| "num_tokens": 203431781.0, | |
| "step": 1915 | |
| }, | |
| { | |
| "entropy": 1.9064750477671624, | |
| "epoch": 1.4320492491372074, | |
| "grad_norm": 2.953125, | |
| "learning_rate": 5.558954321729477e-06, | |
| "loss": 0.9373, | |
| "mean_token_accuracy": 0.7890445157885552, | |
| "num_tokens": 203963211.0, | |
| "step": 1920 | |
| }, | |
| { | |
| "entropy": 1.9172628924250603, | |
| "epoch": 1.4357802443801884, | |
| "grad_norm": 3.015625, | |
| "learning_rate": 5.515758577236951e-06, | |
| "loss": 0.9597, | |
| "mean_token_accuracy": 0.7818316780030727, | |
| "num_tokens": 204493102.0, | |
| "step": 1925 | |
| }, | |
| { | |
| "entropy": 1.9186809375882148, | |
| "epoch": 1.4395112396231695, | |
| "grad_norm": 3.296875, | |
| "learning_rate": 5.472762853145785e-06, | |
| "loss": 0.983, | |
| "mean_token_accuracy": 0.77845314219594, | |
| "num_tokens": 205022866.0, | |
| "step": 1930 | |
| }, | |
| { | |
| "entropy": 1.907158075273037, | |
| "epoch": 1.4432422348661507, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 5.429968717589349e-06, | |
| "loss": 1.0143, | |
| "mean_token_accuracy": 0.7621226042509079, | |
| "num_tokens": 205555650.0, | |
| "step": 1935 | |
| }, | |
| { | |
| "entropy": 1.9154852628707886, | |
| "epoch": 1.4469732301091316, | |
| "grad_norm": 2.9375, | |
| "learning_rate": 5.387377731348715e-06, | |
| "loss": 0.9273, | |
| "mean_token_accuracy": 0.7915920428931713, | |
| "num_tokens": 206089656.0, | |
| "step": 1940 | |
| }, | |
| { | |
| "entropy": 1.9256163939833641, | |
| "epoch": 1.4507042253521127, | |
| "grad_norm": 2.796875, | |
| "learning_rate": 5.344991447795709e-06, | |
| "loss": 0.9501, | |
| "mean_token_accuracy": 0.7945499166846275, | |
| "num_tokens": 206622120.0, | |
| "step": 1945 | |
| }, | |
| { | |
| "entropy": 1.9029963329434394, | |
| "epoch": 1.4544352205950937, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 5.302811412836285e-06, | |
| "loss": 1.0196, | |
| "mean_token_accuracy": 0.7709416255354882, | |
| "num_tokens": 207155611.0, | |
| "step": 1950 | |
| }, | |
| { | |
| "entropy": 1.917876623570919, | |
| "epoch": 1.4581662158380748, | |
| "grad_norm": 2.578125, | |
| "learning_rate": 5.2608391648541276e-06, | |
| "loss": 0.9417, | |
| "mean_token_accuracy": 0.7857843562960625, | |
| "num_tokens": 207686473.0, | |
| "step": 1955 | |
| }, | |
| { | |
| "entropy": 1.9248770505189896, | |
| "epoch": 1.4618972110810557, | |
| "grad_norm": 3.140625, | |
| "learning_rate": 5.219076234654545e-06, | |
| "loss": 0.9953, | |
| "mean_token_accuracy": 0.7756866917014122, | |
| "num_tokens": 208217822.0, | |
| "step": 1960 | |
| }, | |
| { | |
| "entropy": 1.9229801774024964, | |
| "epoch": 1.465628206324037, | |
| "grad_norm": 2.984375, | |
| "learning_rate": 5.177524145408642e-06, | |
| "loss": 0.9483, | |
| "mean_token_accuracy": 0.7806045912206173, | |
| "num_tokens": 208747962.0, | |
| "step": 1965 | |
| }, | |
| { | |
| "entropy": 1.9025382086634637, | |
| "epoch": 1.469359201567018, | |
| "grad_norm": 2.8125, | |
| "learning_rate": 5.136184412597767e-06, | |
| "loss": 0.9272, | |
| "mean_token_accuracy": 0.7886285282671451, | |
| "num_tokens": 209278371.0, | |
| "step": 1970 | |
| }, | |
| { | |
| "entropy": 1.915241926908493, | |
| "epoch": 1.473090196809999, | |
| "grad_norm": 2.90625, | |
| "learning_rate": 5.0950585439582244e-06, | |
| "loss": 0.9676, | |
| "mean_token_accuracy": 0.7825336590409279, | |
| "num_tokens": 209810564.0, | |
| "step": 1975 | |
| }, | |
| { | |
| "entropy": 1.9186094522476196, | |
| "epoch": 1.4768211920529801, | |
| "grad_norm": 2.78125, | |
| "learning_rate": 5.054148039426314e-06, | |
| "loss": 0.979, | |
| "mean_token_accuracy": 0.7762361623346805, | |
| "num_tokens": 210340000.0, | |
| "step": 1980 | |
| }, | |
| { | |
| "entropy": 1.917215932905674, | |
| "epoch": 1.4805521872959613, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 5.013454391083603e-06, | |
| "loss": 1.0244, | |
| "mean_token_accuracy": 0.76511832177639, | |
| "num_tokens": 210871442.0, | |
| "step": 1985 | |
| }, | |
| { | |
| "entropy": 1.9191341713070869, | |
| "epoch": 1.4842831825389422, | |
| "grad_norm": 2.890625, | |
| "learning_rate": 4.972979083102512e-06, | |
| "loss": 0.9806, | |
| "mean_token_accuracy": 0.780594726651907, | |
| "num_tokens": 211401718.0, | |
| "step": 1990 | |
| }, | |
| { | |
| "entropy": 1.9123217433691024, | |
| "epoch": 1.4880141777819234, | |
| "grad_norm": 3.265625, | |
| "learning_rate": 4.9327235916921885e-06, | |
| "loss": 1.0062, | |
| "mean_token_accuracy": 0.776950541883707, | |
| "num_tokens": 211933026.0, | |
| "step": 1995 | |
| }, | |
| { | |
| "entropy": 1.9251987099647523, | |
| "epoch": 1.4917451730249045, | |
| "grad_norm": 2.71875, | |
| "learning_rate": 4.892689385044664e-06, | |
| "loss": 0.958, | |
| "mean_token_accuracy": 0.7888118654489518, | |
| "num_tokens": 212463969.0, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.4917451730249045, | |
| "eval_entropy": 1.923713410504952, | |
| "eval_loss": 0.7941039800643921, | |
| "eval_mean_token_accuracy": 0.7887901699488065, | |
| "eval_num_tokens": 212463969.0, | |
| "eval_runtime": 423.4613, | |
| "eval_samples_per_second": 2.047, | |
| "eval_steps_per_second": 0.512, | |
| "step": 2000 | |
| }, | |
| { | |
| "entropy": 1.9207520872354507, | |
| "epoch": 1.4954761682678854, | |
| "grad_norm": 2.90625, | |
| "learning_rate": 4.852877923281301e-06, | |
| "loss": 0.8589, | |
| "mean_token_accuracy": 0.7933267027139663, | |
| "num_tokens": 212994560.0, | |
| "step": 2005 | |
| }, | |
| { | |
| "entropy": 1.9220597296953201, | |
| "epoch": 1.4992071635108666, | |
| "grad_norm": 3.828125, | |
| "learning_rate": 4.81329065839955e-06, | |
| "loss": 0.9453, | |
| "mean_token_accuracy": 0.7886260092258454, | |
| "num_tokens": 213525059.0, | |
| "step": 2010 | |
| }, | |
| { | |
| "entropy": 1.926292322576046, | |
| "epoch": 1.5029381587538477, | |
| "grad_norm": 2.9375, | |
| "learning_rate": 4.773929034219989e-06, | |
| "loss": 0.924, | |
| "mean_token_accuracy": 0.7947903670370579, | |
| "num_tokens": 214056456.0, | |
| "step": 2015 | |
| }, | |
| { | |
| "entropy": 1.9207703724503518, | |
| "epoch": 1.5066691539968287, | |
| "grad_norm": 3.0, | |
| "learning_rate": 4.734794486333661e-06, | |
| "loss": 0.996, | |
| "mean_token_accuracy": 0.7710816271603107, | |
| "num_tokens": 214589110.0, | |
| "step": 2020 | |
| }, | |
| { | |
| "entropy": 1.9281767308712006, | |
| "epoch": 1.5104001492398096, | |
| "grad_norm": 3.015625, | |
| "learning_rate": 4.6958884420497196e-06, | |
| "loss": 0.936, | |
| "mean_token_accuracy": 0.7833106748759746, | |
| "num_tokens": 215118032.0, | |
| "step": 2025 | |
| }, | |
| { | |
| "entropy": 1.92151879966259, | |
| "epoch": 1.5141311444827907, | |
| "grad_norm": 2.96875, | |
| "learning_rate": 4.657212320343369e-06, | |
| "loss": 0.9275, | |
| "mean_token_accuracy": 0.7913325764238834, | |
| "num_tokens": 215650747.0, | |
| "step": 2030 | |
| }, | |
| { | |
| "entropy": 1.9185984879732132, | |
| "epoch": 1.5178621397257719, | |
| "grad_norm": 2.890625, | |
| "learning_rate": 4.6187675318041085e-06, | |
| "loss": 1.03, | |
| "mean_token_accuracy": 0.7779677748680115, | |
| "num_tokens": 216181946.0, | |
| "step": 2035 | |
| }, | |
| { | |
| "entropy": 1.9180883452296258, | |
| "epoch": 1.5215931349687528, | |
| "grad_norm": 3.15625, | |
| "learning_rate": 4.580555478584295e-06, | |
| "loss": 0.959, | |
| "mean_token_accuracy": 0.7815264448523521, | |
| "num_tokens": 216712813.0, | |
| "step": 2040 | |
| }, | |
| { | |
| "entropy": 1.9216745108366013, | |
| "epoch": 1.525324130211734, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 4.542577554348007e-06, | |
| "loss": 0.9013, | |
| "mean_token_accuracy": 0.7971072472631932, | |
| "num_tokens": 217242416.0, | |
| "step": 2045 | |
| }, | |
| { | |
| "entropy": 1.9199370354413987, | |
| "epoch": 1.5290551254547151, | |
| "grad_norm": 2.625, | |
| "learning_rate": 4.50483514422019e-06, | |
| "loss": 0.9607, | |
| "mean_token_accuracy": 0.7842399850487709, | |
| "num_tokens": 217774340.0, | |
| "step": 2050 | |
| }, | |
| { | |
| "entropy": 1.9149819746613503, | |
| "epoch": 1.532786120697696, | |
| "grad_norm": 2.65625, | |
| "learning_rate": 4.467329624736165e-06, | |
| "loss": 0.9555, | |
| "mean_token_accuracy": 0.7854515843093395, | |
| "num_tokens": 218305918.0, | |
| "step": 2055 | |
| }, | |
| { | |
| "entropy": 1.9093442946672439, | |
| "epoch": 1.5365171159406772, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 4.4300623637914186e-06, | |
| "loss": 0.9692, | |
| "mean_token_accuracy": 0.7805149331688881, | |
| "num_tokens": 218838626.0, | |
| "step": 2060 | |
| }, | |
| { | |
| "entropy": 1.9209594249725341, | |
| "epoch": 1.5402481111836583, | |
| "grad_norm": 2.828125, | |
| "learning_rate": 4.393034720591696e-06, | |
| "loss": 1.005, | |
| "mean_token_accuracy": 0.7798107601702213, | |
| "num_tokens": 219368785.0, | |
| "step": 2065 | |
| }, | |
| { | |
| "entropy": 1.919579316675663, | |
| "epoch": 1.5439791064266393, | |
| "grad_norm": 2.671875, | |
| "learning_rate": 4.356248045603453e-06, | |
| "loss": 0.9529, | |
| "mean_token_accuracy": 0.781716576218605, | |
| "num_tokens": 219899756.0, | |
| "step": 2070 | |
| }, | |
| { | |
| "entropy": 1.922955933213234, | |
| "epoch": 1.5477101016696204, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 4.319703680504589e-06, | |
| "loss": 0.9333, | |
| "mean_token_accuracy": 0.7829143904149533, | |
| "num_tokens": 220433320.0, | |
| "step": 2075 | |
| }, | |
| { | |
| "entropy": 1.9164094612002374, | |
| "epoch": 1.5514410969126016, | |
| "grad_norm": 2.46875, | |
| "learning_rate": 4.283402958135506e-06, | |
| "loss": 1.0076, | |
| "mean_token_accuracy": 0.7693854115903378, | |
| "num_tokens": 220963973.0, | |
| "step": 2080 | |
| }, | |
| { | |
| "entropy": 1.9213256657123565, | |
| "epoch": 1.5551720921555825, | |
| "grad_norm": 2.9375, | |
| "learning_rate": 4.247347202450514e-06, | |
| "loss": 0.9796, | |
| "mean_token_accuracy": 0.7753906600177288, | |
| "num_tokens": 221493799.0, | |
| "step": 2085 | |
| }, | |
| { | |
| "entropy": 1.914214849472046, | |
| "epoch": 1.5589030873985634, | |
| "grad_norm": 2.625, | |
| "learning_rate": 4.211537728469538e-06, | |
| "loss": 0.923, | |
| "mean_token_accuracy": 0.7858444310724735, | |
| "num_tokens": 222025516.0, | |
| "step": 2090 | |
| }, | |
| { | |
| "entropy": 1.9236473813652992, | |
| "epoch": 1.5626340826415448, | |
| "grad_norm": 2.765625, | |
| "learning_rate": 4.175975842230144e-06, | |
| "loss": 0.9964, | |
| "mean_token_accuracy": 0.7722836993634701, | |
| "num_tokens": 222555997.0, | |
| "step": 2095 | |
| }, | |
| { | |
| "entropy": 1.9193670630455018, | |
| "epoch": 1.5663650778845257, | |
| "grad_norm": 2.875, | |
| "learning_rate": 4.140662840739929e-06, | |
| "loss": 1.0129, | |
| "mean_token_accuracy": 0.777188754081726, | |
| "num_tokens": 223086481.0, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.5663650778845257, | |
| "eval_entropy": 1.9263520954940725, | |
| "eval_loss": 0.7939472198486328, | |
| "eval_mean_token_accuracy": 0.789093039002836, | |
| "eval_num_tokens": 223086481.0, | |
| "eval_runtime": 411.5243, | |
| "eval_samples_per_second": 2.107, | |
| "eval_steps_per_second": 0.527, | |
| "step": 2100 | |
| }, | |
| { | |
| "entropy": 1.9265794411301613, | |
| "epoch": 1.5700960731275067, | |
| "grad_norm": 2.484375, | |
| "learning_rate": 4.1056000119292e-06, | |
| "loss": 0.9907, | |
| "mean_token_accuracy": 0.7721577517688274, | |
| "num_tokens": 223616881.0, | |
| "step": 2105 | |
| }, | |
| { | |
| "entropy": 1.9221562936902046, | |
| "epoch": 1.5738270683704878, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 4.070788634603996e-06, | |
| "loss": 0.9787, | |
| "mean_token_accuracy": 0.7774898521602154, | |
| "num_tokens": 224149559.0, | |
| "step": 2110 | |
| }, | |
| { | |
| "entropy": 1.9217603102326393, | |
| "epoch": 1.577558063613469, | |
| "grad_norm": 2.75, | |
| "learning_rate": 4.036229978399471e-06, | |
| "loss": 0.9185, | |
| "mean_token_accuracy": 0.7944407314062119, | |
| "num_tokens": 224678853.0, | |
| "step": 2115 | |
| }, | |
| { | |
| "entropy": 1.9181690692901612, | |
| "epoch": 1.5812890588564499, | |
| "grad_norm": 3.203125, | |
| "learning_rate": 4.001925303733564e-06, | |
| "loss": 0.9609, | |
| "mean_token_accuracy": 0.7815622113645077, | |
| "num_tokens": 225211439.0, | |
| "step": 2120 | |
| }, | |
| { | |
| "entropy": 1.923632562160492, | |
| "epoch": 1.585020054099431, | |
| "grad_norm": 2.9375, | |
| "learning_rate": 3.967875861761037e-06, | |
| "loss": 0.9365, | |
| "mean_token_accuracy": 0.7866649009287358, | |
| "num_tokens": 225742793.0, | |
| "step": 2125 | |
| }, | |
| { | |
| "entropy": 1.919877180457115, | |
| "epoch": 1.5887510493424122, | |
| "grad_norm": 2.890625, | |
| "learning_rate": 3.934082894327855e-06, | |
| "loss": 0.9416, | |
| "mean_token_accuracy": 0.7854848735034465, | |
| "num_tokens": 226273252.0, | |
| "step": 2130 | |
| }, | |
| { | |
| "entropy": 1.9240162417292594, | |
| "epoch": 1.592482044585393, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 3.9005476339258795e-06, | |
| "loss": 0.9857, | |
| "mean_token_accuracy": 0.7773564159870148, | |
| "num_tokens": 226806159.0, | |
| "step": 2135 | |
| }, | |
| { | |
| "entropy": 1.9207270756363868, | |
| "epoch": 1.5962130398283743, | |
| "grad_norm": 3.0, | |
| "learning_rate": 3.867271303647912e-06, | |
| "loss": 0.9065, | |
| "mean_token_accuracy": 0.7894360311329365, | |
| "num_tokens": 227335162.0, | |
| "step": 2140 | |
| }, | |
| { | |
| "entropy": 1.925444918870926, | |
| "epoch": 1.5999440350713554, | |
| "grad_norm": 2.90625, | |
| "learning_rate": 3.834255117143105e-06, | |
| "loss": 0.9146, | |
| "mean_token_accuracy": 0.7939443275332451, | |
| "num_tokens": 227866960.0, | |
| "step": 2145 | |
| }, | |
| { | |
| "entropy": 1.920570534467697, | |
| "epoch": 1.6036750303143363, | |
| "grad_norm": 3.140625, | |
| "learning_rate": 3.8015002785726852e-06, | |
| "loss": 0.9451, | |
| "mean_token_accuracy": 0.7859753273427487, | |
| "num_tokens": 228397933.0, | |
| "step": 2150 | |
| }, | |
| { | |
| "entropy": 1.9137139230966569, | |
| "epoch": 1.6074060255573173, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 3.7690079825660367e-06, | |
| "loss": 0.9853, | |
| "mean_token_accuracy": 0.7792695969343185, | |
| "num_tokens": 228932759.0, | |
| "step": 2155 | |
| }, | |
| { | |
| "entropy": 1.9213504776358605, | |
| "epoch": 1.6111370208002986, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 3.736779414177133e-06, | |
| "loss": 0.8977, | |
| "mean_token_accuracy": 0.7924081102013588, | |
| "num_tokens": 229464578.0, | |
| "step": 2160 | |
| }, | |
| { | |
| "entropy": 1.9174690261483192, | |
| "epoch": 1.6148680160432796, | |
| "grad_norm": 2.671875, | |
| "learning_rate": 3.7048157488413185e-06, | |
| "loss": 1.0169, | |
| "mean_token_accuracy": 0.7713649921119213, | |
| "num_tokens": 229995198.0, | |
| "step": 2165 | |
| }, | |
| { | |
| "entropy": 1.9215390980243683, | |
| "epoch": 1.6185990112862605, | |
| "grad_norm": 3.1875, | |
| "learning_rate": 3.6731181523324234e-06, | |
| "loss": 0.85, | |
| "mean_token_accuracy": 0.8087228052318096, | |
| "num_tokens": 230526460.0, | |
| "step": 2170 | |
| }, | |
| { | |
| "entropy": 1.924245499074459, | |
| "epoch": 1.6223300065292416, | |
| "grad_norm": 2.75, | |
| "learning_rate": 3.6416877807202676e-06, | |
| "loss": 0.9276, | |
| "mean_token_accuracy": 0.788924976438284, | |
| "num_tokens": 231057436.0, | |
| "step": 2175 | |
| }, | |
| { | |
| "entropy": 1.9228363931179047, | |
| "epoch": 1.6260610017722228, | |
| "grad_norm": 3.171875, | |
| "learning_rate": 3.6105257803284844e-06, | |
| "loss": 0.9772, | |
| "mean_token_accuracy": 0.7773720294237136, | |
| "num_tokens": 231589551.0, | |
| "step": 2180 | |
| }, | |
| { | |
| "entropy": 1.9220960274338723, | |
| "epoch": 1.6297919970152037, | |
| "grad_norm": 2.59375, | |
| "learning_rate": 3.579633287692711e-06, | |
| "loss": 0.947, | |
| "mean_token_accuracy": 0.7894782021641731, | |
| "num_tokens": 232121607.0, | |
| "step": 2185 | |
| }, | |
| { | |
| "entropy": 1.9228823781013489, | |
| "epoch": 1.6335229922581849, | |
| "grad_norm": 2.890625, | |
| "learning_rate": 3.549011429519139e-06, | |
| "loss": 0.8958, | |
| "mean_token_accuracy": 0.7975842222571373, | |
| "num_tokens": 232653590.0, | |
| "step": 2190 | |
| }, | |
| { | |
| "entropy": 1.9289898470044136, | |
| "epoch": 1.637253987501166, | |
| "grad_norm": 2.890625, | |
| "learning_rate": 3.5186613226434286e-06, | |
| "loss": 0.9415, | |
| "mean_token_accuracy": 0.7874727994203568, | |
| "num_tokens": 233184465.0, | |
| "step": 2195 | |
| }, | |
| { | |
| "entropy": 1.9162527233362199, | |
| "epoch": 1.640984982744147, | |
| "grad_norm": 2.6875, | |
| "learning_rate": 3.488584073989958e-06, | |
| "loss": 0.981, | |
| "mean_token_accuracy": 0.7749945864081382, | |
| "num_tokens": 233716486.0, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.640984982744147, | |
| "eval_entropy": 1.922694647916451, | |
| "eval_loss": 0.7940070033073425, | |
| "eval_mean_token_accuracy": 0.7886112252688078, | |
| "eval_num_tokens": 233716486.0, | |
| "eval_runtime": 452.226, | |
| "eval_samples_per_second": 1.917, | |
| "eval_steps_per_second": 0.48, | |
| "step": 2200 | |
| }, | |
| { | |
| "entropy": 1.9192370921373367, | |
| "epoch": 1.644715977987128, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 3.4587807805314695e-06, | |
| "loss": 0.9459, | |
| "mean_token_accuracy": 0.7845867499709129, | |
| "num_tokens": 234245589.0, | |
| "step": 2205 | |
| }, | |
| { | |
| "entropy": 1.9262465044856072, | |
| "epoch": 1.6484469732301092, | |
| "grad_norm": 2.875, | |
| "learning_rate": 3.4292525292490544e-06, | |
| "loss": 0.9529, | |
| "mean_token_accuracy": 0.7888288274407387, | |
| "num_tokens": 234776020.0, | |
| "step": 2210 | |
| }, | |
| { | |
| "entropy": 1.9103346571326256, | |
| "epoch": 1.6521779684730902, | |
| "grad_norm": 2.671875, | |
| "learning_rate": 3.4000003970925076e-06, | |
| "loss": 0.9747, | |
| "mean_token_accuracy": 0.7737406581640244, | |
| "num_tokens": 235307381.0, | |
| "step": 2215 | |
| }, | |
| { | |
| "entropy": 1.9194400265812874, | |
| "epoch": 1.655908963716071, | |
| "grad_norm": 3.0625, | |
| "learning_rate": 3.371025450941049e-06, | |
| "loss": 0.985, | |
| "mean_token_accuracy": 0.773327323794365, | |
| "num_tokens": 235835901.0, | |
| "step": 2220 | |
| }, | |
| { | |
| "entropy": 1.9171280801296233, | |
| "epoch": 1.6596399589590525, | |
| "grad_norm": 2.6875, | |
| "learning_rate": 3.342328747564416e-06, | |
| "loss": 0.9619, | |
| "mean_token_accuracy": 0.790045228600502, | |
| "num_tokens": 236366996.0, | |
| "step": 2225 | |
| }, | |
| { | |
| "entropy": 1.9132253170013427, | |
| "epoch": 1.6633709542020334, | |
| "grad_norm": 2.6875, | |
| "learning_rate": 3.313911333584313e-06, | |
| "loss": 1.0102, | |
| "mean_token_accuracy": 0.7748994067311287, | |
| "num_tokens": 236899548.0, | |
| "step": 2230 | |
| }, | |
| { | |
| "entropy": 1.918226708471775, | |
| "epoch": 1.6671019494450143, | |
| "grad_norm": 2.890625, | |
| "learning_rate": 3.2857742454362516e-06, | |
| "loss": 0.9767, | |
| "mean_token_accuracy": 0.7792360559105873, | |
| "num_tokens": 237431409.0, | |
| "step": 2235 | |
| }, | |
| { | |
| "entropy": 1.9195396587252618, | |
| "epoch": 1.6708329446879955, | |
| "grad_norm": 2.78125, | |
| "learning_rate": 3.257918509331741e-06, | |
| "loss": 0.9301, | |
| "mean_token_accuracy": 0.7851594485342502, | |
| "num_tokens": 237963649.0, | |
| "step": 2240 | |
| }, | |
| { | |
| "entropy": 1.912094420194626, | |
| "epoch": 1.6745639399309766, | |
| "grad_norm": 2.953125, | |
| "learning_rate": 3.2303451412208604e-06, | |
| "loss": 0.9567, | |
| "mean_token_accuracy": 0.7778088934719563, | |
| "num_tokens": 238496392.0, | |
| "step": 2245 | |
| }, | |
| { | |
| "entropy": 1.9135541930794715, | |
| "epoch": 1.6782949351739576, | |
| "grad_norm": 2.546875, | |
| "learning_rate": 3.2030551467552087e-06, | |
| "loss": 1.0216, | |
| "mean_token_accuracy": 0.764666422456503, | |
| "num_tokens": 239028705.0, | |
| "step": 2250 | |
| }, | |
| { | |
| "entropy": 1.9229572668671608, | |
| "epoch": 1.6820259304169387, | |
| "grad_norm": 2.65625, | |
| "learning_rate": 3.176049521251229e-06, | |
| "loss": 1.0217, | |
| "mean_token_accuracy": 0.7704686284065246, | |
| "num_tokens": 239559619.0, | |
| "step": 2255 | |
| }, | |
| { | |
| "entropy": 1.9300857797265052, | |
| "epoch": 1.6857569256599199, | |
| "grad_norm": 2.78125, | |
| "learning_rate": 3.149329249653895e-06, | |
| "loss": 0.9225, | |
| "mean_token_accuracy": 0.8011655747890473, | |
| "num_tokens": 240092059.0, | |
| "step": 2260 | |
| }, | |
| { | |
| "entropy": 1.9296444818377494, | |
| "epoch": 1.6894879209029008, | |
| "grad_norm": 2.609375, | |
| "learning_rate": 3.1228953065008035e-06, | |
| "loss": 0.9052, | |
| "mean_token_accuracy": 0.7951169416308403, | |
| "num_tokens": 240622703.0, | |
| "step": 2265 | |
| }, | |
| { | |
| "entropy": 1.9241193488240242, | |
| "epoch": 1.693218916145882, | |
| "grad_norm": 2.75, | |
| "learning_rate": 3.0967486558866257e-06, | |
| "loss": 0.8544, | |
| "mean_token_accuracy": 0.8072010114789009, | |
| "num_tokens": 241152633.0, | |
| "step": 2270 | |
| }, | |
| { | |
| "entropy": 1.9230607852339745, | |
| "epoch": 1.696949911388863, | |
| "grad_norm": 3.59375, | |
| "learning_rate": 3.0708902514279405e-06, | |
| "loss": 0.9734, | |
| "mean_token_accuracy": 0.7778616219758987, | |
| "num_tokens": 241684053.0, | |
| "step": 2275 | |
| }, | |
| { | |
| "entropy": 1.9290795788168906, | |
| "epoch": 1.700680906631844, | |
| "grad_norm": 2.6875, | |
| "learning_rate": 3.045321036228458e-06, | |
| "loss": 0.8386, | |
| "mean_token_accuracy": 0.8009327456355095, | |
| "num_tokens": 242214854.0, | |
| "step": 2280 | |
| }, | |
| { | |
| "entropy": 1.9164558365941047, | |
| "epoch": 1.7044119018748252, | |
| "grad_norm": 2.65625, | |
| "learning_rate": 3.0200419428446276e-06, | |
| "loss": 0.9529, | |
| "mean_token_accuracy": 0.7778381988406181, | |
| "num_tokens": 242746380.0, | |
| "step": 2285 | |
| }, | |
| { | |
| "entropy": 1.9153956204652787, | |
| "epoch": 1.7081428971178063, | |
| "grad_norm": 2.8125, | |
| "learning_rate": 2.9950538932516093e-06, | |
| "loss": 0.9705, | |
| "mean_token_accuracy": 0.7820813551545143, | |
| "num_tokens": 243277935.0, | |
| "step": 2290 | |
| }, | |
| { | |
| "entropy": 1.9179982468485832, | |
| "epoch": 1.7118738923607872, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 2.9703577988096754e-06, | |
| "loss": 0.9666, | |
| "mean_token_accuracy": 0.7841740600764752, | |
| "num_tokens": 243809259.0, | |
| "step": 2295 | |
| }, | |
| { | |
| "entropy": 1.9282338470220566, | |
| "epoch": 1.7156048876037682, | |
| "grad_norm": 2.953125, | |
| "learning_rate": 2.9459545602309403e-06, | |
| "loss": 0.9468, | |
| "mean_token_accuracy": 0.7934271112084389, | |
| "num_tokens": 244338575.0, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.7156048876037682, | |
| "eval_entropy": 1.9274940507203204, | |
| "eval_loss": 0.7935892343521118, | |
| "eval_mean_token_accuracy": 0.7888673678521188, | |
| "eval_num_tokens": 244338575.0, | |
| "eval_runtime": 408.8193, | |
| "eval_samples_per_second": 2.121, | |
| "eval_steps_per_second": 0.531, | |
| "step": 2300 | |
| }, | |
| { | |
| "entropy": 1.9255469009280204, | |
| "epoch": 1.7193358828467493, | |
| "grad_norm": 2.796875, | |
| "learning_rate": 2.9218450675465326e-06, | |
| "loss": 0.9493, | |
| "mean_token_accuracy": 0.7921744890511035, | |
| "num_tokens": 244868407.0, | |
| "step": 2305 | |
| }, | |
| { | |
| "entropy": 1.9082586839795113, | |
| "epoch": 1.7230668780897305, | |
| "grad_norm": 2.640625, | |
| "learning_rate": 2.8980302000741267e-06, | |
| "loss": 0.9779, | |
| "mean_token_accuracy": 0.7783657617866993, | |
| "num_tokens": 245398671.0, | |
| "step": 2310 | |
| }, | |
| { | |
| "entropy": 1.9125275507569313, | |
| "epoch": 1.7267978733327114, | |
| "grad_norm": 2.828125, | |
| "learning_rate": 2.87451082638587e-06, | |
| "loss": 0.9251, | |
| "mean_token_accuracy": 0.7951716847717762, | |
| "num_tokens": 245930302.0, | |
| "step": 2315 | |
| }, | |
| { | |
| "entropy": 1.921560037136078, | |
| "epoch": 1.7305288685756925, | |
| "grad_norm": 3.09375, | |
| "learning_rate": 2.8512878042767027e-06, | |
| "loss": 0.9052, | |
| "mean_token_accuracy": 0.7911626607179642, | |
| "num_tokens": 246462728.0, | |
| "step": 2320 | |
| }, | |
| { | |
| "entropy": 1.926774376630783, | |
| "epoch": 1.7342598638186737, | |
| "grad_norm": 2.5625, | |
| "learning_rate": 2.8283619807330855e-06, | |
| "loss": 0.8988, | |
| "mean_token_accuracy": 0.7861256495118141, | |
| "num_tokens": 246992816.0, | |
| "step": 2325 | |
| }, | |
| { | |
| "entropy": 1.9165738061070443, | |
| "epoch": 1.7379908590616546, | |
| "grad_norm": 3.0625, | |
| "learning_rate": 2.8057341919020906e-06, | |
| "loss": 0.9964, | |
| "mean_token_accuracy": 0.7701143123209476, | |
| "num_tokens": 247526253.0, | |
| "step": 2330 | |
| }, | |
| { | |
| "entropy": 1.913632895052433, | |
| "epoch": 1.7417218543046358, | |
| "grad_norm": 2.703125, | |
| "learning_rate": 2.783405263060918e-06, | |
| "loss": 1.0172, | |
| "mean_token_accuracy": 0.7685214690864086, | |
| "num_tokens": 248057413.0, | |
| "step": 2335 | |
| }, | |
| { | |
| "entropy": 1.9237369418144226, | |
| "epoch": 1.745452849547617, | |
| "grad_norm": 3.09375, | |
| "learning_rate": 2.7613760085867924e-06, | |
| "loss": 0.9882, | |
| "mean_token_accuracy": 0.7725242026150226, | |
| "num_tokens": 248587926.0, | |
| "step": 2340 | |
| }, | |
| { | |
| "entropy": 1.9254556432366372, | |
| "epoch": 1.7491838447905979, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 2.739647231927264e-06, | |
| "loss": 0.9002, | |
| "mean_token_accuracy": 0.7950693652033806, | |
| "num_tokens": 249118942.0, | |
| "step": 2345 | |
| }, | |
| { | |
| "entropy": 1.915513914823532, | |
| "epoch": 1.752914840033579, | |
| "grad_norm": 3.15625, | |
| "learning_rate": 2.7182197255708942e-06, | |
| "loss": 0.976, | |
| "mean_token_accuracy": 0.7857939094305039, | |
| "num_tokens": 249649163.0, | |
| "step": 2350 | |
| }, | |
| { | |
| "entropy": 1.9156290039420127, | |
| "epoch": 1.7566458352765602, | |
| "grad_norm": 2.921875, | |
| "learning_rate": 2.697094271018374e-06, | |
| "loss": 0.9748, | |
| "mean_token_accuracy": 0.7830391086637973, | |
| "num_tokens": 250181840.0, | |
| "step": 2355 | |
| }, | |
| { | |
| "entropy": 1.9220938324928283, | |
| "epoch": 1.760376830519541, | |
| "grad_norm": 2.71875, | |
| "learning_rate": 2.6762716387539956e-06, | |
| "loss": 0.9367, | |
| "mean_token_accuracy": 0.7896655574440956, | |
| "num_tokens": 250712561.0, | |
| "step": 2360 | |
| }, | |
| { | |
| "entropy": 1.9115706831216812, | |
| "epoch": 1.764107825762522, | |
| "grad_norm": 2.609375, | |
| "learning_rate": 2.65575258821757e-06, | |
| "loss": 0.9094, | |
| "mean_token_accuracy": 0.7902532637119293, | |
| "num_tokens": 251244090.0, | |
| "step": 2365 | |
| }, | |
| { | |
| "entropy": 1.9223439544439316, | |
| "epoch": 1.7678388210055034, | |
| "grad_norm": 3.1875, | |
| "learning_rate": 2.6355378677767223e-06, | |
| "loss": 0.9001, | |
| "mean_token_accuracy": 0.7949155509471894, | |
| "num_tokens": 251775524.0, | |
| "step": 2370 | |
| }, | |
| { | |
| "entropy": 1.9269421100616455, | |
| "epoch": 1.7715698162484843, | |
| "grad_norm": 2.65625, | |
| "learning_rate": 2.6156282146995955e-06, | |
| "loss": 0.9287, | |
| "mean_token_accuracy": 0.795907324552536, | |
| "num_tokens": 252304609.0, | |
| "step": 2375 | |
| }, | |
| { | |
| "entropy": 1.9298863634467125, | |
| "epoch": 1.7753008114914652, | |
| "grad_norm": 3.1875, | |
| "learning_rate": 2.5960243551279652e-06, | |
| "loss": 0.884, | |
| "mean_token_accuracy": 0.7974181033670902, | |
| "num_tokens": 252835385.0, | |
| "step": 2380 | |
| }, | |
| { | |
| "entropy": 1.9196127310395241, | |
| "epoch": 1.7790318067344464, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 2.576727004050754e-06, | |
| "loss": 0.8886, | |
| "mean_token_accuracy": 0.7969051510095596, | |
| "num_tokens": 253367813.0, | |
| "step": 2385 | |
| }, | |
| { | |
| "entropy": 1.9148397564888, | |
| "epoch": 1.7827628019774275, | |
| "grad_norm": 3.4375, | |
| "learning_rate": 2.5577368652779495e-06, | |
| "loss": 0.9919, | |
| "mean_token_accuracy": 0.7807718679308892, | |
| "num_tokens": 253899925.0, | |
| "step": 2390 | |
| }, | |
| { | |
| "entropy": 1.92100038677454, | |
| "epoch": 1.7864937972204085, | |
| "grad_norm": 2.90625, | |
| "learning_rate": 2.539054631414946e-06, | |
| "loss": 0.9312, | |
| "mean_token_accuracy": 0.7850274242460727, | |
| "num_tokens": 254428726.0, | |
| "step": 2395 | |
| }, | |
| { | |
| "entropy": 1.9288868740200997, | |
| "epoch": 1.7902247924633896, | |
| "grad_norm": 3.0, | |
| "learning_rate": 2.5206809838372747e-06, | |
| "loss": 0.954, | |
| "mean_token_accuracy": 0.7834418945014476, | |
| "num_tokens": 254958402.0, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.7902247924633896, | |
| "eval_entropy": 1.9260941276901877, | |
| "eval_loss": 0.7932396531105042, | |
| "eval_mean_token_accuracy": 0.7890994557037881, | |
| "eval_num_tokens": 254958402.0, | |
| "eval_runtime": 416.7399, | |
| "eval_samples_per_second": 2.08, | |
| "eval_steps_per_second": 0.521, | |
| "step": 2400 | |
| }, | |
| { | |
| "entropy": 1.9224698156118394, | |
| "epoch": 1.7939557877063708, | |
| "grad_norm": 2.8125, | |
| "learning_rate": 2.502616592665756e-06, | |
| "loss": 1.0307, | |
| "mean_token_accuracy": 0.7735580526292324, | |
| "num_tokens": 255491551.0, | |
| "step": 2405 | |
| }, | |
| { | |
| "entropy": 1.9186719000339507, | |
| "epoch": 1.7976867829493517, | |
| "grad_norm": 2.90625, | |
| "learning_rate": 2.48486211674206e-06, | |
| "loss": 0.9552, | |
| "mean_token_accuracy": 0.7844504326581955, | |
| "num_tokens": 256022334.0, | |
| "step": 2410 | |
| }, | |
| { | |
| "entropy": 1.928916445374489, | |
| "epoch": 1.8014177781923328, | |
| "grad_norm": 2.78125, | |
| "learning_rate": 2.4674182036046756e-06, | |
| "loss": 0.856, | |
| "mean_token_accuracy": 0.8019163817167282, | |
| "num_tokens": 256554715.0, | |
| "step": 2415 | |
| }, | |
| { | |
| "entropy": 1.920437340438366, | |
| "epoch": 1.805148773435314, | |
| "grad_norm": 2.875, | |
| "learning_rate": 2.45028548946529e-06, | |
| "loss": 0.9485, | |
| "mean_token_accuracy": 0.7907397754490375, | |
| "num_tokens": 257087212.0, | |
| "step": 2420 | |
| }, | |
| { | |
| "entropy": 1.9137002557516098, | |
| "epoch": 1.808879768678295, | |
| "grad_norm": 2.796875, | |
| "learning_rate": 2.4334645991855948e-06, | |
| "loss": 0.9036, | |
| "mean_token_accuracy": 0.7897277273237705, | |
| "num_tokens": 257619612.0, | |
| "step": 2425 | |
| }, | |
| { | |
| "entropy": 1.9229405611753463, | |
| "epoch": 1.8126107639212758, | |
| "grad_norm": 2.9375, | |
| "learning_rate": 2.4169561462544875e-06, | |
| "loss": 0.9088, | |
| "mean_token_accuracy": 0.7894883915781975, | |
| "num_tokens": 258151703.0, | |
| "step": 2430 | |
| }, | |
| { | |
| "entropy": 1.921665945649147, | |
| "epoch": 1.8163417591642572, | |
| "grad_norm": 3.109375, | |
| "learning_rate": 2.400760732765699e-06, | |
| "loss": 0.9314, | |
| "mean_token_accuracy": 0.7824103131890296, | |
| "num_tokens": 258683838.0, | |
| "step": 2435 | |
| }, | |
| { | |
| "entropy": 1.9171794831752778, | |
| "epoch": 1.8200727544072381, | |
| "grad_norm": 2.796875, | |
| "learning_rate": 2.384878949395834e-06, | |
| "loss": 1.0209, | |
| "mean_token_accuracy": 0.7705119363963604, | |
| "num_tokens": 259215447.0, | |
| "step": 2440 | |
| }, | |
| { | |
| "entropy": 1.9318658068776131, | |
| "epoch": 1.823803749650219, | |
| "grad_norm": 2.859375, | |
| "learning_rate": 2.3693113753828303e-06, | |
| "loss": 0.9432, | |
| "mean_token_accuracy": 0.790088453143835, | |
| "num_tokens": 259746239.0, | |
| "step": 2445 | |
| }, | |
| { | |
| "entropy": 1.9272696867585182, | |
| "epoch": 1.8275347448932002, | |
| "grad_norm": 2.78125, | |
| "learning_rate": 2.354058578504828e-06, | |
| "loss": 0.9821, | |
| "mean_token_accuracy": 0.7820963867008686, | |
| "num_tokens": 260276474.0, | |
| "step": 2450 | |
| }, | |
| { | |
| "entropy": 1.9249881833791733, | |
| "epoch": 1.8312657401361814, | |
| "grad_norm": 2.625, | |
| "learning_rate": 2.3391211150594658e-06, | |
| "loss": 0.9845, | |
| "mean_token_accuracy": 0.7766280405223369, | |
| "num_tokens": 260807881.0, | |
| "step": 2455 | |
| }, | |
| { | |
| "entropy": 1.9197756513953208, | |
| "epoch": 1.8349967353791623, | |
| "grad_norm": 2.875, | |
| "learning_rate": 2.324499529843591e-06, | |
| "loss": 1.0046, | |
| "mean_token_accuracy": 0.7696422345936298, | |
| "num_tokens": 261338350.0, | |
| "step": 2460 | |
| }, | |
| { | |
| "entropy": 1.9283653423190117, | |
| "epoch": 1.8387277306221435, | |
| "grad_norm": 3.078125, | |
| "learning_rate": 2.310194356133389e-06, | |
| "loss": 0.9167, | |
| "mean_token_accuracy": 0.7916576892137528, | |
| "num_tokens": 261871446.0, | |
| "step": 2465 | |
| }, | |
| { | |
| "entropy": 1.924713484942913, | |
| "epoch": 1.8424587258651246, | |
| "grad_norm": 2.9375, | |
| "learning_rate": 2.296206115664932e-06, | |
| "loss": 0.9699, | |
| "mean_token_accuracy": 0.780182758718729, | |
| "num_tokens": 262404727.0, | |
| "step": 2470 | |
| }, | |
| { | |
| "entropy": 1.9232066422700882, | |
| "epoch": 1.8461897211081055, | |
| "grad_norm": 2.796875, | |
| "learning_rate": 2.282535318615156e-06, | |
| "loss": 0.959, | |
| "mean_token_accuracy": 0.7938723795115947, | |
| "num_tokens": 262937258.0, | |
| "step": 2475 | |
| }, | |
| { | |
| "entropy": 1.9326208502054214, | |
| "epoch": 1.8499207163510867, | |
| "grad_norm": 2.75, | |
| "learning_rate": 2.2691824635832447e-06, | |
| "loss": 0.9705, | |
| "mean_token_accuracy": 0.7897952258586883, | |
| "num_tokens": 263467509.0, | |
| "step": 2480 | |
| }, | |
| { | |
| "entropy": 1.9184764593839645, | |
| "epoch": 1.8536517115940678, | |
| "grad_norm": 2.765625, | |
| "learning_rate": 2.2561480375724545e-06, | |
| "loss": 0.981, | |
| "mean_token_accuracy": 0.7857754305005074, | |
| "num_tokens": 263998964.0, | |
| "step": 2485 | |
| }, | |
| { | |
| "entropy": 1.922873741388321, | |
| "epoch": 1.8573827068370488, | |
| "grad_norm": 2.625, | |
| "learning_rate": 2.2434325159723475e-06, | |
| "loss": 0.9843, | |
| "mean_token_accuracy": 0.7813891164958477, | |
| "num_tokens": 264528676.0, | |
| "step": 2490 | |
| }, | |
| { | |
| "entropy": 1.9227689027786254, | |
| "epoch": 1.8611137020800297, | |
| "grad_norm": 2.6875, | |
| "learning_rate": 2.231036362541451e-06, | |
| "loss": 1.0119, | |
| "mean_token_accuracy": 0.7707612752914429, | |
| "num_tokens": 265058995.0, | |
| "step": 2495 | |
| }, | |
| { | |
| "entropy": 1.9281268939375877, | |
| "epoch": 1.864844697323011, | |
| "grad_norm": 2.796875, | |
| "learning_rate": 2.218960029390347e-06, | |
| "loss": 0.8987, | |
| "mean_token_accuracy": 0.7969741009175777, | |
| "num_tokens": 265589875.0, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.864844697323011, | |
| "eval_entropy": 1.9268543950973018, | |
| "eval_loss": 0.7931507229804993, | |
| "eval_mean_token_accuracy": 0.7893393185281534, | |
| "eval_num_tokens": 265589875.0, | |
| "eval_runtime": 405.8579, | |
| "eval_samples_per_second": 2.136, | |
| "eval_steps_per_second": 0.535, | |
| "step": 2500 | |
| }, | |
| { | |
| "entropy": 1.9152730286121369, | |
| "epoch": 1.868575692565992, | |
| "grad_norm": 2.6875, | |
| "learning_rate": 2.2072039569651845e-06, | |
| "loss": 0.968, | |
| "mean_token_accuracy": 0.7776608653366566, | |
| "num_tokens": 266121755.0, | |
| "step": 2505 | |
| }, | |
| { | |
| "entropy": 1.9201575055718423, | |
| "epoch": 1.872306687808973, | |
| "grad_norm": 3.0625, | |
| "learning_rate": 2.1957685740316082e-06, | |
| "loss": 0.965, | |
| "mean_token_accuracy": 0.7823125168681144, | |
| "num_tokens": 266652176.0, | |
| "step": 2510 | |
| }, | |
| { | |
| "entropy": 1.9179353535175323, | |
| "epoch": 1.876037683051954, | |
| "grad_norm": 2.96875, | |
| "learning_rate": 2.1846542976591307e-06, | |
| "loss": 0.9728, | |
| "mean_token_accuracy": 0.7809740528464317, | |
| "num_tokens": 267184426.0, | |
| "step": 2515 | |
| }, | |
| { | |
| "entropy": 1.925567814707756, | |
| "epoch": 1.8797686782949352, | |
| "grad_norm": 3.015625, | |
| "learning_rate": 2.1738615332059143e-06, | |
| "loss": 0.97, | |
| "mean_token_accuracy": 0.7776124000549316, | |
| "num_tokens": 267714012.0, | |
| "step": 2520 | |
| }, | |
| { | |
| "entropy": 1.9293931931257249, | |
| "epoch": 1.8834996735379161, | |
| "grad_norm": 3.15625, | |
| "learning_rate": 2.163390674303985e-06, | |
| "loss": 0.9549, | |
| "mean_token_accuracy": 0.7903631627559662, | |
| "num_tokens": 268243632.0, | |
| "step": 2525 | |
| }, | |
| { | |
| "entropy": 1.917325484752655, | |
| "epoch": 1.8872306687808973, | |
| "grad_norm": 2.75, | |
| "learning_rate": 2.153242102844884e-06, | |
| "loss": 1.0178, | |
| "mean_token_accuracy": 0.7697039887309074, | |
| "num_tokens": 268774277.0, | |
| "step": 2530 | |
| }, | |
| { | |
| "entropy": 1.9345811545848846, | |
| "epoch": 1.8909616640238784, | |
| "grad_norm": 2.859375, | |
| "learning_rate": 2.1434161889657344e-06, | |
| "loss": 0.9233, | |
| "mean_token_accuracy": 0.7909011483192444, | |
| "num_tokens": 269303608.0, | |
| "step": 2535 | |
| }, | |
| { | |
| "entropy": 1.9219995021820069, | |
| "epoch": 1.8946926592668594, | |
| "grad_norm": 2.640625, | |
| "learning_rate": 2.133913291035738e-06, | |
| "loss": 0.9395, | |
| "mean_token_accuracy": 0.7876539684832096, | |
| "num_tokens": 269836167.0, | |
| "step": 2540 | |
| }, | |
| { | |
| "entropy": 1.9185631155967713, | |
| "epoch": 1.8984236545098405, | |
| "grad_norm": 2.78125, | |
| "learning_rate": 2.1247337556431135e-06, | |
| "loss": 0.9905, | |
| "mean_token_accuracy": 0.7754731863737107, | |
| "num_tokens": 270367576.0, | |
| "step": 2545 | |
| }, | |
| { | |
| "entropy": 1.9295933306217194, | |
| "epoch": 1.9021546497528217, | |
| "grad_norm": 2.703125, | |
| "learning_rate": 2.1158779175824527e-06, | |
| "loss": 0.9171, | |
| "mean_token_accuracy": 0.7968859523534775, | |
| "num_tokens": 270898012.0, | |
| "step": 2550 | |
| }, | |
| { | |
| "entropy": 1.917301008105278, | |
| "epoch": 1.9058856449958026, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 2.107346099842501e-06, | |
| "loss": 0.965, | |
| "mean_token_accuracy": 0.7783635087311268, | |
| "num_tokens": 271427122.0, | |
| "step": 2555 | |
| }, | |
| { | |
| "entropy": 1.9307295560836792, | |
| "epoch": 1.9096166402387837, | |
| "grad_norm": 2.875, | |
| "learning_rate": 2.099138613594394e-06, | |
| "loss": 0.9469, | |
| "mean_token_accuracy": 0.7890574164688587, | |
| "num_tokens": 271956636.0, | |
| "step": 2560 | |
| }, | |
| { | |
| "entropy": 1.9290086671710014, | |
| "epoch": 1.913347635481765, | |
| "grad_norm": 2.78125, | |
| "learning_rate": 2.091255758180293e-06, | |
| "loss": 0.9692, | |
| "mean_token_accuracy": 0.7894337013363838, | |
| "num_tokens": 272486655.0, | |
| "step": 2565 | |
| }, | |
| { | |
| "entropy": 1.9271051108837127, | |
| "epoch": 1.9170786307247458, | |
| "grad_norm": 2.984375, | |
| "learning_rate": 2.0836978211024754e-06, | |
| "loss": 0.9693, | |
| "mean_token_accuracy": 0.7833365269005299, | |
| "num_tokens": 273018975.0, | |
| "step": 2570 | |
| }, | |
| { | |
| "entropy": 1.9174389943480492, | |
| "epoch": 1.9208096259677268, | |
| "grad_norm": 2.8125, | |
| "learning_rate": 2.0764650780128517e-06, | |
| "loss": 0.9338, | |
| "mean_token_accuracy": 0.7890181943774224, | |
| "num_tokens": 273549264.0, | |
| "step": 2575 | |
| }, | |
| { | |
| "entropy": 1.9197008699178695, | |
| "epoch": 1.924540621210708, | |
| "grad_norm": 3.078125, | |
| "learning_rate": 2.069557792702903e-06, | |
| "loss": 0.9289, | |
| "mean_token_accuracy": 0.791838351637125, | |
| "num_tokens": 274080352.0, | |
| "step": 2580 | |
| }, | |
| { | |
| "entropy": 1.9107312351465224, | |
| "epoch": 1.928271616453689, | |
| "grad_norm": 2.5625, | |
| "learning_rate": 2.0629762170940656e-06, | |
| "loss": 1.0158, | |
| "mean_token_accuracy": 0.7829626590013504, | |
| "num_tokens": 274611815.0, | |
| "step": 2585 | |
| }, | |
| { | |
| "entropy": 1.932517835497856, | |
| "epoch": 1.93200261169667, | |
| "grad_norm": 2.765625, | |
| "learning_rate": 2.056720591228543e-06, | |
| "loss": 0.956, | |
| "mean_token_accuracy": 0.7831753470003605, | |
| "num_tokens": 275141325.0, | |
| "step": 2590 | |
| }, | |
| { | |
| "entropy": 1.9160398855805396, | |
| "epoch": 1.9357336069396511, | |
| "grad_norm": 2.765625, | |
| "learning_rate": 2.0507911432605516e-06, | |
| "loss": 0.9787, | |
| "mean_token_accuracy": 0.778945604711771, | |
| "num_tokens": 275673810.0, | |
| "step": 2595 | |
| }, | |
| { | |
| "entropy": 1.9250822380185126, | |
| "epoch": 1.9394646021826323, | |
| "grad_norm": 2.96875, | |
| "learning_rate": 2.045188089447994e-06, | |
| "loss": 0.9509, | |
| "mean_token_accuracy": 0.782188569009304, | |
| "num_tokens": 276205721.0, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.9394646021826323, | |
| "eval_entropy": 1.9263563881271994, | |
| "eval_loss": 0.7933353781700134, | |
| "eval_mean_token_accuracy": 0.7889978152266296, | |
| "eval_num_tokens": 276205721.0, | |
| "eval_runtime": 416.0362, | |
| "eval_samples_per_second": 2.084, | |
| "eval_steps_per_second": 0.522, | |
| "step": 2600 | |
| }, | |
| { | |
| "entropy": 1.9174866080284119, | |
| "epoch": 1.9431955974256132, | |
| "grad_norm": 2.796875, | |
| "learning_rate": 2.0399116341445807e-06, | |
| "loss": 1.006, | |
| "mean_token_accuracy": 0.775168327987194, | |
| "num_tokens": 276736589.0, | |
| "step": 2605 | |
| }, | |
| { | |
| "entropy": 1.9143609598278999, | |
| "epoch": 1.9469265926685944, | |
| "grad_norm": 2.671875, | |
| "learning_rate": 2.0349619697923697e-06, | |
| "loss": 1.0056, | |
| "mean_token_accuracy": 0.7784153208136558, | |
| "num_tokens": 277267929.0, | |
| "step": 2610 | |
| }, | |
| { | |
| "entropy": 1.9196015775203705, | |
| "epoch": 1.9506575879115755, | |
| "grad_norm": 2.703125, | |
| "learning_rate": 2.0303392769147507e-06, | |
| "loss": 0.9649, | |
| "mean_token_accuracy": 0.7793896451592446, | |
| "num_tokens": 277800473.0, | |
| "step": 2615 | |
| }, | |
| { | |
| "entropy": 1.9250148937106133, | |
| "epoch": 1.9543885831545564, | |
| "grad_norm": 2.671875, | |
| "learning_rate": 2.0260437241098584e-06, | |
| "loss": 0.9311, | |
| "mean_token_accuracy": 0.7856952168047429, | |
| "num_tokens": 278332246.0, | |
| "step": 2620 | |
| }, | |
| { | |
| "entropy": 1.9160726517438889, | |
| "epoch": 1.9581195783975376, | |
| "grad_norm": 2.640625, | |
| "learning_rate": 2.0220754680444303e-06, | |
| "loss": 1.0071, | |
| "mean_token_accuracy": 0.7723523326218128, | |
| "num_tokens": 278865988.0, | |
| "step": 2625 | |
| }, | |
| { | |
| "entropy": 1.9222462639212607, | |
| "epoch": 1.9618505736405187, | |
| "grad_norm": 2.90625, | |
| "learning_rate": 2.0184346534480832e-06, | |
| "loss": 0.9767, | |
| "mean_token_accuracy": 0.7792594291269779, | |
| "num_tokens": 279397039.0, | |
| "step": 2630 | |
| }, | |
| { | |
| "entropy": 1.9240744143724442, | |
| "epoch": 1.9655815688834997, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 2.015121413108043e-06, | |
| "loss": 0.9444, | |
| "mean_token_accuracy": 0.789904459565878, | |
| "num_tokens": 279929289.0, | |
| "step": 2635 | |
| }, | |
| { | |
| "entropy": 1.9292493999004363, | |
| "epoch": 1.9693125641264806, | |
| "grad_norm": 2.890625, | |
| "learning_rate": 2.012135867864295e-06, | |
| "loss": 0.9963, | |
| "mean_token_accuracy": 0.7859659023582936, | |
| "num_tokens": 280459438.0, | |
| "step": 2640 | |
| }, | |
| { | |
| "entropy": 1.9246867805719376, | |
| "epoch": 1.973043559369462, | |
| "grad_norm": 2.546875, | |
| "learning_rate": 2.009478126605184e-06, | |
| "loss": 1.0206, | |
| "mean_token_accuracy": 0.7676692776381969, | |
| "num_tokens": 280990158.0, | |
| "step": 2645 | |
| }, | |
| { | |
| "entropy": 1.917986649274826, | |
| "epoch": 1.976774554612443, | |
| "grad_norm": 2.921875, | |
| "learning_rate": 2.0071482862634343e-06, | |
| "loss": 0.8863, | |
| "mean_token_accuracy": 0.7945875555276871, | |
| "num_tokens": 281521698.0, | |
| "step": 2650 | |
| }, | |
| { | |
| "entropy": 1.9185520693659783, | |
| "epoch": 1.9805055498554238, | |
| "grad_norm": 2.78125, | |
| "learning_rate": 2.0051464318126223e-06, | |
| "loss": 1.0, | |
| "mean_token_accuracy": 0.7771862842142582, | |
| "num_tokens": 282052844.0, | |
| "step": 2655 | |
| }, | |
| { | |
| "entropy": 1.9054419621825218, | |
| "epoch": 1.984236545098405, | |
| "grad_norm": 2.984375, | |
| "learning_rate": 2.0034726362640712e-06, | |
| "loss": 0.9117, | |
| "mean_token_accuracy": 0.7958167672157288, | |
| "num_tokens": 282582899.0, | |
| "step": 2660 | |
| }, | |
| { | |
| "entropy": 1.9172074422240257, | |
| "epoch": 1.9879675403413861, | |
| "grad_norm": 2.96875, | |
| "learning_rate": 2.002126960664194e-06, | |
| "loss": 0.9155, | |
| "mean_token_accuracy": 0.7893202118575573, | |
| "num_tokens": 283116002.0, | |
| "step": 2665 | |
| }, | |
| { | |
| "entropy": 1.9196871653199197, | |
| "epoch": 1.991698535584367, | |
| "grad_norm": 2.859375, | |
| "learning_rate": 2.0011094540922605e-06, | |
| "loss": 0.9836, | |
| "mean_token_accuracy": 0.7831322841346264, | |
| "num_tokens": 283646490.0, | |
| "step": 2670 | |
| }, | |
| { | |
| "entropy": 1.924867632985115, | |
| "epoch": 1.9954295308273482, | |
| "grad_norm": 2.75, | |
| "learning_rate": 2.000420153658614e-06, | |
| "loss": 0.9986, | |
| "mean_token_accuracy": 0.7747132256627083, | |
| "num_tokens": 284178743.0, | |
| "step": 2675 | |
| }, | |
| { | |
| "entropy": 1.9152036324143409, | |
| "epoch": 1.9991605260703293, | |
| "grad_norm": 2.640625, | |
| "learning_rate": 2.000059084503312e-06, | |
| "loss": 1.0037, | |
| "mean_token_accuracy": 0.7744490541517735, | |
| "num_tokens": 284710078.0, | |
| "step": 2680 | |
| }, | |
| { | |
| "entropy": 1.9348924954732258, | |
| "epoch": 2.0, | |
| "mean_token_accuracy": 0.8092464572853513, | |
| "num_tokens": 284829214.0, | |
| "step": 2682, | |
| "total_flos": 4.071862729311437e+17, | |
| "train_loss": 1.0256049086316854, | |
| "train_runtime": 118640.8071, | |
| "train_samples_per_second": 1.446, | |
| "train_steps_per_second": 0.023 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 2682, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 1, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.071862729311437e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |