| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.719208870242733, |
| "eval_steps": 500, |
| "global_step": 900, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 1.3359488248825073, |
| "epoch": 0.0079912096693637, |
| "grad_norm": 13.5, |
| "learning_rate": 0.00018, |
| "loss": 1.1391, |
| "mean_token_accuracy": 0.7321531124413013, |
| "num_tokens": 17863.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 0.8153514951467514, |
| "epoch": 0.0159824193387274, |
| "grad_norm": 0.357421875, |
| "learning_rate": 0.00019855072463768116, |
| "loss": 0.735, |
| "mean_token_accuracy": 0.806717099994421, |
| "num_tokens": 35538.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 0.7226301684975625, |
| "epoch": 0.0239736290080911, |
| "grad_norm": 0.27734375, |
| "learning_rate": 0.00019694041867954914, |
| "loss": 0.6906, |
| "mean_token_accuracy": 0.8121421404182911, |
| "num_tokens": 52898.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 0.7096233293414116, |
| "epoch": 0.0319648386774548, |
| "grad_norm": 0.408203125, |
| "learning_rate": 0.00019533011272141707, |
| "loss": 0.6794, |
| "mean_token_accuracy": 0.8093454599380493, |
| "num_tokens": 71120.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 0.6432753155007959, |
| "epoch": 0.0399560483468185, |
| "grad_norm": 0.29296875, |
| "learning_rate": 0.00019371980676328502, |
| "loss": 0.5778, |
| "mean_token_accuracy": 0.8227488771080971, |
| "num_tokens": 89183.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 0.6528786711394787, |
| "epoch": 0.0479472580161822, |
| "grad_norm": 0.19921875, |
| "learning_rate": 0.000192109500805153, |
| "loss": 0.6056, |
| "mean_token_accuracy": 0.8218209922313691, |
| "num_tokens": 108013.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 0.6535129006952047, |
| "epoch": 0.055938467685545896, |
| "grad_norm": 0.2236328125, |
| "learning_rate": 0.00019049919484702096, |
| "loss": 0.5954, |
| "mean_token_accuracy": 0.8255642831325531, |
| "num_tokens": 126649.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 0.6079864472150802, |
| "epoch": 0.0639296773549096, |
| "grad_norm": 0.2001953125, |
| "learning_rate": 0.00018888888888888888, |
| "loss": 0.5911, |
| "mean_token_accuracy": 0.8231404431164264, |
| "num_tokens": 144182.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 0.6695162910968065, |
| "epoch": 0.0719208870242733, |
| "grad_norm": 0.1962890625, |
| "learning_rate": 0.00018727858293075687, |
| "loss": 0.6312, |
| "mean_token_accuracy": 0.8185268670320511, |
| "num_tokens": 163634.0, |
| "step": 90 |
| }, |
| { |
| "entropy": 0.6382982328534126, |
| "epoch": 0.079912096693637, |
| "grad_norm": 0.2109375, |
| "learning_rate": 0.00018566827697262482, |
| "loss": 0.5965, |
| "mean_token_accuracy": 0.8219615206122398, |
| "num_tokens": 182899.0, |
| "step": 100 |
| }, |
| { |
| "entropy": 0.615644377656281, |
| "epoch": 0.0879033063630007, |
| "grad_norm": 0.17578125, |
| "learning_rate": 0.00018405797101449275, |
| "loss": 0.555, |
| "mean_token_accuracy": 0.8339135125279427, |
| "num_tokens": 201540.0, |
| "step": 110 |
| }, |
| { |
| "entropy": 0.6227292243391276, |
| "epoch": 0.0958945160323644, |
| "grad_norm": 0.2392578125, |
| "learning_rate": 0.00018244766505636073, |
| "loss": 0.5958, |
| "mean_token_accuracy": 0.822028624266386, |
| "num_tokens": 220163.0, |
| "step": 120 |
| }, |
| { |
| "entropy": 0.6280987083911895, |
| "epoch": 0.1038857257017281, |
| "grad_norm": 0.2177734375, |
| "learning_rate": 0.00018083735909822868, |
| "loss": 0.5827, |
| "mean_token_accuracy": 0.8300345286726951, |
| "num_tokens": 237989.0, |
| "step": 130 |
| }, |
| { |
| "entropy": 0.6323467470705509, |
| "epoch": 0.11187693537109179, |
| "grad_norm": 0.154296875, |
| "learning_rate": 0.00017922705314009664, |
| "loss": 0.5986, |
| "mean_token_accuracy": 0.8197977431118488, |
| "num_tokens": 256250.0, |
| "step": 140 |
| }, |
| { |
| "entropy": 0.6162901744246483, |
| "epoch": 0.1198681450404555, |
| "grad_norm": 0.1552734375, |
| "learning_rate": 0.00017761674718196456, |
| "loss": 0.5769, |
| "mean_token_accuracy": 0.8255695670843124, |
| "num_tokens": 274386.0, |
| "step": 150 |
| }, |
| { |
| "entropy": 0.6158512964844703, |
| "epoch": 0.1278593547098192, |
| "grad_norm": 0.203125, |
| "learning_rate": 0.00017600644122383254, |
| "loss": 0.5713, |
| "mean_token_accuracy": 0.8270042009651661, |
| "num_tokens": 292835.0, |
| "step": 160 |
| }, |
| { |
| "entropy": 0.6406407546252012, |
| "epoch": 0.1358505643791829, |
| "grad_norm": 0.2119140625, |
| "learning_rate": 0.0001743961352657005, |
| "loss": 0.6104, |
| "mean_token_accuracy": 0.8200316116213798, |
| "num_tokens": 310392.0, |
| "step": 170 |
| }, |
| { |
| "entropy": 0.6069310043007136, |
| "epoch": 0.1438417740485466, |
| "grad_norm": 0.1640625, |
| "learning_rate": 0.00017278582930756842, |
| "loss": 0.5624, |
| "mean_token_accuracy": 0.8317995510995388, |
| "num_tokens": 331305.0, |
| "step": 180 |
| }, |
| { |
| "entropy": 0.6235411781817675, |
| "epoch": 0.1518329837179103, |
| "grad_norm": 0.1640625, |
| "learning_rate": 0.0001711755233494364, |
| "loss": 0.5852, |
| "mean_token_accuracy": 0.8278815999627114, |
| "num_tokens": 349604.0, |
| "step": 190 |
| }, |
| { |
| "entropy": 0.6172796195372939, |
| "epoch": 0.159824193387274, |
| "grad_norm": 0.1669921875, |
| "learning_rate": 0.00016956521739130436, |
| "loss": 0.5764, |
| "mean_token_accuracy": 0.8313593462109565, |
| "num_tokens": 367876.0, |
| "step": 200 |
| }, |
| { |
| "entropy": 0.6155283484607935, |
| "epoch": 0.1678154030566377, |
| "grad_norm": 0.1865234375, |
| "learning_rate": 0.00016795491143317231, |
| "loss": 0.5773, |
| "mean_token_accuracy": 0.8269082359969616, |
| "num_tokens": 385573.0, |
| "step": 210 |
| }, |
| { |
| "entropy": 0.6083606427535415, |
| "epoch": 0.1758066127260014, |
| "grad_norm": 0.154296875, |
| "learning_rate": 0.00016634460547504027, |
| "loss": 0.5704, |
| "mean_token_accuracy": 0.8263973362743855, |
| "num_tokens": 404851.0, |
| "step": 220 |
| }, |
| { |
| "entropy": 0.6131238225847483, |
| "epoch": 0.1837978223953651, |
| "grad_norm": 0.20703125, |
| "learning_rate": 0.00016473429951690822, |
| "loss": 0.5817, |
| "mean_token_accuracy": 0.8245558224618434, |
| "num_tokens": 422809.0, |
| "step": 230 |
| }, |
| { |
| "entropy": 0.6223553754389286, |
| "epoch": 0.1917890320647288, |
| "grad_norm": 0.234375, |
| "learning_rate": 0.00016312399355877618, |
| "loss": 0.5871, |
| "mean_token_accuracy": 0.8232570059597493, |
| "num_tokens": 439086.0, |
| "step": 240 |
| }, |
| { |
| "entropy": 0.6230555597692728, |
| "epoch": 0.1997802417340925, |
| "grad_norm": 0.171875, |
| "learning_rate": 0.00016151368760064413, |
| "loss": 0.5751, |
| "mean_token_accuracy": 0.8289580881595612, |
| "num_tokens": 457157.0, |
| "step": 250 |
| }, |
| { |
| "entropy": 0.5794363841414452, |
| "epoch": 0.2077714514034562, |
| "grad_norm": 0.2294921875, |
| "learning_rate": 0.00015990338164251208, |
| "loss": 0.5627, |
| "mean_token_accuracy": 0.8365659207105637, |
| "num_tokens": 474701.0, |
| "step": 260 |
| }, |
| { |
| "entropy": 0.5860258772969246, |
| "epoch": 0.2157626610728199, |
| "grad_norm": 0.1484375, |
| "learning_rate": 0.00015829307568438004, |
| "loss": 0.5363, |
| "mean_token_accuracy": 0.8401569269597531, |
| "num_tokens": 495405.0, |
| "step": 270 |
| }, |
| { |
| "entropy": 0.581408916413784, |
| "epoch": 0.22375387074218359, |
| "grad_norm": 0.205078125, |
| "learning_rate": 0.000156682769726248, |
| "loss": 0.5593, |
| "mean_token_accuracy": 0.8319723285734654, |
| "num_tokens": 512629.0, |
| "step": 280 |
| }, |
| { |
| "entropy": 0.5774631313979626, |
| "epoch": 0.2317450804115473, |
| "grad_norm": 0.171875, |
| "learning_rate": 0.00015507246376811595, |
| "loss": 0.5445, |
| "mean_token_accuracy": 0.8400227598845958, |
| "num_tokens": 531652.0, |
| "step": 290 |
| }, |
| { |
| "entropy": 0.5888700131326914, |
| "epoch": 0.239736290080911, |
| "grad_norm": 0.1884765625, |
| "learning_rate": 0.0001534621578099839, |
| "loss": 0.5475, |
| "mean_token_accuracy": 0.8398719631135464, |
| "num_tokens": 551807.0, |
| "step": 300 |
| }, |
| { |
| "entropy": 0.6303706657141447, |
| "epoch": 0.2477274997502747, |
| "grad_norm": 0.185546875, |
| "learning_rate": 0.00015185185185185185, |
| "loss": 0.5994, |
| "mean_token_accuracy": 0.8221785329282284, |
| "num_tokens": 570173.0, |
| "step": 310 |
| }, |
| { |
| "entropy": 0.591961058229208, |
| "epoch": 0.2557187094196384, |
| "grad_norm": 0.1708984375, |
| "learning_rate": 0.0001502415458937198, |
| "loss": 0.5588, |
| "mean_token_accuracy": 0.8339079335331917, |
| "num_tokens": 587517.0, |
| "step": 320 |
| }, |
| { |
| "entropy": 0.6203833676874637, |
| "epoch": 0.2637099190890021, |
| "grad_norm": 0.158203125, |
| "learning_rate": 0.00014863123993558776, |
| "loss": 0.5993, |
| "mean_token_accuracy": 0.8254540674388409, |
| "num_tokens": 605533.0, |
| "step": 330 |
| }, |
| { |
| "entropy": 0.5948904637247324, |
| "epoch": 0.2717011287583658, |
| "grad_norm": 0.1689453125, |
| "learning_rate": 0.00014702093397745574, |
| "loss": 0.5386, |
| "mean_token_accuracy": 0.835470549017191, |
| "num_tokens": 623145.0, |
| "step": 340 |
| }, |
| { |
| "entropy": 0.5892129261046648, |
| "epoch": 0.2796923384277295, |
| "grad_norm": 0.2041015625, |
| "learning_rate": 0.00014541062801932367, |
| "loss": 0.5445, |
| "mean_token_accuracy": 0.8327487081289291, |
| "num_tokens": 642429.0, |
| "step": 350 |
| }, |
| { |
| "entropy": 0.58230458535254, |
| "epoch": 0.2876835480970932, |
| "grad_norm": 0.1748046875, |
| "learning_rate": 0.00014380032206119162, |
| "loss": 0.5458, |
| "mean_token_accuracy": 0.8369288526475429, |
| "num_tokens": 660595.0, |
| "step": 360 |
| }, |
| { |
| "entropy": 0.5953514769673347, |
| "epoch": 0.2956747577664569, |
| "grad_norm": 0.1494140625, |
| "learning_rate": 0.0001421900161030596, |
| "loss": 0.5564, |
| "mean_token_accuracy": 0.8314083501696586, |
| "num_tokens": 680301.0, |
| "step": 370 |
| }, |
| { |
| "entropy": 0.6272314839065075, |
| "epoch": 0.3036659674358206, |
| "grad_norm": 0.189453125, |
| "learning_rate": 0.00014057971014492753, |
| "loss": 0.5879, |
| "mean_token_accuracy": 0.8269149273633957, |
| "num_tokens": 698836.0, |
| "step": 380 |
| }, |
| { |
| "entropy": 0.5974850662052631, |
| "epoch": 0.3116571771051843, |
| "grad_norm": 0.1875, |
| "learning_rate": 0.0001389694041867955, |
| "loss": 0.5567, |
| "mean_token_accuracy": 0.8330555327236653, |
| "num_tokens": 717301.0, |
| "step": 390 |
| }, |
| { |
| "entropy": 0.610439121723175, |
| "epoch": 0.319648386774548, |
| "grad_norm": 0.1943359375, |
| "learning_rate": 0.00013735909822866347, |
| "loss": 0.5798, |
| "mean_token_accuracy": 0.8273908801376819, |
| "num_tokens": 735623.0, |
| "step": 400 |
| }, |
| { |
| "entropy": 0.6218720726668835, |
| "epoch": 0.3276395964439117, |
| "grad_norm": 0.1689453125, |
| "learning_rate": 0.00013574879227053142, |
| "loss": 0.5681, |
| "mean_token_accuracy": 0.8264160886406898, |
| "num_tokens": 754095.0, |
| "step": 410 |
| }, |
| { |
| "entropy": 0.5961160399019718, |
| "epoch": 0.3356308061132754, |
| "grad_norm": 0.130859375, |
| "learning_rate": 0.00013413848631239935, |
| "loss": 0.5649, |
| "mean_token_accuracy": 0.8278753645718098, |
| "num_tokens": 772932.0, |
| "step": 420 |
| }, |
| { |
| "entropy": 0.5970222994685173, |
| "epoch": 0.3436220157826391, |
| "grad_norm": 0.1552734375, |
| "learning_rate": 0.0001325281803542673, |
| "loss": 0.5717, |
| "mean_token_accuracy": 0.8289826177060604, |
| "num_tokens": 791954.0, |
| "step": 430 |
| }, |
| { |
| "entropy": 0.5869237255305052, |
| "epoch": 0.3516132254520028, |
| "grad_norm": 0.23828125, |
| "learning_rate": 0.00013091787439613528, |
| "loss": 0.5424, |
| "mean_token_accuracy": 0.8353226915001869, |
| "num_tokens": 810372.0, |
| "step": 440 |
| }, |
| { |
| "entropy": 0.6047268303111195, |
| "epoch": 0.3596044351213665, |
| "grad_norm": 0.16015625, |
| "learning_rate": 0.0001293075684380032, |
| "loss": 0.5816, |
| "mean_token_accuracy": 0.8292522899806499, |
| "num_tokens": 828031.0, |
| "step": 450 |
| }, |
| { |
| "entropy": 0.6398113902658225, |
| "epoch": 0.3675956447907302, |
| "grad_norm": 0.193359375, |
| "learning_rate": 0.00012769726247987117, |
| "loss": 0.587, |
| "mean_token_accuracy": 0.8254243724048138, |
| "num_tokens": 844965.0, |
| "step": 460 |
| }, |
| { |
| "entropy": 0.5699722157791257, |
| "epoch": 0.3755868544600939, |
| "grad_norm": 0.150390625, |
| "learning_rate": 0.00012608695652173915, |
| "loss": 0.5302, |
| "mean_token_accuracy": 0.8379433415830135, |
| "num_tokens": 864068.0, |
| "step": 470 |
| }, |
| { |
| "entropy": 0.6004057168960572, |
| "epoch": 0.3835780641294576, |
| "grad_norm": 0.1689453125, |
| "learning_rate": 0.0001244766505636071, |
| "loss": 0.5735, |
| "mean_token_accuracy": 0.8319472163915634, |
| "num_tokens": 882516.0, |
| "step": 480 |
| }, |
| { |
| "entropy": 0.612379564717412, |
| "epoch": 0.3915692737988213, |
| "grad_norm": 0.17578125, |
| "learning_rate": 0.00012286634460547503, |
| "loss": 0.5605, |
| "mean_token_accuracy": 0.8312513306736946, |
| "num_tokens": 901332.0, |
| "step": 490 |
| }, |
| { |
| "entropy": 0.5999802689999342, |
| "epoch": 0.399560483468185, |
| "grad_norm": 0.2236328125, |
| "learning_rate": 0.00012125603864734301, |
| "loss": 0.5844, |
| "mean_token_accuracy": 0.8295043386518955, |
| "num_tokens": 918902.0, |
| "step": 500 |
| }, |
| { |
| "entropy": 0.6438330963253975, |
| "epoch": 0.4075516931375487, |
| "grad_norm": 0.181640625, |
| "learning_rate": 0.00011964573268921095, |
| "loss": 0.6039, |
| "mean_token_accuracy": 0.8217731453478336, |
| "num_tokens": 937381.0, |
| "step": 510 |
| }, |
| { |
| "entropy": 0.557589478418231, |
| "epoch": 0.4155429028069124, |
| "grad_norm": 0.1748046875, |
| "learning_rate": 0.0001180354267310789, |
| "loss": 0.5347, |
| "mean_token_accuracy": 0.8419624336063862, |
| "num_tokens": 956408.0, |
| "step": 520 |
| }, |
| { |
| "entropy": 0.5831106752157211, |
| "epoch": 0.4235341124762761, |
| "grad_norm": 0.15625, |
| "learning_rate": 0.00011642512077294687, |
| "loss": 0.5566, |
| "mean_token_accuracy": 0.8344054028391839, |
| "num_tokens": 974727.0, |
| "step": 530 |
| }, |
| { |
| "entropy": 0.6096597962081433, |
| "epoch": 0.4315253221456398, |
| "grad_norm": 0.16015625, |
| "learning_rate": 0.00011481481481481482, |
| "loss": 0.5906, |
| "mean_token_accuracy": 0.8249844819307327, |
| "num_tokens": 992039.0, |
| "step": 540 |
| }, |
| { |
| "entropy": 0.6296380385756493, |
| "epoch": 0.4395165318150035, |
| "grad_norm": 0.185546875, |
| "learning_rate": 0.00011320450885668277, |
| "loss": 0.5774, |
| "mean_token_accuracy": 0.8290597923099995, |
| "num_tokens": 1010746.0, |
| "step": 550 |
| }, |
| { |
| "entropy": 0.5989726323634386, |
| "epoch": 0.44750774148436717, |
| "grad_norm": 0.1552734375, |
| "learning_rate": 0.00011159420289855073, |
| "loss": 0.5668, |
| "mean_token_accuracy": 0.8317835494875908, |
| "num_tokens": 1029302.0, |
| "step": 560 |
| }, |
| { |
| "entropy": 0.5985535632818937, |
| "epoch": 0.4554989511537309, |
| "grad_norm": 0.1533203125, |
| "learning_rate": 0.00010998389694041869, |
| "loss": 0.5927, |
| "mean_token_accuracy": 0.8251331336796284, |
| "num_tokens": 1047787.0, |
| "step": 570 |
| }, |
| { |
| "entropy": 0.5919383157044649, |
| "epoch": 0.4634901608230946, |
| "grad_norm": 0.140625, |
| "learning_rate": 0.00010837359098228663, |
| "loss": 0.5584, |
| "mean_token_accuracy": 0.8338681124150753, |
| "num_tokens": 1067471.0, |
| "step": 580 |
| }, |
| { |
| "entropy": 0.5655450899153948, |
| "epoch": 0.4714813704924583, |
| "grad_norm": 0.146484375, |
| "learning_rate": 0.00010676328502415461, |
| "loss": 0.5343, |
| "mean_token_accuracy": 0.8383485890924931, |
| "num_tokens": 1086046.0, |
| "step": 590 |
| }, |
| { |
| "entropy": 0.616737426072359, |
| "epoch": 0.479472580161822, |
| "grad_norm": 0.173828125, |
| "learning_rate": 0.00010515297906602255, |
| "loss": 0.5908, |
| "mean_token_accuracy": 0.8193590499460697, |
| "num_tokens": 1103227.0, |
| "step": 600 |
| }, |
| { |
| "entropy": 0.5877503883093596, |
| "epoch": 0.4874637898311857, |
| "grad_norm": 0.16796875, |
| "learning_rate": 0.0001035426731078905, |
| "loss": 0.5505, |
| "mean_token_accuracy": 0.8355500593781471, |
| "num_tokens": 1121994.0, |
| "step": 610 |
| }, |
| { |
| "entropy": 0.5908785469830036, |
| "epoch": 0.4954549995005494, |
| "grad_norm": 0.2255859375, |
| "learning_rate": 0.00010193236714975847, |
| "loss": 0.5794, |
| "mean_token_accuracy": 0.8315194040536881, |
| "num_tokens": 1139965.0, |
| "step": 620 |
| }, |
| { |
| "entropy": 0.6211531057953834, |
| "epoch": 0.5034462091699131, |
| "grad_norm": 0.134765625, |
| "learning_rate": 0.00010032206119162641, |
| "loss": 0.5664, |
| "mean_token_accuracy": 0.8258850328624249, |
| "num_tokens": 1159075.0, |
| "step": 630 |
| }, |
| { |
| "entropy": 0.5950863931328059, |
| "epoch": 0.5114374188392768, |
| "grad_norm": 0.1630859375, |
| "learning_rate": 9.871175523349438e-05, |
| "loss": 0.5497, |
| "mean_token_accuracy": 0.8346662126481533, |
| "num_tokens": 1176494.0, |
| "step": 640 |
| }, |
| { |
| "entropy": 0.5760080838575959, |
| "epoch": 0.5194286285086405, |
| "grad_norm": 0.23828125, |
| "learning_rate": 9.710144927536232e-05, |
| "loss": 0.5632, |
| "mean_token_accuracy": 0.8364547491073608, |
| "num_tokens": 1195371.0, |
| "step": 650 |
| }, |
| { |
| "entropy": 0.5897768154740334, |
| "epoch": 0.5274198381780042, |
| "grad_norm": 0.150390625, |
| "learning_rate": 9.549114331723029e-05, |
| "loss": 0.5611, |
| "mean_token_accuracy": 0.8353584706783295, |
| "num_tokens": 1215474.0, |
| "step": 660 |
| }, |
| { |
| "entropy": 0.6259935267269612, |
| "epoch": 0.5354110478473679, |
| "grad_norm": 0.19921875, |
| "learning_rate": 9.388083735909823e-05, |
| "loss": 0.5834, |
| "mean_token_accuracy": 0.8251566261053085, |
| "num_tokens": 1233066.0, |
| "step": 670 |
| }, |
| { |
| "entropy": 0.5858545243740082, |
| "epoch": 0.5434022575167315, |
| "grad_norm": 0.2080078125, |
| "learning_rate": 9.227053140096618e-05, |
| "loss": 0.5709, |
| "mean_token_accuracy": 0.8273489251732826, |
| "num_tokens": 1249355.0, |
| "step": 680 |
| }, |
| { |
| "entropy": 0.6020776845514775, |
| "epoch": 0.5513934671860953, |
| "grad_norm": 0.171875, |
| "learning_rate": 9.066022544283415e-05, |
| "loss": 0.5657, |
| "mean_token_accuracy": 0.8260138787329196, |
| "num_tokens": 1267301.0, |
| "step": 690 |
| }, |
| { |
| "entropy": 0.596510236337781, |
| "epoch": 0.559384676855459, |
| "grad_norm": 0.154296875, |
| "learning_rate": 8.904991948470209e-05, |
| "loss": 0.5557, |
| "mean_token_accuracy": 0.834468311816454, |
| "num_tokens": 1285467.0, |
| "step": 700 |
| }, |
| { |
| "entropy": 0.5882966015487909, |
| "epoch": 0.5673758865248227, |
| "grad_norm": 0.166015625, |
| "learning_rate": 8.743961352657006e-05, |
| "loss": 0.5423, |
| "mean_token_accuracy": 0.8352835536003113, |
| "num_tokens": 1304357.0, |
| "step": 710 |
| }, |
| { |
| "entropy": 0.6191790480166673, |
| "epoch": 0.5753670961941864, |
| "grad_norm": 0.1533203125, |
| "learning_rate": 8.582930756843801e-05, |
| "loss": 0.5759, |
| "mean_token_accuracy": 0.8274984866380691, |
| "num_tokens": 1321602.0, |
| "step": 720 |
| }, |
| { |
| "entropy": 0.6024752855300903, |
| "epoch": 0.5833583058635501, |
| "grad_norm": 0.2001953125, |
| "learning_rate": 8.421900161030597e-05, |
| "loss": 0.5638, |
| "mean_token_accuracy": 0.8288030169904232, |
| "num_tokens": 1340012.0, |
| "step": 730 |
| }, |
| { |
| "entropy": 0.5633068412542344, |
| "epoch": 0.5913495155329138, |
| "grad_norm": 0.1796875, |
| "learning_rate": 8.260869565217392e-05, |
| "loss": 0.5262, |
| "mean_token_accuracy": 0.8409125037491322, |
| "num_tokens": 1358549.0, |
| "step": 740 |
| }, |
| { |
| "entropy": 0.6121923718601465, |
| "epoch": 0.5993407252022775, |
| "grad_norm": 0.1640625, |
| "learning_rate": 8.099838969404187e-05, |
| "loss": 0.5782, |
| "mean_token_accuracy": 0.8247248627245426, |
| "num_tokens": 1376295.0, |
| "step": 750 |
| }, |
| { |
| "entropy": 0.5850671246647835, |
| "epoch": 0.6073319348716412, |
| "grad_norm": 0.12255859375, |
| "learning_rate": 7.938808373590983e-05, |
| "loss": 0.5481, |
| "mean_token_accuracy": 0.8378213487565518, |
| "num_tokens": 1396825.0, |
| "step": 760 |
| }, |
| { |
| "entropy": 0.6004991352558136, |
| "epoch": 0.6153231445410049, |
| "grad_norm": 0.1484375, |
| "learning_rate": 7.777777777777778e-05, |
| "loss": 0.5697, |
| "mean_token_accuracy": 0.8314851686358452, |
| "num_tokens": 1415779.0, |
| "step": 770 |
| }, |
| { |
| "entropy": 0.615888693742454, |
| "epoch": 0.6233143542103686, |
| "grad_norm": 0.1494140625, |
| "learning_rate": 7.616747181964574e-05, |
| "loss": 0.586, |
| "mean_token_accuracy": 0.8290720954537392, |
| "num_tokens": 1433844.0, |
| "step": 780 |
| }, |
| { |
| "entropy": 0.631605738401413, |
| "epoch": 0.6313055638797322, |
| "grad_norm": 0.1787109375, |
| "learning_rate": 7.455716586151369e-05, |
| "loss": 0.5896, |
| "mean_token_accuracy": 0.823421498388052, |
| "num_tokens": 1452173.0, |
| "step": 790 |
| }, |
| { |
| "entropy": 0.5806491080671549, |
| "epoch": 0.639296773549096, |
| "grad_norm": 0.1767578125, |
| "learning_rate": 7.294685990338164e-05, |
| "loss": 0.5541, |
| "mean_token_accuracy": 0.8376387834548951, |
| "num_tokens": 1469089.0, |
| "step": 800 |
| }, |
| { |
| "entropy": 0.5787392556667328, |
| "epoch": 0.6472879832184597, |
| "grad_norm": 0.2734375, |
| "learning_rate": 7.13365539452496e-05, |
| "loss": 0.5344, |
| "mean_token_accuracy": 0.832699004560709, |
| "num_tokens": 1488541.0, |
| "step": 810 |
| }, |
| { |
| "entropy": 0.5935858219861985, |
| "epoch": 0.6552791928878234, |
| "grad_norm": 0.1435546875, |
| "learning_rate": 6.972624798711755e-05, |
| "loss": 0.549, |
| "mean_token_accuracy": 0.8358408592641353, |
| "num_tokens": 1506966.0, |
| "step": 820 |
| }, |
| { |
| "entropy": 0.6146302495151759, |
| "epoch": 0.663270402557187, |
| "grad_norm": 0.15234375, |
| "learning_rate": 6.811594202898552e-05, |
| "loss": 0.5794, |
| "mean_token_accuracy": 0.8260477609932423, |
| "num_tokens": 1526428.0, |
| "step": 830 |
| }, |
| { |
| "entropy": 0.6146373618394136, |
| "epoch": 0.6712616122265508, |
| "grad_norm": 0.169921875, |
| "learning_rate": 6.650563607085346e-05, |
| "loss": 0.5917, |
| "mean_token_accuracy": 0.8253330059349537, |
| "num_tokens": 1543859.0, |
| "step": 840 |
| }, |
| { |
| "entropy": 0.5822377149015665, |
| "epoch": 0.6792528218959145, |
| "grad_norm": 0.1962890625, |
| "learning_rate": 6.489533011272141e-05, |
| "loss": 0.5561, |
| "mean_token_accuracy": 0.8367624327540397, |
| "num_tokens": 1562062.0, |
| "step": 850 |
| }, |
| { |
| "entropy": 0.5773209661245347, |
| "epoch": 0.6872440315652782, |
| "grad_norm": 0.1650390625, |
| "learning_rate": 6.328502415458938e-05, |
| "loss": 0.5144, |
| "mean_token_accuracy": 0.83621421828866, |
| "num_tokens": 1580374.0, |
| "step": 860 |
| }, |
| { |
| "entropy": 0.5891423657536506, |
| "epoch": 0.6952352412346419, |
| "grad_norm": 0.18359375, |
| "learning_rate": 6.167471819645732e-05, |
| "loss": 0.5766, |
| "mean_token_accuracy": 0.8288635179400444, |
| "num_tokens": 1598383.0, |
| "step": 870 |
| }, |
| { |
| "entropy": 0.5979194710031152, |
| "epoch": 0.7032264509040056, |
| "grad_norm": 0.15234375, |
| "learning_rate": 6.006441223832528e-05, |
| "loss": 0.5452, |
| "mean_token_accuracy": 0.8346437945961952, |
| "num_tokens": 1617322.0, |
| "step": 880 |
| }, |
| { |
| "entropy": 0.6381862349808216, |
| "epoch": 0.7112176605733693, |
| "grad_norm": 0.173828125, |
| "learning_rate": 5.8454106280193244e-05, |
| "loss": 0.6008, |
| "mean_token_accuracy": 0.8242271035909653, |
| "num_tokens": 1633941.0, |
| "step": 890 |
| }, |
| { |
| "entropy": 0.5802713014185429, |
| "epoch": 0.719208870242733, |
| "grad_norm": 0.15625, |
| "learning_rate": 5.684380032206119e-05, |
| "loss": 0.5462, |
| "mean_token_accuracy": 0.8342008836567402, |
| "num_tokens": 1651765.0, |
| "step": 900 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 1252, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 8.51066844059566e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
