| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 804, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 1.1184664368629456, |
| "epoch": 0.003734827264239029, |
| "grad_norm": 0.411286324262619, |
| "learning_rate": 0.0002, |
| "loss": 2.457291841506958, |
| "mean_token_accuracy": 0.5408388376235962, |
| "num_tokens": 16491.0, |
| "step": 1 |
| }, |
| { |
| "entropy": 1.2453091144561768, |
| "epoch": 0.007469654528478058, |
| "grad_norm": 0.37089085578918457, |
| "learning_rate": 0.0002, |
| "loss": 2.1685681343078613, |
| "mean_token_accuracy": 0.5649923086166382, |
| "num_tokens": 32759.0, |
| "step": 2 |
| }, |
| { |
| "entropy": 1.4064331948757172, |
| "epoch": 0.011204481792717087, |
| "grad_norm": 0.2906820774078369, |
| "learning_rate": 0.0002, |
| "loss": 1.710010051727295, |
| "mean_token_accuracy": 0.5920955091714859, |
| "num_tokens": 49020.0, |
| "step": 3 |
| }, |
| { |
| "entropy": 1.364386886358261, |
| "epoch": 0.014939309056956116, |
| "grad_norm": 0.22797873616218567, |
| "learning_rate": 0.0002, |
| "loss": 1.3888747692108154, |
| "mean_token_accuracy": 0.6421842128038406, |
| "num_tokens": 65604.0, |
| "step": 4 |
| }, |
| { |
| "entropy": 1.3538264036178589, |
| "epoch": 0.018674136321195144, |
| "grad_norm": 0.2804432809352875, |
| "learning_rate": 0.0002, |
| "loss": 1.29875648021698, |
| "mean_token_accuracy": 0.6417761594057083, |
| "num_tokens": 81941.0, |
| "step": 5 |
| }, |
| { |
| "entropy": 1.2739673852920532, |
| "epoch": 0.022408963585434174, |
| "grad_norm": 0.15289267897605896, |
| "learning_rate": 0.0002, |
| "loss": 1.1843445301055908, |
| "mean_token_accuracy": 0.6661720275878906, |
| "num_tokens": 98022.0, |
| "step": 6 |
| }, |
| { |
| "entropy": 1.1963406801223755, |
| "epoch": 0.026143790849673203, |
| "grad_norm": 0.1057928279042244, |
| "learning_rate": 0.0002, |
| "loss": 1.089585304260254, |
| "mean_token_accuracy": 0.6709173172712326, |
| "num_tokens": 114552.0, |
| "step": 7 |
| }, |
| { |
| "entropy": 1.1228278279304504, |
| "epoch": 0.029878618113912233, |
| "grad_norm": 0.10864286869764328, |
| "learning_rate": 0.0002, |
| "loss": 1.028782844543457, |
| "mean_token_accuracy": 0.6796794384717941, |
| "num_tokens": 130943.0, |
| "step": 8 |
| }, |
| { |
| "entropy": 1.0330480933189392, |
| "epoch": 0.03361344537815126, |
| "grad_norm": 0.1194700375199318, |
| "learning_rate": 0.0002, |
| "loss": 0.978877067565918, |
| "mean_token_accuracy": 0.6896098554134369, |
| "num_tokens": 147432.0, |
| "step": 9 |
| }, |
| { |
| "entropy": 0.9659490436315536, |
| "epoch": 0.03734827264239029, |
| "grad_norm": 0.13075368106365204, |
| "learning_rate": 0.0002, |
| "loss": 0.93321692943573, |
| "mean_token_accuracy": 0.6966541409492493, |
| "num_tokens": 163753.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 0.9611389189958572, |
| "epoch": 0.04108309990662932, |
| "grad_norm": 0.10369610041379929, |
| "learning_rate": 0.0002, |
| "loss": 0.8770816922187805, |
| "mean_token_accuracy": 0.7034913301467896, |
| "num_tokens": 180090.0, |
| "step": 11 |
| }, |
| { |
| "entropy": 0.9063249081373215, |
| "epoch": 0.04481792717086835, |
| "grad_norm": 0.10426584631204605, |
| "learning_rate": 0.0002, |
| "loss": 0.8171504139900208, |
| "mean_token_accuracy": 0.7150022834539413, |
| "num_tokens": 196381.0, |
| "step": 12 |
| }, |
| { |
| "entropy": 0.8290252089500427, |
| "epoch": 0.04855275443510738, |
| "grad_norm": 0.10911860316991806, |
| "learning_rate": 0.0002, |
| "loss": 0.7891132831573486, |
| "mean_token_accuracy": 0.7208491563796997, |
| "num_tokens": 212795.0, |
| "step": 13 |
| }, |
| { |
| "entropy": 0.7808938026428223, |
| "epoch": 0.05228758169934641, |
| "grad_norm": 0.10144662111997604, |
| "learning_rate": 0.0002, |
| "loss": 0.7427304983139038, |
| "mean_token_accuracy": 0.7313003540039062, |
| "num_tokens": 228936.0, |
| "step": 14 |
| }, |
| { |
| "entropy": 0.7421854734420776, |
| "epoch": 0.056022408963585436, |
| "grad_norm": 0.6942080855369568, |
| "learning_rate": 0.0002, |
| "loss": 0.7379668354988098, |
| "mean_token_accuracy": 0.7287779599428177, |
| "num_tokens": 245241.0, |
| "step": 15 |
| }, |
| { |
| "entropy": 0.7045212388038635, |
| "epoch": 0.059757236227824466, |
| "grad_norm": 0.16263937950134277, |
| "learning_rate": 0.0002, |
| "loss": 0.7117007374763489, |
| "mean_token_accuracy": 0.7335064858198166, |
| "num_tokens": 261386.0, |
| "step": 16 |
| }, |
| { |
| "entropy": 0.6911872327327728, |
| "epoch": 0.06349206349206349, |
| "grad_norm": 0.08423176407814026, |
| "learning_rate": 0.0002, |
| "loss": 0.6914121508598328, |
| "mean_token_accuracy": 0.7408997714519501, |
| "num_tokens": 278017.0, |
| "step": 17 |
| }, |
| { |
| "entropy": 0.6928284466266632, |
| "epoch": 0.06722689075630252, |
| "grad_norm": 0.08306165784597397, |
| "learning_rate": 0.0002, |
| "loss": 0.679314911365509, |
| "mean_token_accuracy": 0.7417374551296234, |
| "num_tokens": 294613.0, |
| "step": 18 |
| }, |
| { |
| "entropy": 0.6805895417928696, |
| "epoch": 0.07096171802054155, |
| "grad_norm": 0.7392253279685974, |
| "learning_rate": 0.0002, |
| "loss": 0.6667531728744507, |
| "mean_token_accuracy": 0.7472580522298813, |
| "num_tokens": 311040.0, |
| "step": 19 |
| }, |
| { |
| "entropy": 0.6846933215856552, |
| "epoch": 0.07469654528478058, |
| "grad_norm": 0.08478110283613205, |
| "learning_rate": 0.0002, |
| "loss": 0.6531012654304504, |
| "mean_token_accuracy": 0.7482306957244873, |
| "num_tokens": 327255.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 0.6761725544929504, |
| "epoch": 0.0784313725490196, |
| "grad_norm": 0.07354654371738434, |
| "learning_rate": 0.0002, |
| "loss": 0.6507971882820129, |
| "mean_token_accuracy": 0.7495593726634979, |
| "num_tokens": 343726.0, |
| "step": 21 |
| }, |
| { |
| "entropy": 0.6475691944360733, |
| "epoch": 0.08216619981325864, |
| "grad_norm": 0.0701100155711174, |
| "learning_rate": 0.0002, |
| "loss": 0.6324924826622009, |
| "mean_token_accuracy": 0.7519394010305405, |
| "num_tokens": 360032.0, |
| "step": 22 |
| }, |
| { |
| "entropy": 0.6286474466323853, |
| "epoch": 0.08590102707749767, |
| "grad_norm": 0.07334811985492706, |
| "learning_rate": 0.0002, |
| "loss": 0.6221117377281189, |
| "mean_token_accuracy": 0.7562299370765686, |
| "num_tokens": 376211.0, |
| "step": 23 |
| }, |
| { |
| "entropy": 0.6444061696529388, |
| "epoch": 0.0896358543417367, |
| "grad_norm": 0.10214248299598694, |
| "learning_rate": 0.0002, |
| "loss": 0.6270927786827087, |
| "mean_token_accuracy": 0.7587939649820328, |
| "num_tokens": 392746.0, |
| "step": 24 |
| }, |
| { |
| "entropy": 0.6239012628793716, |
| "epoch": 0.09337068160597572, |
| "grad_norm": 0.07120268046855927, |
| "learning_rate": 0.0002, |
| "loss": 0.6152804493904114, |
| "mean_token_accuracy": 0.7588517516851425, |
| "num_tokens": 409085.0, |
| "step": 25 |
| }, |
| { |
| "entropy": 0.6276111602783203, |
| "epoch": 0.09710550887021475, |
| "grad_norm": 0.05954922363162041, |
| "learning_rate": 0.0002, |
| "loss": 0.6084893345832825, |
| "mean_token_accuracy": 0.7613021731376648, |
| "num_tokens": 425336.0, |
| "step": 26 |
| }, |
| { |
| "entropy": 0.6411866247653961, |
| "epoch": 0.10084033613445378, |
| "grad_norm": 0.05856655165553093, |
| "learning_rate": 0.0002, |
| "loss": 0.6222058534622192, |
| "mean_token_accuracy": 0.7564119845628738, |
| "num_tokens": 441729.0, |
| "step": 27 |
| }, |
| { |
| "entropy": 0.6264622807502747, |
| "epoch": 0.10457516339869281, |
| "grad_norm": 0.06027727574110031, |
| "learning_rate": 0.0002, |
| "loss": 0.6105791330337524, |
| "mean_token_accuracy": 0.7609841376543045, |
| "num_tokens": 457957.0, |
| "step": 28 |
| }, |
| { |
| "entropy": 0.6167244166135788, |
| "epoch": 0.10830999066293184, |
| "grad_norm": 0.07074937224388123, |
| "learning_rate": 0.0002, |
| "loss": 0.6111780405044556, |
| "mean_token_accuracy": 0.7601886689662933, |
| "num_tokens": 474399.0, |
| "step": 29 |
| }, |
| { |
| "entropy": 0.6115850210189819, |
| "epoch": 0.11204481792717087, |
| "grad_norm": 0.07707173377275467, |
| "learning_rate": 0.0002, |
| "loss": 0.6015152335166931, |
| "mean_token_accuracy": 0.7627497315406799, |
| "num_tokens": 490919.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 0.6094368547201157, |
| "epoch": 0.1157796451914099, |
| "grad_norm": 0.059265896677970886, |
| "learning_rate": 0.0002, |
| "loss": 0.6023207902908325, |
| "mean_token_accuracy": 0.758778989315033, |
| "num_tokens": 507283.0, |
| "step": 31 |
| }, |
| { |
| "entropy": 0.6125481128692627, |
| "epoch": 0.11951447245564893, |
| "grad_norm": 0.07099295407533646, |
| "learning_rate": 0.0002, |
| "loss": 0.603573203086853, |
| "mean_token_accuracy": 0.7601557075977325, |
| "num_tokens": 523521.0, |
| "step": 32 |
| }, |
| { |
| "entropy": 0.6020256727933884, |
| "epoch": 0.12324929971988796, |
| "grad_norm": 0.05661124736070633, |
| "learning_rate": 0.0002, |
| "loss": 0.5916649103164673, |
| "mean_token_accuracy": 0.7667604386806488, |
| "num_tokens": 540024.0, |
| "step": 33 |
| }, |
| { |
| "entropy": 0.5748983919620514, |
| "epoch": 0.12698412698412698, |
| "grad_norm": 0.05405418947339058, |
| "learning_rate": 0.0002, |
| "loss": 0.5715272426605225, |
| "mean_token_accuracy": 0.7717257738113403, |
| "num_tokens": 555993.0, |
| "step": 34 |
| }, |
| { |
| "entropy": 0.5811779201030731, |
| "epoch": 0.13071895424836602, |
| "grad_norm": 0.04870233312249184, |
| "learning_rate": 0.0002, |
| "loss": 0.5783013701438904, |
| "mean_token_accuracy": 0.7701490372419357, |
| "num_tokens": 572358.0, |
| "step": 35 |
| }, |
| { |
| "entropy": 0.574293926358223, |
| "epoch": 0.13445378151260504, |
| "grad_norm": 0.05332570523023605, |
| "learning_rate": 0.0002, |
| "loss": 0.5724313259124756, |
| "mean_token_accuracy": 0.7740762829780579, |
| "num_tokens": 588766.0, |
| "step": 36 |
| }, |
| { |
| "entropy": 0.5665481090545654, |
| "epoch": 0.13818860877684408, |
| "grad_norm": 0.0575035996735096, |
| "learning_rate": 0.0002, |
| "loss": 0.5736980438232422, |
| "mean_token_accuracy": 0.7706244140863419, |
| "num_tokens": 604968.0, |
| "step": 37 |
| }, |
| { |
| "entropy": 0.5721801668405533, |
| "epoch": 0.1419234360410831, |
| "grad_norm": 0.07653734087944031, |
| "learning_rate": 0.0002, |
| "loss": 0.5833261013031006, |
| "mean_token_accuracy": 0.7672377377748489, |
| "num_tokens": 621192.0, |
| "step": 38 |
| }, |
| { |
| "entropy": 0.5661971271038055, |
| "epoch": 0.14565826330532214, |
| "grad_norm": 0.052845459431409836, |
| "learning_rate": 0.0002, |
| "loss": 0.5691311955451965, |
| "mean_token_accuracy": 0.7725834846496582, |
| "num_tokens": 637384.0, |
| "step": 39 |
| }, |
| { |
| "entropy": 0.5870122313499451, |
| "epoch": 0.14939309056956115, |
| "grad_norm": 0.05704643577337265, |
| "learning_rate": 0.0002, |
| "loss": 0.5838981866836548, |
| "mean_token_accuracy": 0.7632379680871964, |
| "num_tokens": 653697.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 0.5808418691158295, |
| "epoch": 0.1531279178338002, |
| "grad_norm": 0.05715522915124893, |
| "learning_rate": 0.0002, |
| "loss": 0.5737625360488892, |
| "mean_token_accuracy": 0.7728984951972961, |
| "num_tokens": 670046.0, |
| "step": 41 |
| }, |
| { |
| "entropy": 0.5726363211870193, |
| "epoch": 0.1568627450980392, |
| "grad_norm": 0.053971655666828156, |
| "learning_rate": 0.0002, |
| "loss": 0.5629984736442566, |
| "mean_token_accuracy": 0.7752888798713684, |
| "num_tokens": 686076.0, |
| "step": 42 |
| }, |
| { |
| "entropy": 0.5652015507221222, |
| "epoch": 0.16059757236227826, |
| "grad_norm": 0.04180985689163208, |
| "learning_rate": 0.0002, |
| "loss": 0.5623056292533875, |
| "mean_token_accuracy": 0.7748470306396484, |
| "num_tokens": 702484.0, |
| "step": 43 |
| }, |
| { |
| "entropy": 0.5733779072761536, |
| "epoch": 0.16433239962651727, |
| "grad_norm": 0.050310708582401276, |
| "learning_rate": 0.0002, |
| "loss": 0.5759532451629639, |
| "mean_token_accuracy": 0.7717497199773788, |
| "num_tokens": 718709.0, |
| "step": 44 |
| }, |
| { |
| "entropy": 0.5682821422815323, |
| "epoch": 0.16806722689075632, |
| "grad_norm": 0.049945104867219925, |
| "learning_rate": 0.0002, |
| "loss": 0.5656522512435913, |
| "mean_token_accuracy": 0.7735471576452255, |
| "num_tokens": 735195.0, |
| "step": 45 |
| }, |
| { |
| "entropy": 0.5685591697692871, |
| "epoch": 0.17180205415499533, |
| "grad_norm": 0.044939614832401276, |
| "learning_rate": 0.0002, |
| "loss": 0.5674217939376831, |
| "mean_token_accuracy": 0.7736205905675888, |
| "num_tokens": 751212.0, |
| "step": 46 |
| }, |
| { |
| "entropy": 0.5851640552282333, |
| "epoch": 0.17553688141923435, |
| "grad_norm": 0.0478069968521595, |
| "learning_rate": 0.0002, |
| "loss": 0.5874634981155396, |
| "mean_token_accuracy": 0.7659626305103302, |
| "num_tokens": 767689.0, |
| "step": 47 |
| }, |
| { |
| "entropy": 0.5731439292430878, |
| "epoch": 0.1792717086834734, |
| "grad_norm": 0.046887464821338654, |
| "learning_rate": 0.0002, |
| "loss": 0.571601152420044, |
| "mean_token_accuracy": 0.7696335017681122, |
| "num_tokens": 784074.0, |
| "step": 48 |
| }, |
| { |
| "entropy": 0.5621766149997711, |
| "epoch": 0.1830065359477124, |
| "grad_norm": 0.04711559787392616, |
| "learning_rate": 0.0002, |
| "loss": 0.5606247782707214, |
| "mean_token_accuracy": 0.7760322690010071, |
| "num_tokens": 800292.0, |
| "step": 49 |
| }, |
| { |
| "entropy": 0.5671460330486298, |
| "epoch": 0.18674136321195145, |
| "grad_norm": 0.04404276981949806, |
| "learning_rate": 0.0002, |
| "loss": 0.5589705109596252, |
| "mean_token_accuracy": 0.7788618206977844, |
| "num_tokens": 816651.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 0.5850909501314163, |
| "epoch": 0.19047619047619047, |
| "grad_norm": 0.04509448632597923, |
| "learning_rate": 0.0002, |
| "loss": 0.5727294683456421, |
| "mean_token_accuracy": 0.7689620703458786, |
| "num_tokens": 833150.0, |
| "step": 51 |
| }, |
| { |
| "entropy": 0.585056334733963, |
| "epoch": 0.1942110177404295, |
| "grad_norm": 0.04984965920448303, |
| "learning_rate": 0.0002, |
| "loss": 0.5666245818138123, |
| "mean_token_accuracy": 0.771300658583641, |
| "num_tokens": 849637.0, |
| "step": 52 |
| }, |
| { |
| "entropy": 0.5864798873662949, |
| "epoch": 0.19794584500466852, |
| "grad_norm": 0.03626571223139763, |
| "learning_rate": 0.0002, |
| "loss": 0.5745272636413574, |
| "mean_token_accuracy": 0.7683106511831284, |
| "num_tokens": 865989.0, |
| "step": 53 |
| }, |
| { |
| "entropy": 0.5780556201934814, |
| "epoch": 0.20168067226890757, |
| "grad_norm": 0.043707672506570816, |
| "learning_rate": 0.0002, |
| "loss": 0.5741198062896729, |
| "mean_token_accuracy": 0.7700863778591156, |
| "num_tokens": 882298.0, |
| "step": 54 |
| }, |
| { |
| "entropy": 0.5698854774236679, |
| "epoch": 0.20541549953314658, |
| "grad_norm": 0.04839429631829262, |
| "learning_rate": 0.0002, |
| "loss": 0.5747280120849609, |
| "mean_token_accuracy": 0.7678831219673157, |
| "num_tokens": 898608.0, |
| "step": 55 |
| }, |
| { |
| "entropy": 0.5627169758081436, |
| "epoch": 0.20915032679738563, |
| "grad_norm": 0.04472200199961662, |
| "learning_rate": 0.0002, |
| "loss": 0.5670843124389648, |
| "mean_token_accuracy": 0.7717523276805878, |
| "num_tokens": 914851.0, |
| "step": 56 |
| }, |
| { |
| "entropy": 0.5779636800289154, |
| "epoch": 0.21288515406162464, |
| "grad_norm": 0.040940672159194946, |
| "learning_rate": 0.0002, |
| "loss": 0.5778319239616394, |
| "mean_token_accuracy": 0.7675311863422394, |
| "num_tokens": 931487.0, |
| "step": 57 |
| }, |
| { |
| "entropy": 0.563320592045784, |
| "epoch": 0.2166199813258637, |
| "grad_norm": 0.0448877178132534, |
| "learning_rate": 0.0002, |
| "loss": 0.5575067400932312, |
| "mean_token_accuracy": 0.7765846252441406, |
| "num_tokens": 947878.0, |
| "step": 58 |
| }, |
| { |
| "entropy": 0.6058623939752579, |
| "epoch": 0.2203548085901027, |
| "grad_norm": 0.04985905811190605, |
| "learning_rate": 0.0002, |
| "loss": 0.6082996726036072, |
| "mean_token_accuracy": 0.7539926767349243, |
| "num_tokens": 964324.0, |
| "step": 59 |
| }, |
| { |
| "entropy": 0.5625719428062439, |
| "epoch": 0.22408963585434175, |
| "grad_norm": 0.038407351821660995, |
| "learning_rate": 0.0002, |
| "loss": 0.5598542094230652, |
| "mean_token_accuracy": 0.7735666781663895, |
| "num_tokens": 980437.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 0.5738561451435089, |
| "epoch": 0.22782446311858076, |
| "grad_norm": 0.04555477574467659, |
| "learning_rate": 0.0002, |
| "loss": 0.5709559917449951, |
| "mean_token_accuracy": 0.7690570503473282, |
| "num_tokens": 996568.0, |
| "step": 61 |
| }, |
| { |
| "entropy": 0.5673829317092896, |
| "epoch": 0.2315592903828198, |
| "grad_norm": 0.04602229222655296, |
| "learning_rate": 0.0002, |
| "loss": 0.5713279843330383, |
| "mean_token_accuracy": 0.7713401615619659, |
| "num_tokens": 1012870.0, |
| "step": 62 |
| }, |
| { |
| "entropy": 0.5517095476388931, |
| "epoch": 0.23529411764705882, |
| "grad_norm": 0.043136853724718094, |
| "learning_rate": 0.0002, |
| "loss": 0.5557603240013123, |
| "mean_token_accuracy": 0.7759266495704651, |
| "num_tokens": 1029066.0, |
| "step": 63 |
| }, |
| { |
| "entropy": 0.5658771097660065, |
| "epoch": 0.23902894491129786, |
| "grad_norm": 0.04121146723628044, |
| "learning_rate": 0.0002, |
| "loss": 0.5609080791473389, |
| "mean_token_accuracy": 0.7747898399829865, |
| "num_tokens": 1045590.0, |
| "step": 64 |
| }, |
| { |
| "entropy": 0.549357607960701, |
| "epoch": 0.24276377217553688, |
| "grad_norm": 0.044083524495363235, |
| "learning_rate": 0.0002, |
| "loss": 0.5459793210029602, |
| "mean_token_accuracy": 0.7811493426561356, |
| "num_tokens": 1061874.0, |
| "step": 65 |
| }, |
| { |
| "entropy": 0.5573842078447342, |
| "epoch": 0.24649859943977592, |
| "grad_norm": 0.04087769240140915, |
| "learning_rate": 0.0002, |
| "loss": 0.5592548847198486, |
| "mean_token_accuracy": 0.775547593832016, |
| "num_tokens": 1078103.0, |
| "step": 66 |
| }, |
| { |
| "entropy": 0.5658538043498993, |
| "epoch": 0.25023342670401494, |
| "grad_norm": 0.03777799755334854, |
| "learning_rate": 0.0002, |
| "loss": 0.5519559979438782, |
| "mean_token_accuracy": 0.776710718870163, |
| "num_tokens": 1094650.0, |
| "step": 67 |
| }, |
| { |
| "entropy": 0.583881214261055, |
| "epoch": 0.25396825396825395, |
| "grad_norm": 0.044072795659303665, |
| "learning_rate": 0.0002, |
| "loss": 0.5742916464805603, |
| "mean_token_accuracy": 0.7709541469812393, |
| "num_tokens": 1110961.0, |
| "step": 68 |
| }, |
| { |
| "entropy": 0.5731556266546249, |
| "epoch": 0.25770308123249297, |
| "grad_norm": 0.045354213565588, |
| "learning_rate": 0.0002, |
| "loss": 0.5748150944709778, |
| "mean_token_accuracy": 0.7677215486764908, |
| "num_tokens": 1127571.0, |
| "step": 69 |
| }, |
| { |
| "entropy": 0.5605138093233109, |
| "epoch": 0.26143790849673204, |
| "grad_norm": 0.03672546148300171, |
| "learning_rate": 0.0002, |
| "loss": 0.5605238080024719, |
| "mean_token_accuracy": 0.7723149508237839, |
| "num_tokens": 1143932.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 0.5381516218185425, |
| "epoch": 0.26517273576097106, |
| "grad_norm": 0.04045504331588745, |
| "learning_rate": 0.0002, |
| "loss": 0.5391750335693359, |
| "mean_token_accuracy": 0.7822330445051193, |
| "num_tokens": 1159972.0, |
| "step": 71 |
| }, |
| { |
| "entropy": 0.5469133257865906, |
| "epoch": 0.2689075630252101, |
| "grad_norm": 0.03917838633060455, |
| "learning_rate": 0.0002, |
| "loss": 0.552070140838623, |
| "mean_token_accuracy": 0.776424303650856, |
| "num_tokens": 1176122.0, |
| "step": 72 |
| }, |
| { |
| "entropy": 0.5674256831407547, |
| "epoch": 0.2726423902894491, |
| "grad_norm": 0.0378127247095108, |
| "learning_rate": 0.0002, |
| "loss": 0.5667495727539062, |
| "mean_token_accuracy": 0.7705131769180298, |
| "num_tokens": 1192483.0, |
| "step": 73 |
| }, |
| { |
| "entropy": 0.568048432469368, |
| "epoch": 0.27637721755368816, |
| "grad_norm": 0.035798948258161545, |
| "learning_rate": 0.0002, |
| "loss": 0.5668107867240906, |
| "mean_token_accuracy": 0.7710251212120056, |
| "num_tokens": 1209110.0, |
| "step": 74 |
| }, |
| { |
| "entropy": 0.5850978642702103, |
| "epoch": 0.2801120448179272, |
| "grad_norm": 0.03812864422798157, |
| "learning_rate": 0.0002, |
| "loss": 0.5801389217376709, |
| "mean_token_accuracy": 0.7685801237821579, |
| "num_tokens": 1225656.0, |
| "step": 75 |
| }, |
| { |
| "entropy": 0.5744365155696869, |
| "epoch": 0.2838468720821662, |
| "grad_norm": 0.03252263367176056, |
| "learning_rate": 0.0002, |
| "loss": 0.5715938806533813, |
| "mean_token_accuracy": 0.7678718268871307, |
| "num_tokens": 1241986.0, |
| "step": 76 |
| }, |
| { |
| "entropy": 0.5737413763999939, |
| "epoch": 0.2875816993464052, |
| "grad_norm": 0.03566081449389458, |
| "learning_rate": 0.0002, |
| "loss": 0.5768669843673706, |
| "mean_token_accuracy": 0.768094465136528, |
| "num_tokens": 1258437.0, |
| "step": 77 |
| }, |
| { |
| "entropy": 0.5403539538383484, |
| "epoch": 0.2913165266106443, |
| "grad_norm": 0.03335001692175865, |
| "learning_rate": 0.0002, |
| "loss": 0.5388357639312744, |
| "mean_token_accuracy": 0.7831095159053802, |
| "num_tokens": 1274706.0, |
| "step": 78 |
| }, |
| { |
| "entropy": 0.5797998905181885, |
| "epoch": 0.2950513538748833, |
| "grad_norm": 0.036791976541280746, |
| "learning_rate": 0.0002, |
| "loss": 0.5749024152755737, |
| "mean_token_accuracy": 0.7673221081495285, |
| "num_tokens": 1291375.0, |
| "step": 79 |
| }, |
| { |
| "entropy": 0.5663541257381439, |
| "epoch": 0.2987861811391223, |
| "grad_norm": 0.04374934732913971, |
| "learning_rate": 0.0002, |
| "loss": 0.5602323412895203, |
| "mean_token_accuracy": 0.7732456177473068, |
| "num_tokens": 1307621.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 0.5841106921434402, |
| "epoch": 0.3025210084033613, |
| "grad_norm": 0.03585761412978172, |
| "learning_rate": 0.0002, |
| "loss": 0.5774515271186829, |
| "mean_token_accuracy": 0.7695471197366714, |
| "num_tokens": 1324292.0, |
| "step": 81 |
| }, |
| { |
| "entropy": 0.5769794583320618, |
| "epoch": 0.3062558356676004, |
| "grad_norm": 0.032680612057447433, |
| "learning_rate": 0.0002, |
| "loss": 0.5758101940155029, |
| "mean_token_accuracy": 0.7648481875658035, |
| "num_tokens": 1340714.0, |
| "step": 82 |
| }, |
| { |
| "entropy": 0.557876318693161, |
| "epoch": 0.3099906629318394, |
| "grad_norm": 0.036271534860134125, |
| "learning_rate": 0.0002, |
| "loss": 0.5576061010360718, |
| "mean_token_accuracy": 0.7769448161125183, |
| "num_tokens": 1357063.0, |
| "step": 83 |
| }, |
| { |
| "entropy": 0.5480719208717346, |
| "epoch": 0.3137254901960784, |
| "grad_norm": 0.04093662649393082, |
| "learning_rate": 0.0002, |
| "loss": 0.5554815530776978, |
| "mean_token_accuracy": 0.7730589210987091, |
| "num_tokens": 1373048.0, |
| "step": 84 |
| }, |
| { |
| "entropy": 0.5651550590991974, |
| "epoch": 0.31746031746031744, |
| "grad_norm": 0.03605310246348381, |
| "learning_rate": 0.0002, |
| "loss": 0.5752359628677368, |
| "mean_token_accuracy": 0.767627626657486, |
| "num_tokens": 1389533.0, |
| "step": 85 |
| }, |
| { |
| "entropy": 0.5644277483224869, |
| "epoch": 0.3211951447245565, |
| "grad_norm": 0.03757842630147934, |
| "learning_rate": 0.0002, |
| "loss": 0.5678563117980957, |
| "mean_token_accuracy": 0.7691835910081863, |
| "num_tokens": 1406026.0, |
| "step": 86 |
| }, |
| { |
| "entropy": 0.5682397186756134, |
| "epoch": 0.32492997198879553, |
| "grad_norm": 0.033709567040205, |
| "learning_rate": 0.0002, |
| "loss": 0.5628086924552917, |
| "mean_token_accuracy": 0.7722707390785217, |
| "num_tokens": 1422562.0, |
| "step": 87 |
| }, |
| { |
| "entropy": 0.5635691732168198, |
| "epoch": 0.32866479925303455, |
| "grad_norm": 0.03606971353292465, |
| "learning_rate": 0.0002, |
| "loss": 0.5536225438117981, |
| "mean_token_accuracy": 0.7781998217105865, |
| "num_tokens": 1438929.0, |
| "step": 88 |
| }, |
| { |
| "entropy": 0.5673100650310516, |
| "epoch": 0.33239962651727356, |
| "grad_norm": 0.03673219308257103, |
| "learning_rate": 0.0002, |
| "loss": 0.5621542930603027, |
| "mean_token_accuracy": 0.7736853212118149, |
| "num_tokens": 1455379.0, |
| "step": 89 |
| }, |
| { |
| "entropy": 0.5614307522773743, |
| "epoch": 0.33613445378151263, |
| "grad_norm": 0.037591755390167236, |
| "learning_rate": 0.0002, |
| "loss": 0.5566410422325134, |
| "mean_token_accuracy": 0.7733979523181915, |
| "num_tokens": 1471484.0, |
| "step": 90 |
| }, |
| { |
| "entropy": 0.5533501952886581, |
| "epoch": 0.33986928104575165, |
| "grad_norm": 0.03392329066991806, |
| "learning_rate": 0.0002, |
| "loss": 0.5534408092498779, |
| "mean_token_accuracy": 0.7756673395633698, |
| "num_tokens": 1487940.0, |
| "step": 91 |
| }, |
| { |
| "entropy": 0.5670682638883591, |
| "epoch": 0.34360410830999066, |
| "grad_norm": 0.038744084537029266, |
| "learning_rate": 0.0002, |
| "loss": 0.5757073760032654, |
| "mean_token_accuracy": 0.7674537003040314, |
| "num_tokens": 1504516.0, |
| "step": 92 |
| }, |
| { |
| "entropy": 0.5437405109405518, |
| "epoch": 0.3473389355742297, |
| "grad_norm": 0.03382673114538193, |
| "learning_rate": 0.0002, |
| "loss": 0.5484196543693542, |
| "mean_token_accuracy": 0.7756420075893402, |
| "num_tokens": 1520914.0, |
| "step": 93 |
| }, |
| { |
| "entropy": 0.5495916306972504, |
| "epoch": 0.3510737628384687, |
| "grad_norm": 0.03743721917271614, |
| "learning_rate": 0.0002, |
| "loss": 0.5565813183784485, |
| "mean_token_accuracy": 0.7735388725996017, |
| "num_tokens": 1537124.0, |
| "step": 94 |
| }, |
| { |
| "entropy": 0.568208858370781, |
| "epoch": 0.35480859010270777, |
| "grad_norm": 0.03229435160756111, |
| "learning_rate": 0.0002, |
| "loss": 0.5690167546272278, |
| "mean_token_accuracy": 0.7696976512670517, |
| "num_tokens": 1553562.0, |
| "step": 95 |
| }, |
| { |
| "entropy": 0.5612770318984985, |
| "epoch": 0.3585434173669468, |
| "grad_norm": 0.03424388915300369, |
| "learning_rate": 0.0002, |
| "loss": 0.5587109923362732, |
| "mean_token_accuracy": 0.774835541844368, |
| "num_tokens": 1569896.0, |
| "step": 96 |
| }, |
| { |
| "entropy": 0.5718783587217331, |
| "epoch": 0.3622782446311858, |
| "grad_norm": 0.033101778477430344, |
| "learning_rate": 0.0002, |
| "loss": 0.5643482208251953, |
| "mean_token_accuracy": 0.7721461206674576, |
| "num_tokens": 1586284.0, |
| "step": 97 |
| }, |
| { |
| "entropy": 0.5654337555170059, |
| "epoch": 0.3660130718954248, |
| "grad_norm": 0.035547658801078796, |
| "learning_rate": 0.0002, |
| "loss": 0.5555263757705688, |
| "mean_token_accuracy": 0.7783078551292419, |
| "num_tokens": 1602584.0, |
| "step": 98 |
| }, |
| { |
| "entropy": 0.5639571994543076, |
| "epoch": 0.3697478991596639, |
| "grad_norm": 0.03868361935019493, |
| "learning_rate": 0.0002, |
| "loss": 0.5630732178688049, |
| "mean_token_accuracy": 0.773595780134201, |
| "num_tokens": 1618810.0, |
| "step": 99 |
| }, |
| { |
| "entropy": 0.568704292178154, |
| "epoch": 0.3734827264239029, |
| "grad_norm": 0.03236787021160126, |
| "learning_rate": 0.0002, |
| "loss": 0.5669816732406616, |
| "mean_token_accuracy": 0.7704071253538132, |
| "num_tokens": 1635290.0, |
| "step": 100 |
| }, |
| { |
| "entropy": 0.551744356751442, |
| "epoch": 0.3772175536881419, |
| "grad_norm": 0.03913586586713791, |
| "learning_rate": 0.0002, |
| "loss": 0.5576678514480591, |
| "mean_token_accuracy": 0.7771230936050415, |
| "num_tokens": 1651818.0, |
| "step": 101 |
| }, |
| { |
| "entropy": 0.5260472893714905, |
| "epoch": 0.38095238095238093, |
| "grad_norm": 0.035290028899908066, |
| "learning_rate": 0.0002, |
| "loss": 0.5295023918151855, |
| "mean_token_accuracy": 0.7862183749675751, |
| "num_tokens": 1668252.0, |
| "step": 102 |
| }, |
| { |
| "entropy": 0.5585302114486694, |
| "epoch": 0.38468720821662, |
| "grad_norm": 0.03497280925512314, |
| "learning_rate": 0.0002, |
| "loss": 0.5631093978881836, |
| "mean_token_accuracy": 0.7744487524032593, |
| "num_tokens": 1684730.0, |
| "step": 103 |
| }, |
| { |
| "entropy": 0.5317506641149521, |
| "epoch": 0.388422035480859, |
| "grad_norm": 0.038267575204372406, |
| "learning_rate": 0.0002, |
| "loss": 0.5366777777671814, |
| "mean_token_accuracy": 0.7837612628936768, |
| "num_tokens": 1700724.0, |
| "step": 104 |
| }, |
| { |
| "entropy": 0.5369188189506531, |
| "epoch": 0.39215686274509803, |
| "grad_norm": 0.03429935500025749, |
| "learning_rate": 0.0002, |
| "loss": 0.5283028483390808, |
| "mean_token_accuracy": 0.7885325402021408, |
| "num_tokens": 1717105.0, |
| "step": 105 |
| }, |
| { |
| "entropy": 0.5693536698818207, |
| "epoch": 0.39589169000933705, |
| "grad_norm": 0.038153599947690964, |
| "learning_rate": 0.0002, |
| "loss": 0.5606598258018494, |
| "mean_token_accuracy": 0.7737682908773422, |
| "num_tokens": 1733363.0, |
| "step": 106 |
| }, |
| { |
| "entropy": 0.5737781524658203, |
| "epoch": 0.3996265172735761, |
| "grad_norm": 0.034137699753046036, |
| "learning_rate": 0.0002, |
| "loss": 0.5676036477088928, |
| "mean_token_accuracy": 0.7725923210382462, |
| "num_tokens": 1749928.0, |
| "step": 107 |
| }, |
| { |
| "entropy": 0.5680664926767349, |
| "epoch": 0.40336134453781514, |
| "grad_norm": 0.035801518708467484, |
| "learning_rate": 0.0002, |
| "loss": 0.5669195055961609, |
| "mean_token_accuracy": 0.7720014601945877, |
| "num_tokens": 1766520.0, |
| "step": 108 |
| }, |
| { |
| "entropy": 0.5640780180692673, |
| "epoch": 0.40709617180205415, |
| "grad_norm": 0.036836352199316025, |
| "learning_rate": 0.0002, |
| "loss": 0.5703918933868408, |
| "mean_token_accuracy": 0.7716377079486847, |
| "num_tokens": 1783002.0, |
| "step": 109 |
| }, |
| { |
| "entropy": 0.554967850446701, |
| "epoch": 0.41083099906629317, |
| "grad_norm": 0.03882612660527229, |
| "learning_rate": 0.0002, |
| "loss": 0.5642282962799072, |
| "mean_token_accuracy": 0.7699488997459412, |
| "num_tokens": 1799237.0, |
| "step": 110 |
| }, |
| { |
| "entropy": 0.5514571368694305, |
| "epoch": 0.41456582633053224, |
| "grad_norm": 0.03324515372514725, |
| "learning_rate": 0.0002, |
| "loss": 0.5484537482261658, |
| "mean_token_accuracy": 0.7782372832298279, |
| "num_tokens": 1815769.0, |
| "step": 111 |
| }, |
| { |
| "entropy": 0.573599174618721, |
| "epoch": 0.41830065359477125, |
| "grad_norm": 0.03034473955631256, |
| "learning_rate": 0.0002, |
| "loss": 0.5679251551628113, |
| "mean_token_accuracy": 0.7719407975673676, |
| "num_tokens": 1831989.0, |
| "step": 112 |
| }, |
| { |
| "entropy": 0.5896201282739639, |
| "epoch": 0.42203548085901027, |
| "grad_norm": 0.03557023033499718, |
| "learning_rate": 0.0002, |
| "loss": 0.5836873054504395, |
| "mean_token_accuracy": 0.7634387165307999, |
| "num_tokens": 1848590.0, |
| "step": 113 |
| }, |
| { |
| "entropy": 0.5535563677549362, |
| "epoch": 0.4257703081232493, |
| "grad_norm": 0.032203588634729385, |
| "learning_rate": 0.0002, |
| "loss": 0.5510682463645935, |
| "mean_token_accuracy": 0.7764001041650772, |
| "num_tokens": 1864862.0, |
| "step": 114 |
| }, |
| { |
| "entropy": 0.5557997226715088, |
| "epoch": 0.4295051353874883, |
| "grad_norm": 0.033370040357112885, |
| "learning_rate": 0.0002, |
| "loss": 0.5584062933921814, |
| "mean_token_accuracy": 0.7749063074588776, |
| "num_tokens": 1881168.0, |
| "step": 115 |
| }, |
| { |
| "entropy": 0.5543448776006699, |
| "epoch": 0.4332399626517274, |
| "grad_norm": 0.030230488628149033, |
| "learning_rate": 0.0002, |
| "loss": 0.5530171990394592, |
| "mean_token_accuracy": 0.7758816778659821, |
| "num_tokens": 1897482.0, |
| "step": 116 |
| }, |
| { |
| "entropy": 0.5602561086416245, |
| "epoch": 0.4369747899159664, |
| "grad_norm": 0.03355773538351059, |
| "learning_rate": 0.0002, |
| "loss": 0.5631951093673706, |
| "mean_token_accuracy": 0.7723173201084137, |
| "num_tokens": 1913520.0, |
| "step": 117 |
| }, |
| { |
| "entropy": 0.5448198318481445, |
| "epoch": 0.4407096171802054, |
| "grad_norm": 0.03538920357823372, |
| "learning_rate": 0.0002, |
| "loss": 0.5498956441879272, |
| "mean_token_accuracy": 0.7779627591371536, |
| "num_tokens": 1929827.0, |
| "step": 118 |
| }, |
| { |
| "entropy": 0.5492925643920898, |
| "epoch": 0.4444444444444444, |
| "grad_norm": 0.03334996476769447, |
| "learning_rate": 0.0002, |
| "loss": 0.5524949431419373, |
| "mean_token_accuracy": 0.7753683775663376, |
| "num_tokens": 1946145.0, |
| "step": 119 |
| }, |
| { |
| "entropy": 0.5578335374593735, |
| "epoch": 0.4481792717086835, |
| "grad_norm": 0.029814472422003746, |
| "learning_rate": 0.0002, |
| "loss": 0.5506975650787354, |
| "mean_token_accuracy": 0.7767714560031891, |
| "num_tokens": 1962460.0, |
| "step": 120 |
| }, |
| { |
| "entropy": 0.5471834242343903, |
| "epoch": 0.4519140989729225, |
| "grad_norm": 0.030702516436576843, |
| "learning_rate": 0.0002, |
| "loss": 0.5459597110748291, |
| "mean_token_accuracy": 0.7779918015003204, |
| "num_tokens": 1978468.0, |
| "step": 121 |
| }, |
| { |
| "entropy": 0.5746940076351166, |
| "epoch": 0.4556489262371615, |
| "grad_norm": 0.028086913749575615, |
| "learning_rate": 0.0002, |
| "loss": 0.5758755207061768, |
| "mean_token_accuracy": 0.766986295580864, |
| "num_tokens": 1994816.0, |
| "step": 122 |
| }, |
| { |
| "entropy": 0.5609753727912903, |
| "epoch": 0.45938375350140054, |
| "grad_norm": 0.027476167306303978, |
| "learning_rate": 0.0002, |
| "loss": 0.5596047639846802, |
| "mean_token_accuracy": 0.7727872580289841, |
| "num_tokens": 2011498.0, |
| "step": 123 |
| }, |
| { |
| "entropy": 0.5600833296775818, |
| "epoch": 0.4631185807656396, |
| "grad_norm": 0.03369581326842308, |
| "learning_rate": 0.0002, |
| "loss": 0.5641721487045288, |
| "mean_token_accuracy": 0.7693867385387421, |
| "num_tokens": 2027843.0, |
| "step": 124 |
| }, |
| { |
| "entropy": 0.5480703115463257, |
| "epoch": 0.4668534080298786, |
| "grad_norm": 0.029643159359693527, |
| "learning_rate": 0.0002, |
| "loss": 0.554192841053009, |
| "mean_token_accuracy": 0.7775781005620956, |
| "num_tokens": 2044099.0, |
| "step": 125 |
| }, |
| { |
| "entropy": 0.5571865439414978, |
| "epoch": 0.47058823529411764, |
| "grad_norm": 0.032963886857032776, |
| "learning_rate": 0.0002, |
| "loss": 0.5603472590446472, |
| "mean_token_accuracy": 0.7727210968732834, |
| "num_tokens": 2060417.0, |
| "step": 126 |
| }, |
| { |
| "entropy": 0.5587971061468124, |
| "epoch": 0.47432306255835666, |
| "grad_norm": 0.028774971142411232, |
| "learning_rate": 0.0002, |
| "loss": 0.5552476644515991, |
| "mean_token_accuracy": 0.7738739997148514, |
| "num_tokens": 2076710.0, |
| "step": 127 |
| }, |
| { |
| "entropy": 0.5658144652843475, |
| "epoch": 0.4780578898225957, |
| "grad_norm": 0.03230098634958267, |
| "learning_rate": 0.0002, |
| "loss": 0.557459831237793, |
| "mean_token_accuracy": 0.7754161208868027, |
| "num_tokens": 2093196.0, |
| "step": 128 |
| }, |
| { |
| "entropy": 0.5515187084674835, |
| "epoch": 0.48179271708683474, |
| "grad_norm": 0.03461001068353653, |
| "learning_rate": 0.0002, |
| "loss": 0.547848641872406, |
| "mean_token_accuracy": 0.7798665314912796, |
| "num_tokens": 2109091.0, |
| "step": 129 |
| }, |
| { |
| "entropy": 0.5527725219726562, |
| "epoch": 0.48552754435107376, |
| "grad_norm": 0.03391197323799133, |
| "learning_rate": 0.0002, |
| "loss": 0.5531637072563171, |
| "mean_token_accuracy": 0.7753576338291168, |
| "num_tokens": 2125292.0, |
| "step": 130 |
| }, |
| { |
| "entropy": 0.5310224145650864, |
| "epoch": 0.4892623716153128, |
| "grad_norm": 0.037288419902324677, |
| "learning_rate": 0.0002, |
| "loss": 0.5368673801422119, |
| "mean_token_accuracy": 0.7833587974309921, |
| "num_tokens": 2141768.0, |
| "step": 131 |
| }, |
| { |
| "entropy": 0.5471584349870682, |
| "epoch": 0.49299719887955185, |
| "grad_norm": 0.03433871641755104, |
| "learning_rate": 0.0002, |
| "loss": 0.5525721907615662, |
| "mean_token_accuracy": 0.776105523109436, |
| "num_tokens": 2158143.0, |
| "step": 132 |
| }, |
| { |
| "entropy": 0.5587402433156967, |
| "epoch": 0.49673202614379086, |
| "grad_norm": 0.03347739949822426, |
| "learning_rate": 0.0002, |
| "loss": 0.5661599636077881, |
| "mean_token_accuracy": 0.7718635648488998, |
| "num_tokens": 2174416.0, |
| "step": 133 |
| }, |
| { |
| "entropy": 0.5683765709400177, |
| "epoch": 0.5004668534080299, |
| "grad_norm": 0.03381507471203804, |
| "learning_rate": 0.0002, |
| "loss": 0.5622847080230713, |
| "mean_token_accuracy": 0.7744656354188919, |
| "num_tokens": 2190880.0, |
| "step": 134 |
| }, |
| { |
| "entropy": 0.5644540786743164, |
| "epoch": 0.5042016806722689, |
| "grad_norm": 0.03272015228867531, |
| "learning_rate": 0.0002, |
| "loss": 0.5552080869674683, |
| "mean_token_accuracy": 0.7752301692962646, |
| "num_tokens": 2207174.0, |
| "step": 135 |
| }, |
| { |
| "entropy": 0.5678849667310715, |
| "epoch": 0.5079365079365079, |
| "grad_norm": 0.031616441905498505, |
| "learning_rate": 0.0002, |
| "loss": 0.5582877993583679, |
| "mean_token_accuracy": 0.7729764580726624, |
| "num_tokens": 2223657.0, |
| "step": 136 |
| }, |
| { |
| "entropy": 0.560051366686821, |
| "epoch": 0.5116713352007469, |
| "grad_norm": 0.03558259457349777, |
| "learning_rate": 0.0002, |
| "loss": 0.5536358952522278, |
| "mean_token_accuracy": 0.7764490097761154, |
| "num_tokens": 2239931.0, |
| "step": 137 |
| }, |
| { |
| "entropy": 0.5550469309091568, |
| "epoch": 0.5154061624649859, |
| "grad_norm": 0.034295059740543365, |
| "learning_rate": 0.0002, |
| "loss": 0.5614034533500671, |
| "mean_token_accuracy": 0.7718400210142136, |
| "num_tokens": 2256301.0, |
| "step": 138 |
| }, |
| { |
| "entropy": 0.5675243437290192, |
| "epoch": 0.5191409897292251, |
| "grad_norm": 0.03538001328706741, |
| "learning_rate": 0.0002, |
| "loss": 0.5784004926681519, |
| "mean_token_accuracy": 0.7684118300676346, |
| "num_tokens": 2272718.0, |
| "step": 139 |
| }, |
| { |
| "entropy": 0.5533763766288757, |
| "epoch": 0.5228758169934641, |
| "grad_norm": 0.034997887909412384, |
| "learning_rate": 0.0002, |
| "loss": 0.563084602355957, |
| "mean_token_accuracy": 0.7709241509437561, |
| "num_tokens": 2289039.0, |
| "step": 140 |
| }, |
| { |
| "entropy": 0.5602118372917175, |
| "epoch": 0.5266106442577031, |
| "grad_norm": 0.033439598977565765, |
| "learning_rate": 0.0002, |
| "loss": 0.5643538236618042, |
| "mean_token_accuracy": 0.7725736945867538, |
| "num_tokens": 2305409.0, |
| "step": 141 |
| }, |
| { |
| "entropy": 0.572220578789711, |
| "epoch": 0.5303454715219421, |
| "grad_norm": 0.02899010293185711, |
| "learning_rate": 0.0002, |
| "loss": 0.56317138671875, |
| "mean_token_accuracy": 0.7727230340242386, |
| "num_tokens": 2321812.0, |
| "step": 142 |
| }, |
| { |
| "entropy": 0.5518327206373215, |
| "epoch": 0.5340802987861811, |
| "grad_norm": 0.03380458429455757, |
| "learning_rate": 0.0002, |
| "loss": 0.5400616526603699, |
| "mean_token_accuracy": 0.7813573479652405, |
| "num_tokens": 2338293.0, |
| "step": 143 |
| }, |
| { |
| "entropy": 0.59617879986763, |
| "epoch": 0.5378151260504201, |
| "grad_norm": 0.03466860204935074, |
| "learning_rate": 0.0002, |
| "loss": 0.58748859167099, |
| "mean_token_accuracy": 0.7642232924699783, |
| "num_tokens": 2354694.0, |
| "step": 144 |
| }, |
| { |
| "entropy": 0.5574633181095123, |
| "epoch": 0.5415499533146592, |
| "grad_norm": 0.030799690634012222, |
| "learning_rate": 0.0002, |
| "loss": 0.5586976408958435, |
| "mean_token_accuracy": 0.774814635515213, |
| "num_tokens": 2370998.0, |
| "step": 145 |
| }, |
| { |
| "entropy": 0.5298123508691788, |
| "epoch": 0.5452847805788982, |
| "grad_norm": 0.032734956592321396, |
| "learning_rate": 0.0002, |
| "loss": 0.5359174609184265, |
| "mean_token_accuracy": 0.782838299870491, |
| "num_tokens": 2387173.0, |
| "step": 146 |
| }, |
| { |
| "entropy": 0.5436026155948639, |
| "epoch": 0.5490196078431373, |
| "grad_norm": 0.03734711930155754, |
| "learning_rate": 0.0002, |
| "loss": 0.5544965267181396, |
| "mean_token_accuracy": 0.7772063612937927, |
| "num_tokens": 2403457.0, |
| "step": 147 |
| }, |
| { |
| "entropy": 0.5453614443540573, |
| "epoch": 0.5527544351073763, |
| "grad_norm": 0.030067089945077896, |
| "learning_rate": 0.0002, |
| "loss": 0.5510781407356262, |
| "mean_token_accuracy": 0.7755871117115021, |
| "num_tokens": 2419735.0, |
| "step": 148 |
| }, |
| { |
| "entropy": 0.55818210542202, |
| "epoch": 0.5564892623716153, |
| "grad_norm": 0.02786589413881302, |
| "learning_rate": 0.0002, |
| "loss": 0.5563390851020813, |
| "mean_token_accuracy": 0.7738417237997055, |
| "num_tokens": 2436098.0, |
| "step": 149 |
| }, |
| { |
| "entropy": 0.5619741082191467, |
| "epoch": 0.5602240896358543, |
| "grad_norm": 0.030777357518672943, |
| "learning_rate": 0.0002, |
| "loss": 0.5554664134979248, |
| "mean_token_accuracy": 0.7789015769958496, |
| "num_tokens": 2452471.0, |
| "step": 150 |
| }, |
| { |
| "entropy": 0.5570534616708755, |
| "epoch": 0.5639589169000934, |
| "grad_norm": 0.03233370929956436, |
| "learning_rate": 0.0002, |
| "loss": 0.5482333898544312, |
| "mean_token_accuracy": 0.7772232443094254, |
| "num_tokens": 2468628.0, |
| "step": 151 |
| }, |
| { |
| "entropy": 0.5588962733745575, |
| "epoch": 0.5676937441643324, |
| "grad_norm": 0.03047763742506504, |
| "learning_rate": 0.0002, |
| "loss": 0.5532917380332947, |
| "mean_token_accuracy": 0.7753781825304031, |
| "num_tokens": 2485072.0, |
| "step": 152 |
| }, |
| { |
| "entropy": 0.549691841006279, |
| "epoch": 0.5714285714285714, |
| "grad_norm": 0.02944052591919899, |
| "learning_rate": 0.0002, |
| "loss": 0.5515119433403015, |
| "mean_token_accuracy": 0.7769780606031418, |
| "num_tokens": 2501327.0, |
| "step": 153 |
| }, |
| { |
| "entropy": 0.5404879450798035, |
| "epoch": 0.5751633986928104, |
| "grad_norm": 0.032262854278087616, |
| "learning_rate": 0.0002, |
| "loss": 0.5476431846618652, |
| "mean_token_accuracy": 0.7793239504098892, |
| "num_tokens": 2517799.0, |
| "step": 154 |
| }, |
| { |
| "entropy": 0.5289865881204605, |
| "epoch": 0.5788982259570495, |
| "grad_norm": 0.03042609617114067, |
| "learning_rate": 0.0002, |
| "loss": 0.531823992729187, |
| "mean_token_accuracy": 0.7862056195735931, |
| "num_tokens": 2534300.0, |
| "step": 155 |
| }, |
| { |
| "entropy": 0.5359181612730026, |
| "epoch": 0.5826330532212886, |
| "grad_norm": 0.030735395848751068, |
| "learning_rate": 0.0002, |
| "loss": 0.5355162024497986, |
| "mean_token_accuracy": 0.7830311506986618, |
| "num_tokens": 2550561.0, |
| "step": 156 |
| }, |
| { |
| "entropy": 0.555221676826477, |
| "epoch": 0.5863678804855276, |
| "grad_norm": 0.03072836995124817, |
| "learning_rate": 0.0002, |
| "loss": 0.5626713037490845, |
| "mean_token_accuracy": 0.7714420855045319, |
| "num_tokens": 2566961.0, |
| "step": 157 |
| }, |
| { |
| "entropy": 0.553142175078392, |
| "epoch": 0.5901027077497666, |
| "grad_norm": 0.030098870396614075, |
| "learning_rate": 0.0002, |
| "loss": 0.5467352867126465, |
| "mean_token_accuracy": 0.7787252068519592, |
| "num_tokens": 2583507.0, |
| "step": 158 |
| }, |
| { |
| "entropy": 0.5665386617183685, |
| "epoch": 0.5938375350140056, |
| "grad_norm": 0.03258649259805679, |
| "learning_rate": 0.0002, |
| "loss": 0.5577669143676758, |
| "mean_token_accuracy": 0.7736402750015259, |
| "num_tokens": 2599944.0, |
| "step": 159 |
| }, |
| { |
| "entropy": 0.5569501370191574, |
| "epoch": 0.5975723622782446, |
| "grad_norm": 0.03186054900288582, |
| "learning_rate": 0.0002, |
| "loss": 0.5573895573616028, |
| "mean_token_accuracy": 0.776360809803009, |
| "num_tokens": 2616293.0, |
| "step": 160 |
| }, |
| { |
| "entropy": 0.5284514650702477, |
| "epoch": 0.6013071895424836, |
| "grad_norm": 0.029392873868346214, |
| "learning_rate": 0.0002, |
| "loss": 0.53591388463974, |
| "mean_token_accuracy": 0.7802938669919968, |
| "num_tokens": 2632542.0, |
| "step": 161 |
| }, |
| { |
| "entropy": 0.5517806857824326, |
| "epoch": 0.6050420168067226, |
| "grad_norm": 0.03547659516334534, |
| "learning_rate": 0.0002, |
| "loss": 0.5624344348907471, |
| "mean_token_accuracy": 0.7713066786527634, |
| "num_tokens": 2648855.0, |
| "step": 162 |
| }, |
| { |
| "entropy": 0.5444875061511993, |
| "epoch": 0.6087768440709617, |
| "grad_norm": 0.032323673367500305, |
| "learning_rate": 0.0002, |
| "loss": 0.5506078004837036, |
| "mean_token_accuracy": 0.7763939499855042, |
| "num_tokens": 2665389.0, |
| "step": 163 |
| }, |
| { |
| "entropy": 0.552508682012558, |
| "epoch": 0.6125116713352008, |
| "grad_norm": 0.029938260093331337, |
| "learning_rate": 0.0002, |
| "loss": 0.5556696653366089, |
| "mean_token_accuracy": 0.774255782365799, |
| "num_tokens": 2681574.0, |
| "step": 164 |
| }, |
| { |
| "entropy": 0.5732054561376572, |
| "epoch": 0.6162464985994398, |
| "grad_norm": 0.027899837121367455, |
| "learning_rate": 0.0002, |
| "loss": 0.5643041133880615, |
| "mean_token_accuracy": 0.7738403379917145, |
| "num_tokens": 2697956.0, |
| "step": 165 |
| }, |
| { |
| "entropy": 0.5575381070375443, |
| "epoch": 0.6199813258636788, |
| "grad_norm": 0.03164415806531906, |
| "learning_rate": 0.0002, |
| "loss": 0.5456005930900574, |
| "mean_token_accuracy": 0.7768769711256027, |
| "num_tokens": 2714390.0, |
| "step": 166 |
| }, |
| { |
| "entropy": 0.5516810864210129, |
| "epoch": 0.6237161531279178, |
| "grad_norm": 0.02569694072008133, |
| "learning_rate": 0.0002, |
| "loss": 0.5495009422302246, |
| "mean_token_accuracy": 0.774631917476654, |
| "num_tokens": 2730912.0, |
| "step": 167 |
| }, |
| { |
| "entropy": 0.5496233999729156, |
| "epoch": 0.6274509803921569, |
| "grad_norm": 0.03019907884299755, |
| "learning_rate": 0.0002, |
| "loss": 0.5496887564659119, |
| "mean_token_accuracy": 0.7817335277795792, |
| "num_tokens": 2747282.0, |
| "step": 168 |
| }, |
| { |
| "entropy": 0.5489860326051712, |
| "epoch": 0.6311858076563959, |
| "grad_norm": 0.03389516472816467, |
| "learning_rate": 0.0002, |
| "loss": 0.5572369694709778, |
| "mean_token_accuracy": 0.7735096365213394, |
| "num_tokens": 2763708.0, |
| "step": 169 |
| }, |
| { |
| "entropy": 0.5558005720376968, |
| "epoch": 0.6349206349206349, |
| "grad_norm": 0.02765459194779396, |
| "learning_rate": 0.0002, |
| "loss": 0.5571833848953247, |
| "mean_token_accuracy": 0.7726074606180191, |
| "num_tokens": 2780084.0, |
| "step": 170 |
| }, |
| { |
| "entropy": 0.5543476939201355, |
| "epoch": 0.6386554621848739, |
| "grad_norm": 0.0267086960375309, |
| "learning_rate": 0.0002, |
| "loss": 0.5579585433006287, |
| "mean_token_accuracy": 0.7720465064048767, |
| "num_tokens": 2796592.0, |
| "step": 171 |
| }, |
| { |
| "entropy": 0.5531720370054245, |
| "epoch": 0.642390289449113, |
| "grad_norm": 0.03003924898803234, |
| "learning_rate": 0.0002, |
| "loss": 0.5539361238479614, |
| "mean_token_accuracy": 0.7745767682790756, |
| "num_tokens": 2813004.0, |
| "step": 172 |
| }, |
| { |
| "entropy": 0.5696417987346649, |
| "epoch": 0.646125116713352, |
| "grad_norm": 0.030649833381175995, |
| "learning_rate": 0.0002, |
| "loss": 0.5720299482345581, |
| "mean_token_accuracy": 0.7685467600822449, |
| "num_tokens": 2829346.0, |
| "step": 173 |
| }, |
| { |
| "entropy": 0.5682009905576706, |
| "epoch": 0.6498599439775911, |
| "grad_norm": 0.028095850721001625, |
| "learning_rate": 0.0002, |
| "loss": 0.5576902627944946, |
| "mean_token_accuracy": 0.7762027978897095, |
| "num_tokens": 2845908.0, |
| "step": 174 |
| }, |
| { |
| "entropy": 0.5714679658412933, |
| "epoch": 0.6535947712418301, |
| "grad_norm": 0.028559835627675056, |
| "learning_rate": 0.0002, |
| "loss": 0.5658706426620483, |
| "mean_token_accuracy": 0.7675664275884628, |
| "num_tokens": 2862417.0, |
| "step": 175 |
| }, |
| { |
| "entropy": 0.5519525855779648, |
| "epoch": 0.6573295985060691, |
| "grad_norm": 0.034554384648799896, |
| "learning_rate": 0.0002, |
| "loss": 0.5615457892417908, |
| "mean_token_accuracy": 0.7730480134487152, |
| "num_tokens": 2878691.0, |
| "step": 176 |
| }, |
| { |
| "entropy": 0.5469972342252731, |
| "epoch": 0.6610644257703081, |
| "grad_norm": 0.038470808416604996, |
| "learning_rate": 0.0002, |
| "loss": 0.5615893006324768, |
| "mean_token_accuracy": 0.7721795290708542, |
| "num_tokens": 2894997.0, |
| "step": 177 |
| }, |
| { |
| "entropy": 0.5659243762493134, |
| "epoch": 0.6647992530345471, |
| "grad_norm": 0.028726449236273766, |
| "learning_rate": 0.0002, |
| "loss": 0.5627461671829224, |
| "mean_token_accuracy": 0.7720647305250168, |
| "num_tokens": 2911504.0, |
| "step": 178 |
| }, |
| { |
| "entropy": 0.5529140681028366, |
| "epoch": 0.6685340802987861, |
| "grad_norm": 0.02865666151046753, |
| "learning_rate": 0.0002, |
| "loss": 0.551171064376831, |
| "mean_token_accuracy": 0.7765299677848816, |
| "num_tokens": 2927890.0, |
| "step": 179 |
| }, |
| { |
| "entropy": 0.5597221851348877, |
| "epoch": 0.6722689075630253, |
| "grad_norm": 0.030919602140784264, |
| "learning_rate": 0.0002, |
| "loss": 0.5537790656089783, |
| "mean_token_accuracy": 0.7759328931570053, |
| "num_tokens": 2944242.0, |
| "step": 180 |
| }, |
| { |
| "entropy": 0.562122106552124, |
| "epoch": 0.6760037348272643, |
| "grad_norm": 0.03044375404715538, |
| "learning_rate": 0.0002, |
| "loss": 0.5568514466285706, |
| "mean_token_accuracy": 0.7706819474697113, |
| "num_tokens": 2960500.0, |
| "step": 181 |
| }, |
| { |
| "entropy": 0.5697348713874817, |
| "epoch": 0.6797385620915033, |
| "grad_norm": 0.031796056777238846, |
| "learning_rate": 0.0002, |
| "loss": 0.5688814520835876, |
| "mean_token_accuracy": 0.7685033828020096, |
| "num_tokens": 2976732.0, |
| "step": 182 |
| }, |
| { |
| "entropy": 0.5696271657943726, |
| "epoch": 0.6834733893557423, |
| "grad_norm": 0.034152235835790634, |
| "learning_rate": 0.0002, |
| "loss": 0.570652186870575, |
| "mean_token_accuracy": 0.7676333039999008, |
| "num_tokens": 2993011.0, |
| "step": 183 |
| }, |
| { |
| "entropy": 0.5509230494499207, |
| "epoch": 0.6872082166199813, |
| "grad_norm": 0.030170850455760956, |
| "learning_rate": 0.0002, |
| "loss": 0.5528304576873779, |
| "mean_token_accuracy": 0.7786384671926498, |
| "num_tokens": 3009475.0, |
| "step": 184 |
| }, |
| { |
| "entropy": 0.549485370516777, |
| "epoch": 0.6909430438842203, |
| "grad_norm": 0.03623858466744423, |
| "learning_rate": 0.0002, |
| "loss": 0.5553773045539856, |
| "mean_token_accuracy": 0.7744152545928955, |
| "num_tokens": 3025920.0, |
| "step": 185 |
| }, |
| { |
| "entropy": 0.5484632700681686, |
| "epoch": 0.6946778711484594, |
| "grad_norm": 0.033118441700935364, |
| "learning_rate": 0.0002, |
| "loss": 0.5544424653053284, |
| "mean_token_accuracy": 0.7758429795503616, |
| "num_tokens": 3042293.0, |
| "step": 186 |
| }, |
| { |
| "entropy": 0.5471510142087936, |
| "epoch": 0.6984126984126984, |
| "grad_norm": 0.027027102187275887, |
| "learning_rate": 0.0002, |
| "loss": 0.5416866540908813, |
| "mean_token_accuracy": 0.7816910296678543, |
| "num_tokens": 3058771.0, |
| "step": 187 |
| }, |
| { |
| "entropy": 0.5579911917448044, |
| "epoch": 0.7021475256769374, |
| "grad_norm": 0.03291584923863411, |
| "learning_rate": 0.0002, |
| "loss": 0.5471009016036987, |
| "mean_token_accuracy": 0.7790512144565582, |
| "num_tokens": 3075134.0, |
| "step": 188 |
| }, |
| { |
| "entropy": 0.5525984019041061, |
| "epoch": 0.7058823529411765, |
| "grad_norm": 0.029011745005846024, |
| "learning_rate": 0.0002, |
| "loss": 0.5483554005622864, |
| "mean_token_accuracy": 0.7763502299785614, |
| "num_tokens": 3091306.0, |
| "step": 189 |
| }, |
| { |
| "entropy": 0.5610422939062119, |
| "epoch": 0.7096171802054155, |
| "grad_norm": 0.02904326282441616, |
| "learning_rate": 0.0002, |
| "loss": 0.5617838501930237, |
| "mean_token_accuracy": 0.7707021087408066, |
| "num_tokens": 3107639.0, |
| "step": 190 |
| }, |
| { |
| "entropy": 0.5382349342107773, |
| "epoch": 0.7133520074696545, |
| "grad_norm": 0.027915941551327705, |
| "learning_rate": 0.0002, |
| "loss": 0.5406217575073242, |
| "mean_token_accuracy": 0.7792213708162308, |
| "num_tokens": 3123888.0, |
| "step": 191 |
| }, |
| { |
| "entropy": 0.5334387570619583, |
| "epoch": 0.7170868347338936, |
| "grad_norm": 0.024687422439455986, |
| "learning_rate": 0.0002, |
| "loss": 0.5337969660758972, |
| "mean_token_accuracy": 0.7827744781970978, |
| "num_tokens": 3140136.0, |
| "step": 192 |
| }, |
| { |
| "entropy": 0.5519388318061829, |
| "epoch": 0.7208216619981326, |
| "grad_norm": 0.03399450331926346, |
| "learning_rate": 0.0002, |
| "loss": 0.5664753317832947, |
| "mean_token_accuracy": 0.7712263911962509, |
| "num_tokens": 3156560.0, |
| "step": 193 |
| }, |
| { |
| "entropy": 0.5329768806695938, |
| "epoch": 0.7245564892623716, |
| "grad_norm": 0.03143489733338356, |
| "learning_rate": 0.0002, |
| "loss": 0.5424296259880066, |
| "mean_token_accuracy": 0.7808002233505249, |
| "num_tokens": 3172868.0, |
| "step": 194 |
| }, |
| { |
| "entropy": 0.5407986044883728, |
| "epoch": 0.7282913165266106, |
| "grad_norm": 0.02865898422896862, |
| "learning_rate": 0.0002, |
| "loss": 0.5426485538482666, |
| "mean_token_accuracy": 0.7797252386808395, |
| "num_tokens": 3188845.0, |
| "step": 195 |
| }, |
| { |
| "entropy": 0.5540356040000916, |
| "epoch": 0.7320261437908496, |
| "grad_norm": 0.031195135787129402, |
| "learning_rate": 0.0002, |
| "loss": 0.5537624359130859, |
| "mean_token_accuracy": 0.772818997502327, |
| "num_tokens": 3205059.0, |
| "step": 196 |
| }, |
| { |
| "entropy": 0.547016367316246, |
| "epoch": 0.7357609710550888, |
| "grad_norm": 0.026600942015647888, |
| "learning_rate": 0.0002, |
| "loss": 0.5409566164016724, |
| "mean_token_accuracy": 0.7801954299211502, |
| "num_tokens": 3221339.0, |
| "step": 197 |
| }, |
| { |
| "entropy": 0.5571199655532837, |
| "epoch": 0.7394957983193278, |
| "grad_norm": 0.027464795857667923, |
| "learning_rate": 0.0002, |
| "loss": 0.5505565404891968, |
| "mean_token_accuracy": 0.7758535593748093, |
| "num_tokens": 3237556.0, |
| "step": 198 |
| }, |
| { |
| "entropy": 0.5562743991613388, |
| "epoch": 0.7432306255835668, |
| "grad_norm": 0.029805589467287064, |
| "learning_rate": 0.0002, |
| "loss": 0.5526044368743896, |
| "mean_token_accuracy": 0.7738559246063232, |
| "num_tokens": 3253871.0, |
| "step": 199 |
| }, |
| { |
| "entropy": 0.5585610568523407, |
| "epoch": 0.7469654528478058, |
| "grad_norm": 0.03004448115825653, |
| "learning_rate": 0.0002, |
| "loss": 0.5598405599594116, |
| "mean_token_accuracy": 0.7726627141237259, |
| "num_tokens": 3269973.0, |
| "step": 200 |
| }, |
| { |
| "entropy": 0.5488641411066055, |
| "epoch": 0.7507002801120448, |
| "grad_norm": 0.027654554694890976, |
| "learning_rate": 0.0002, |
| "loss": 0.5513002276420593, |
| "mean_token_accuracy": 0.7737944573163986, |
| "num_tokens": 3286201.0, |
| "step": 201 |
| }, |
| { |
| "entropy": 0.5287523940205574, |
| "epoch": 0.7544351073762838, |
| "grad_norm": 0.03466613590717316, |
| "learning_rate": 0.0002, |
| "loss": 0.5311362743377686, |
| "mean_token_accuracy": 0.7847718745470047, |
| "num_tokens": 3302467.0, |
| "step": 202 |
| }, |
| { |
| "entropy": 0.5560965240001678, |
| "epoch": 0.7581699346405228, |
| "grad_norm": 0.034095581620931625, |
| "learning_rate": 0.0002, |
| "loss": 0.5613946914672852, |
| "mean_token_accuracy": 0.7737453281879425, |
| "num_tokens": 3318768.0, |
| "step": 203 |
| }, |
| { |
| "entropy": 0.5630687177181244, |
| "epoch": 0.7619047619047619, |
| "grad_norm": 0.03233996778726578, |
| "learning_rate": 0.0002, |
| "loss": 0.564468264579773, |
| "mean_token_accuracy": 0.7691166549921036, |
| "num_tokens": 3335233.0, |
| "step": 204 |
| }, |
| { |
| "entropy": 0.5651765614748001, |
| "epoch": 0.765639589169001, |
| "grad_norm": 0.030395060777664185, |
| "learning_rate": 0.0002, |
| "loss": 0.5597318410873413, |
| "mean_token_accuracy": 0.7716515213251114, |
| "num_tokens": 3351439.0, |
| "step": 205 |
| }, |
| { |
| "entropy": 0.5476003587245941, |
| "epoch": 0.76937441643324, |
| "grad_norm": 0.03382452204823494, |
| "learning_rate": 0.0002, |
| "loss": 0.5447301864624023, |
| "mean_token_accuracy": 0.7816700637340546, |
| "num_tokens": 3367520.0, |
| "step": 206 |
| }, |
| { |
| "entropy": 0.5484471321105957, |
| "epoch": 0.773109243697479, |
| "grad_norm": 0.02830951102077961, |
| "learning_rate": 0.0002, |
| "loss": 0.5454609394073486, |
| "mean_token_accuracy": 0.7790801376104355, |
| "num_tokens": 3383667.0, |
| "step": 207 |
| }, |
| { |
| "entropy": 0.5659755617380142, |
| "epoch": 0.776844070961718, |
| "grad_norm": 0.02530798688530922, |
| "learning_rate": 0.0002, |
| "loss": 0.5655397772789001, |
| "mean_token_accuracy": 0.770569920539856, |
| "num_tokens": 3400150.0, |
| "step": 208 |
| }, |
| { |
| "entropy": 0.5427214205265045, |
| "epoch": 0.780578898225957, |
| "grad_norm": 0.03361448645591736, |
| "learning_rate": 0.0002, |
| "loss": 0.5476981401443481, |
| "mean_token_accuracy": 0.7780336290597916, |
| "num_tokens": 3416165.0, |
| "step": 209 |
| }, |
| { |
| "entropy": 0.5494136065244675, |
| "epoch": 0.7843137254901961, |
| "grad_norm": 0.029303058981895447, |
| "learning_rate": 0.0002, |
| "loss": 0.555971086025238, |
| "mean_token_accuracy": 0.7742915004491806, |
| "num_tokens": 3432668.0, |
| "step": 210 |
| }, |
| { |
| "entropy": 0.5408063977956772, |
| "epoch": 0.7880485527544351, |
| "grad_norm": 0.024706227704882622, |
| "learning_rate": 0.0002, |
| "loss": 0.5423460006713867, |
| "mean_token_accuracy": 0.7791419923305511, |
| "num_tokens": 3449230.0, |
| "step": 211 |
| }, |
| { |
| "entropy": 0.5585084557533264, |
| "epoch": 0.7917833800186741, |
| "grad_norm": 0.031753819435834885, |
| "learning_rate": 0.0002, |
| "loss": 0.5534642934799194, |
| "mean_token_accuracy": 0.7761369943618774, |
| "num_tokens": 3465888.0, |
| "step": 212 |
| }, |
| { |
| "entropy": 0.5470991730690002, |
| "epoch": 0.7955182072829131, |
| "grad_norm": 0.02627946063876152, |
| "learning_rate": 0.0002, |
| "loss": 0.543735921382904, |
| "mean_token_accuracy": 0.7773504257202148, |
| "num_tokens": 3482200.0, |
| "step": 213 |
| }, |
| { |
| "entropy": 0.5522027462720871, |
| "epoch": 0.7992530345471522, |
| "grad_norm": 0.02693161368370056, |
| "learning_rate": 0.0002, |
| "loss": 0.5497567057609558, |
| "mean_token_accuracy": 0.7760942578315735, |
| "num_tokens": 3498472.0, |
| "step": 214 |
| }, |
| { |
| "entropy": 0.5438102185726166, |
| "epoch": 0.8029878618113913, |
| "grad_norm": 0.029677148908376694, |
| "learning_rate": 0.0002, |
| "loss": 0.5449556112289429, |
| "mean_token_accuracy": 0.7757529467344284, |
| "num_tokens": 3514748.0, |
| "step": 215 |
| }, |
| { |
| "entropy": 0.5440456867218018, |
| "epoch": 0.8067226890756303, |
| "grad_norm": 0.028825437650084496, |
| "learning_rate": 0.0002, |
| "loss": 0.5460283160209656, |
| "mean_token_accuracy": 0.7805955857038498, |
| "num_tokens": 3530910.0, |
| "step": 216 |
| }, |
| { |
| "entropy": 0.5444321483373642, |
| "epoch": 0.8104575163398693, |
| "grad_norm": 0.023829322308301926, |
| "learning_rate": 0.0002, |
| "loss": 0.5420593023300171, |
| "mean_token_accuracy": 0.7787522822618484, |
| "num_tokens": 3547036.0, |
| "step": 217 |
| }, |
| { |
| "entropy": 0.5498476177453995, |
| "epoch": 0.8141923436041083, |
| "grad_norm": 0.025729795917868614, |
| "learning_rate": 0.0002, |
| "loss": 0.5429421067237854, |
| "mean_token_accuracy": 0.7785259187221527, |
| "num_tokens": 3563357.0, |
| "step": 218 |
| }, |
| { |
| "entropy": 0.544920951128006, |
| "epoch": 0.8179271708683473, |
| "grad_norm": 0.027102749794721603, |
| "learning_rate": 0.0002, |
| "loss": 0.5383168458938599, |
| "mean_token_accuracy": 0.7817831486463547, |
| "num_tokens": 3579822.0, |
| "step": 219 |
| }, |
| { |
| "entropy": 0.5497463345527649, |
| "epoch": 0.8216619981325863, |
| "grad_norm": 0.0323423407971859, |
| "learning_rate": 0.0002, |
| "loss": 0.5521490573883057, |
| "mean_token_accuracy": 0.7747017741203308, |
| "num_tokens": 3596053.0, |
| "step": 220 |
| }, |
| { |
| "entropy": 0.5389717519283295, |
| "epoch": 0.8253968253968254, |
| "grad_norm": 0.027372388169169426, |
| "learning_rate": 0.0002, |
| "loss": 0.540256679058075, |
| "mean_token_accuracy": 0.7825071215629578, |
| "num_tokens": 3612271.0, |
| "step": 221 |
| }, |
| { |
| "entropy": 0.5472569465637207, |
| "epoch": 0.8291316526610645, |
| "grad_norm": 0.028159258887171745, |
| "learning_rate": 0.0002, |
| "loss": 0.5517306327819824, |
| "mean_token_accuracy": 0.7758912444114685, |
| "num_tokens": 3628658.0, |
| "step": 222 |
| }, |
| { |
| "entropy": 0.5441670119762421, |
| "epoch": 0.8328664799253035, |
| "grad_norm": 0.0357636883854866, |
| "learning_rate": 0.0002, |
| "loss": 0.5485156178474426, |
| "mean_token_accuracy": 0.7771351188421249, |
| "num_tokens": 3645179.0, |
| "step": 223 |
| }, |
| { |
| "entropy": 0.5535278022289276, |
| "epoch": 0.8366013071895425, |
| "grad_norm": 0.032881151884794235, |
| "learning_rate": 0.0002, |
| "loss": 0.5619751811027527, |
| "mean_token_accuracy": 0.7715311944484711, |
| "num_tokens": 3661296.0, |
| "step": 224 |
| }, |
| { |
| "entropy": 0.5683074444532394, |
| "epoch": 0.8403361344537815, |
| "grad_norm": 0.03166094422340393, |
| "learning_rate": 0.0002, |
| "loss": 0.5676220059394836, |
| "mean_token_accuracy": 0.7721768617630005, |
| "num_tokens": 3677506.0, |
| "step": 225 |
| }, |
| { |
| "entropy": 0.5672677755355835, |
| "epoch": 0.8440709617180205, |
| "grad_norm": 0.029754942283034325, |
| "learning_rate": 0.0002, |
| "loss": 0.5636724233627319, |
| "mean_token_accuracy": 0.7715145349502563, |
| "num_tokens": 3693949.0, |
| "step": 226 |
| }, |
| { |
| "entropy": 0.5544100105762482, |
| "epoch": 0.8478057889822596, |
| "grad_norm": 0.027808941900730133, |
| "learning_rate": 0.0002, |
| "loss": 0.5551161170005798, |
| "mean_token_accuracy": 0.7762546241283417, |
| "num_tokens": 3710403.0, |
| "step": 227 |
| }, |
| { |
| "entropy": 0.5428061038255692, |
| "epoch": 0.8515406162464986, |
| "grad_norm": 0.032082680612802505, |
| "learning_rate": 0.0002, |
| "loss": 0.5452495813369751, |
| "mean_token_accuracy": 0.7784813046455383, |
| "num_tokens": 3726407.0, |
| "step": 228 |
| }, |
| { |
| "entropy": 0.5473134368658066, |
| "epoch": 0.8552754435107376, |
| "grad_norm": 0.030095776543021202, |
| "learning_rate": 0.0002, |
| "loss": 0.5461854934692383, |
| "mean_token_accuracy": 0.7758107632398605, |
| "num_tokens": 3742861.0, |
| "step": 229 |
| }, |
| { |
| "entropy": 0.5752474963665009, |
| "epoch": 0.8590102707749766, |
| "grad_norm": 0.030156588181853294, |
| "learning_rate": 0.0002, |
| "loss": 0.5713618397712708, |
| "mean_token_accuracy": 0.7695687711238861, |
| "num_tokens": 3759464.0, |
| "step": 230 |
| }, |
| { |
| "entropy": 0.5410983264446259, |
| "epoch": 0.8627450980392157, |
| "grad_norm": 0.026288261637091637, |
| "learning_rate": 0.0002, |
| "loss": 0.5398176908493042, |
| "mean_token_accuracy": 0.7807286381721497, |
| "num_tokens": 3775673.0, |
| "step": 231 |
| }, |
| { |
| "entropy": 0.5493600815534592, |
| "epoch": 0.8664799253034547, |
| "grad_norm": 0.03065655194222927, |
| "learning_rate": 0.0002, |
| "loss": 0.5482011437416077, |
| "mean_token_accuracy": 0.7772542536258698, |
| "num_tokens": 3791787.0, |
| "step": 232 |
| }, |
| { |
| "entropy": 0.5542360842227936, |
| "epoch": 0.8702147525676938, |
| "grad_norm": 0.032031431794166565, |
| "learning_rate": 0.0002, |
| "loss": 0.5554019212722778, |
| "mean_token_accuracy": 0.7739447802305222, |
| "num_tokens": 3808316.0, |
| "step": 233 |
| }, |
| { |
| "entropy": 0.5599103569984436, |
| "epoch": 0.8739495798319328, |
| "grad_norm": 0.027463702484965324, |
| "learning_rate": 0.0002, |
| "loss": 0.5579502582550049, |
| "mean_token_accuracy": 0.771759495139122, |
| "num_tokens": 3824701.0, |
| "step": 234 |
| }, |
| { |
| "entropy": 0.5677217245101929, |
| "epoch": 0.8776844070961718, |
| "grad_norm": 0.03142165020108223, |
| "learning_rate": 0.0002, |
| "loss": 0.5663169622421265, |
| "mean_token_accuracy": 0.7691013365983963, |
| "num_tokens": 3841435.0, |
| "step": 235 |
| }, |
| { |
| "entropy": 0.5482347160577774, |
| "epoch": 0.8814192343604108, |
| "grad_norm": 0.031262561678886414, |
| "learning_rate": 0.0002, |
| "loss": 0.552081823348999, |
| "mean_token_accuracy": 0.7783354371786118, |
| "num_tokens": 3857866.0, |
| "step": 236 |
| }, |
| { |
| "entropy": 0.5391282737255096, |
| "epoch": 0.8851540616246498, |
| "grad_norm": 0.030781790614128113, |
| "learning_rate": 0.0002, |
| "loss": 0.5469714403152466, |
| "mean_token_accuracy": 0.7780267000198364, |
| "num_tokens": 3874216.0, |
| "step": 237 |
| }, |
| { |
| "entropy": 0.5443921983242035, |
| "epoch": 0.8888888888888888, |
| "grad_norm": 0.032567523419857025, |
| "learning_rate": 0.0002, |
| "loss": 0.549781084060669, |
| "mean_token_accuracy": 0.7772793620824814, |
| "num_tokens": 3890382.0, |
| "step": 238 |
| }, |
| { |
| "entropy": 0.5604461878538132, |
| "epoch": 0.892623716153128, |
| "grad_norm": 0.02667226456105709, |
| "learning_rate": 0.0002, |
| "loss": 0.5538907051086426, |
| "mean_token_accuracy": 0.7770420461893082, |
| "num_tokens": 3906697.0, |
| "step": 239 |
| }, |
| { |
| "entropy": 0.5541103631258011, |
| "epoch": 0.896358543417367, |
| "grad_norm": 0.027397198602557182, |
| "learning_rate": 0.0002, |
| "loss": 0.5516767501831055, |
| "mean_token_accuracy": 0.7767754942178726, |
| "num_tokens": 3922978.0, |
| "step": 240 |
| }, |
| { |
| "entropy": 0.5521068722009659, |
| "epoch": 0.900093370681606, |
| "grad_norm": 0.032886214554309845, |
| "learning_rate": 0.0002, |
| "loss": 0.5538557171821594, |
| "mean_token_accuracy": 0.7769301533699036, |
| "num_tokens": 3939282.0, |
| "step": 241 |
| }, |
| { |
| "entropy": 0.5449024885892868, |
| "epoch": 0.903828197945845, |
| "grad_norm": 0.026176048442721367, |
| "learning_rate": 0.0002, |
| "loss": 0.5478168725967407, |
| "mean_token_accuracy": 0.7779200524091721, |
| "num_tokens": 3955520.0, |
| "step": 242 |
| }, |
| { |
| "entropy": 0.5615669041872025, |
| "epoch": 0.907563025210084, |
| "grad_norm": 0.02917352132499218, |
| "learning_rate": 0.0002, |
| "loss": 0.5631118416786194, |
| "mean_token_accuracy": 0.769850417971611, |
| "num_tokens": 3971679.0, |
| "step": 243 |
| }, |
| { |
| "entropy": 0.5360025763511658, |
| "epoch": 0.911297852474323, |
| "grad_norm": 0.028804168105125427, |
| "learning_rate": 0.0002, |
| "loss": 0.5399969816207886, |
| "mean_token_accuracy": 0.7786188125610352, |
| "num_tokens": 3987832.0, |
| "step": 244 |
| }, |
| { |
| "entropy": 0.5670223534107208, |
| "epoch": 0.9150326797385621, |
| "grad_norm": 0.032523807138204575, |
| "learning_rate": 0.0002, |
| "loss": 0.568830668926239, |
| "mean_token_accuracy": 0.7703544050455093, |
| "num_tokens": 4004046.0, |
| "step": 245 |
| }, |
| { |
| "entropy": 0.5482122004032135, |
| "epoch": 0.9187675070028011, |
| "grad_norm": 0.024507107213139534, |
| "learning_rate": 0.0002, |
| "loss": 0.5461756587028503, |
| "mean_token_accuracy": 0.7785715907812119, |
| "num_tokens": 4020396.0, |
| "step": 246 |
| }, |
| { |
| "entropy": 0.5435233414173126, |
| "epoch": 0.9225023342670402, |
| "grad_norm": 0.026535481214523315, |
| "learning_rate": 0.0002, |
| "loss": 0.5347612500190735, |
| "mean_token_accuracy": 0.7819430381059647, |
| "num_tokens": 4036657.0, |
| "step": 247 |
| }, |
| { |
| "entropy": 0.5606936663389206, |
| "epoch": 0.9262371615312792, |
| "grad_norm": 0.03222998231649399, |
| "learning_rate": 0.0002, |
| "loss": 0.5588559508323669, |
| "mean_token_accuracy": 0.7731847912073135, |
| "num_tokens": 4052932.0, |
| "step": 248 |
| }, |
| { |
| "entropy": 0.5559582114219666, |
| "epoch": 0.9299719887955182, |
| "grad_norm": 0.027079764753580093, |
| "learning_rate": 0.0002, |
| "loss": 0.5551950931549072, |
| "mean_token_accuracy": 0.7739483118057251, |
| "num_tokens": 4069465.0, |
| "step": 249 |
| }, |
| { |
| "entropy": 0.5464590489864349, |
| "epoch": 0.9337068160597572, |
| "grad_norm": 0.025224287062883377, |
| "learning_rate": 0.0002, |
| "loss": 0.548494815826416, |
| "mean_token_accuracy": 0.7777067720890045, |
| "num_tokens": 4085793.0, |
| "step": 250 |
| }, |
| { |
| "entropy": 0.5697829127311707, |
| "epoch": 0.9374416433239963, |
| "grad_norm": 0.03149845451116562, |
| "learning_rate": 0.0002, |
| "loss": 0.5725698471069336, |
| "mean_token_accuracy": 0.7667296230792999, |
| "num_tokens": 4102389.0, |
| "step": 251 |
| }, |
| { |
| "entropy": 0.5524837523698807, |
| "epoch": 0.9411764705882353, |
| "grad_norm": 0.027573609724640846, |
| "learning_rate": 0.0002, |
| "loss": 0.5497711896896362, |
| "mean_token_accuracy": 0.7749225348234177, |
| "num_tokens": 4118604.0, |
| "step": 252 |
| }, |
| { |
| "entropy": 0.5428849905729294, |
| "epoch": 0.9449112978524743, |
| "grad_norm": 0.025667617097496986, |
| "learning_rate": 0.0002, |
| "loss": 0.5428351163864136, |
| "mean_token_accuracy": 0.7771738916635513, |
| "num_tokens": 4135001.0, |
| "step": 253 |
| }, |
| { |
| "entropy": 0.5520694851875305, |
| "epoch": 0.9486461251167133, |
| "grad_norm": 0.035842686891555786, |
| "learning_rate": 0.0002, |
| "loss": 0.550408661365509, |
| "mean_token_accuracy": 0.7740647196769714, |
| "num_tokens": 4151260.0, |
| "step": 254 |
| }, |
| { |
| "entropy": 0.5418593287467957, |
| "epoch": 0.9523809523809523, |
| "grad_norm": 0.0381033793091774, |
| "learning_rate": 0.0002, |
| "loss": 0.5492621660232544, |
| "mean_token_accuracy": 0.7769514173269272, |
| "num_tokens": 4167360.0, |
| "step": 255 |
| }, |
| { |
| "entropy": 0.5375488549470901, |
| "epoch": 0.9561157796451915, |
| "grad_norm": 0.029893534258008003, |
| "learning_rate": 0.0002, |
| "loss": 0.5434277057647705, |
| "mean_token_accuracy": 0.7754911035299301, |
| "num_tokens": 4183517.0, |
| "step": 256 |
| }, |
| { |
| "entropy": 0.5487121939659119, |
| "epoch": 0.9598506069094305, |
| "grad_norm": 0.03323543071746826, |
| "learning_rate": 0.0002, |
| "loss": 0.549543559551239, |
| "mean_token_accuracy": 0.7791514545679092, |
| "num_tokens": 4200020.0, |
| "step": 257 |
| }, |
| { |
| "entropy": 0.5533169955015182, |
| "epoch": 0.9635854341736695, |
| "grad_norm": 0.1564125418663025, |
| "learning_rate": 0.0002, |
| "loss": 0.5513023138046265, |
| "mean_token_accuracy": 0.7750032246112823, |
| "num_tokens": 4216280.0, |
| "step": 258 |
| }, |
| { |
| "entropy": 0.5475684553384781, |
| "epoch": 0.9673202614379085, |
| "grad_norm": 0.05765023082494736, |
| "learning_rate": 0.0002, |
| "loss": 0.5540170073509216, |
| "mean_token_accuracy": 0.778236523270607, |
| "num_tokens": 4232501.0, |
| "step": 259 |
| }, |
| { |
| "entropy": 0.5620233714580536, |
| "epoch": 0.9710550887021475, |
| "grad_norm": 0.046510934829711914, |
| "learning_rate": 0.0002, |
| "loss": 0.5589131712913513, |
| "mean_token_accuracy": 0.7736849784851074, |
| "num_tokens": 4248855.0, |
| "step": 260 |
| }, |
| { |
| "entropy": 0.565828487277031, |
| "epoch": 0.9747899159663865, |
| "grad_norm": 0.0395890548825264, |
| "learning_rate": 0.0002, |
| "loss": 0.5624877214431763, |
| "mean_token_accuracy": 0.7722225338220596, |
| "num_tokens": 4265077.0, |
| "step": 261 |
| }, |
| { |
| "entropy": 0.5551140010356903, |
| "epoch": 0.9785247432306255, |
| "grad_norm": 0.03330749273300171, |
| "learning_rate": 0.0002, |
| "loss": 0.5576150417327881, |
| "mean_token_accuracy": 0.7741483747959137, |
| "num_tokens": 4281357.0, |
| "step": 262 |
| }, |
| { |
| "entropy": 0.5746229141950607, |
| "epoch": 0.9822595704948646, |
| "grad_norm": 0.03519619628787041, |
| "learning_rate": 0.0002, |
| "loss": 0.582584023475647, |
| "mean_token_accuracy": 0.7654829919338226, |
| "num_tokens": 4297699.0, |
| "step": 263 |
| }, |
| { |
| "entropy": 0.5782353579998016, |
| "epoch": 0.9859943977591037, |
| "grad_norm": 0.03913693502545357, |
| "learning_rate": 0.0002, |
| "loss": 0.5755780339241028, |
| "mean_token_accuracy": 0.7660959511995316, |
| "num_tokens": 4314249.0, |
| "step": 264 |
| }, |
| { |
| "entropy": 0.5513299107551575, |
| "epoch": 0.9897292250233427, |
| "grad_norm": 0.030444784089922905, |
| "learning_rate": 0.0002, |
| "loss": 0.5514294505119324, |
| "mean_token_accuracy": 0.7750695049762726, |
| "num_tokens": 4330437.0, |
| "step": 265 |
| }, |
| { |
| "entropy": 0.5386128276586533, |
| "epoch": 0.9934640522875817, |
| "grad_norm": 0.03275322541594505, |
| "learning_rate": 0.0002, |
| "loss": 0.540998637676239, |
| "mean_token_accuracy": 0.7796358019113541, |
| "num_tokens": 4346677.0, |
| "step": 266 |
| }, |
| { |
| "entropy": 0.5513150691986084, |
| "epoch": 0.9971988795518207, |
| "grad_norm": 0.03458503261208534, |
| "learning_rate": 0.0002, |
| "loss": 0.5484628677368164, |
| "mean_token_accuracy": 0.779531255364418, |
| "num_tokens": 4363004.0, |
| "step": 267 |
| }, |
| { |
| "entropy": 0.5694002906481425, |
| "epoch": 1.0, |
| "grad_norm": 0.033372946083545685, |
| "learning_rate": 0.0002, |
| "loss": 0.5757001638412476, |
| "mean_token_accuracy": 0.7725784182548523, |
| "num_tokens": 4364721.0, |
| "step": 268 |
| }, |
| { |
| "entropy": 0.5490456074476242, |
| "epoch": 1.003734827264239, |
| "grad_norm": 0.030816873535513878, |
| "learning_rate": 0.0002, |
| "loss": 0.5466992855072021, |
| "mean_token_accuracy": 0.7772593349218369, |
| "num_tokens": 4380959.0, |
| "step": 269 |
| }, |
| { |
| "entropy": 0.5297957360744476, |
| "epoch": 1.007469654528478, |
| "grad_norm": 0.0300835482776165, |
| "learning_rate": 0.0002, |
| "loss": 0.5296781063079834, |
| "mean_token_accuracy": 0.7851966172456741, |
| "num_tokens": 4397319.0, |
| "step": 270 |
| }, |
| { |
| "entropy": 0.5426550507545471, |
| "epoch": 1.011204481792717, |
| "grad_norm": 0.0309379193931818, |
| "learning_rate": 0.0002, |
| "loss": 0.5401790142059326, |
| "mean_token_accuracy": 0.7784202843904495, |
| "num_tokens": 4413503.0, |
| "step": 271 |
| }, |
| { |
| "entropy": 0.536088228225708, |
| "epoch": 1.014939309056956, |
| "grad_norm": 0.030822666361927986, |
| "learning_rate": 0.0002, |
| "loss": 0.533880352973938, |
| "mean_token_accuracy": 0.7821955978870392, |
| "num_tokens": 4429731.0, |
| "step": 272 |
| }, |
| { |
| "entropy": 0.5376520156860352, |
| "epoch": 1.018674136321195, |
| "grad_norm": 0.03910338878631592, |
| "learning_rate": 0.0002, |
| "loss": 0.5515881776809692, |
| "mean_token_accuracy": 0.7752164155244827, |
| "num_tokens": 4445975.0, |
| "step": 273 |
| }, |
| { |
| "entropy": 0.5337154120206833, |
| "epoch": 1.022408963585434, |
| "grad_norm": 0.030765611678361893, |
| "learning_rate": 0.0002, |
| "loss": 0.5412506461143494, |
| "mean_token_accuracy": 0.7780167758464813, |
| "num_tokens": 4462105.0, |
| "step": 274 |
| }, |
| { |
| "entropy": 0.5487084090709686, |
| "epoch": 1.026143790849673, |
| "grad_norm": 0.03003527596592903, |
| "learning_rate": 0.0002, |
| "loss": 0.540929913520813, |
| "mean_token_accuracy": 0.7784045934677124, |
| "num_tokens": 4478591.0, |
| "step": 275 |
| }, |
| { |
| "entropy": 0.5385126918554306, |
| "epoch": 1.0298786181139121, |
| "grad_norm": 0.027475042268633842, |
| "learning_rate": 0.0002, |
| "loss": 0.5318593978881836, |
| "mean_token_accuracy": 0.7862093448638916, |
| "num_tokens": 4495044.0, |
| "step": 276 |
| }, |
| { |
| "entropy": 0.5600587129592896, |
| "epoch": 1.0336134453781514, |
| "grad_norm": 0.029431000351905823, |
| "learning_rate": 0.0002, |
| "loss": 0.5559869408607483, |
| "mean_token_accuracy": 0.7744521498680115, |
| "num_tokens": 4511459.0, |
| "step": 277 |
| }, |
| { |
| "entropy": 0.5381200164556503, |
| "epoch": 1.0373482726423904, |
| "grad_norm": 0.02848048508167267, |
| "learning_rate": 0.0002, |
| "loss": 0.5395113229751587, |
| "mean_token_accuracy": 0.7798527628183365, |
| "num_tokens": 4527903.0, |
| "step": 278 |
| }, |
| { |
| "entropy": 0.5346540361642838, |
| "epoch": 1.0410830999066294, |
| "grad_norm": 0.033454034477472305, |
| "learning_rate": 0.0002, |
| "loss": 0.5404960513114929, |
| "mean_token_accuracy": 0.7793795019388199, |
| "num_tokens": 4544182.0, |
| "step": 279 |
| }, |
| { |
| "entropy": 0.544955238699913, |
| "epoch": 1.0448179271708684, |
| "grad_norm": 0.02894734963774681, |
| "learning_rate": 0.0002, |
| "loss": 0.5436176061630249, |
| "mean_token_accuracy": 0.7777452617883682, |
| "num_tokens": 4560880.0, |
| "step": 280 |
| }, |
| { |
| "entropy": 0.5431416183710098, |
| "epoch": 1.0485527544351074, |
| "grad_norm": 0.02903336100280285, |
| "learning_rate": 0.0002, |
| "loss": 0.5436229109764099, |
| "mean_token_accuracy": 0.7780826389789581, |
| "num_tokens": 4577183.0, |
| "step": 281 |
| }, |
| { |
| "entropy": 0.5408187806606293, |
| "epoch": 1.0522875816993464, |
| "grad_norm": 0.029271787032485008, |
| "learning_rate": 0.0002, |
| "loss": 0.5370380282402039, |
| "mean_token_accuracy": 0.7815099805593491, |
| "num_tokens": 4593864.0, |
| "step": 282 |
| }, |
| { |
| "entropy": 0.5497590750455856, |
| "epoch": 1.0560224089635855, |
| "grad_norm": 0.028807660564780235, |
| "learning_rate": 0.0002, |
| "loss": 0.5504873991012573, |
| "mean_token_accuracy": 0.777531310915947, |
| "num_tokens": 4610349.0, |
| "step": 283 |
| }, |
| { |
| "entropy": 0.5368742346763611, |
| "epoch": 1.0597572362278245, |
| "grad_norm": 0.031959034502506256, |
| "learning_rate": 0.0002, |
| "loss": 0.5419926643371582, |
| "mean_token_accuracy": 0.7784341871738434, |
| "num_tokens": 4626437.0, |
| "step": 284 |
| }, |
| { |
| "entropy": 0.5532872825860977, |
| "epoch": 1.0634920634920635, |
| "grad_norm": 0.028826460242271423, |
| "learning_rate": 0.0002, |
| "loss": 0.5571930408477783, |
| "mean_token_accuracy": 0.7746778875589371, |
| "num_tokens": 4642633.0, |
| "step": 285 |
| }, |
| { |
| "entropy": 0.5407113283872604, |
| "epoch": 1.0672268907563025, |
| "grad_norm": 0.03065388835966587, |
| "learning_rate": 0.0002, |
| "loss": 0.5436424612998962, |
| "mean_token_accuracy": 0.779659166932106, |
| "num_tokens": 4658940.0, |
| "step": 286 |
| }, |
| { |
| "entropy": 0.5552934855222702, |
| "epoch": 1.0709617180205415, |
| "grad_norm": 0.03264114633202553, |
| "learning_rate": 0.0002, |
| "loss": 0.5482615232467651, |
| "mean_token_accuracy": 0.7754945755004883, |
| "num_tokens": 4675263.0, |
| "step": 287 |
| }, |
| { |
| "entropy": 0.5442743301391602, |
| "epoch": 1.0746965452847805, |
| "grad_norm": 0.031116079539060593, |
| "learning_rate": 0.0002, |
| "loss": 0.538812518119812, |
| "mean_token_accuracy": 0.7806833982467651, |
| "num_tokens": 4691415.0, |
| "step": 288 |
| }, |
| { |
| "entropy": 0.5530855804681778, |
| "epoch": 1.0784313725490196, |
| "grad_norm": 0.03077593445777893, |
| "learning_rate": 0.0002, |
| "loss": 0.548968493938446, |
| "mean_token_accuracy": 0.7756039202213287, |
| "num_tokens": 4707736.0, |
| "step": 289 |
| }, |
| { |
| "entropy": 0.5455960035324097, |
| "epoch": 1.0821661998132586, |
| "grad_norm": 0.028605274856090546, |
| "learning_rate": 0.0002, |
| "loss": 0.5435131788253784, |
| "mean_token_accuracy": 0.7795460671186447, |
| "num_tokens": 4724095.0, |
| "step": 290 |
| }, |
| { |
| "entropy": 0.5397526025772095, |
| "epoch": 1.0859010270774976, |
| "grad_norm": 0.03644070401787758, |
| "learning_rate": 0.0002, |
| "loss": 0.5488567352294922, |
| "mean_token_accuracy": 0.7778657674789429, |
| "num_tokens": 4740602.0, |
| "step": 291 |
| }, |
| { |
| "entropy": 0.5470818132162094, |
| "epoch": 1.0896358543417366, |
| "grad_norm": 0.033212918788194656, |
| "learning_rate": 0.0002, |
| "loss": 0.555572509765625, |
| "mean_token_accuracy": 0.7734686136245728, |
| "num_tokens": 4756842.0, |
| "step": 292 |
| }, |
| { |
| "entropy": 0.5398264974355698, |
| "epoch": 1.0933706816059758, |
| "grad_norm": 0.027302522212266922, |
| "learning_rate": 0.0002, |
| "loss": 0.5371235013008118, |
| "mean_token_accuracy": 0.7826644480228424, |
| "num_tokens": 4773499.0, |
| "step": 293 |
| }, |
| { |
| "entropy": 0.564954400062561, |
| "epoch": 1.0971055088702149, |
| "grad_norm": 0.02829107642173767, |
| "learning_rate": 0.0002, |
| "loss": 0.5558594465255737, |
| "mean_token_accuracy": 0.7749541401863098, |
| "num_tokens": 4790183.0, |
| "step": 294 |
| }, |
| { |
| "entropy": 0.5593573749065399, |
| "epoch": 1.1008403361344539, |
| "grad_norm": 0.027547527104616165, |
| "learning_rate": 0.0002, |
| "loss": 0.5560394525527954, |
| "mean_token_accuracy": 0.7725719660520554, |
| "num_tokens": 4806455.0, |
| "step": 295 |
| }, |
| { |
| "entropy": 0.5377779453992844, |
| "epoch": 1.1045751633986929, |
| "grad_norm": 0.03161724656820297, |
| "learning_rate": 0.0002, |
| "loss": 0.5370453596115112, |
| "mean_token_accuracy": 0.782875582575798, |
| "num_tokens": 4822731.0, |
| "step": 296 |
| }, |
| { |
| "entropy": 0.5386165231466293, |
| "epoch": 1.108309990662932, |
| "grad_norm": 0.03147651255130768, |
| "learning_rate": 0.0002, |
| "loss": 0.5423634648323059, |
| "mean_token_accuracy": 0.7768422961235046, |
| "num_tokens": 4839112.0, |
| "step": 297 |
| }, |
| { |
| "entropy": 0.5279396325349808, |
| "epoch": 1.112044817927171, |
| "grad_norm": 0.031283456832170486, |
| "learning_rate": 0.0002, |
| "loss": 0.5321308970451355, |
| "mean_token_accuracy": 0.7849069982767105, |
| "num_tokens": 4855229.0, |
| "step": 298 |
| }, |
| { |
| "entropy": 0.5327593311667442, |
| "epoch": 1.11577964519141, |
| "grad_norm": 0.03042989782989025, |
| "learning_rate": 0.0002, |
| "loss": 0.5393236875534058, |
| "mean_token_accuracy": 0.7804521471261978, |
| "num_tokens": 4871644.0, |
| "step": 299 |
| }, |
| { |
| "entropy": 0.560793936252594, |
| "epoch": 1.119514472455649, |
| "grad_norm": 0.029397251084446907, |
| "learning_rate": 0.0002, |
| "loss": 0.5557554960250854, |
| "mean_token_accuracy": 0.7728655338287354, |
| "num_tokens": 4887992.0, |
| "step": 300 |
| }, |
| { |
| "entropy": 0.5604539066553116, |
| "epoch": 1.123249299719888, |
| "grad_norm": 0.02948898635804653, |
| "learning_rate": 0.0002, |
| "loss": 0.5545894503593445, |
| "mean_token_accuracy": 0.7743670493364334, |
| "num_tokens": 4904384.0, |
| "step": 301 |
| }, |
| { |
| "entropy": 0.5394376814365387, |
| "epoch": 1.126984126984127, |
| "grad_norm": 0.029182471334934235, |
| "learning_rate": 0.0002, |
| "loss": 0.5341510772705078, |
| "mean_token_accuracy": 0.7823253571987152, |
| "num_tokens": 4920587.0, |
| "step": 302 |
| }, |
| { |
| "entropy": 0.5301040560007095, |
| "epoch": 1.130718954248366, |
| "grad_norm": 0.03680079057812691, |
| "learning_rate": 0.0002, |
| "loss": 0.5372604131698608, |
| "mean_token_accuracy": 0.7793124318122864, |
| "num_tokens": 4937055.0, |
| "step": 303 |
| }, |
| { |
| "entropy": 0.5290943831205368, |
| "epoch": 1.134453781512605, |
| "grad_norm": 0.03931280970573425, |
| "learning_rate": 0.0002, |
| "loss": 0.5391898155212402, |
| "mean_token_accuracy": 0.7829029709100723, |
| "num_tokens": 4953281.0, |
| "step": 304 |
| }, |
| { |
| "entropy": 0.5609545707702637, |
| "epoch": 1.138188608776844, |
| "grad_norm": 0.030014565214514732, |
| "learning_rate": 0.0002, |
| "loss": 0.5609763264656067, |
| "mean_token_accuracy": 0.7726535797119141, |
| "num_tokens": 4969665.0, |
| "step": 305 |
| }, |
| { |
| "entropy": 0.5205260962247849, |
| "epoch": 1.141923436041083, |
| "grad_norm": 0.03301642835140228, |
| "learning_rate": 0.0002, |
| "loss": 0.5286065340042114, |
| "mean_token_accuracy": 0.7840328961610794, |
| "num_tokens": 4985863.0, |
| "step": 306 |
| }, |
| { |
| "entropy": 0.5605068057775497, |
| "epoch": 1.145658263305322, |
| "grad_norm": 0.029299437999725342, |
| "learning_rate": 0.0002, |
| "loss": 0.5569101572036743, |
| "mean_token_accuracy": 0.7721403539180756, |
| "num_tokens": 5002543.0, |
| "step": 307 |
| }, |
| { |
| "entropy": 0.552753359079361, |
| "epoch": 1.149393090569561, |
| "grad_norm": 0.027307430282235146, |
| "learning_rate": 0.0002, |
| "loss": 0.5464527606964111, |
| "mean_token_accuracy": 0.7777755260467529, |
| "num_tokens": 5019035.0, |
| "step": 308 |
| }, |
| { |
| "entropy": 0.5565258711576462, |
| "epoch": 1.1531279178338, |
| "grad_norm": 0.028590641915798187, |
| "learning_rate": 0.0002, |
| "loss": 0.551773726940155, |
| "mean_token_accuracy": 0.7753841280937195, |
| "num_tokens": 5035778.0, |
| "step": 309 |
| }, |
| { |
| "entropy": 0.5335747301578522, |
| "epoch": 1.156862745098039, |
| "grad_norm": 0.02846100926399231, |
| "learning_rate": 0.0002, |
| "loss": 0.5332034826278687, |
| "mean_token_accuracy": 0.7849084585905075, |
| "num_tokens": 5052106.0, |
| "step": 310 |
| }, |
| { |
| "entropy": 0.5462342649698257, |
| "epoch": 1.1605975723622783, |
| "grad_norm": 0.03037341870367527, |
| "learning_rate": 0.0002, |
| "loss": 0.5533976554870605, |
| "mean_token_accuracy": 0.7761731296777725, |
| "num_tokens": 5068494.0, |
| "step": 311 |
| }, |
| { |
| "entropy": 0.5365739315748215, |
| "epoch": 1.1643323996265174, |
| "grad_norm": 0.0328284353017807, |
| "learning_rate": 0.0002, |
| "loss": 0.5443044900894165, |
| "mean_token_accuracy": 0.7775984853506088, |
| "num_tokens": 5084698.0, |
| "step": 312 |
| }, |
| { |
| "entropy": 0.5469802767038345, |
| "epoch": 1.1680672268907564, |
| "grad_norm": 0.029220817610621452, |
| "learning_rate": 0.0002, |
| "loss": 0.5449838638305664, |
| "mean_token_accuracy": 0.7794362902641296, |
| "num_tokens": 5101231.0, |
| "step": 313 |
| }, |
| { |
| "entropy": 0.5534107983112335, |
| "epoch": 1.1718020541549954, |
| "grad_norm": 0.03240218386054039, |
| "learning_rate": 0.0002, |
| "loss": 0.5596653819084167, |
| "mean_token_accuracy": 0.7733468264341354, |
| "num_tokens": 5117669.0, |
| "step": 314 |
| }, |
| { |
| "entropy": 0.5505286902189255, |
| "epoch": 1.1755368814192344, |
| "grad_norm": 0.030088460072875023, |
| "learning_rate": 0.0002, |
| "loss": 0.5460378527641296, |
| "mean_token_accuracy": 0.7785163521766663, |
| "num_tokens": 5134044.0, |
| "step": 315 |
| }, |
| { |
| "entropy": 0.5583444237709045, |
| "epoch": 1.1792717086834734, |
| "grad_norm": 0.03908608481287956, |
| "learning_rate": 0.0002, |
| "loss": 0.5499372482299805, |
| "mean_token_accuracy": 0.7741111516952515, |
| "num_tokens": 5150155.0, |
| "step": 316 |
| }, |
| { |
| "entropy": 0.5583514273166656, |
| "epoch": 1.1830065359477124, |
| "grad_norm": 0.03262948617339134, |
| "learning_rate": 0.0002, |
| "loss": 0.5514504909515381, |
| "mean_token_accuracy": 0.7749726176261902, |
| "num_tokens": 5166653.0, |
| "step": 317 |
| }, |
| { |
| "entropy": 0.54158616065979, |
| "epoch": 1.1867413632119514, |
| "grad_norm": 0.030375484377145767, |
| "learning_rate": 0.0002, |
| "loss": 0.535007119178772, |
| "mean_token_accuracy": 0.78143410384655, |
| "num_tokens": 5182849.0, |
| "step": 318 |
| }, |
| { |
| "entropy": 0.5355552136898041, |
| "epoch": 1.1904761904761905, |
| "grad_norm": 0.034217700362205505, |
| "learning_rate": 0.0002, |
| "loss": 0.5416175723075867, |
| "mean_token_accuracy": 0.7821937054395676, |
| "num_tokens": 5199310.0, |
| "step": 319 |
| }, |
| { |
| "entropy": 0.5375736951828003, |
| "epoch": 1.1942110177404295, |
| "grad_norm": 0.03742173686623573, |
| "learning_rate": 0.0002, |
| "loss": 0.5497441291809082, |
| "mean_token_accuracy": 0.779162734746933, |
| "num_tokens": 5215628.0, |
| "step": 320 |
| }, |
| { |
| "entropy": 0.5327057242393494, |
| "epoch": 1.1979458450046685, |
| "grad_norm": 0.03143603354692459, |
| "learning_rate": 0.0002, |
| "loss": 0.5377879738807678, |
| "mean_token_accuracy": 0.7819731533527374, |
| "num_tokens": 5232104.0, |
| "step": 321 |
| }, |
| { |
| "entropy": 0.5589822083711624, |
| "epoch": 1.2016806722689075, |
| "grad_norm": 0.030957849696278572, |
| "learning_rate": 0.0002, |
| "loss": 0.5600837469100952, |
| "mean_token_accuracy": 0.772526428103447, |
| "num_tokens": 5248228.0, |
| "step": 322 |
| }, |
| { |
| "entropy": 0.5267817825078964, |
| "epoch": 1.2054154995331465, |
| "grad_norm": 0.028181420639157295, |
| "learning_rate": 0.0002, |
| "loss": 0.5258863568305969, |
| "mean_token_accuracy": 0.7852722406387329, |
| "num_tokens": 5264722.0, |
| "step": 323 |
| }, |
| { |
| "entropy": 0.5596602708101273, |
| "epoch": 1.2091503267973855, |
| "grad_norm": 0.0294583011418581, |
| "learning_rate": 0.0002, |
| "loss": 0.5542659163475037, |
| "mean_token_accuracy": 0.7757792323827744, |
| "num_tokens": 5281102.0, |
| "step": 324 |
| }, |
| { |
| "entropy": 0.5631477683782578, |
| "epoch": 1.2128851540616246, |
| "grad_norm": 0.028790894895792007, |
| "learning_rate": 0.0002, |
| "loss": 0.5568723678588867, |
| "mean_token_accuracy": 0.771973267197609, |
| "num_tokens": 5297684.0, |
| "step": 325 |
| }, |
| { |
| "entropy": 0.5380028486251831, |
| "epoch": 1.2166199813258638, |
| "grad_norm": 0.031924713402986526, |
| "learning_rate": 0.0002, |
| "loss": 0.5376958847045898, |
| "mean_token_accuracy": 0.7829422205686569, |
| "num_tokens": 5313908.0, |
| "step": 326 |
| }, |
| { |
| "entropy": 0.5375301241874695, |
| "epoch": 1.2203548085901028, |
| "grad_norm": 0.03397483006119728, |
| "learning_rate": 0.0002, |
| "loss": 0.5478475093841553, |
| "mean_token_accuracy": 0.7765705734491348, |
| "num_tokens": 5329966.0, |
| "step": 327 |
| }, |
| { |
| "entropy": 0.5427165776491165, |
| "epoch": 1.2240896358543418, |
| "grad_norm": 0.035384900867938995, |
| "learning_rate": 0.0002, |
| "loss": 0.5524033308029175, |
| "mean_token_accuracy": 0.7745779901742935, |
| "num_tokens": 5346453.0, |
| "step": 328 |
| }, |
| { |
| "entropy": 0.5400120764970779, |
| "epoch": 1.2278244631185808, |
| "grad_norm": 0.030376868322491646, |
| "learning_rate": 0.0002, |
| "loss": 0.5346859097480774, |
| "mean_token_accuracy": 0.7804136276245117, |
| "num_tokens": 5362598.0, |
| "step": 329 |
| }, |
| { |
| "entropy": 0.5525883883237839, |
| "epoch": 1.2315592903828199, |
| "grad_norm": 0.029532834887504578, |
| "learning_rate": 0.0002, |
| "loss": 0.5460601449012756, |
| "mean_token_accuracy": 0.7782909572124481, |
| "num_tokens": 5378809.0, |
| "step": 330 |
| }, |
| { |
| "entropy": 0.5435810536146164, |
| "epoch": 1.2352941176470589, |
| "grad_norm": 0.02912810444831848, |
| "learning_rate": 0.0002, |
| "loss": 0.5412687659263611, |
| "mean_token_accuracy": 0.7805328518152237, |
| "num_tokens": 5394964.0, |
| "step": 331 |
| }, |
| { |
| "entropy": 0.5558127015829086, |
| "epoch": 1.239028944911298, |
| "grad_norm": 0.03399093821644783, |
| "learning_rate": 0.0002, |
| "loss": 0.5503210425376892, |
| "mean_token_accuracy": 0.7771144658327103, |
| "num_tokens": 5411296.0, |
| "step": 332 |
| }, |
| { |
| "entropy": 0.5612344145774841, |
| "epoch": 1.242763772175537, |
| "grad_norm": 0.028297265991568565, |
| "learning_rate": 0.0002, |
| "loss": 0.561404824256897, |
| "mean_token_accuracy": 0.7735303044319153, |
| "num_tokens": 5427522.0, |
| "step": 333 |
| }, |
| { |
| "entropy": 0.5317913144826889, |
| "epoch": 1.246498599439776, |
| "grad_norm": 0.03494315594434738, |
| "learning_rate": 0.0002, |
| "loss": 0.5433036684989929, |
| "mean_token_accuracy": 0.7796971648931503, |
| "num_tokens": 5443757.0, |
| "step": 334 |
| }, |
| { |
| "entropy": 0.542137622833252, |
| "epoch": 1.250233426704015, |
| "grad_norm": 0.02819279581308365, |
| "learning_rate": 0.0002, |
| "loss": 0.5451513528823853, |
| "mean_token_accuracy": 0.7785246819257736, |
| "num_tokens": 5460219.0, |
| "step": 335 |
| }, |
| { |
| "entropy": 0.5389015078544617, |
| "epoch": 1.253968253968254, |
| "grad_norm": 0.029153091832995415, |
| "learning_rate": 0.0002, |
| "loss": 0.5426021218299866, |
| "mean_token_accuracy": 0.7783170789480209, |
| "num_tokens": 5476465.0, |
| "step": 336 |
| }, |
| { |
| "entropy": 0.5529672205448151, |
| "epoch": 1.257703081232493, |
| "grad_norm": 0.03458336368203163, |
| "learning_rate": 0.0002, |
| "loss": 0.540812611579895, |
| "mean_token_accuracy": 0.7807324081659317, |
| "num_tokens": 5492565.0, |
| "step": 337 |
| }, |
| { |
| "entropy": 0.581393301486969, |
| "epoch": 1.261437908496732, |
| "grad_norm": 0.031111041083931923, |
| "learning_rate": 0.0002, |
| "loss": 0.5751311779022217, |
| "mean_token_accuracy": 0.7666933685541153, |
| "num_tokens": 5509003.0, |
| "step": 338 |
| }, |
| { |
| "entropy": 0.5588483065366745, |
| "epoch": 1.265172735760971, |
| "grad_norm": 0.030144309625029564, |
| "learning_rate": 0.0002, |
| "loss": 0.5589640140533447, |
| "mean_token_accuracy": 0.7755171656608582, |
| "num_tokens": 5525262.0, |
| "step": 339 |
| }, |
| { |
| "entropy": 0.5336481779813766, |
| "epoch": 1.26890756302521, |
| "grad_norm": 0.03417432680726051, |
| "learning_rate": 0.0002, |
| "loss": 0.5390788316726685, |
| "mean_token_accuracy": 0.780031830072403, |
| "num_tokens": 5541654.0, |
| "step": 340 |
| }, |
| { |
| "entropy": 0.5282999128103256, |
| "epoch": 1.272642390289449, |
| "grad_norm": 0.03498517721891403, |
| "learning_rate": 0.0002, |
| "loss": 0.5387616157531738, |
| "mean_token_accuracy": 0.7800437808036804, |
| "num_tokens": 5557983.0, |
| "step": 341 |
| }, |
| { |
| "entropy": 0.5369831025600433, |
| "epoch": 1.276377217553688, |
| "grad_norm": 0.029845617711544037, |
| "learning_rate": 0.0002, |
| "loss": 0.535378634929657, |
| "mean_token_accuracy": 0.7823457568883896, |
| "num_tokens": 5574311.0, |
| "step": 342 |
| }, |
| { |
| "entropy": 0.5538373440504074, |
| "epoch": 1.280112044817927, |
| "grad_norm": 0.027923226356506348, |
| "learning_rate": 0.0002, |
| "loss": 0.5500721335411072, |
| "mean_token_accuracy": 0.7771336436271667, |
| "num_tokens": 5590547.0, |
| "step": 343 |
| }, |
| { |
| "entropy": 0.5545977205038071, |
| "epoch": 1.283846872082166, |
| "grad_norm": 0.0305513683706522, |
| "learning_rate": 0.0002, |
| "loss": 0.5511223077774048, |
| "mean_token_accuracy": 0.7757980972528458, |
| "num_tokens": 5606717.0, |
| "step": 344 |
| }, |
| { |
| "entropy": 0.560431718826294, |
| "epoch": 1.287581699346405, |
| "grad_norm": 0.029267068952322006, |
| "learning_rate": 0.0002, |
| "loss": 0.5540031790733337, |
| "mean_token_accuracy": 0.7738614529371262, |
| "num_tokens": 5623238.0, |
| "step": 345 |
| }, |
| { |
| "entropy": 0.5598475635051727, |
| "epoch": 1.2913165266106443, |
| "grad_norm": 0.032441407442092896, |
| "learning_rate": 0.0002, |
| "loss": 0.5511676669120789, |
| "mean_token_accuracy": 0.775727853178978, |
| "num_tokens": 5639482.0, |
| "step": 346 |
| }, |
| { |
| "entropy": 0.532151535153389, |
| "epoch": 1.2950513538748833, |
| "grad_norm": 0.03496084734797478, |
| "learning_rate": 0.0002, |
| "loss": 0.5387351512908936, |
| "mean_token_accuracy": 0.7811897695064545, |
| "num_tokens": 5655745.0, |
| "step": 347 |
| }, |
| { |
| "entropy": 0.5362464487552643, |
| "epoch": 1.2987861811391224, |
| "grad_norm": 0.03774246945977211, |
| "learning_rate": 0.0002, |
| "loss": 0.5451931953430176, |
| "mean_token_accuracy": 0.7775505632162094, |
| "num_tokens": 5672305.0, |
| "step": 348 |
| }, |
| { |
| "entropy": 0.5285972878336906, |
| "epoch": 1.3025210084033614, |
| "grad_norm": 0.0332336500287056, |
| "learning_rate": 0.0002, |
| "loss": 0.5353838801383972, |
| "mean_token_accuracy": 0.7838114500045776, |
| "num_tokens": 5688630.0, |
| "step": 349 |
| }, |
| { |
| "entropy": 0.5421172678470612, |
| "epoch": 1.3062558356676004, |
| "grad_norm": 0.03457598015666008, |
| "learning_rate": 0.0002, |
| "loss": 0.5392417311668396, |
| "mean_token_accuracy": 0.7807410657405853, |
| "num_tokens": 5705054.0, |
| "step": 350 |
| }, |
| { |
| "entropy": 0.5382883250713348, |
| "epoch": 1.3099906629318394, |
| "grad_norm": 0.031050430610775948, |
| "learning_rate": 0.0002, |
| "loss": 0.5347834825515747, |
| "mean_token_accuracy": 0.7828159481287003, |
| "num_tokens": 5721382.0, |
| "step": 351 |
| }, |
| { |
| "entropy": 0.550368145108223, |
| "epoch": 1.3137254901960784, |
| "grad_norm": 0.03463875129818916, |
| "learning_rate": 0.0002, |
| "loss": 0.5514199137687683, |
| "mean_token_accuracy": 0.7735539227724075, |
| "num_tokens": 5737730.0, |
| "step": 352 |
| }, |
| { |
| "entropy": 0.538982629776001, |
| "epoch": 1.3174603174603174, |
| "grad_norm": 0.03956155851483345, |
| "learning_rate": 0.0002, |
| "loss": 0.5469655990600586, |
| "mean_token_accuracy": 0.7747407406568527, |
| "num_tokens": 5753795.0, |
| "step": 353 |
| }, |
| { |
| "entropy": 0.5339585244655609, |
| "epoch": 1.3211951447245565, |
| "grad_norm": 0.029367057606577873, |
| "learning_rate": 0.0002, |
| "loss": 0.536923348903656, |
| "mean_token_accuracy": 0.7791249603033066, |
| "num_tokens": 5770100.0, |
| "step": 354 |
| }, |
| { |
| "entropy": 0.5469655245542526, |
| "epoch": 1.3249299719887955, |
| "grad_norm": 0.044070687144994736, |
| "learning_rate": 0.0002, |
| "loss": 0.5485926270484924, |
| "mean_token_accuracy": 0.7760020345449448, |
| "num_tokens": 5786242.0, |
| "step": 355 |
| }, |
| { |
| "entropy": 0.5686767846345901, |
| "epoch": 1.3286647992530345, |
| "grad_norm": 0.0298174861818552, |
| "learning_rate": 0.0002, |
| "loss": 0.5646032691001892, |
| "mean_token_accuracy": 0.7700935900211334, |
| "num_tokens": 5802594.0, |
| "step": 356 |
| }, |
| { |
| "entropy": 0.5524211078882217, |
| "epoch": 1.3323996265172735, |
| "grad_norm": 0.03443749621510506, |
| "learning_rate": 0.0002, |
| "loss": 0.5538625717163086, |
| "mean_token_accuracy": 0.7730942517518997, |
| "num_tokens": 5818733.0, |
| "step": 357 |
| }, |
| { |
| "entropy": 0.5450694710016251, |
| "epoch": 1.3361344537815127, |
| "grad_norm": 0.042639389634132385, |
| "learning_rate": 0.0002, |
| "loss": 0.5457915663719177, |
| "mean_token_accuracy": 0.7793462425470352, |
| "num_tokens": 5834966.0, |
| "step": 358 |
| }, |
| { |
| "entropy": 0.5628755837678909, |
| "epoch": 1.3398692810457518, |
| "grad_norm": 0.031939953565597534, |
| "learning_rate": 0.0002, |
| "loss": 0.5615131855010986, |
| "mean_token_accuracy": 0.7720433920621872, |
| "num_tokens": 5851352.0, |
| "step": 359 |
| }, |
| { |
| "entropy": 0.5299947410821915, |
| "epoch": 1.3436041083099908, |
| "grad_norm": 0.03047833777964115, |
| "learning_rate": 0.0002, |
| "loss": 0.5295021533966064, |
| "mean_token_accuracy": 0.7874699085950851, |
| "num_tokens": 5867820.0, |
| "step": 360 |
| }, |
| { |
| "entropy": 0.5308109223842621, |
| "epoch": 1.3473389355742298, |
| "grad_norm": 0.032848697155714035, |
| "learning_rate": 0.0002, |
| "loss": 0.5431129336357117, |
| "mean_token_accuracy": 0.7857107818126678, |
| "num_tokens": 5883984.0, |
| "step": 361 |
| }, |
| { |
| "entropy": 0.5426601469516754, |
| "epoch": 1.3510737628384688, |
| "grad_norm": 0.033830493688583374, |
| "learning_rate": 0.0002, |
| "loss": 0.5514194965362549, |
| "mean_token_accuracy": 0.77635657787323, |
| "num_tokens": 5900290.0, |
| "step": 362 |
| }, |
| { |
| "entropy": 0.5411643236875534, |
| "epoch": 1.3548085901027078, |
| "grad_norm": 0.029694274067878723, |
| "learning_rate": 0.0002, |
| "loss": 0.5333205461502075, |
| "mean_token_accuracy": 0.7832283675670624, |
| "num_tokens": 5916469.0, |
| "step": 363 |
| }, |
| { |
| "entropy": 0.5501731634140015, |
| "epoch": 1.3585434173669468, |
| "grad_norm": 0.03007029928267002, |
| "learning_rate": 0.0002, |
| "loss": 0.5431393980979919, |
| "mean_token_accuracy": 0.7804041355848312, |
| "num_tokens": 5932693.0, |
| "step": 364 |
| }, |
| { |
| "entropy": 0.5419217795133591, |
| "epoch": 1.3622782446311859, |
| "grad_norm": 0.030986929312348366, |
| "learning_rate": 0.0002, |
| "loss": 0.5391764044761658, |
| "mean_token_accuracy": 0.7810684144496918, |
| "num_tokens": 5949053.0, |
| "step": 365 |
| }, |
| { |
| "entropy": 0.529257670044899, |
| "epoch": 1.3660130718954249, |
| "grad_norm": 0.0282028466463089, |
| "learning_rate": 0.0002, |
| "loss": 0.5282759666442871, |
| "mean_token_accuracy": 0.7846860438585281, |
| "num_tokens": 5965428.0, |
| "step": 366 |
| }, |
| { |
| "entropy": 0.5425796508789062, |
| "epoch": 1.3697478991596639, |
| "grad_norm": 0.03842358663678169, |
| "learning_rate": 0.0002, |
| "loss": 0.5492331981658936, |
| "mean_token_accuracy": 0.7747556120157242, |
| "num_tokens": 5981730.0, |
| "step": 367 |
| }, |
| { |
| "entropy": 0.5349410325288773, |
| "epoch": 1.373482726423903, |
| "grad_norm": 0.033598389476537704, |
| "learning_rate": 0.0002, |
| "loss": 0.5436474084854126, |
| "mean_token_accuracy": 0.7797878831624985, |
| "num_tokens": 5997949.0, |
| "step": 368 |
| }, |
| { |
| "entropy": 0.552407756447792, |
| "epoch": 1.377217553688142, |
| "grad_norm": 0.03342469781637192, |
| "learning_rate": 0.0002, |
| "loss": 0.5567049980163574, |
| "mean_token_accuracy": 0.7723858207464218, |
| "num_tokens": 6014178.0, |
| "step": 369 |
| }, |
| { |
| "entropy": 0.5454883426427841, |
| "epoch": 1.380952380952381, |
| "grad_norm": 0.03550714999437332, |
| "learning_rate": 0.0002, |
| "loss": 0.5418342351913452, |
| "mean_token_accuracy": 0.7798961699008942, |
| "num_tokens": 6030806.0, |
| "step": 370 |
| }, |
| { |
| "entropy": 0.552109032869339, |
| "epoch": 1.38468720821662, |
| "grad_norm": 0.03026903234422207, |
| "learning_rate": 0.0002, |
| "loss": 0.5456339120864868, |
| "mean_token_accuracy": 0.7773927599191666, |
| "num_tokens": 6046782.0, |
| "step": 371 |
| }, |
| { |
| "entropy": 0.5603116452693939, |
| "epoch": 1.388422035480859, |
| "grad_norm": 0.03449714556336403, |
| "learning_rate": 0.0002, |
| "loss": 0.5605192184448242, |
| "mean_token_accuracy": 0.7709443271160126, |
| "num_tokens": 6063178.0, |
| "step": 372 |
| }, |
| { |
| "entropy": 0.5442145317792892, |
| "epoch": 1.392156862745098, |
| "grad_norm": 0.03407449275255203, |
| "learning_rate": 0.0002, |
| "loss": 0.5482808947563171, |
| "mean_token_accuracy": 0.7804455161094666, |
| "num_tokens": 6079813.0, |
| "step": 373 |
| }, |
| { |
| "entropy": 0.5443685501813889, |
| "epoch": 1.395891690009337, |
| "grad_norm": 0.03118809685111046, |
| "learning_rate": 0.0002, |
| "loss": 0.5504392385482788, |
| "mean_token_accuracy": 0.7759056687355042, |
| "num_tokens": 6096208.0, |
| "step": 374 |
| }, |
| { |
| "entropy": 0.5544550269842148, |
| "epoch": 1.399626517273576, |
| "grad_norm": 0.03532007709145546, |
| "learning_rate": 0.0002, |
| "loss": 0.5569352507591248, |
| "mean_token_accuracy": 0.7748352587223053, |
| "num_tokens": 6112356.0, |
| "step": 375 |
| }, |
| { |
| "entropy": 0.5439307242631912, |
| "epoch": 1.403361344537815, |
| "grad_norm": 0.0334586501121521, |
| "learning_rate": 0.0002, |
| "loss": 0.542488694190979, |
| "mean_token_accuracy": 0.777744397521019, |
| "num_tokens": 6128800.0, |
| "step": 376 |
| }, |
| { |
| "entropy": 0.5407049357891083, |
| "epoch": 1.407096171802054, |
| "grad_norm": 0.029349738731980324, |
| "learning_rate": 0.0002, |
| "loss": 0.5370444655418396, |
| "mean_token_accuracy": 0.7816447019577026, |
| "num_tokens": 6145053.0, |
| "step": 377 |
| }, |
| { |
| "entropy": 0.5527060329914093, |
| "epoch": 1.410830999066293, |
| "grad_norm": 0.030373841524124146, |
| "learning_rate": 0.0002, |
| "loss": 0.5530543327331543, |
| "mean_token_accuracy": 0.775768980383873, |
| "num_tokens": 6161518.0, |
| "step": 378 |
| }, |
| { |
| "entropy": 0.5383686721324921, |
| "epoch": 1.4145658263305323, |
| "grad_norm": 0.033442895859479904, |
| "learning_rate": 0.0002, |
| "loss": 0.539923369884491, |
| "mean_token_accuracy": 0.7825078517198563, |
| "num_tokens": 6177817.0, |
| "step": 379 |
| }, |
| { |
| "entropy": 0.5557737052440643, |
| "epoch": 1.4183006535947713, |
| "grad_norm": 0.03396908566355705, |
| "learning_rate": 0.0002, |
| "loss": 0.5632482767105103, |
| "mean_token_accuracy": 0.7692397683858871, |
| "num_tokens": 6194312.0, |
| "step": 380 |
| }, |
| { |
| "entropy": 0.5457819253206253, |
| "epoch": 1.4220354808590103, |
| "grad_norm": 0.02866293303668499, |
| "learning_rate": 0.0002, |
| "loss": 0.5467988848686218, |
| "mean_token_accuracy": 0.7775601893663406, |
| "num_tokens": 6210818.0, |
| "step": 381 |
| }, |
| { |
| "entropy": 0.5640534311532974, |
| "epoch": 1.4257703081232493, |
| "grad_norm": 0.027476362884044647, |
| "learning_rate": 0.0002, |
| "loss": 0.5636141896247864, |
| "mean_token_accuracy": 0.7717417329549789, |
| "num_tokens": 6227080.0, |
| "step": 382 |
| }, |
| { |
| "entropy": 0.560546487569809, |
| "epoch": 1.4295051353874884, |
| "grad_norm": 0.030654683709144592, |
| "learning_rate": 0.0002, |
| "loss": 0.5566866397857666, |
| "mean_token_accuracy": 0.7725766897201538, |
| "num_tokens": 6243654.0, |
| "step": 383 |
| }, |
| { |
| "entropy": 0.5566196143627167, |
| "epoch": 1.4332399626517274, |
| "grad_norm": 0.03377790376543999, |
| "learning_rate": 0.0002, |
| "loss": 0.5511550903320312, |
| "mean_token_accuracy": 0.7775295376777649, |
| "num_tokens": 6259998.0, |
| "step": 384 |
| }, |
| { |
| "entropy": 0.5302538275718689, |
| "epoch": 1.4369747899159664, |
| "grad_norm": 0.028172362595796585, |
| "learning_rate": 0.0002, |
| "loss": 0.5359051823616028, |
| "mean_token_accuracy": 0.7816868871450424, |
| "num_tokens": 6276398.0, |
| "step": 385 |
| }, |
| { |
| "entropy": 0.543848991394043, |
| "epoch": 1.4407096171802054, |
| "grad_norm": 0.03123684599995613, |
| "learning_rate": 0.0002, |
| "loss": 0.5530490875244141, |
| "mean_token_accuracy": 0.7756175249814987, |
| "num_tokens": 6292623.0, |
| "step": 386 |
| }, |
| { |
| "entropy": 0.5351638197898865, |
| "epoch": 1.4444444444444444, |
| "grad_norm": 0.032041870057582855, |
| "learning_rate": 0.0002, |
| "loss": 0.5453383326530457, |
| "mean_token_accuracy": 0.7787481844425201, |
| "num_tokens": 6308980.0, |
| "step": 387 |
| }, |
| { |
| "entropy": 0.5499856919050217, |
| "epoch": 1.4481792717086834, |
| "grad_norm": 0.03275283798575401, |
| "learning_rate": 0.0002, |
| "loss": 0.5510199666023254, |
| "mean_token_accuracy": 0.7770793437957764, |
| "num_tokens": 6325352.0, |
| "step": 388 |
| }, |
| { |
| "entropy": 0.5473773032426834, |
| "epoch": 1.4519140989729225, |
| "grad_norm": 0.02793571725487709, |
| "learning_rate": 0.0002, |
| "loss": 0.540398120880127, |
| "mean_token_accuracy": 0.7805086821317673, |
| "num_tokens": 6341686.0, |
| "step": 389 |
| }, |
| { |
| "entropy": 0.553907573223114, |
| "epoch": 1.4556489262371615, |
| "grad_norm": 0.02763449028134346, |
| "learning_rate": 0.0002, |
| "loss": 0.5470324754714966, |
| "mean_token_accuracy": 0.7763955593109131, |
| "num_tokens": 6358367.0, |
| "step": 390 |
| }, |
| { |
| "entropy": 0.54300856590271, |
| "epoch": 1.4593837535014005, |
| "grad_norm": 0.0320272259414196, |
| "learning_rate": 0.0002, |
| "loss": 0.5394243001937866, |
| "mean_token_accuracy": 0.7796929031610489, |
| "num_tokens": 6374332.0, |
| "step": 391 |
| }, |
| { |
| "entropy": 0.5419201552867889, |
| "epoch": 1.4631185807656397, |
| "grad_norm": 0.029694141820073128, |
| "learning_rate": 0.0002, |
| "loss": 0.5459417104721069, |
| "mean_token_accuracy": 0.7794879227876663, |
| "num_tokens": 6390817.0, |
| "step": 392 |
| }, |
| { |
| "entropy": 0.533346489071846, |
| "epoch": 1.4668534080298787, |
| "grad_norm": 0.031921736896038055, |
| "learning_rate": 0.0002, |
| "loss": 0.5339134335517883, |
| "mean_token_accuracy": 0.7845402210950851, |
| "num_tokens": 6407105.0, |
| "step": 393 |
| }, |
| { |
| "entropy": 0.5490029752254486, |
| "epoch": 1.4705882352941178, |
| "grad_norm": 0.031292662024497986, |
| "learning_rate": 0.0002, |
| "loss": 0.5461300611495972, |
| "mean_token_accuracy": 0.7792785912752151, |
| "num_tokens": 6423432.0, |
| "step": 394 |
| }, |
| { |
| "entropy": 0.5407290160655975, |
| "epoch": 1.4743230625583568, |
| "grad_norm": 0.029509229585528374, |
| "learning_rate": 0.0002, |
| "loss": 0.5409979224205017, |
| "mean_token_accuracy": 0.7798801958560944, |
| "num_tokens": 6440111.0, |
| "step": 395 |
| }, |
| { |
| "entropy": 0.5352925509214401, |
| "epoch": 1.4780578898225958, |
| "grad_norm": 0.03132627159357071, |
| "learning_rate": 0.0002, |
| "loss": 0.5360226035118103, |
| "mean_token_accuracy": 0.7835162281990051, |
| "num_tokens": 6456553.0, |
| "step": 396 |
| }, |
| { |
| "entropy": 0.5409245789051056, |
| "epoch": 1.4817927170868348, |
| "grad_norm": 0.032262932509183884, |
| "learning_rate": 0.0002, |
| "loss": 0.5367339253425598, |
| "mean_token_accuracy": 0.779682844877243, |
| "num_tokens": 6472831.0, |
| "step": 397 |
| }, |
| { |
| "entropy": 0.5202168971300125, |
| "epoch": 1.4855275443510738, |
| "grad_norm": 0.033896930515766144, |
| "learning_rate": 0.0002, |
| "loss": 0.5268123149871826, |
| "mean_token_accuracy": 0.7819826900959015, |
| "num_tokens": 6488931.0, |
| "step": 398 |
| }, |
| { |
| "entropy": 0.5325956791639328, |
| "epoch": 1.4892623716153128, |
| "grad_norm": 0.03540036827325821, |
| "learning_rate": 0.0002, |
| "loss": 0.5433887839317322, |
| "mean_token_accuracy": 0.778034120798111, |
| "num_tokens": 6505354.0, |
| "step": 399 |
| }, |
| { |
| "entropy": 0.5327711254358292, |
| "epoch": 1.4929971988795518, |
| "grad_norm": 0.02958959899842739, |
| "learning_rate": 0.0002, |
| "loss": 0.5335476398468018, |
| "mean_token_accuracy": 0.7828179448843002, |
| "num_tokens": 6521544.0, |
| "step": 400 |
| }, |
| { |
| "entropy": 0.5357908606529236, |
| "epoch": 1.4967320261437909, |
| "grad_norm": 0.027617521584033966, |
| "learning_rate": 0.0002, |
| "loss": 0.5293720364570618, |
| "mean_token_accuracy": 0.7868403792381287, |
| "num_tokens": 6537889.0, |
| "step": 401 |
| }, |
| { |
| "entropy": 0.5473283380270004, |
| "epoch": 1.5004668534080299, |
| "grad_norm": 0.028360038995742798, |
| "learning_rate": 0.0002, |
| "loss": 0.5436528325080872, |
| "mean_token_accuracy": 0.7810066491365433, |
| "num_tokens": 6554149.0, |
| "step": 402 |
| }, |
| { |
| "entropy": 0.5518513321876526, |
| "epoch": 1.504201680672269, |
| "grad_norm": 0.031041931360960007, |
| "learning_rate": 0.0002, |
| "loss": 0.545119047164917, |
| "mean_token_accuracy": 0.7779288738965988, |
| "num_tokens": 6570521.0, |
| "step": 403 |
| }, |
| { |
| "entropy": 0.5428237915039062, |
| "epoch": 1.507936507936508, |
| "grad_norm": 0.032197825610637665, |
| "learning_rate": 0.0002, |
| "loss": 0.5472823977470398, |
| "mean_token_accuracy": 0.7758528888225555, |
| "num_tokens": 6587086.0, |
| "step": 404 |
| }, |
| { |
| "entropy": 0.5483403950929642, |
| "epoch": 1.511671335200747, |
| "grad_norm": 0.03174825757741928, |
| "learning_rate": 0.0002, |
| "loss": 0.5524789094924927, |
| "mean_token_accuracy": 0.7772649824619293, |
| "num_tokens": 6603513.0, |
| "step": 405 |
| }, |
| { |
| "entropy": 0.5337469726800919, |
| "epoch": 1.515406162464986, |
| "grad_norm": 0.03365413472056389, |
| "learning_rate": 0.0002, |
| "loss": 0.5418713688850403, |
| "mean_token_accuracy": 0.7772432267665863, |
| "num_tokens": 6619737.0, |
| "step": 406 |
| }, |
| { |
| "entropy": 0.5614880919456482, |
| "epoch": 1.519140989729225, |
| "grad_norm": 0.030781377106904984, |
| "learning_rate": 0.0002, |
| "loss": 0.5604795217514038, |
| "mean_token_accuracy": 0.7718411535024643, |
| "num_tokens": 6636097.0, |
| "step": 407 |
| }, |
| { |
| "entropy": 0.5390657633543015, |
| "epoch": 1.522875816993464, |
| "grad_norm": 0.02782733179628849, |
| "learning_rate": 0.0002, |
| "loss": 0.5329728126525879, |
| "mean_token_accuracy": 0.7839234322309494, |
| "num_tokens": 6652406.0, |
| "step": 408 |
| }, |
| { |
| "entropy": 0.5573919266462326, |
| "epoch": 1.526610644257703, |
| "grad_norm": 0.027401108294725418, |
| "learning_rate": 0.0002, |
| "loss": 0.5554807186126709, |
| "mean_token_accuracy": 0.7726366519927979, |
| "num_tokens": 6668812.0, |
| "step": 409 |
| }, |
| { |
| "entropy": 0.5391197204589844, |
| "epoch": 1.530345471521942, |
| "grad_norm": 0.03163023665547371, |
| "learning_rate": 0.0002, |
| "loss": 0.5407525897026062, |
| "mean_token_accuracy": 0.7810121178627014, |
| "num_tokens": 6685040.0, |
| "step": 410 |
| }, |
| { |
| "entropy": 0.5353195369243622, |
| "epoch": 1.534080298786181, |
| "grad_norm": 0.026917260140180588, |
| "learning_rate": 0.0002, |
| "loss": 0.5328407883644104, |
| "mean_token_accuracy": 0.7829948961734772, |
| "num_tokens": 6701433.0, |
| "step": 411 |
| }, |
| { |
| "entropy": 0.5223068818449974, |
| "epoch": 1.53781512605042, |
| "grad_norm": 0.03261617571115494, |
| "learning_rate": 0.0002, |
| "loss": 0.5255942344665527, |
| "mean_token_accuracy": 0.785964623093605, |
| "num_tokens": 6717710.0, |
| "step": 412 |
| }, |
| { |
| "entropy": 0.5453132838010788, |
| "epoch": 1.541549953314659, |
| "grad_norm": 0.03235824778676033, |
| "learning_rate": 0.0002, |
| "loss": 0.5518944263458252, |
| "mean_token_accuracy": 0.7770064026117325, |
| "num_tokens": 6733942.0, |
| "step": 413 |
| }, |
| { |
| "entropy": 0.5489854216575623, |
| "epoch": 1.545284780578898, |
| "grad_norm": 0.02913379855453968, |
| "learning_rate": 0.0002, |
| "loss": 0.5539657473564148, |
| "mean_token_accuracy": 0.7730102986097336, |
| "num_tokens": 6749978.0, |
| "step": 414 |
| }, |
| { |
| "entropy": 0.5504709929227829, |
| "epoch": 1.5490196078431373, |
| "grad_norm": 0.03497619554400444, |
| "learning_rate": 0.0002, |
| "loss": 0.5534422397613525, |
| "mean_token_accuracy": 0.7738368958234787, |
| "num_tokens": 6766386.0, |
| "step": 415 |
| }, |
| { |
| "entropy": 0.5360163599252701, |
| "epoch": 1.5527544351073763, |
| "grad_norm": 0.03147003799676895, |
| "learning_rate": 0.0002, |
| "loss": 0.5354920625686646, |
| "mean_token_accuracy": 0.7844124883413315, |
| "num_tokens": 6782497.0, |
| "step": 416 |
| }, |
| { |
| "entropy": 0.5680203884840012, |
| "epoch": 1.5564892623716153, |
| "grad_norm": 0.030537011101841927, |
| "learning_rate": 0.0002, |
| "loss": 0.5605371594429016, |
| "mean_token_accuracy": 0.772536501288414, |
| "num_tokens": 6799059.0, |
| "step": 417 |
| }, |
| { |
| "entropy": 0.5505528301000595, |
| "epoch": 1.5602240896358543, |
| "grad_norm": 0.028710143640637398, |
| "learning_rate": 0.0002, |
| "loss": 0.5522081255912781, |
| "mean_token_accuracy": 0.7738733440637589, |
| "num_tokens": 6815363.0, |
| "step": 418 |
| }, |
| { |
| "entropy": 0.5502945929765701, |
| "epoch": 1.5639589169000934, |
| "grad_norm": 0.0320894755423069, |
| "learning_rate": 0.0002, |
| "loss": 0.5519194006919861, |
| "mean_token_accuracy": 0.775145635008812, |
| "num_tokens": 6831823.0, |
| "step": 419 |
| }, |
| { |
| "entropy": 0.5572039783000946, |
| "epoch": 1.5676937441643324, |
| "grad_norm": 0.028658481314778328, |
| "learning_rate": 0.0002, |
| "loss": 0.5568941831588745, |
| "mean_token_accuracy": 0.7728902250528336, |
| "num_tokens": 6848346.0, |
| "step": 420 |
| }, |
| { |
| "entropy": 0.5431763082742691, |
| "epoch": 1.5714285714285714, |
| "grad_norm": 0.027273258194327354, |
| "learning_rate": 0.0002, |
| "loss": 0.5424181818962097, |
| "mean_token_accuracy": 0.7814328521490097, |
| "num_tokens": 6864537.0, |
| "step": 421 |
| }, |
| { |
| "entropy": 0.5466543883085251, |
| "epoch": 1.5751633986928104, |
| "grad_norm": 0.02875494956970215, |
| "learning_rate": 0.0002, |
| "loss": 0.5450119972229004, |
| "mean_token_accuracy": 0.7765506953001022, |
| "num_tokens": 6881053.0, |
| "step": 422 |
| }, |
| { |
| "entropy": 0.5499023944139481, |
| "epoch": 1.5788982259570497, |
| "grad_norm": 0.02958599291741848, |
| "learning_rate": 0.0002, |
| "loss": 0.5486996173858643, |
| "mean_token_accuracy": 0.778396338224411, |
| "num_tokens": 6897409.0, |
| "step": 423 |
| }, |
| { |
| "entropy": 0.5387710481882095, |
| "epoch": 1.5826330532212887, |
| "grad_norm": 0.030644621700048447, |
| "learning_rate": 0.0002, |
| "loss": 0.5404931306838989, |
| "mean_token_accuracy": 0.7786550223827362, |
| "num_tokens": 6913681.0, |
| "step": 424 |
| }, |
| { |
| "entropy": 0.5346106290817261, |
| "epoch": 1.5863678804855277, |
| "grad_norm": 0.028904983773827553, |
| "learning_rate": 0.0002, |
| "loss": 0.5413768887519836, |
| "mean_token_accuracy": 0.7797856479883194, |
| "num_tokens": 6930096.0, |
| "step": 425 |
| }, |
| { |
| "entropy": 0.5166824460029602, |
| "epoch": 1.5901027077497667, |
| "grad_norm": 0.03321892023086548, |
| "learning_rate": 0.0002, |
| "loss": 0.5238149166107178, |
| "mean_token_accuracy": 0.7857634872198105, |
| "num_tokens": 6946449.0, |
| "step": 426 |
| }, |
| { |
| "entropy": 0.5426425486803055, |
| "epoch": 1.5938375350140057, |
| "grad_norm": 0.030873097479343414, |
| "learning_rate": 0.0002, |
| "loss": 0.5491586923599243, |
| "mean_token_accuracy": 0.7750476896762848, |
| "num_tokens": 6962805.0, |
| "step": 427 |
| }, |
| { |
| "entropy": 0.555439367890358, |
| "epoch": 1.5975723622782447, |
| "grad_norm": 0.030430428683757782, |
| "learning_rate": 0.0002, |
| "loss": 0.5504173040390015, |
| "mean_token_accuracy": 0.7780658453702927, |
| "num_tokens": 6979378.0, |
| "step": 428 |
| }, |
| { |
| "entropy": 0.5425661355257034, |
| "epoch": 1.6013071895424837, |
| "grad_norm": 0.033183399587869644, |
| "learning_rate": 0.0002, |
| "loss": 0.5338144302368164, |
| "mean_token_accuracy": 0.7815939337015152, |
| "num_tokens": 6995576.0, |
| "step": 429 |
| }, |
| { |
| "entropy": 0.5580693334341049, |
| "epoch": 1.6050420168067228, |
| "grad_norm": 0.02936139702796936, |
| "learning_rate": 0.0002, |
| "loss": 0.5471250414848328, |
| "mean_token_accuracy": 0.7805830985307693, |
| "num_tokens": 7011887.0, |
| "step": 430 |
| }, |
| { |
| "entropy": 0.5445709973573685, |
| "epoch": 1.6087768440709618, |
| "grad_norm": 0.029686426743865013, |
| "learning_rate": 0.0002, |
| "loss": 0.5449705719947815, |
| "mean_token_accuracy": 0.7791666090488434, |
| "num_tokens": 7028245.0, |
| "step": 431 |
| }, |
| { |
| "entropy": 0.5352734625339508, |
| "epoch": 1.6125116713352008, |
| "grad_norm": 0.0335598923265934, |
| "learning_rate": 0.0002, |
| "loss": 0.5456029772758484, |
| "mean_token_accuracy": 0.7778525203466415, |
| "num_tokens": 7044490.0, |
| "step": 432 |
| }, |
| { |
| "entropy": 0.548936665058136, |
| "epoch": 1.6162464985994398, |
| "grad_norm": 0.03590673953294754, |
| "learning_rate": 0.0002, |
| "loss": 0.5520269870758057, |
| "mean_token_accuracy": 0.7742140144109726, |
| "num_tokens": 7060917.0, |
| "step": 433 |
| }, |
| { |
| "entropy": 0.5434507131576538, |
| "epoch": 1.6199813258636788, |
| "grad_norm": 0.028407955542206764, |
| "learning_rate": 0.0002, |
| "loss": 0.5414606332778931, |
| "mean_token_accuracy": 0.778694823384285, |
| "num_tokens": 7077100.0, |
| "step": 434 |
| }, |
| { |
| "entropy": 0.5490714907646179, |
| "epoch": 1.6237161531279178, |
| "grad_norm": 0.0324469618499279, |
| "learning_rate": 0.0002, |
| "loss": 0.5481012463569641, |
| "mean_token_accuracy": 0.7763958275318146, |
| "num_tokens": 7093665.0, |
| "step": 435 |
| }, |
| { |
| "entropy": 0.5379714071750641, |
| "epoch": 1.6274509803921569, |
| "grad_norm": 0.030424365773797035, |
| "learning_rate": 0.0002, |
| "loss": 0.5396856665611267, |
| "mean_token_accuracy": 0.7815098166465759, |
| "num_tokens": 7110174.0, |
| "step": 436 |
| }, |
| { |
| "entropy": 0.5480812042951584, |
| "epoch": 1.6311858076563959, |
| "grad_norm": 0.029105886816978455, |
| "learning_rate": 0.0002, |
| "loss": 0.5511510372161865, |
| "mean_token_accuracy": 0.7754542678594589, |
| "num_tokens": 7126486.0, |
| "step": 437 |
| }, |
| { |
| "entropy": 0.5540740191936493, |
| "epoch": 1.6349206349206349, |
| "grad_norm": 0.027599727734923363, |
| "learning_rate": 0.0002, |
| "loss": 0.5574399828910828, |
| "mean_token_accuracy": 0.7723194360733032, |
| "num_tokens": 7143064.0, |
| "step": 438 |
| }, |
| { |
| "entropy": 0.5382533967494965, |
| "epoch": 1.638655462184874, |
| "grad_norm": 0.02985025756061077, |
| "learning_rate": 0.0002, |
| "loss": 0.542414665222168, |
| "mean_token_accuracy": 0.7797781080007553, |
| "num_tokens": 7159194.0, |
| "step": 439 |
| }, |
| { |
| "entropy": 0.545093446969986, |
| "epoch": 1.642390289449113, |
| "grad_norm": 0.033221568912267685, |
| "learning_rate": 0.0002, |
| "loss": 0.5397443771362305, |
| "mean_token_accuracy": 0.781465008854866, |
| "num_tokens": 7175448.0, |
| "step": 440 |
| }, |
| { |
| "entropy": 0.547942727804184, |
| "epoch": 1.646125116713352, |
| "grad_norm": 0.030130675062537193, |
| "learning_rate": 0.0002, |
| "loss": 0.5471298098564148, |
| "mean_token_accuracy": 0.7778923958539963, |
| "num_tokens": 7191951.0, |
| "step": 441 |
| }, |
| { |
| "entropy": 0.5388812720775604, |
| "epoch": 1.649859943977591, |
| "grad_norm": 0.03608401492238045, |
| "learning_rate": 0.0002, |
| "loss": 0.5405545234680176, |
| "mean_token_accuracy": 0.7795072197914124, |
| "num_tokens": 7208082.0, |
| "step": 442 |
| }, |
| { |
| "entropy": 0.5480445921421051, |
| "epoch": 1.65359477124183, |
| "grad_norm": 0.03251367062330246, |
| "learning_rate": 0.0002, |
| "loss": 0.5486726760864258, |
| "mean_token_accuracy": 0.7771764397621155, |
| "num_tokens": 7224432.0, |
| "step": 443 |
| }, |
| { |
| "entropy": 0.5502856224775314, |
| "epoch": 1.657329598506069, |
| "grad_norm": 0.03557496517896652, |
| "learning_rate": 0.0002, |
| "loss": 0.5455541014671326, |
| "mean_token_accuracy": 0.7788678556680679, |
| "num_tokens": 7241112.0, |
| "step": 444 |
| }, |
| { |
| "entropy": 0.5650181323289871, |
| "epoch": 1.661064425770308, |
| "grad_norm": 0.036821287125349045, |
| "learning_rate": 0.0002, |
| "loss": 0.5659928321838379, |
| "mean_token_accuracy": 0.7705142349004745, |
| "num_tokens": 7257646.0, |
| "step": 445 |
| }, |
| { |
| "entropy": 0.5301887840032578, |
| "epoch": 1.664799253034547, |
| "grad_norm": 0.028849398717284203, |
| "learning_rate": 0.0002, |
| "loss": 0.5311304926872253, |
| "mean_token_accuracy": 0.7853154540061951, |
| "num_tokens": 7273883.0, |
| "step": 446 |
| }, |
| { |
| "entropy": 0.5287686139345169, |
| "epoch": 1.668534080298786, |
| "grad_norm": 0.027796290814876556, |
| "learning_rate": 0.0002, |
| "loss": 0.5300359129905701, |
| "mean_token_accuracy": 0.7818829715251923, |
| "num_tokens": 7290094.0, |
| "step": 447 |
| }, |
| { |
| "entropy": 0.5384389162063599, |
| "epoch": 1.6722689075630253, |
| "grad_norm": 0.03137550130486488, |
| "learning_rate": 0.0002, |
| "loss": 0.5358840227127075, |
| "mean_token_accuracy": 0.7822984606027603, |
| "num_tokens": 7306318.0, |
| "step": 448 |
| }, |
| { |
| "entropy": 0.5409219712018967, |
| "epoch": 1.6760037348272643, |
| "grad_norm": 0.03238392993807793, |
| "learning_rate": 0.0002, |
| "loss": 0.5490888357162476, |
| "mean_token_accuracy": 0.7757006883621216, |
| "num_tokens": 7322518.0, |
| "step": 449 |
| }, |
| { |
| "entropy": 0.5399473458528519, |
| "epoch": 1.6797385620915033, |
| "grad_norm": 0.03108685463666916, |
| "learning_rate": 0.0002, |
| "loss": 0.5397608876228333, |
| "mean_token_accuracy": 0.7774724215269089, |
| "num_tokens": 7338931.0, |
| "step": 450 |
| }, |
| { |
| "entropy": 0.5551822930574417, |
| "epoch": 1.6834733893557423, |
| "grad_norm": 0.02780800126492977, |
| "learning_rate": 0.0002, |
| "loss": 0.5481570959091187, |
| "mean_token_accuracy": 0.7780963182449341, |
| "num_tokens": 7355336.0, |
| "step": 451 |
| }, |
| { |
| "entropy": 0.54237399995327, |
| "epoch": 1.6872082166199813, |
| "grad_norm": 0.04012434557080269, |
| "learning_rate": 0.0002, |
| "loss": 0.5462750792503357, |
| "mean_token_accuracy": 0.7741427570581436, |
| "num_tokens": 7371655.0, |
| "step": 452 |
| }, |
| { |
| "entropy": 0.5476243197917938, |
| "epoch": 1.6909430438842203, |
| "grad_norm": 0.031238745898008347, |
| "learning_rate": 0.0002, |
| "loss": 0.5490629076957703, |
| "mean_token_accuracy": 0.7778069078922272, |
| "num_tokens": 7387779.0, |
| "step": 453 |
| }, |
| { |
| "entropy": 0.5370198786258698, |
| "epoch": 1.6946778711484594, |
| "grad_norm": 0.0672907754778862, |
| "learning_rate": 0.0002, |
| "loss": 0.5387383699417114, |
| "mean_token_accuracy": 0.7835952490568161, |
| "num_tokens": 7404160.0, |
| "step": 454 |
| }, |
| { |
| "entropy": 0.5476315915584564, |
| "epoch": 1.6984126984126984, |
| "grad_norm": 0.029196592047810555, |
| "learning_rate": 0.0002, |
| "loss": 0.5511754751205444, |
| "mean_token_accuracy": 0.7767634838819504, |
| "num_tokens": 7420779.0, |
| "step": 455 |
| }, |
| { |
| "entropy": 0.5495481044054031, |
| "epoch": 1.7021475256769374, |
| "grad_norm": 0.03591341897845268, |
| "learning_rate": 0.0002, |
| "loss": 0.5475634336471558, |
| "mean_token_accuracy": 0.7761732786893845, |
| "num_tokens": 7437268.0, |
| "step": 456 |
| }, |
| { |
| "entropy": 0.5471929609775543, |
| "epoch": 1.7058823529411766, |
| "grad_norm": 0.07272505015134811, |
| "learning_rate": 0.0002, |
| "loss": 0.5460875630378723, |
| "mean_token_accuracy": 0.7771887481212616, |
| "num_tokens": 7453407.0, |
| "step": 457 |
| }, |
| { |
| "entropy": 0.5470087379217148, |
| "epoch": 1.7096171802054156, |
| "grad_norm": 0.027592960745096207, |
| "learning_rate": 0.0002, |
| "loss": 0.544583797454834, |
| "mean_token_accuracy": 0.7774143517017365, |
| "num_tokens": 7469641.0, |
| "step": 458 |
| }, |
| { |
| "entropy": 0.5607744753360748, |
| "epoch": 1.7133520074696547, |
| "grad_norm": 0.031071651726961136, |
| "learning_rate": 0.0002, |
| "loss": 0.5542961955070496, |
| "mean_token_accuracy": 0.7748319655656815, |
| "num_tokens": 7486190.0, |
| "step": 459 |
| }, |
| { |
| "entropy": 0.5514983385801315, |
| "epoch": 1.7170868347338937, |
| "grad_norm": 0.03477690741419792, |
| "learning_rate": 0.0002, |
| "loss": 0.5511950254440308, |
| "mean_token_accuracy": 0.7754039019346237, |
| "num_tokens": 7502685.0, |
| "step": 460 |
| }, |
| { |
| "entropy": 0.5462844371795654, |
| "epoch": 1.7208216619981327, |
| "grad_norm": 0.02956387773156166, |
| "learning_rate": 0.0002, |
| "loss": 0.5578323602676392, |
| "mean_token_accuracy": 0.7759933173656464, |
| "num_tokens": 7518976.0, |
| "step": 461 |
| }, |
| { |
| "entropy": 0.5413178950548172, |
| "epoch": 1.7245564892623717, |
| "grad_norm": 0.03515993058681488, |
| "learning_rate": 0.0002, |
| "loss": 0.5494832992553711, |
| "mean_token_accuracy": 0.7766997069120407, |
| "num_tokens": 7535230.0, |
| "step": 462 |
| }, |
| { |
| "entropy": 0.5519613027572632, |
| "epoch": 1.7282913165266107, |
| "grad_norm": 0.03921071067452431, |
| "learning_rate": 0.0002, |
| "loss": 0.5593541860580444, |
| "mean_token_accuracy": 0.7729771286249161, |
| "num_tokens": 7551766.0, |
| "step": 463 |
| }, |
| { |
| "entropy": 0.5483202934265137, |
| "epoch": 1.7320261437908497, |
| "grad_norm": 0.02950095944106579, |
| "learning_rate": 0.0002, |
| "loss": 0.5464847683906555, |
| "mean_token_accuracy": 0.7769839763641357, |
| "num_tokens": 7568028.0, |
| "step": 464 |
| }, |
| { |
| "entropy": 0.5524065643548965, |
| "epoch": 1.7357609710550888, |
| "grad_norm": 0.038918618112802505, |
| "learning_rate": 0.0002, |
| "loss": 0.5422624945640564, |
| "mean_token_accuracy": 0.7797468602657318, |
| "num_tokens": 7584397.0, |
| "step": 465 |
| }, |
| { |
| "entropy": 0.546732097864151, |
| "epoch": 1.7394957983193278, |
| "grad_norm": 0.03082694672048092, |
| "learning_rate": 0.0002, |
| "loss": 0.5352342128753662, |
| "mean_token_accuracy": 0.78376704454422, |
| "num_tokens": 7600719.0, |
| "step": 466 |
| }, |
| { |
| "entropy": 0.557578444480896, |
| "epoch": 1.7432306255835668, |
| "grad_norm": 0.031017586588859558, |
| "learning_rate": 0.0002, |
| "loss": 0.54631108045578, |
| "mean_token_accuracy": 0.7787049263715744, |
| "num_tokens": 7617277.0, |
| "step": 467 |
| }, |
| { |
| "entropy": 0.5322857201099396, |
| "epoch": 1.7469654528478058, |
| "grad_norm": 0.0356813408434391, |
| "learning_rate": 0.0002, |
| "loss": 0.5350920557975769, |
| "mean_token_accuracy": 0.7820670753717422, |
| "num_tokens": 7633468.0, |
| "step": 468 |
| }, |
| { |
| "entropy": 0.5373670607805252, |
| "epoch": 1.7507002801120448, |
| "grad_norm": 0.0339689627289772, |
| "learning_rate": 0.0002, |
| "loss": 0.5516907572746277, |
| "mean_token_accuracy": 0.7766174525022507, |
| "num_tokens": 7649778.0, |
| "step": 469 |
| }, |
| { |
| "entropy": 0.522003561258316, |
| "epoch": 1.7544351073762838, |
| "grad_norm": 0.034353625029325485, |
| "learning_rate": 0.0002, |
| "loss": 0.533075749874115, |
| "mean_token_accuracy": 0.7833420485258102, |
| "num_tokens": 7666182.0, |
| "step": 470 |
| }, |
| { |
| "entropy": 0.5592000931501389, |
| "epoch": 1.7581699346405228, |
| "grad_norm": 0.029966510832309723, |
| "learning_rate": 0.0002, |
| "loss": 0.5585059523582458, |
| "mean_token_accuracy": 0.7732168585062027, |
| "num_tokens": 7682572.0, |
| "step": 471 |
| }, |
| { |
| "entropy": 0.5302631109952927, |
| "epoch": 1.7619047619047619, |
| "grad_norm": 0.030881982296705246, |
| "learning_rate": 0.0002, |
| "loss": 0.5330703854560852, |
| "mean_token_accuracy": 0.7825835943222046, |
| "num_tokens": 7698564.0, |
| "step": 472 |
| }, |
| { |
| "entropy": 0.5615632385015488, |
| "epoch": 1.7656395891690009, |
| "grad_norm": 0.03000018559396267, |
| "learning_rate": 0.0002, |
| "loss": 0.5536789298057556, |
| "mean_token_accuracy": 0.7739888280630112, |
| "num_tokens": 7714922.0, |
| "step": 473 |
| }, |
| { |
| "entropy": 0.5522587448358536, |
| "epoch": 1.76937441643324, |
| "grad_norm": 0.031349826604127884, |
| "learning_rate": 0.0002, |
| "loss": 0.551250696182251, |
| "mean_token_accuracy": 0.7755384594202042, |
| "num_tokens": 7731301.0, |
| "step": 474 |
| }, |
| { |
| "entropy": 0.5275092422962189, |
| "epoch": 1.773109243697479, |
| "grad_norm": 0.026553746312856674, |
| "learning_rate": 0.0002, |
| "loss": 0.5240329504013062, |
| "mean_token_accuracy": 0.7870848327875137, |
| "num_tokens": 7747693.0, |
| "step": 475 |
| }, |
| { |
| "entropy": 0.5298073589801788, |
| "epoch": 1.776844070961718, |
| "grad_norm": 0.03024754300713539, |
| "learning_rate": 0.0002, |
| "loss": 0.5267937183380127, |
| "mean_token_accuracy": 0.7867465615272522, |
| "num_tokens": 7763990.0, |
| "step": 476 |
| }, |
| { |
| "entropy": 0.5466170459985733, |
| "epoch": 1.780578898225957, |
| "grad_norm": 0.03677600622177124, |
| "learning_rate": 0.0002, |
| "loss": 0.5455999374389648, |
| "mean_token_accuracy": 0.7789721339941025, |
| "num_tokens": 7780428.0, |
| "step": 477 |
| }, |
| { |
| "entropy": 0.5342886596918106, |
| "epoch": 1.784313725490196, |
| "grad_norm": 0.03470218554139137, |
| "learning_rate": 0.0002, |
| "loss": 0.5434668660163879, |
| "mean_token_accuracy": 0.7787842005491257, |
| "num_tokens": 7796524.0, |
| "step": 478 |
| }, |
| { |
| "entropy": 0.5427644997835159, |
| "epoch": 1.788048552754435, |
| "grad_norm": 0.026957696303725243, |
| "learning_rate": 0.0002, |
| "loss": 0.5418925285339355, |
| "mean_token_accuracy": 0.7785145193338394, |
| "num_tokens": 7813105.0, |
| "step": 479 |
| }, |
| { |
| "entropy": 0.528566911816597, |
| "epoch": 1.791783380018674, |
| "grad_norm": 0.037975575774908066, |
| "learning_rate": 0.0002, |
| "loss": 0.5284658074378967, |
| "mean_token_accuracy": 0.7871547490358353, |
| "num_tokens": 7829398.0, |
| "step": 480 |
| }, |
| { |
| "entropy": 0.5551463812589645, |
| "epoch": 1.795518207282913, |
| "grad_norm": 0.028514336794614792, |
| "learning_rate": 0.0002, |
| "loss": 0.556096076965332, |
| "mean_token_accuracy": 0.7756756544113159, |
| "num_tokens": 7845626.0, |
| "step": 481 |
| }, |
| { |
| "entropy": 0.5317743271589279, |
| "epoch": 1.7992530345471522, |
| "grad_norm": 0.03154602646827698, |
| "learning_rate": 0.0002, |
| "loss": 0.5321435332298279, |
| "mean_token_accuracy": 0.7815971374511719, |
| "num_tokens": 7861817.0, |
| "step": 482 |
| }, |
| { |
| "entropy": 0.547456681728363, |
| "epoch": 1.8029878618113913, |
| "grad_norm": 0.03746788948774338, |
| "learning_rate": 0.0002, |
| "loss": 0.5512088537216187, |
| "mean_token_accuracy": 0.7785567492246628, |
| "num_tokens": 7878075.0, |
| "step": 483 |
| }, |
| { |
| "entropy": 0.5500114560127258, |
| "epoch": 1.8067226890756303, |
| "grad_norm": 0.030493978410959244, |
| "learning_rate": 0.0002, |
| "loss": 0.5513818264007568, |
| "mean_token_accuracy": 0.773513063788414, |
| "num_tokens": 7894502.0, |
| "step": 484 |
| }, |
| { |
| "entropy": 0.543748289346695, |
| "epoch": 1.8104575163398693, |
| "grad_norm": 0.036304932087659836, |
| "learning_rate": 0.0002, |
| "loss": 0.5411792993545532, |
| "mean_token_accuracy": 0.7785163670778275, |
| "num_tokens": 7910890.0, |
| "step": 485 |
| }, |
| { |
| "entropy": 0.5393827706575394, |
| "epoch": 1.8141923436041083, |
| "grad_norm": 0.03712041303515434, |
| "learning_rate": 0.0002, |
| "loss": 0.540428876876831, |
| "mean_token_accuracy": 0.7790835350751877, |
| "num_tokens": 7927094.0, |
| "step": 486 |
| }, |
| { |
| "entropy": 0.5430537164211273, |
| "epoch": 1.8179271708683473, |
| "grad_norm": 0.03853759169578552, |
| "learning_rate": 0.0002, |
| "loss": 0.5471268892288208, |
| "mean_token_accuracy": 0.7801193594932556, |
| "num_tokens": 7943326.0, |
| "step": 487 |
| }, |
| { |
| "entropy": 0.5636092722415924, |
| "epoch": 1.8216619981325863, |
| "grad_norm": 0.0457291305065155, |
| "learning_rate": 0.0002, |
| "loss": 0.5627254843711853, |
| "mean_token_accuracy": 0.7725824415683746, |
| "num_tokens": 7959760.0, |
| "step": 488 |
| }, |
| { |
| "entropy": 0.543666809797287, |
| "epoch": 1.8253968253968254, |
| "grad_norm": 0.02919071726500988, |
| "learning_rate": 0.0002, |
| "loss": 0.5421757102012634, |
| "mean_token_accuracy": 0.7801477611064911, |
| "num_tokens": 7975860.0, |
| "step": 489 |
| }, |
| { |
| "entropy": 0.5545783638954163, |
| "epoch": 1.8291316526610646, |
| "grad_norm": 0.03340514004230499, |
| "learning_rate": 0.0002, |
| "loss": 0.5518795251846313, |
| "mean_token_accuracy": 0.7791309058666229, |
| "num_tokens": 7992340.0, |
| "step": 490 |
| }, |
| { |
| "entropy": 0.5608565956354141, |
| "epoch": 1.8328664799253036, |
| "grad_norm": 0.03725928068161011, |
| "learning_rate": 0.0002, |
| "loss": 0.5564695596694946, |
| "mean_token_accuracy": 0.7749106585979462, |
| "num_tokens": 8008783.0, |
| "step": 491 |
| }, |
| { |
| "entropy": 0.5600428581237793, |
| "epoch": 1.8366013071895426, |
| "grad_norm": 0.030761808156967163, |
| "learning_rate": 0.0002, |
| "loss": 0.5595075488090515, |
| "mean_token_accuracy": 0.7733119577169418, |
| "num_tokens": 8025204.0, |
| "step": 492 |
| }, |
| { |
| "entropy": 0.5233868211507797, |
| "epoch": 1.8403361344537816, |
| "grad_norm": 0.030873069539666176, |
| "learning_rate": 0.0002, |
| "loss": 0.5303994417190552, |
| "mean_token_accuracy": 0.784132570028305, |
| "num_tokens": 8041524.0, |
| "step": 493 |
| }, |
| { |
| "entropy": 0.5531543642282486, |
| "epoch": 1.8440709617180207, |
| "grad_norm": 0.037785280495882034, |
| "learning_rate": 0.0002, |
| "loss": 0.5541731119155884, |
| "mean_token_accuracy": 0.7754590958356857, |
| "num_tokens": 8057944.0, |
| "step": 494 |
| }, |
| { |
| "entropy": 0.542868971824646, |
| "epoch": 1.8478057889822597, |
| "grad_norm": 0.03054802305996418, |
| "learning_rate": 0.0002, |
| "loss": 0.5407766699790955, |
| "mean_token_accuracy": 0.7781128138303757, |
| "num_tokens": 8074585.0, |
| "step": 495 |
| }, |
| { |
| "entropy": 0.5384076237678528, |
| "epoch": 1.8515406162464987, |
| "grad_norm": 0.024639198556542397, |
| "learning_rate": 0.0002, |
| "loss": 0.5381752848625183, |
| "mean_token_accuracy": 0.7817619889974594, |
| "num_tokens": 8091097.0, |
| "step": 496 |
| }, |
| { |
| "entropy": 0.5398432165384293, |
| "epoch": 1.8552754435107377, |
| "grad_norm": 0.04202251881361008, |
| "learning_rate": 0.0002, |
| "loss": 0.5468040704727173, |
| "mean_token_accuracy": 0.7771125733852386, |
| "num_tokens": 8107370.0, |
| "step": 497 |
| }, |
| { |
| "entropy": 0.5353098064661026, |
| "epoch": 1.8590102707749767, |
| "grad_norm": 0.03730052337050438, |
| "learning_rate": 0.0002, |
| "loss": 0.5450741052627563, |
| "mean_token_accuracy": 0.7791319042444229, |
| "num_tokens": 8123388.0, |
| "step": 498 |
| }, |
| { |
| "entropy": 0.537789598107338, |
| "epoch": 1.8627450980392157, |
| "grad_norm": 0.02861681580543518, |
| "learning_rate": 0.0002, |
| "loss": 0.5363599061965942, |
| "mean_token_accuracy": 0.7793796509504318, |
| "num_tokens": 8139491.0, |
| "step": 499 |
| }, |
| { |
| "entropy": 0.5609306395053864, |
| "epoch": 1.8664799253034547, |
| "grad_norm": 0.04193006083369255, |
| "learning_rate": 0.0002, |
| "loss": 0.5556061267852783, |
| "mean_token_accuracy": 0.7729236781597137, |
| "num_tokens": 8155893.0, |
| "step": 500 |
| }, |
| { |
| "entropy": 0.5393400639295578, |
| "epoch": 1.8702147525676938, |
| "grad_norm": 0.030415907502174377, |
| "learning_rate": 0.0002, |
| "loss": 0.5372475385665894, |
| "mean_token_accuracy": 0.7827758193016052, |
| "num_tokens": 8172021.0, |
| "step": 501 |
| }, |
| { |
| "entropy": 0.5631109476089478, |
| "epoch": 1.8739495798319328, |
| "grad_norm": 0.030597561970353127, |
| "learning_rate": 0.0002, |
| "loss": 0.56128990650177, |
| "mean_token_accuracy": 0.7722143828868866, |
| "num_tokens": 8188761.0, |
| "step": 502 |
| }, |
| { |
| "entropy": 0.540698915719986, |
| "epoch": 1.8776844070961718, |
| "grad_norm": 0.03197801113128662, |
| "learning_rate": 0.0002, |
| "loss": 0.5419467687606812, |
| "mean_token_accuracy": 0.7789603024721146, |
| "num_tokens": 8205080.0, |
| "step": 503 |
| }, |
| { |
| "entropy": 0.5343400835990906, |
| "epoch": 1.8814192343604108, |
| "grad_norm": 0.03577344864606857, |
| "learning_rate": 0.0002, |
| "loss": 0.5340043306350708, |
| "mean_token_accuracy": 0.7837951481342316, |
| "num_tokens": 8221164.0, |
| "step": 504 |
| }, |
| { |
| "entropy": 0.5417536497116089, |
| "epoch": 1.8851540616246498, |
| "grad_norm": 0.029083728790283203, |
| "learning_rate": 0.0002, |
| "loss": 0.5438728332519531, |
| "mean_token_accuracy": 0.7775007486343384, |
| "num_tokens": 8237535.0, |
| "step": 505 |
| }, |
| { |
| "entropy": 0.5649835765361786, |
| "epoch": 1.8888888888888888, |
| "grad_norm": 0.03408566117286682, |
| "learning_rate": 0.0002, |
| "loss": 0.5633872151374817, |
| "mean_token_accuracy": 0.7726111114025116, |
| "num_tokens": 8253827.0, |
| "step": 506 |
| }, |
| { |
| "entropy": 0.5582909733057022, |
| "epoch": 1.8926237161531279, |
| "grad_norm": 0.028437087312340736, |
| "learning_rate": 0.0002, |
| "loss": 0.556007981300354, |
| "mean_token_accuracy": 0.7727185785770416, |
| "num_tokens": 8270404.0, |
| "step": 507 |
| }, |
| { |
| "entropy": 0.5577380061149597, |
| "epoch": 1.8963585434173669, |
| "grad_norm": 0.029986968263983727, |
| "learning_rate": 0.0002, |
| "loss": 0.5514963865280151, |
| "mean_token_accuracy": 0.7755957692861557, |
| "num_tokens": 8286963.0, |
| "step": 508 |
| }, |
| { |
| "entropy": 0.5398396402597427, |
| "epoch": 1.9000933706816059, |
| "grad_norm": 0.030943697318434715, |
| "learning_rate": 0.0002, |
| "loss": 0.5466131567955017, |
| "mean_token_accuracy": 0.7787002176046371, |
| "num_tokens": 8303122.0, |
| "step": 509 |
| }, |
| { |
| "entropy": 0.536215141415596, |
| "epoch": 1.903828197945845, |
| "grad_norm": 0.03370903804898262, |
| "learning_rate": 0.0002, |
| "loss": 0.5468170046806335, |
| "mean_token_accuracy": 0.7753093987703323, |
| "num_tokens": 8319505.0, |
| "step": 510 |
| }, |
| { |
| "entropy": 0.5411160290241241, |
| "epoch": 1.907563025210084, |
| "grad_norm": 0.028430534526705742, |
| "learning_rate": 0.0002, |
| "loss": 0.5434973835945129, |
| "mean_token_accuracy": 0.7790606617927551, |
| "num_tokens": 8335861.0, |
| "step": 511 |
| }, |
| { |
| "entropy": 0.5555713921785355, |
| "epoch": 1.911297852474323, |
| "grad_norm": 0.029101036489009857, |
| "learning_rate": 0.0002, |
| "loss": 0.5541608929634094, |
| "mean_token_accuracy": 0.7740498781204224, |
| "num_tokens": 8352413.0, |
| "step": 512 |
| }, |
| { |
| "entropy": 0.5440339744091034, |
| "epoch": 1.915032679738562, |
| "grad_norm": 0.029705537483096123, |
| "learning_rate": 0.0002, |
| "loss": 0.5449399352073669, |
| "mean_token_accuracy": 0.7799241691827774, |
| "num_tokens": 8368524.0, |
| "step": 513 |
| }, |
| { |
| "entropy": 0.5385466068983078, |
| "epoch": 1.918767507002801, |
| "grad_norm": 0.02762160450220108, |
| "learning_rate": 0.0002, |
| "loss": 0.5408512353897095, |
| "mean_token_accuracy": 0.7800593823194504, |
| "num_tokens": 8384881.0, |
| "step": 514 |
| }, |
| { |
| "entropy": 0.5469230860471725, |
| "epoch": 1.9225023342670402, |
| "grad_norm": 0.02923613414168358, |
| "learning_rate": 0.0002, |
| "loss": 0.5409518480300903, |
| "mean_token_accuracy": 0.7801833301782608, |
| "num_tokens": 8401135.0, |
| "step": 515 |
| }, |
| { |
| "entropy": 0.5446400791406631, |
| "epoch": 1.9262371615312792, |
| "grad_norm": 0.031235719099640846, |
| "learning_rate": 0.0002, |
| "loss": 0.5424818992614746, |
| "mean_token_accuracy": 0.7767819166183472, |
| "num_tokens": 8417485.0, |
| "step": 516 |
| }, |
| { |
| "entropy": 0.5608149170875549, |
| "epoch": 1.9299719887955182, |
| "grad_norm": 0.027529114857316017, |
| "learning_rate": 0.0002, |
| "loss": 0.5587472915649414, |
| "mean_token_accuracy": 0.7713829576969147, |
| "num_tokens": 8433808.0, |
| "step": 517 |
| }, |
| { |
| "entropy": 0.560915470123291, |
| "epoch": 1.9337068160597572, |
| "grad_norm": 0.03099709376692772, |
| "learning_rate": 0.0002, |
| "loss": 0.5625618100166321, |
| "mean_token_accuracy": 0.7697023302316666, |
| "num_tokens": 8450212.0, |
| "step": 518 |
| }, |
| { |
| "entropy": 0.5411669313907623, |
| "epoch": 1.9374416433239963, |
| "grad_norm": 0.03581510856747627, |
| "learning_rate": 0.0002, |
| "loss": 0.5449709892272949, |
| "mean_token_accuracy": 0.779253363609314, |
| "num_tokens": 8466650.0, |
| "step": 519 |
| }, |
| { |
| "entropy": 0.5495533496141434, |
| "epoch": 1.9411764705882353, |
| "grad_norm": 0.02863345853984356, |
| "learning_rate": 0.0002, |
| "loss": 0.5461183786392212, |
| "mean_token_accuracy": 0.7790695428848267, |
| "num_tokens": 8482819.0, |
| "step": 520 |
| }, |
| { |
| "entropy": 0.5496646910905838, |
| "epoch": 1.9449112978524743, |
| "grad_norm": 0.028455862775444984, |
| "learning_rate": 0.0002, |
| "loss": 0.5562914609909058, |
| "mean_token_accuracy": 0.7747850865125656, |
| "num_tokens": 8499201.0, |
| "step": 521 |
| }, |
| { |
| "entropy": 0.5566077679395676, |
| "epoch": 1.9486461251167133, |
| "grad_norm": 0.030010810121893883, |
| "learning_rate": 0.0002, |
| "loss": 0.551722526550293, |
| "mean_token_accuracy": 0.7771954238414764, |
| "num_tokens": 8515798.0, |
| "step": 522 |
| }, |
| { |
| "entropy": 0.5467117130756378, |
| "epoch": 1.9523809523809523, |
| "grad_norm": 0.027012262493371964, |
| "learning_rate": 0.0002, |
| "loss": 0.5425857305526733, |
| "mean_token_accuracy": 0.7798562794923782, |
| "num_tokens": 8531958.0, |
| "step": 523 |
| }, |
| { |
| "entropy": 0.5346378833055496, |
| "epoch": 1.9561157796451916, |
| "grad_norm": 0.028377590700984, |
| "learning_rate": 0.0002, |
| "loss": 0.5295640230178833, |
| "mean_token_accuracy": 0.7838203459978104, |
| "num_tokens": 8548384.0, |
| "step": 524 |
| }, |
| { |
| "entropy": 0.5571393668651581, |
| "epoch": 1.9598506069094306, |
| "grad_norm": 0.02818567305803299, |
| "learning_rate": 0.0002, |
| "loss": 0.5521214008331299, |
| "mean_token_accuracy": 0.7728232592344284, |
| "num_tokens": 8564872.0, |
| "step": 525 |
| }, |
| { |
| "entropy": 0.5285107642412186, |
| "epoch": 1.9635854341736696, |
| "grad_norm": 0.03457087650895119, |
| "learning_rate": 0.0002, |
| "loss": 0.5370362401008606, |
| "mean_token_accuracy": 0.7813837081193924, |
| "num_tokens": 8581245.0, |
| "step": 526 |
| }, |
| { |
| "entropy": 0.5266488045454025, |
| "epoch": 1.9673202614379086, |
| "grad_norm": 0.030525686219334602, |
| "learning_rate": 0.0002, |
| "loss": 0.5345274806022644, |
| "mean_token_accuracy": 0.7815807163715363, |
| "num_tokens": 8597625.0, |
| "step": 527 |
| }, |
| { |
| "entropy": 0.5280887708067894, |
| "epoch": 1.9710550887021476, |
| "grad_norm": 0.03248651325702667, |
| "learning_rate": 0.0002, |
| "loss": 0.536238431930542, |
| "mean_token_accuracy": 0.781073585152626, |
| "num_tokens": 8613792.0, |
| "step": 528 |
| }, |
| { |
| "entropy": 0.5472559034824371, |
| "epoch": 1.9747899159663866, |
| "grad_norm": 0.029427766799926758, |
| "learning_rate": 0.0002, |
| "loss": 0.5451797842979431, |
| "mean_token_accuracy": 0.7770361602306366, |
| "num_tokens": 8629870.0, |
| "step": 529 |
| }, |
| { |
| "entropy": 0.5381799042224884, |
| "epoch": 1.9785247432306257, |
| "grad_norm": 0.028413154184818268, |
| "learning_rate": 0.0002, |
| "loss": 0.5342366695404053, |
| "mean_token_accuracy": 0.7803498655557632, |
| "num_tokens": 8646077.0, |
| "step": 530 |
| }, |
| { |
| "entropy": 0.5565104633569717, |
| "epoch": 1.9822595704948647, |
| "grad_norm": 0.031074564903974533, |
| "learning_rate": 0.0002, |
| "loss": 0.5515958666801453, |
| "mean_token_accuracy": 0.7759076505899429, |
| "num_tokens": 8662535.0, |
| "step": 531 |
| }, |
| { |
| "entropy": 0.5381414890289307, |
| "epoch": 1.9859943977591037, |
| "grad_norm": 0.027250438928604126, |
| "learning_rate": 0.0002, |
| "loss": 0.534949004650116, |
| "mean_token_accuracy": 0.7819445878267288, |
| "num_tokens": 8679064.0, |
| "step": 532 |
| }, |
| { |
| "entropy": 0.550770565867424, |
| "epoch": 1.9897292250233427, |
| "grad_norm": 0.03366328775882721, |
| "learning_rate": 0.0002, |
| "loss": 0.560295045375824, |
| "mean_token_accuracy": 0.7720893323421478, |
| "num_tokens": 8695198.0, |
| "step": 533 |
| }, |
| { |
| "entropy": 0.5551019459962845, |
| "epoch": 1.9934640522875817, |
| "grad_norm": 0.03133872151374817, |
| "learning_rate": 0.0002, |
| "loss": 0.5596403479576111, |
| "mean_token_accuracy": 0.7717682421207428, |
| "num_tokens": 8711690.0, |
| "step": 534 |
| }, |
| { |
| "entropy": 0.5346082448959351, |
| "epoch": 1.9971988795518207, |
| "grad_norm": 0.027525832876563072, |
| "learning_rate": 0.0002, |
| "loss": 0.5321208834648132, |
| "mean_token_accuracy": 0.7810429036617279, |
| "num_tokens": 8727828.0, |
| "step": 535 |
| }, |
| { |
| "entropy": 0.5438209176063538, |
| "epoch": 2.0, |
| "grad_norm": 0.03134825825691223, |
| "learning_rate": 0.0002, |
| "loss": 0.5398504734039307, |
| "mean_token_accuracy": 0.7799929777781168, |
| "num_tokens": 8729600.0, |
| "step": 536 |
| }, |
| { |
| "entropy": 0.5402208417654037, |
| "epoch": 2.003734827264239, |
| "grad_norm": 0.03922782838344574, |
| "learning_rate": 0.0002, |
| "loss": 0.5171674489974976, |
| "mean_token_accuracy": 0.7900938540697098, |
| "num_tokens": 8745809.0, |
| "step": 537 |
| }, |
| { |
| "entropy": 0.5227422267198563, |
| "epoch": 2.007469654528478, |
| "grad_norm": 0.032982293516397476, |
| "learning_rate": 0.0002, |
| "loss": 0.5183929204940796, |
| "mean_token_accuracy": 0.7890477329492569, |
| "num_tokens": 8762197.0, |
| "step": 538 |
| }, |
| { |
| "entropy": 0.5411823242902756, |
| "epoch": 2.011204481792717, |
| "grad_norm": 0.043377745896577835, |
| "learning_rate": 0.0002, |
| "loss": 0.5554962158203125, |
| "mean_token_accuracy": 0.7736512869596481, |
| "num_tokens": 8778400.0, |
| "step": 539 |
| }, |
| { |
| "entropy": 0.5156290903687477, |
| "epoch": 2.014939309056956, |
| "grad_norm": 0.05257771536707878, |
| "learning_rate": 0.0002, |
| "loss": 0.5335375666618347, |
| "mean_token_accuracy": 0.7833946198225021, |
| "num_tokens": 8794851.0, |
| "step": 540 |
| }, |
| { |
| "entropy": 0.5122585743665695, |
| "epoch": 2.018674136321195, |
| "grad_norm": 0.03504469618201256, |
| "learning_rate": 0.0002, |
| "loss": 0.5155843496322632, |
| "mean_token_accuracy": 0.7894317060709, |
| "num_tokens": 8811019.0, |
| "step": 541 |
| }, |
| { |
| "entropy": 0.5448772013187408, |
| "epoch": 2.022408963585434, |
| "grad_norm": 0.0317138209939003, |
| "learning_rate": 0.0002, |
| "loss": 0.5368859171867371, |
| "mean_token_accuracy": 0.7842776328325272, |
| "num_tokens": 8827258.0, |
| "step": 542 |
| }, |
| { |
| "entropy": 0.5527419149875641, |
| "epoch": 2.026143790849673, |
| "grad_norm": 0.03476279601454735, |
| "learning_rate": 0.0002, |
| "loss": 0.5388182997703552, |
| "mean_token_accuracy": 0.7820452451705933, |
| "num_tokens": 8843634.0, |
| "step": 543 |
| }, |
| { |
| "entropy": 0.5452789962291718, |
| "epoch": 2.029878618113912, |
| "grad_norm": 0.036034028977155685, |
| "learning_rate": 0.0002, |
| "loss": 0.5357140302658081, |
| "mean_token_accuracy": 0.7825983464717865, |
| "num_tokens": 8859977.0, |
| "step": 544 |
| }, |
| { |
| "entropy": 0.5304267108440399, |
| "epoch": 2.033613445378151, |
| "grad_norm": 0.02969290129840374, |
| "learning_rate": 0.0002, |
| "loss": 0.5306066870689392, |
| "mean_token_accuracy": 0.7856841534376144, |
| "num_tokens": 8876314.0, |
| "step": 545 |
| }, |
| { |
| "entropy": 0.5096816495060921, |
| "epoch": 2.03734827264239, |
| "grad_norm": 0.043957311660051346, |
| "learning_rate": 0.0002, |
| "loss": 0.5185045599937439, |
| "mean_token_accuracy": 0.7923233062028885, |
| "num_tokens": 8892568.0, |
| "step": 546 |
| }, |
| { |
| "entropy": 0.5319265872240067, |
| "epoch": 2.041083099906629, |
| "grad_norm": 0.035869866609573364, |
| "learning_rate": 0.0002, |
| "loss": 0.5334051847457886, |
| "mean_token_accuracy": 0.7822142988443375, |
| "num_tokens": 8909094.0, |
| "step": 547 |
| }, |
| { |
| "entropy": 0.527954563498497, |
| "epoch": 2.044817927170868, |
| "grad_norm": 0.034570369869470596, |
| "learning_rate": 0.0002, |
| "loss": 0.5274232029914856, |
| "mean_token_accuracy": 0.7842770516872406, |
| "num_tokens": 8925492.0, |
| "step": 548 |
| }, |
| { |
| "entropy": 0.5419287383556366, |
| "epoch": 2.048552754435107, |
| "grad_norm": 0.03259408101439476, |
| "learning_rate": 0.0002, |
| "loss": 0.5387848615646362, |
| "mean_token_accuracy": 0.7804249227046967, |
| "num_tokens": 8941717.0, |
| "step": 549 |
| }, |
| { |
| "entropy": 0.5271529629826546, |
| "epoch": 2.052287581699346, |
| "grad_norm": 0.03245944157242775, |
| "learning_rate": 0.0002, |
| "loss": 0.5230631828308105, |
| "mean_token_accuracy": 0.785658523440361, |
| "num_tokens": 8957856.0, |
| "step": 550 |
| }, |
| { |
| "entropy": 0.5363311916589737, |
| "epoch": 2.0560224089635852, |
| "grad_norm": 0.035185229033231735, |
| "learning_rate": 0.0002, |
| "loss": 0.5378749370574951, |
| "mean_token_accuracy": 0.781972661614418, |
| "num_tokens": 8974161.0, |
| "step": 551 |
| }, |
| { |
| "entropy": 0.513224758207798, |
| "epoch": 2.0597572362278243, |
| "grad_norm": 0.032956283539533615, |
| "learning_rate": 0.0002, |
| "loss": 0.5172683000564575, |
| "mean_token_accuracy": 0.7906839847564697, |
| "num_tokens": 8990304.0, |
| "step": 552 |
| }, |
| { |
| "entropy": 0.5387901067733765, |
| "epoch": 2.0634920634920633, |
| "grad_norm": 0.03281653672456741, |
| "learning_rate": 0.0002, |
| "loss": 0.5435392260551453, |
| "mean_token_accuracy": 0.7788385599851608, |
| "num_tokens": 9006661.0, |
| "step": 553 |
| }, |
| { |
| "entropy": 0.5324967205524445, |
| "epoch": 2.0672268907563027, |
| "grad_norm": 0.03808191418647766, |
| "learning_rate": 0.0002, |
| "loss": 0.5265247225761414, |
| "mean_token_accuracy": 0.7839124202728271, |
| "num_tokens": 9022887.0, |
| "step": 554 |
| }, |
| { |
| "entropy": 0.513438269495964, |
| "epoch": 2.0709617180205417, |
| "grad_norm": 0.033963609486818314, |
| "learning_rate": 0.0002, |
| "loss": 0.5105268955230713, |
| "mean_token_accuracy": 0.7911703735589981, |
| "num_tokens": 9039478.0, |
| "step": 555 |
| }, |
| { |
| "entropy": 0.526850014925003, |
| "epoch": 2.0746965452847808, |
| "grad_norm": 0.03211839497089386, |
| "learning_rate": 0.0002, |
| "loss": 0.5205508470535278, |
| "mean_token_accuracy": 0.7859012186527252, |
| "num_tokens": 9055612.0, |
| "step": 556 |
| }, |
| { |
| "entropy": 0.5130272284150124, |
| "epoch": 2.0784313725490198, |
| "grad_norm": 0.03543682396411896, |
| "learning_rate": 0.0002, |
| "loss": 0.5140283703804016, |
| "mean_token_accuracy": 0.7925766706466675, |
| "num_tokens": 9072145.0, |
| "step": 557 |
| }, |
| { |
| "entropy": 0.540324792265892, |
| "epoch": 2.082166199813259, |
| "grad_norm": 0.037342023104429245, |
| "learning_rate": 0.0002, |
| "loss": 0.5462511777877808, |
| "mean_token_accuracy": 0.7783039510250092, |
| "num_tokens": 9088571.0, |
| "step": 558 |
| }, |
| { |
| "entropy": 0.5168541818857193, |
| "epoch": 2.085901027077498, |
| "grad_norm": 0.03552469611167908, |
| "learning_rate": 0.0002, |
| "loss": 0.5188402533531189, |
| "mean_token_accuracy": 0.7880326211452484, |
| "num_tokens": 9104869.0, |
| "step": 559 |
| }, |
| { |
| "entropy": 0.5319818705320358, |
| "epoch": 2.089635854341737, |
| "grad_norm": 0.03719151020050049, |
| "learning_rate": 0.0002, |
| "loss": 0.5254620313644409, |
| "mean_token_accuracy": 0.7848033308982849, |
| "num_tokens": 9121231.0, |
| "step": 560 |
| }, |
| { |
| "entropy": 0.5197737812995911, |
| "epoch": 2.093370681605976, |
| "grad_norm": 0.03636628016829491, |
| "learning_rate": 0.0002, |
| "loss": 0.5256960988044739, |
| "mean_token_accuracy": 0.7841715961694717, |
| "num_tokens": 9137375.0, |
| "step": 561 |
| }, |
| { |
| "entropy": 0.5284384936094284, |
| "epoch": 2.097105508870215, |
| "grad_norm": 0.04217526316642761, |
| "learning_rate": 0.0002, |
| "loss": 0.5343865752220154, |
| "mean_token_accuracy": 0.7833265513181686, |
| "num_tokens": 9153783.0, |
| "step": 562 |
| }, |
| { |
| "entropy": 0.541428878903389, |
| "epoch": 2.100840336134454, |
| "grad_norm": 0.035067781805992126, |
| "learning_rate": 0.0002, |
| "loss": 0.532885730266571, |
| "mean_token_accuracy": 0.7817672491073608, |
| "num_tokens": 9170090.0, |
| "step": 563 |
| }, |
| { |
| "entropy": 0.5429966300725937, |
| "epoch": 2.104575163398693, |
| "grad_norm": 0.0392267219722271, |
| "learning_rate": 0.0002, |
| "loss": 0.541841447353363, |
| "mean_token_accuracy": 0.7772143185138702, |
| "num_tokens": 9186453.0, |
| "step": 564 |
| }, |
| { |
| "entropy": 0.5249236822128296, |
| "epoch": 2.108309990662932, |
| "grad_norm": 0.036935608834028244, |
| "learning_rate": 0.0002, |
| "loss": 0.5244463086128235, |
| "mean_token_accuracy": 0.7873810976743698, |
| "num_tokens": 9202852.0, |
| "step": 565 |
| }, |
| { |
| "entropy": 0.5256126970052719, |
| "epoch": 2.112044817927171, |
| "grad_norm": 0.03337714821100235, |
| "learning_rate": 0.0002, |
| "loss": 0.5264843702316284, |
| "mean_token_accuracy": 0.7856813371181488, |
| "num_tokens": 9219197.0, |
| "step": 566 |
| }, |
| { |
| "entropy": 0.5338774845004082, |
| "epoch": 2.11577964519141, |
| "grad_norm": 0.03405802696943283, |
| "learning_rate": 0.0002, |
| "loss": 0.5289718508720398, |
| "mean_token_accuracy": 0.7856559157371521, |
| "num_tokens": 9235376.0, |
| "step": 567 |
| }, |
| { |
| "entropy": 0.5203371495008469, |
| "epoch": 2.119514472455649, |
| "grad_norm": 0.0316944345831871, |
| "learning_rate": 0.0002, |
| "loss": 0.5218056440353394, |
| "mean_token_accuracy": 0.7897576838731766, |
| "num_tokens": 9251814.0, |
| "step": 568 |
| }, |
| { |
| "entropy": 0.5288322418928146, |
| "epoch": 2.123249299719888, |
| "grad_norm": 0.03991817682981491, |
| "learning_rate": 0.0002, |
| "loss": 0.538847029209137, |
| "mean_token_accuracy": 0.7831858396530151, |
| "num_tokens": 9268205.0, |
| "step": 569 |
| }, |
| { |
| "entropy": 0.5342643857002258, |
| "epoch": 2.126984126984127, |
| "grad_norm": 0.030493905767798424, |
| "learning_rate": 0.0002, |
| "loss": 0.5326664447784424, |
| "mean_token_accuracy": 0.7838881760835648, |
| "num_tokens": 9284834.0, |
| "step": 570 |
| }, |
| { |
| "entropy": 0.5280385613441467, |
| "epoch": 2.130718954248366, |
| "grad_norm": 0.033054206520318985, |
| "learning_rate": 0.0002, |
| "loss": 0.5298633575439453, |
| "mean_token_accuracy": 0.7841726392507553, |
| "num_tokens": 9301172.0, |
| "step": 571 |
| }, |
| { |
| "entropy": 0.5260151326656342, |
| "epoch": 2.134453781512605, |
| "grad_norm": 0.03629712015390396, |
| "learning_rate": 0.0002, |
| "loss": 0.5276213884353638, |
| "mean_token_accuracy": 0.7840316295623779, |
| "num_tokens": 9317580.0, |
| "step": 572 |
| }, |
| { |
| "entropy": 0.5471695214509964, |
| "epoch": 2.138188608776844, |
| "grad_norm": 0.036552250385284424, |
| "learning_rate": 0.0002, |
| "loss": 0.5418487787246704, |
| "mean_token_accuracy": 0.7832918912172318, |
| "num_tokens": 9333967.0, |
| "step": 573 |
| }, |
| { |
| "entropy": 0.5421722680330276, |
| "epoch": 2.141923436041083, |
| "grad_norm": 0.03261527791619301, |
| "learning_rate": 0.0002, |
| "loss": 0.535561203956604, |
| "mean_token_accuracy": 0.7817313969135284, |
| "num_tokens": 9350202.0, |
| "step": 574 |
| }, |
| { |
| "entropy": 0.5255165547132492, |
| "epoch": 2.145658263305322, |
| "grad_norm": 0.04084421694278717, |
| "learning_rate": 0.0002, |
| "loss": 0.531385064125061, |
| "mean_token_accuracy": 0.7830993682146072, |
| "num_tokens": 9366633.0, |
| "step": 575 |
| }, |
| { |
| "entropy": 0.5387750118970871, |
| "epoch": 2.149393090569561, |
| "grad_norm": 0.03884339705109596, |
| "learning_rate": 0.0002, |
| "loss": 0.5440813302993774, |
| "mean_token_accuracy": 0.7815608382225037, |
| "num_tokens": 9382903.0, |
| "step": 576 |
| }, |
| { |
| "entropy": 0.5333912819623947, |
| "epoch": 2.1531279178338, |
| "grad_norm": 0.03951586037874222, |
| "learning_rate": 0.0002, |
| "loss": 0.5371235013008118, |
| "mean_token_accuracy": 0.7820965349674225, |
| "num_tokens": 9399354.0, |
| "step": 577 |
| }, |
| { |
| "entropy": 0.5337669998407364, |
| "epoch": 2.156862745098039, |
| "grad_norm": 0.03831348195672035, |
| "learning_rate": 0.0002, |
| "loss": 0.5345415472984314, |
| "mean_token_accuracy": 0.7816608846187592, |
| "num_tokens": 9415670.0, |
| "step": 578 |
| }, |
| { |
| "entropy": 0.5471907705068588, |
| "epoch": 2.160597572362278, |
| "grad_norm": 0.04574183374643326, |
| "learning_rate": 0.0002, |
| "loss": 0.5423465967178345, |
| "mean_token_accuracy": 0.7815522998571396, |
| "num_tokens": 9432026.0, |
| "step": 579 |
| }, |
| { |
| "entropy": 0.5296851545572281, |
| "epoch": 2.164332399626517, |
| "grad_norm": 0.036245960742235184, |
| "learning_rate": 0.0002, |
| "loss": 0.5283267498016357, |
| "mean_token_accuracy": 0.782764196395874, |
| "num_tokens": 9448243.0, |
| "step": 580 |
| }, |
| { |
| "entropy": 0.5230330973863602, |
| "epoch": 2.168067226890756, |
| "grad_norm": 0.042745113372802734, |
| "learning_rate": 0.0002, |
| "loss": 0.5258357524871826, |
| "mean_token_accuracy": 0.7882087379693985, |
| "num_tokens": 9464651.0, |
| "step": 581 |
| }, |
| { |
| "entropy": 0.527550533413887, |
| "epoch": 2.171802054154995, |
| "grad_norm": 0.037547484040260315, |
| "learning_rate": 0.0002, |
| "loss": 0.5317714214324951, |
| "mean_token_accuracy": 0.7830660939216614, |
| "num_tokens": 9480840.0, |
| "step": 582 |
| }, |
| { |
| "entropy": 0.5365846008062363, |
| "epoch": 2.175536881419234, |
| "grad_norm": 0.031849246472120285, |
| "learning_rate": 0.0002, |
| "loss": 0.5385018587112427, |
| "mean_token_accuracy": 0.7798628509044647, |
| "num_tokens": 9497134.0, |
| "step": 583 |
| }, |
| { |
| "entropy": 0.5381672978401184, |
| "epoch": 2.179271708683473, |
| "grad_norm": 0.03450456261634827, |
| "learning_rate": 0.0002, |
| "loss": 0.534706711769104, |
| "mean_token_accuracy": 0.7828627675771713, |
| "num_tokens": 9513638.0, |
| "step": 584 |
| }, |
| { |
| "entropy": 0.5432828962802887, |
| "epoch": 2.183006535947712, |
| "grad_norm": 0.03337936848402023, |
| "learning_rate": 0.0002, |
| "loss": 0.537329375743866, |
| "mean_token_accuracy": 0.7817478477954865, |
| "num_tokens": 9530154.0, |
| "step": 585 |
| }, |
| { |
| "entropy": 0.5273857861757278, |
| "epoch": 2.1867413632119517, |
| "grad_norm": 0.03686324506998062, |
| "learning_rate": 0.0002, |
| "loss": 0.5241349339485168, |
| "mean_token_accuracy": 0.7857643216848373, |
| "num_tokens": 9546371.0, |
| "step": 586 |
| }, |
| { |
| "entropy": 0.5210235714912415, |
| "epoch": 2.1904761904761907, |
| "grad_norm": 0.036837268620729446, |
| "learning_rate": 0.0002, |
| "loss": 0.52490234375, |
| "mean_token_accuracy": 0.7855679392814636, |
| "num_tokens": 9562751.0, |
| "step": 587 |
| }, |
| { |
| "entropy": 0.5189210176467896, |
| "epoch": 2.1942110177404297, |
| "grad_norm": 0.034773845225572586, |
| "learning_rate": 0.0002, |
| "loss": 0.5269665718078613, |
| "mean_token_accuracy": 0.7840563803911209, |
| "num_tokens": 9579070.0, |
| "step": 588 |
| }, |
| { |
| "entropy": 0.5213501304388046, |
| "epoch": 2.1979458450046687, |
| "grad_norm": 0.03593657165765762, |
| "learning_rate": 0.0002, |
| "loss": 0.5271462798118591, |
| "mean_token_accuracy": 0.7872640639543533, |
| "num_tokens": 9595317.0, |
| "step": 589 |
| }, |
| { |
| "entropy": 0.5206883400678635, |
| "epoch": 2.2016806722689077, |
| "grad_norm": 0.04565085843205452, |
| "learning_rate": 0.0002, |
| "loss": 0.5203741192817688, |
| "mean_token_accuracy": 0.7881180793046951, |
| "num_tokens": 9611799.0, |
| "step": 590 |
| }, |
| { |
| "entropy": 0.5511275231838226, |
| "epoch": 2.2054154995331468, |
| "grad_norm": 0.03642827644944191, |
| "learning_rate": 0.0002, |
| "loss": 0.543250322341919, |
| "mean_token_accuracy": 0.7804217487573624, |
| "num_tokens": 9628251.0, |
| "step": 591 |
| }, |
| { |
| "entropy": 0.5495842546224594, |
| "epoch": 2.2091503267973858, |
| "grad_norm": 0.03284912183880806, |
| "learning_rate": 0.0002, |
| "loss": 0.5446897745132446, |
| "mean_token_accuracy": 0.7783705443143845, |
| "num_tokens": 9644703.0, |
| "step": 592 |
| }, |
| { |
| "entropy": 0.5297017693519592, |
| "epoch": 2.212885154061625, |
| "grad_norm": 0.04696131870150566, |
| "learning_rate": 0.0002, |
| "loss": 0.5325087308883667, |
| "mean_token_accuracy": 0.7825257629156113, |
| "num_tokens": 9660837.0, |
| "step": 593 |
| }, |
| { |
| "entropy": 0.5143487304449081, |
| "epoch": 2.216619981325864, |
| "grad_norm": 0.03802449256181717, |
| "learning_rate": 0.0002, |
| "loss": 0.5171544551849365, |
| "mean_token_accuracy": 0.7884373366832733, |
| "num_tokens": 9676767.0, |
| "step": 594 |
| }, |
| { |
| "entropy": 0.5370919853448868, |
| "epoch": 2.220354808590103, |
| "grad_norm": 0.0338297039270401, |
| "learning_rate": 0.0002, |
| "loss": 0.5430178046226501, |
| "mean_token_accuracy": 0.7808142453432083, |
| "num_tokens": 9693155.0, |
| "step": 595 |
| }, |
| { |
| "entropy": 0.5210085138678551, |
| "epoch": 2.224089635854342, |
| "grad_norm": 0.04106014966964722, |
| "learning_rate": 0.0002, |
| "loss": 0.5282027125358582, |
| "mean_token_accuracy": 0.7855826020240784, |
| "num_tokens": 9709374.0, |
| "step": 596 |
| }, |
| { |
| "entropy": 0.516735278069973, |
| "epoch": 2.227824463118581, |
| "grad_norm": 0.03890896216034889, |
| "learning_rate": 0.0002, |
| "loss": 0.5173130035400391, |
| "mean_token_accuracy": 0.7897009253501892, |
| "num_tokens": 9725684.0, |
| "step": 597 |
| }, |
| { |
| "entropy": 0.5427378565073013, |
| "epoch": 2.23155929038282, |
| "grad_norm": 0.038357146084308624, |
| "learning_rate": 0.0002, |
| "loss": 0.5421530604362488, |
| "mean_token_accuracy": 0.7789111882448196, |
| "num_tokens": 9742139.0, |
| "step": 598 |
| }, |
| { |
| "entropy": 0.5454076677560806, |
| "epoch": 2.235294117647059, |
| "grad_norm": 0.037645429372787476, |
| "learning_rate": 0.0002, |
| "loss": 0.5428951978683472, |
| "mean_token_accuracy": 0.7789873778820038, |
| "num_tokens": 9758607.0, |
| "step": 599 |
| }, |
| { |
| "entropy": 0.5404632985591888, |
| "epoch": 2.239028944911298, |
| "grad_norm": 0.039499301463365555, |
| "learning_rate": 0.0002, |
| "loss": 0.5404936075210571, |
| "mean_token_accuracy": 0.7793222069740295, |
| "num_tokens": 9775018.0, |
| "step": 600 |
| }, |
| { |
| "entropy": 0.530501589179039, |
| "epoch": 2.242763772175537, |
| "grad_norm": 0.040064238011837006, |
| "learning_rate": 0.0002, |
| "loss": 0.5247729420661926, |
| "mean_token_accuracy": 0.7874402105808258, |
| "num_tokens": 9791324.0, |
| "step": 601 |
| }, |
| { |
| "entropy": 0.5369330644607544, |
| "epoch": 2.246498599439776, |
| "grad_norm": 0.037321336567401886, |
| "learning_rate": 0.0002, |
| "loss": 0.5377377271652222, |
| "mean_token_accuracy": 0.782483384013176, |
| "num_tokens": 9807623.0, |
| "step": 602 |
| }, |
| { |
| "entropy": 0.5428077727556229, |
| "epoch": 2.250233426704015, |
| "grad_norm": 0.03844759240746498, |
| "learning_rate": 0.0002, |
| "loss": 0.5476452112197876, |
| "mean_token_accuracy": 0.776596188545227, |
| "num_tokens": 9824163.0, |
| "step": 603 |
| }, |
| { |
| "entropy": 0.5409123748540878, |
| "epoch": 2.253968253968254, |
| "grad_norm": 0.03608860820531845, |
| "learning_rate": 0.0002, |
| "loss": 0.5434892177581787, |
| "mean_token_accuracy": 0.7794551849365234, |
| "num_tokens": 9840911.0, |
| "step": 604 |
| }, |
| { |
| "entropy": 0.5327287763357162, |
| "epoch": 2.257703081232493, |
| "grad_norm": 0.037285350263118744, |
| "learning_rate": 0.0002, |
| "loss": 0.5284507274627686, |
| "mean_token_accuracy": 0.7831137478351593, |
| "num_tokens": 9857296.0, |
| "step": 605 |
| }, |
| { |
| "entropy": 0.5373975485563278, |
| "epoch": 2.261437908496732, |
| "grad_norm": 0.03957006335258484, |
| "learning_rate": 0.0002, |
| "loss": 0.5341996550559998, |
| "mean_token_accuracy": 0.7810620963573456, |
| "num_tokens": 9873850.0, |
| "step": 606 |
| }, |
| { |
| "entropy": 0.5290782749652863, |
| "epoch": 2.265172735760971, |
| "grad_norm": 0.040026333183050156, |
| "learning_rate": 0.0002, |
| "loss": 0.5341078042984009, |
| "mean_token_accuracy": 0.780807763338089, |
| "num_tokens": 9890140.0, |
| "step": 607 |
| }, |
| { |
| "entropy": 0.5333269834518433, |
| "epoch": 2.26890756302521, |
| "grad_norm": 0.03453996032476425, |
| "learning_rate": 0.0002, |
| "loss": 0.5351240634918213, |
| "mean_token_accuracy": 0.7807765603065491, |
| "num_tokens": 9906713.0, |
| "step": 608 |
| }, |
| { |
| "entropy": 0.5285785049200058, |
| "epoch": 2.272642390289449, |
| "grad_norm": 0.04334354028105736, |
| "learning_rate": 0.0002, |
| "loss": 0.5339541435241699, |
| "mean_token_accuracy": 0.7852969169616699, |
| "num_tokens": 9922956.0, |
| "step": 609 |
| }, |
| { |
| "entropy": 0.5360069870948792, |
| "epoch": 2.276377217553688, |
| "grad_norm": 0.03924287483096123, |
| "learning_rate": 0.0002, |
| "loss": 0.5359759330749512, |
| "mean_token_accuracy": 0.7819220721721649, |
| "num_tokens": 9939069.0, |
| "step": 610 |
| }, |
| { |
| "entropy": 0.5435689836740494, |
| "epoch": 2.280112044817927, |
| "grad_norm": 0.037971340119838715, |
| "learning_rate": 0.0002, |
| "loss": 0.5404746532440186, |
| "mean_token_accuracy": 0.779410719871521, |
| "num_tokens": 9955662.0, |
| "step": 611 |
| }, |
| { |
| "entropy": 0.5445673018693924, |
| "epoch": 2.283846872082166, |
| "grad_norm": 0.03730984404683113, |
| "learning_rate": 0.0002, |
| "loss": 0.5418494939804077, |
| "mean_token_accuracy": 0.7813813239336014, |
| "num_tokens": 9971957.0, |
| "step": 612 |
| }, |
| { |
| "entropy": 0.5419572293758392, |
| "epoch": 2.287581699346405, |
| "grad_norm": 0.041550587862730026, |
| "learning_rate": 0.0002, |
| "loss": 0.5388907194137573, |
| "mean_token_accuracy": 0.7824303805828094, |
| "num_tokens": 9988368.0, |
| "step": 613 |
| }, |
| { |
| "entropy": 0.5267663449048996, |
| "epoch": 2.291316526610644, |
| "grad_norm": 0.03576701879501343, |
| "learning_rate": 0.0002, |
| "loss": 0.5305144786834717, |
| "mean_token_accuracy": 0.784039780497551, |
| "num_tokens": 10004679.0, |
| "step": 614 |
| }, |
| { |
| "entropy": 0.5274334847927094, |
| "epoch": 2.295051353874883, |
| "grad_norm": 0.03758349269628525, |
| "learning_rate": 0.0002, |
| "loss": 0.5307276844978333, |
| "mean_token_accuracy": 0.7834599912166595, |
| "num_tokens": 10021146.0, |
| "step": 615 |
| }, |
| { |
| "entropy": 0.5317062586545944, |
| "epoch": 2.298786181139122, |
| "grad_norm": 0.04096253216266632, |
| "learning_rate": 0.0002, |
| "loss": 0.5370841026306152, |
| "mean_token_accuracy": 0.7823186218738556, |
| "num_tokens": 10037433.0, |
| "step": 616 |
| }, |
| { |
| "entropy": 0.5429483950138092, |
| "epoch": 2.302521008403361, |
| "grad_norm": 0.04739284887909889, |
| "learning_rate": 0.0002, |
| "loss": 0.5423600673675537, |
| "mean_token_accuracy": 0.7782929539680481, |
| "num_tokens": 10053809.0, |
| "step": 617 |
| }, |
| { |
| "entropy": 0.5375621318817139, |
| "epoch": 2.3062558356676, |
| "grad_norm": 0.03586879000067711, |
| "learning_rate": 0.0002, |
| "loss": 0.5351011157035828, |
| "mean_token_accuracy": 0.7827189415693283, |
| "num_tokens": 10070403.0, |
| "step": 618 |
| }, |
| { |
| "entropy": 0.5332229882478714, |
| "epoch": 2.309990662931839, |
| "grad_norm": 0.039749447256326675, |
| "learning_rate": 0.0002, |
| "loss": 0.5316674113273621, |
| "mean_token_accuracy": 0.7804222106933594, |
| "num_tokens": 10086520.0, |
| "step": 619 |
| }, |
| { |
| "entropy": 0.5367073863744736, |
| "epoch": 2.313725490196078, |
| "grad_norm": 0.03144790232181549, |
| "learning_rate": 0.0002, |
| "loss": 0.5297679305076599, |
| "mean_token_accuracy": 0.7887496650218964, |
| "num_tokens": 10102990.0, |
| "step": 620 |
| }, |
| { |
| "entropy": 0.5359086692333221, |
| "epoch": 2.317460317460317, |
| "grad_norm": 0.03297298401594162, |
| "learning_rate": 0.0002, |
| "loss": 0.5307391881942749, |
| "mean_token_accuracy": 0.7840029001235962, |
| "num_tokens": 10119527.0, |
| "step": 621 |
| }, |
| { |
| "entropy": 0.5245398730039597, |
| "epoch": 2.3211951447245567, |
| "grad_norm": 0.04077174887061119, |
| "learning_rate": 0.0002, |
| "loss": 0.5315594673156738, |
| "mean_token_accuracy": 0.7830156534910202, |
| "num_tokens": 10135668.0, |
| "step": 622 |
| }, |
| { |
| "entropy": 0.5435569882392883, |
| "epoch": 2.3249299719887957, |
| "grad_norm": 0.037014640867710114, |
| "learning_rate": 0.0002, |
| "loss": 0.5420113801956177, |
| "mean_token_accuracy": 0.7790663093328476, |
| "num_tokens": 10152032.0, |
| "step": 623 |
| }, |
| { |
| "entropy": 0.5408807992935181, |
| "epoch": 2.3286647992530347, |
| "grad_norm": 0.040016841143369675, |
| "learning_rate": 0.0002, |
| "loss": 0.5407621264457703, |
| "mean_token_accuracy": 0.7807969450950623, |
| "num_tokens": 10168548.0, |
| "step": 624 |
| }, |
| { |
| "entropy": 0.5394706726074219, |
| "epoch": 2.3323996265172737, |
| "grad_norm": 0.038603588938713074, |
| "learning_rate": 0.0002, |
| "loss": 0.5371181964874268, |
| "mean_token_accuracy": 0.7830179631710052, |
| "num_tokens": 10185087.0, |
| "step": 625 |
| }, |
| { |
| "entropy": 0.5331766307353973, |
| "epoch": 2.3361344537815127, |
| "grad_norm": 0.03732473403215408, |
| "learning_rate": 0.0002, |
| "loss": 0.5403282046318054, |
| "mean_token_accuracy": 0.7811668664216995, |
| "num_tokens": 10201643.0, |
| "step": 626 |
| }, |
| { |
| "entropy": 0.5270423144102097, |
| "epoch": 2.3398692810457518, |
| "grad_norm": 0.039125435054302216, |
| "learning_rate": 0.0002, |
| "loss": 0.5314643383026123, |
| "mean_token_accuracy": 0.7847079634666443, |
| "num_tokens": 10218028.0, |
| "step": 627 |
| }, |
| { |
| "entropy": 0.5217768847942352, |
| "epoch": 2.3436041083099908, |
| "grad_norm": 0.031856924295425415, |
| "learning_rate": 0.0002, |
| "loss": 0.5211607813835144, |
| "mean_token_accuracy": 0.787055104970932, |
| "num_tokens": 10234302.0, |
| "step": 628 |
| }, |
| { |
| "entropy": 0.5297789797186852, |
| "epoch": 2.34733893557423, |
| "grad_norm": 0.044731732457876205, |
| "learning_rate": 0.0002, |
| "loss": 0.5366175174713135, |
| "mean_token_accuracy": 0.7815698832273483, |
| "num_tokens": 10250527.0, |
| "step": 629 |
| }, |
| { |
| "entropy": 0.5372533053159714, |
| "epoch": 2.351073762838469, |
| "grad_norm": 0.03578559309244156, |
| "learning_rate": 0.0002, |
| "loss": 0.5398249626159668, |
| "mean_token_accuracy": 0.782914400100708, |
| "num_tokens": 10266845.0, |
| "step": 630 |
| }, |
| { |
| "entropy": 0.5397268682718277, |
| "epoch": 2.354808590102708, |
| "grad_norm": 0.04053846001625061, |
| "learning_rate": 0.0002, |
| "loss": 0.5417327880859375, |
| "mean_token_accuracy": 0.7793487906455994, |
| "num_tokens": 10283134.0, |
| "step": 631 |
| }, |
| { |
| "entropy": 0.5457513332366943, |
| "epoch": 2.358543417366947, |
| "grad_norm": 0.039855144917964935, |
| "learning_rate": 0.0002, |
| "loss": 0.5377854704856873, |
| "mean_token_accuracy": 0.7803535759449005, |
| "num_tokens": 10299673.0, |
| "step": 632 |
| }, |
| { |
| "entropy": 0.5374201238155365, |
| "epoch": 2.362278244631186, |
| "grad_norm": 0.03583669289946556, |
| "learning_rate": 0.0002, |
| "loss": 0.5346733331680298, |
| "mean_token_accuracy": 0.7818557769060135, |
| "num_tokens": 10316146.0, |
| "step": 633 |
| }, |
| { |
| "entropy": 0.5228708907961845, |
| "epoch": 2.366013071895425, |
| "grad_norm": 0.0356278158724308, |
| "learning_rate": 0.0002, |
| "loss": 0.5220701694488525, |
| "mean_token_accuracy": 0.7894868850708008, |
| "num_tokens": 10332482.0, |
| "step": 634 |
| }, |
| { |
| "entropy": 0.5448856949806213, |
| "epoch": 2.369747899159664, |
| "grad_norm": 0.045307550579309464, |
| "learning_rate": 0.0002, |
| "loss": 0.555870771408081, |
| "mean_token_accuracy": 0.7770739197731018, |
| "num_tokens": 10348970.0, |
| "step": 635 |
| }, |
| { |
| "entropy": 0.5384282767772675, |
| "epoch": 2.373482726423903, |
| "grad_norm": 0.03949993476271629, |
| "learning_rate": 0.0002, |
| "loss": 0.5424531102180481, |
| "mean_token_accuracy": 0.7787595987319946, |
| "num_tokens": 10365074.0, |
| "step": 636 |
| }, |
| { |
| "entropy": 0.532962828874588, |
| "epoch": 2.377217553688142, |
| "grad_norm": 0.0345122404396534, |
| "learning_rate": 0.0002, |
| "loss": 0.5286644697189331, |
| "mean_token_accuracy": 0.7851764559745789, |
| "num_tokens": 10381036.0, |
| "step": 637 |
| }, |
| { |
| "entropy": 0.5396641790866852, |
| "epoch": 2.380952380952381, |
| "grad_norm": 0.038070570677518845, |
| "learning_rate": 0.0002, |
| "loss": 0.5350325703620911, |
| "mean_token_accuracy": 0.783138781785965, |
| "num_tokens": 10397441.0, |
| "step": 638 |
| }, |
| { |
| "entropy": 0.5453281551599503, |
| "epoch": 2.38468720821662, |
| "grad_norm": 0.03477659448981285, |
| "learning_rate": 0.0002, |
| "loss": 0.5431845188140869, |
| "mean_token_accuracy": 0.7779907435178757, |
| "num_tokens": 10413843.0, |
| "step": 639 |
| }, |
| { |
| "entropy": 0.5235247910022736, |
| "epoch": 2.388422035480859, |
| "grad_norm": 0.04054819047451019, |
| "learning_rate": 0.0002, |
| "loss": 0.5272566080093384, |
| "mean_token_accuracy": 0.7897930145263672, |
| "num_tokens": 10430041.0, |
| "step": 640 |
| }, |
| { |
| "entropy": 0.5263708084821701, |
| "epoch": 2.392156862745098, |
| "grad_norm": 0.042338334023952484, |
| "learning_rate": 0.0002, |
| "loss": 0.5340385437011719, |
| "mean_token_accuracy": 0.7824059575796127, |
| "num_tokens": 10446100.0, |
| "step": 641 |
| }, |
| { |
| "entropy": 0.543594166636467, |
| "epoch": 2.395891690009337, |
| "grad_norm": 0.04357817769050598, |
| "learning_rate": 0.0002, |
| "loss": 0.5377992391586304, |
| "mean_token_accuracy": 0.781853511929512, |
| "num_tokens": 10462519.0, |
| "step": 642 |
| }, |
| { |
| "entropy": 0.5444612801074982, |
| "epoch": 2.399626517273576, |
| "grad_norm": 0.03883645310997963, |
| "learning_rate": 0.0002, |
| "loss": 0.5423793196678162, |
| "mean_token_accuracy": 0.7786720097064972, |
| "num_tokens": 10478807.0, |
| "step": 643 |
| }, |
| { |
| "entropy": 0.5298498719930649, |
| "epoch": 2.403361344537815, |
| "grad_norm": 0.03690332546830177, |
| "learning_rate": 0.0002, |
| "loss": 0.5272641181945801, |
| "mean_token_accuracy": 0.782812237739563, |
| "num_tokens": 10494864.0, |
| "step": 644 |
| }, |
| { |
| "entropy": 0.528311550617218, |
| "epoch": 2.407096171802054, |
| "grad_norm": 0.04098167642951012, |
| "learning_rate": 0.0002, |
| "loss": 0.5349369049072266, |
| "mean_token_accuracy": 0.7804581671953201, |
| "num_tokens": 10511211.0, |
| "step": 645 |
| }, |
| { |
| "entropy": 0.5355981737375259, |
| "epoch": 2.410830999066293, |
| "grad_norm": 0.040713947266340256, |
| "learning_rate": 0.0002, |
| "loss": 0.5427882075309753, |
| "mean_token_accuracy": 0.7789115309715271, |
| "num_tokens": 10527252.0, |
| "step": 646 |
| }, |
| { |
| "entropy": 0.5335679203271866, |
| "epoch": 2.414565826330532, |
| "grad_norm": 0.03578624129295349, |
| "learning_rate": 0.0002, |
| "loss": 0.5237961411476135, |
| "mean_token_accuracy": 0.7891885042190552, |
| "num_tokens": 10543508.0, |
| "step": 647 |
| }, |
| { |
| "entropy": 0.550647184252739, |
| "epoch": 2.418300653594771, |
| "grad_norm": 0.041548412293195724, |
| "learning_rate": 0.0002, |
| "loss": 0.5482417941093445, |
| "mean_token_accuracy": 0.7743094116449356, |
| "num_tokens": 10559883.0, |
| "step": 648 |
| }, |
| { |
| "entropy": 0.5099608227610588, |
| "epoch": 2.42203548085901, |
| "grad_norm": 0.035532381385564804, |
| "learning_rate": 0.0002, |
| "loss": 0.5146307349205017, |
| "mean_token_accuracy": 0.7876965999603271, |
| "num_tokens": 10576102.0, |
| "step": 649 |
| }, |
| { |
| "entropy": 0.5289439111948013, |
| "epoch": 2.425770308123249, |
| "grad_norm": 0.03995847702026367, |
| "learning_rate": 0.0002, |
| "loss": 0.529523491859436, |
| "mean_token_accuracy": 0.7849718630313873, |
| "num_tokens": 10592278.0, |
| "step": 650 |
| }, |
| { |
| "entropy": 0.5271874070167542, |
| "epoch": 2.429505135387488, |
| "grad_norm": 0.038978736847639084, |
| "learning_rate": 0.0002, |
| "loss": 0.5379216074943542, |
| "mean_token_accuracy": 0.7814365327358246, |
| "num_tokens": 10608707.0, |
| "step": 651 |
| }, |
| { |
| "entropy": 0.5211434736847878, |
| "epoch": 2.4332399626517276, |
| "grad_norm": 0.04277133196592331, |
| "learning_rate": 0.0002, |
| "loss": 0.5224626660346985, |
| "mean_token_accuracy": 0.7893835753202438, |
| "num_tokens": 10625209.0, |
| "step": 652 |
| }, |
| { |
| "entropy": 0.5353395342826843, |
| "epoch": 2.4369747899159666, |
| "grad_norm": 0.03804321959614754, |
| "learning_rate": 0.0002, |
| "loss": 0.5317578911781311, |
| "mean_token_accuracy": 0.7827101796865463, |
| "num_tokens": 10641678.0, |
| "step": 653 |
| }, |
| { |
| "entropy": 0.5419681817293167, |
| "epoch": 2.4407096171802056, |
| "grad_norm": 0.03237481042742729, |
| "learning_rate": 0.0002, |
| "loss": 0.5347220301628113, |
| "mean_token_accuracy": 0.7828710377216339, |
| "num_tokens": 10658020.0, |
| "step": 654 |
| }, |
| { |
| "entropy": 0.54988232254982, |
| "epoch": 2.4444444444444446, |
| "grad_norm": 0.0367792509496212, |
| "learning_rate": 0.0002, |
| "loss": 0.548277735710144, |
| "mean_token_accuracy": 0.7793003767728806, |
| "num_tokens": 10674273.0, |
| "step": 655 |
| }, |
| { |
| "entropy": 0.5270714908838272, |
| "epoch": 2.4481792717086837, |
| "grad_norm": 0.04078115150332451, |
| "learning_rate": 0.0002, |
| "loss": 0.5275436639785767, |
| "mean_token_accuracy": 0.7857778370380402, |
| "num_tokens": 10690682.0, |
| "step": 656 |
| }, |
| { |
| "entropy": 0.5229745805263519, |
| "epoch": 2.4519140989729227, |
| "grad_norm": 0.03635413572192192, |
| "learning_rate": 0.0002, |
| "loss": 0.5259315967559814, |
| "mean_token_accuracy": 0.7876160591840744, |
| "num_tokens": 10706935.0, |
| "step": 657 |
| }, |
| { |
| "entropy": 0.520149365067482, |
| "epoch": 2.4556489262371617, |
| "grad_norm": 0.04523176699876785, |
| "learning_rate": 0.0002, |
| "loss": 0.5284128189086914, |
| "mean_token_accuracy": 0.7826286852359772, |
| "num_tokens": 10723130.0, |
| "step": 658 |
| }, |
| { |
| "entropy": 0.5226980745792389, |
| "epoch": 2.4593837535014007, |
| "grad_norm": 0.04385685920715332, |
| "learning_rate": 0.0002, |
| "loss": 0.5277330279350281, |
| "mean_token_accuracy": 0.7842638790607452, |
| "num_tokens": 10739706.0, |
| "step": 659 |
| }, |
| { |
| "entropy": 0.5327855497598648, |
| "epoch": 2.4631185807656397, |
| "grad_norm": 0.03833289071917534, |
| "learning_rate": 0.0002, |
| "loss": 0.529242753982544, |
| "mean_token_accuracy": 0.784681499004364, |
| "num_tokens": 10756135.0, |
| "step": 660 |
| }, |
| { |
| "entropy": 0.5270693749189377, |
| "epoch": 2.4668534080298787, |
| "grad_norm": 0.04420669376850128, |
| "learning_rate": 0.0002, |
| "loss": 0.5234766602516174, |
| "mean_token_accuracy": 0.7881586104631424, |
| "num_tokens": 10772473.0, |
| "step": 661 |
| }, |
| { |
| "entropy": 0.5432615429162979, |
| "epoch": 2.4705882352941178, |
| "grad_norm": 0.03388570621609688, |
| "learning_rate": 0.0002, |
| "loss": 0.5459257364273071, |
| "mean_token_accuracy": 0.7780051380395889, |
| "num_tokens": 10788831.0, |
| "step": 662 |
| }, |
| { |
| "entropy": 0.5488771200180054, |
| "epoch": 2.4743230625583568, |
| "grad_norm": 0.04762876406311989, |
| "learning_rate": 0.0002, |
| "loss": 0.5534912943840027, |
| "mean_token_accuracy": 0.7749715596437454, |
| "num_tokens": 10805527.0, |
| "step": 663 |
| }, |
| { |
| "entropy": 0.5422950983047485, |
| "epoch": 2.478057889822596, |
| "grad_norm": 0.03591262549161911, |
| "learning_rate": 0.0002, |
| "loss": 0.5398073792457581, |
| "mean_token_accuracy": 0.779995933175087, |
| "num_tokens": 10821915.0, |
| "step": 664 |
| }, |
| { |
| "entropy": 0.567908450961113, |
| "epoch": 2.481792717086835, |
| "grad_norm": 0.04293651878833771, |
| "learning_rate": 0.0002, |
| "loss": 0.5645220875740051, |
| "mean_token_accuracy": 0.771768257021904, |
| "num_tokens": 10838601.0, |
| "step": 665 |
| }, |
| { |
| "entropy": 0.534419909119606, |
| "epoch": 2.485527544351074, |
| "grad_norm": 0.036424651741981506, |
| "learning_rate": 0.0002, |
| "loss": 0.5309603214263916, |
| "mean_token_accuracy": 0.786093220114708, |
| "num_tokens": 10854981.0, |
| "step": 666 |
| }, |
| { |
| "entropy": 0.5380399525165558, |
| "epoch": 2.489262371615313, |
| "grad_norm": 0.04585183784365654, |
| "learning_rate": 0.0002, |
| "loss": 0.5384916067123413, |
| "mean_token_accuracy": 0.7809207290410995, |
| "num_tokens": 10871328.0, |
| "step": 667 |
| }, |
| { |
| "entropy": 0.5118337720632553, |
| "epoch": 2.492997198879552, |
| "grad_norm": 0.03870607912540436, |
| "learning_rate": 0.0002, |
| "loss": 0.5148553252220154, |
| "mean_token_accuracy": 0.7906211614608765, |
| "num_tokens": 10887543.0, |
| "step": 668 |
| }, |
| { |
| "entropy": 0.539421871304512, |
| "epoch": 2.496732026143791, |
| "grad_norm": 0.04092569276690483, |
| "learning_rate": 0.0002, |
| "loss": 0.5474343299865723, |
| "mean_token_accuracy": 0.7810823172330856, |
| "num_tokens": 10904063.0, |
| "step": 669 |
| }, |
| { |
| "entropy": 0.5357869118452072, |
| "epoch": 2.50046685340803, |
| "grad_norm": 0.03857175633311272, |
| "learning_rate": 0.0002, |
| "loss": 0.5365599393844604, |
| "mean_token_accuracy": 0.7816625684499741, |
| "num_tokens": 10920474.0, |
| "step": 670 |
| }, |
| { |
| "entropy": 0.5330220460891724, |
| "epoch": 2.504201680672269, |
| "grad_norm": 0.03685252368450165, |
| "learning_rate": 0.0002, |
| "loss": 0.5331542491912842, |
| "mean_token_accuracy": 0.7820776700973511, |
| "num_tokens": 10936663.0, |
| "step": 671 |
| }, |
| { |
| "entropy": 0.524094969034195, |
| "epoch": 2.507936507936508, |
| "grad_norm": 0.03893151134252548, |
| "learning_rate": 0.0002, |
| "loss": 0.5277613997459412, |
| "mean_token_accuracy": 0.7860450148582458, |
| "num_tokens": 10952950.0, |
| "step": 672 |
| }, |
| { |
| "entropy": 0.5463172346353531, |
| "epoch": 2.511671335200747, |
| "grad_norm": 0.039967626333236694, |
| "learning_rate": 0.0002, |
| "loss": 0.5425282716751099, |
| "mean_token_accuracy": 0.7801816016435623, |
| "num_tokens": 10969412.0, |
| "step": 673 |
| }, |
| { |
| "entropy": 0.5239230394363403, |
| "epoch": 2.515406162464986, |
| "grad_norm": 0.046231936663389206, |
| "learning_rate": 0.0002, |
| "loss": 0.5241309404373169, |
| "mean_token_accuracy": 0.787441685795784, |
| "num_tokens": 10985869.0, |
| "step": 674 |
| }, |
| { |
| "entropy": 0.5359321981668472, |
| "epoch": 2.519140989729225, |
| "grad_norm": 0.040779855102300644, |
| "learning_rate": 0.0002, |
| "loss": 0.536766767501831, |
| "mean_token_accuracy": 0.7817385196685791, |
| "num_tokens": 11002074.0, |
| "step": 675 |
| }, |
| { |
| "entropy": 0.5319357812404633, |
| "epoch": 2.522875816993464, |
| "grad_norm": 0.03476366400718689, |
| "learning_rate": 0.0002, |
| "loss": 0.5311717391014099, |
| "mean_token_accuracy": 0.7856648862361908, |
| "num_tokens": 11018648.0, |
| "step": 676 |
| }, |
| { |
| "entropy": 0.5231706351041794, |
| "epoch": 2.526610644257703, |
| "grad_norm": 0.03785642236471176, |
| "learning_rate": 0.0002, |
| "loss": 0.5269960165023804, |
| "mean_token_accuracy": 0.7866117358207703, |
| "num_tokens": 11034686.0, |
| "step": 677 |
| }, |
| { |
| "entropy": 0.5381273478269577, |
| "epoch": 2.530345471521942, |
| "grad_norm": 0.03976747393608093, |
| "learning_rate": 0.0002, |
| "loss": 0.5381407141685486, |
| "mean_token_accuracy": 0.7849810570478439, |
| "num_tokens": 11050922.0, |
| "step": 678 |
| }, |
| { |
| "entropy": 0.5456480979919434, |
| "epoch": 2.534080298786181, |
| "grad_norm": 0.039225250482559204, |
| "learning_rate": 0.0002, |
| "loss": 0.5425232648849487, |
| "mean_token_accuracy": 0.7785615175962448, |
| "num_tokens": 11067148.0, |
| "step": 679 |
| }, |
| { |
| "entropy": 0.5407412797212601, |
| "epoch": 2.53781512605042, |
| "grad_norm": 0.03705086559057236, |
| "learning_rate": 0.0002, |
| "loss": 0.536932110786438, |
| "mean_token_accuracy": 0.7821008861064911, |
| "num_tokens": 11083363.0, |
| "step": 680 |
| }, |
| { |
| "entropy": 0.5263440012931824, |
| "epoch": 2.541549953314659, |
| "grad_norm": 0.0353594608604908, |
| "learning_rate": 0.0002, |
| "loss": 0.5256474018096924, |
| "mean_token_accuracy": 0.7849348187446594, |
| "num_tokens": 11099785.0, |
| "step": 681 |
| }, |
| { |
| "entropy": 0.5354757159948349, |
| "epoch": 2.545284780578898, |
| "grad_norm": 0.04532964155077934, |
| "learning_rate": 0.0002, |
| "loss": 0.5450004935264587, |
| "mean_token_accuracy": 0.7807293385267258, |
| "num_tokens": 11115892.0, |
| "step": 682 |
| }, |
| { |
| "entropy": 0.5281579941511154, |
| "epoch": 2.549019607843137, |
| "grad_norm": 0.03604253754019737, |
| "learning_rate": 0.0002, |
| "loss": 0.5311046838760376, |
| "mean_token_accuracy": 0.7845126688480377, |
| "num_tokens": 11132189.0, |
| "step": 683 |
| }, |
| { |
| "entropy": 0.5354526489973068, |
| "epoch": 2.552754435107376, |
| "grad_norm": 0.03747657313942909, |
| "learning_rate": 0.0002, |
| "loss": 0.5361717343330383, |
| "mean_token_accuracy": 0.7801252007484436, |
| "num_tokens": 11148681.0, |
| "step": 684 |
| }, |
| { |
| "entropy": 0.5386267453432083, |
| "epoch": 2.556489262371615, |
| "grad_norm": 0.037825409322977066, |
| "learning_rate": 0.0002, |
| "loss": 0.5390512347221375, |
| "mean_token_accuracy": 0.7815877050161362, |
| "num_tokens": 11165013.0, |
| "step": 685 |
| }, |
| { |
| "entropy": 0.530585527420044, |
| "epoch": 2.560224089635854, |
| "grad_norm": 0.03970746695995331, |
| "learning_rate": 0.0002, |
| "loss": 0.5291422009468079, |
| "mean_token_accuracy": 0.7839111536741257, |
| "num_tokens": 11181301.0, |
| "step": 686 |
| }, |
| { |
| "entropy": 0.5292850136756897, |
| "epoch": 2.563958916900093, |
| "grad_norm": 0.03387298434972763, |
| "learning_rate": 0.0002, |
| "loss": 0.5319269299507141, |
| "mean_token_accuracy": 0.7840193659067154, |
| "num_tokens": 11197537.0, |
| "step": 687 |
| }, |
| { |
| "entropy": 0.5399095267057419, |
| "epoch": 2.567693744164332, |
| "grad_norm": 0.038681600242853165, |
| "learning_rate": 0.0002, |
| "loss": 0.5435532331466675, |
| "mean_token_accuracy": 0.7806709408760071, |
| "num_tokens": 11213896.0, |
| "step": 688 |
| }, |
| { |
| "entropy": 0.5498056858778, |
| "epoch": 2.571428571428571, |
| "grad_norm": 0.03758297860622406, |
| "learning_rate": 0.0002, |
| "loss": 0.5467256307601929, |
| "mean_token_accuracy": 0.7782751470804214, |
| "num_tokens": 11230383.0, |
| "step": 689 |
| }, |
| { |
| "entropy": 0.5476771891117096, |
| "epoch": 2.57516339869281, |
| "grad_norm": 0.03605665639042854, |
| "learning_rate": 0.0002, |
| "loss": 0.541588544845581, |
| "mean_token_accuracy": 0.7791445404291153, |
| "num_tokens": 11246749.0, |
| "step": 690 |
| }, |
| { |
| "entropy": 0.542407214641571, |
| "epoch": 2.5788982259570497, |
| "grad_norm": 0.04616822302341461, |
| "learning_rate": 0.0002, |
| "loss": 0.535969614982605, |
| "mean_token_accuracy": 0.7812883108854294, |
| "num_tokens": 11263093.0, |
| "step": 691 |
| }, |
| { |
| "entropy": 0.5215721130371094, |
| "epoch": 2.5826330532212887, |
| "grad_norm": 0.040278688073158264, |
| "learning_rate": 0.0002, |
| "loss": 0.5306443572044373, |
| "mean_token_accuracy": 0.783096119761467, |
| "num_tokens": 11279295.0, |
| "step": 692 |
| }, |
| { |
| "entropy": 0.5300876200199127, |
| "epoch": 2.5863678804855277, |
| "grad_norm": 0.04465034604072571, |
| "learning_rate": 0.0002, |
| "loss": 0.5408331751823425, |
| "mean_token_accuracy": 0.781616821885109, |
| "num_tokens": 11295488.0, |
| "step": 693 |
| }, |
| { |
| "entropy": 0.529060423374176, |
| "epoch": 2.5901027077497667, |
| "grad_norm": 0.03697149083018303, |
| "learning_rate": 0.0002, |
| "loss": 0.5315713286399841, |
| "mean_token_accuracy": 0.784434586763382, |
| "num_tokens": 11311910.0, |
| "step": 694 |
| }, |
| { |
| "entropy": 0.5421274900436401, |
| "epoch": 2.5938375350140057, |
| "grad_norm": 0.03769063949584961, |
| "learning_rate": 0.0002, |
| "loss": 0.5342295169830322, |
| "mean_token_accuracy": 0.7821343541145325, |
| "num_tokens": 11328227.0, |
| "step": 695 |
| }, |
| { |
| "entropy": 0.5521349608898163, |
| "epoch": 2.5975723622782447, |
| "grad_norm": 0.037369053810834885, |
| "learning_rate": 0.0002, |
| "loss": 0.5406404733657837, |
| "mean_token_accuracy": 0.7816728502511978, |
| "num_tokens": 11344754.0, |
| "step": 696 |
| }, |
| { |
| "entropy": 0.5276040434837341, |
| "epoch": 2.6013071895424837, |
| "grad_norm": 0.04295807331800461, |
| "learning_rate": 0.0002, |
| "loss": 0.531209409236908, |
| "mean_token_accuracy": 0.781694307923317, |
| "num_tokens": 11360846.0, |
| "step": 697 |
| }, |
| { |
| "entropy": 0.5329545885324478, |
| "epoch": 2.6050420168067228, |
| "grad_norm": 0.04680144414305687, |
| "learning_rate": 0.0002, |
| "loss": 0.5448673963546753, |
| "mean_token_accuracy": 0.7803032696247101, |
| "num_tokens": 11376984.0, |
| "step": 698 |
| }, |
| { |
| "entropy": 0.5330372750759125, |
| "epoch": 2.6087768440709618, |
| "grad_norm": 0.038128506392240524, |
| "learning_rate": 0.0002, |
| "loss": 0.5345317125320435, |
| "mean_token_accuracy": 0.7848279774188995, |
| "num_tokens": 11393192.0, |
| "step": 699 |
| }, |
| { |
| "entropy": 0.5620173513889313, |
| "epoch": 2.612511671335201, |
| "grad_norm": 0.0405871607363224, |
| "learning_rate": 0.0002, |
| "loss": 0.5558884143829346, |
| "mean_token_accuracy": 0.7717028856277466, |
| "num_tokens": 11409571.0, |
| "step": 700 |
| }, |
| { |
| "entropy": 0.5401062965393066, |
| "epoch": 2.61624649859944, |
| "grad_norm": 0.033952489495277405, |
| "learning_rate": 0.0002, |
| "loss": 0.5324668884277344, |
| "mean_token_accuracy": 0.7836252152919769, |
| "num_tokens": 11426157.0, |
| "step": 701 |
| }, |
| { |
| "entropy": 0.5401272624731064, |
| "epoch": 2.619981325863679, |
| "grad_norm": 0.03486888110637665, |
| "learning_rate": 0.0002, |
| "loss": 0.5405600666999817, |
| "mean_token_accuracy": 0.780670240521431, |
| "num_tokens": 11442706.0, |
| "step": 702 |
| }, |
| { |
| "entropy": 0.5286990851163864, |
| "epoch": 2.623716153127918, |
| "grad_norm": 0.03971569985151291, |
| "learning_rate": 0.0002, |
| "loss": 0.5301419496536255, |
| "mean_token_accuracy": 0.7845329642295837, |
| "num_tokens": 11459059.0, |
| "step": 703 |
| }, |
| { |
| "entropy": 0.5408699810504913, |
| "epoch": 2.627450980392157, |
| "grad_norm": 0.03566860780119896, |
| "learning_rate": 0.0002, |
| "loss": 0.5422340631484985, |
| "mean_token_accuracy": 0.7786179780960083, |
| "num_tokens": 11475473.0, |
| "step": 704 |
| }, |
| { |
| "entropy": 0.5306770950555801, |
| "epoch": 2.631185807656396, |
| "grad_norm": 0.038531865924596786, |
| "learning_rate": 0.0002, |
| "loss": 0.5311087965965271, |
| "mean_token_accuracy": 0.784186452627182, |
| "num_tokens": 11491765.0, |
| "step": 705 |
| }, |
| { |
| "entropy": 0.5391299277544022, |
| "epoch": 2.634920634920635, |
| "grad_norm": 0.036147549748420715, |
| "learning_rate": 0.0002, |
| "loss": 0.5403758883476257, |
| "mean_token_accuracy": 0.7817845791578293, |
| "num_tokens": 11508291.0, |
| "step": 706 |
| }, |
| { |
| "entropy": 0.5316940769553185, |
| "epoch": 2.638655462184874, |
| "grad_norm": 0.036513980478048325, |
| "learning_rate": 0.0002, |
| "loss": 0.5340716242790222, |
| "mean_token_accuracy": 0.7847382575273514, |
| "num_tokens": 11524811.0, |
| "step": 707 |
| }, |
| { |
| "entropy": 0.5237598121166229, |
| "epoch": 2.642390289449113, |
| "grad_norm": 0.03360476344823837, |
| "learning_rate": 0.0002, |
| "loss": 0.5258880257606506, |
| "mean_token_accuracy": 0.7865117788314819, |
| "num_tokens": 11541335.0, |
| "step": 708 |
| }, |
| { |
| "entropy": 0.5325336754322052, |
| "epoch": 2.646125116713352, |
| "grad_norm": 0.03501066192984581, |
| "learning_rate": 0.0002, |
| "loss": 0.5358341336250305, |
| "mean_token_accuracy": 0.7841547876596451, |
| "num_tokens": 11557859.0, |
| "step": 709 |
| }, |
| { |
| "entropy": 0.5220260694622993, |
| "epoch": 2.649859943977591, |
| "grad_norm": 0.038072340190410614, |
| "learning_rate": 0.0002, |
| "loss": 0.5222914814949036, |
| "mean_token_accuracy": 0.7870404571294785, |
| "num_tokens": 11574116.0, |
| "step": 710 |
| }, |
| { |
| "entropy": 0.5257419422268867, |
| "epoch": 2.65359477124183, |
| "grad_norm": 0.03713792935013771, |
| "learning_rate": 0.0002, |
| "loss": 0.5267120599746704, |
| "mean_token_accuracy": 0.7852788418531418, |
| "num_tokens": 11590295.0, |
| "step": 711 |
| }, |
| { |
| "entropy": 0.5383759438991547, |
| "epoch": 2.657329598506069, |
| "grad_norm": 0.04603256285190582, |
| "learning_rate": 0.0002, |
| "loss": 0.5421494841575623, |
| "mean_token_accuracy": 0.781136080622673, |
| "num_tokens": 11606581.0, |
| "step": 712 |
| }, |
| { |
| "entropy": 0.5336297005414963, |
| "epoch": 2.661064425770308, |
| "grad_norm": 0.03931435942649841, |
| "learning_rate": 0.0002, |
| "loss": 0.5313882231712341, |
| "mean_token_accuracy": 0.7825400978326797, |
| "num_tokens": 11622793.0, |
| "step": 713 |
| }, |
| { |
| "entropy": 0.5316190719604492, |
| "epoch": 2.664799253034547, |
| "grad_norm": 0.03564710542559624, |
| "learning_rate": 0.0002, |
| "loss": 0.530137836933136, |
| "mean_token_accuracy": 0.7861842215061188, |
| "num_tokens": 11638909.0, |
| "step": 714 |
| }, |
| { |
| "entropy": 0.529007188975811, |
| "epoch": 2.668534080298786, |
| "grad_norm": 0.03671964257955551, |
| "learning_rate": 0.0002, |
| "loss": 0.5294506549835205, |
| "mean_token_accuracy": 0.7843856066465378, |
| "num_tokens": 11655048.0, |
| "step": 715 |
| }, |
| { |
| "entropy": 0.5391807407140732, |
| "epoch": 2.6722689075630255, |
| "grad_norm": 0.043020427227020264, |
| "learning_rate": 0.0002, |
| "loss": 0.5463923215866089, |
| "mean_token_accuracy": 0.7798423320055008, |
| "num_tokens": 11671616.0, |
| "step": 716 |
| }, |
| { |
| "entropy": 0.5369218289852142, |
| "epoch": 2.6760037348272645, |
| "grad_norm": 0.04039768502116203, |
| "learning_rate": 0.0002, |
| "loss": 0.5428373217582703, |
| "mean_token_accuracy": 0.7810155898332596, |
| "num_tokens": 11687981.0, |
| "step": 717 |
| }, |
| { |
| "entropy": 0.5410373359918594, |
| "epoch": 2.6797385620915035, |
| "grad_norm": 0.032212115824222565, |
| "learning_rate": 0.0002, |
| "loss": 0.538726806640625, |
| "mean_token_accuracy": 0.7823937833309174, |
| "num_tokens": 11704497.0, |
| "step": 718 |
| }, |
| { |
| "entropy": 0.5408433228731155, |
| "epoch": 2.6834733893557425, |
| "grad_norm": 0.04190416634082794, |
| "learning_rate": 0.0002, |
| "loss": 0.5312804579734802, |
| "mean_token_accuracy": 0.7858607023954391, |
| "num_tokens": 11720759.0, |
| "step": 719 |
| }, |
| { |
| "entropy": 0.52065759152174, |
| "epoch": 2.6872082166199815, |
| "grad_norm": 0.03749416023492813, |
| "learning_rate": 0.0002, |
| "loss": 0.5172442197799683, |
| "mean_token_accuracy": 0.7908001989126205, |
| "num_tokens": 11736897.0, |
| "step": 720 |
| }, |
| { |
| "entropy": 0.5223864614963531, |
| "epoch": 2.6909430438842206, |
| "grad_norm": 0.03889421746134758, |
| "learning_rate": 0.0002, |
| "loss": 0.5262103080749512, |
| "mean_token_accuracy": 0.7863954603672028, |
| "num_tokens": 11753026.0, |
| "step": 721 |
| }, |
| { |
| "entropy": 0.5417105704545975, |
| "epoch": 2.6946778711484596, |
| "grad_norm": 0.03900585323572159, |
| "learning_rate": 0.0002, |
| "loss": 0.548478901386261, |
| "mean_token_accuracy": 0.7769544124603271, |
| "num_tokens": 11769364.0, |
| "step": 722 |
| }, |
| { |
| "entropy": 0.5348965376615524, |
| "epoch": 2.6984126984126986, |
| "grad_norm": 0.040531598031520844, |
| "learning_rate": 0.0002, |
| "loss": 0.5366338491439819, |
| "mean_token_accuracy": 0.7824574261903763, |
| "num_tokens": 11785662.0, |
| "step": 723 |
| }, |
| { |
| "entropy": 0.5472202748060226, |
| "epoch": 2.7021475256769376, |
| "grad_norm": 0.03544607013463974, |
| "learning_rate": 0.0002, |
| "loss": 0.546108067035675, |
| "mean_token_accuracy": 0.7778937071561813, |
| "num_tokens": 11802091.0, |
| "step": 724 |
| }, |
| { |
| "entropy": 0.5445298254489899, |
| "epoch": 2.7058823529411766, |
| "grad_norm": 0.045996710658073425, |
| "learning_rate": 0.0002, |
| "loss": 0.5458025336265564, |
| "mean_token_accuracy": 0.7784214168787003, |
| "num_tokens": 11818307.0, |
| "step": 725 |
| }, |
| { |
| "entropy": 0.5437731146812439, |
| "epoch": 2.7096171802054156, |
| "grad_norm": 0.040692199021577835, |
| "learning_rate": 0.0002, |
| "loss": 0.5425392389297485, |
| "mean_token_accuracy": 0.7800037413835526, |
| "num_tokens": 11834733.0, |
| "step": 726 |
| }, |
| { |
| "entropy": 0.5586313903331757, |
| "epoch": 2.7133520074696547, |
| "grad_norm": 0.05102645978331566, |
| "learning_rate": 0.0002, |
| "loss": 0.5646232962608337, |
| "mean_token_accuracy": 0.7713905870914459, |
| "num_tokens": 11851346.0, |
| "step": 727 |
| }, |
| { |
| "entropy": 0.5276175439357758, |
| "epoch": 2.7170868347338937, |
| "grad_norm": 0.04199473559856415, |
| "learning_rate": 0.0002, |
| "loss": 0.5330867767333984, |
| "mean_token_accuracy": 0.7841922342777252, |
| "num_tokens": 11867709.0, |
| "step": 728 |
| }, |
| { |
| "entropy": 0.5365078300237656, |
| "epoch": 2.7208216619981327, |
| "grad_norm": 0.038084954023361206, |
| "learning_rate": 0.0002, |
| "loss": 0.5328811407089233, |
| "mean_token_accuracy": 0.7830130755901337, |
| "num_tokens": 11884172.0, |
| "step": 729 |
| }, |
| { |
| "entropy": 0.5306914746761322, |
| "epoch": 2.7245564892623717, |
| "grad_norm": 0.04009576886892319, |
| "learning_rate": 0.0002, |
| "loss": 0.5335056185722351, |
| "mean_token_accuracy": 0.784161165356636, |
| "num_tokens": 11900524.0, |
| "step": 730 |
| }, |
| { |
| "entropy": 0.5325679033994675, |
| "epoch": 2.7282913165266107, |
| "grad_norm": 0.0398661270737648, |
| "learning_rate": 0.0002, |
| "loss": 0.5311678051948547, |
| "mean_token_accuracy": 0.7866542786359787, |
| "num_tokens": 11916696.0, |
| "step": 731 |
| }, |
| { |
| "entropy": 0.5234319120645523, |
| "epoch": 2.7320261437908497, |
| "grad_norm": 0.03887765109539032, |
| "learning_rate": 0.0002, |
| "loss": 0.5243536233901978, |
| "mean_token_accuracy": 0.786685973405838, |
| "num_tokens": 11933375.0, |
| "step": 732 |
| }, |
| { |
| "entropy": 0.5323622822761536, |
| "epoch": 2.7357609710550888, |
| "grad_norm": 0.041390158236026764, |
| "learning_rate": 0.0002, |
| "loss": 0.5382110476493835, |
| "mean_token_accuracy": 0.7813025563955307, |
| "num_tokens": 11949641.0, |
| "step": 733 |
| }, |
| { |
| "entropy": 0.5282771736383438, |
| "epoch": 2.7394957983193278, |
| "grad_norm": 0.03821795806288719, |
| "learning_rate": 0.0002, |
| "loss": 0.5237923860549927, |
| "mean_token_accuracy": 0.7858958840370178, |
| "num_tokens": 11965904.0, |
| "step": 734 |
| }, |
| { |
| "entropy": 0.5336133688688278, |
| "epoch": 2.743230625583567, |
| "grad_norm": 0.040790773928165436, |
| "learning_rate": 0.0002, |
| "loss": 0.5322080850601196, |
| "mean_token_accuracy": 0.7814221978187561, |
| "num_tokens": 11982242.0, |
| "step": 735 |
| }, |
| { |
| "entropy": 0.5447276085615158, |
| "epoch": 2.746965452847806, |
| "grad_norm": 0.03733038902282715, |
| "learning_rate": 0.0002, |
| "loss": 0.5435236096382141, |
| "mean_token_accuracy": 0.7783806473016739, |
| "num_tokens": 11998525.0, |
| "step": 736 |
| }, |
| { |
| "entropy": 0.5370974391698837, |
| "epoch": 2.750700280112045, |
| "grad_norm": 0.035691265016794205, |
| "learning_rate": 0.0002, |
| "loss": 0.5391957759857178, |
| "mean_token_accuracy": 0.7787430435419083, |
| "num_tokens": 12014726.0, |
| "step": 737 |
| }, |
| { |
| "entropy": 0.5190877616405487, |
| "epoch": 2.754435107376284, |
| "grad_norm": 0.037242453545331955, |
| "learning_rate": 0.0002, |
| "loss": 0.5239222645759583, |
| "mean_token_accuracy": 0.7867171913385391, |
| "num_tokens": 12030648.0, |
| "step": 738 |
| }, |
| { |
| "entropy": 0.5201060324907303, |
| "epoch": 2.758169934640523, |
| "grad_norm": 0.03840528428554535, |
| "learning_rate": 0.0002, |
| "loss": 0.5264686942100525, |
| "mean_token_accuracy": 0.7854082137346268, |
| "num_tokens": 12046824.0, |
| "step": 739 |
| }, |
| { |
| "entropy": 0.5208890736103058, |
| "epoch": 2.761904761904762, |
| "grad_norm": 0.038443028926849365, |
| "learning_rate": 0.0002, |
| "loss": 0.5207111239433289, |
| "mean_token_accuracy": 0.7860049307346344, |
| "num_tokens": 12063182.0, |
| "step": 740 |
| }, |
| { |
| "entropy": 0.5337280184030533, |
| "epoch": 2.765639589169001, |
| "grad_norm": 0.0408535934984684, |
| "learning_rate": 0.0002, |
| "loss": 0.5295891165733337, |
| "mean_token_accuracy": 0.7857932895421982, |
| "num_tokens": 12079411.0, |
| "step": 741 |
| }, |
| { |
| "entropy": 0.5374506562948227, |
| "epoch": 2.76937441643324, |
| "grad_norm": 0.04354558512568474, |
| "learning_rate": 0.0002, |
| "loss": 0.5414345860481262, |
| "mean_token_accuracy": 0.7807870209217072, |
| "num_tokens": 12095874.0, |
| "step": 742 |
| }, |
| { |
| "entropy": 0.5360343009233475, |
| "epoch": 2.773109243697479, |
| "grad_norm": 0.03928976133465767, |
| "learning_rate": 0.0002, |
| "loss": 0.5380703210830688, |
| "mean_token_accuracy": 0.7798075079917908, |
| "num_tokens": 12112215.0, |
| "step": 743 |
| }, |
| { |
| "entropy": 0.5264292061328888, |
| "epoch": 2.776844070961718, |
| "grad_norm": 0.03775021806359291, |
| "learning_rate": 0.0002, |
| "loss": 0.5281617045402527, |
| "mean_token_accuracy": 0.7842919081449509, |
| "num_tokens": 12128361.0, |
| "step": 744 |
| }, |
| { |
| "entropy": 0.5419831871986389, |
| "epoch": 2.780578898225957, |
| "grad_norm": 0.032331038266420364, |
| "learning_rate": 0.0002, |
| "loss": 0.5362944602966309, |
| "mean_token_accuracy": 0.7816326916217804, |
| "num_tokens": 12144755.0, |
| "step": 745 |
| }, |
| { |
| "entropy": 0.5174460113048553, |
| "epoch": 2.784313725490196, |
| "grad_norm": 0.03798742592334747, |
| "learning_rate": 0.0002, |
| "loss": 0.515007495880127, |
| "mean_token_accuracy": 0.7882062345743179, |
| "num_tokens": 12161034.0, |
| "step": 746 |
| }, |
| { |
| "entropy": 0.5355328992009163, |
| "epoch": 2.788048552754435, |
| "grad_norm": 0.036557331681251526, |
| "learning_rate": 0.0002, |
| "loss": 0.5344611406326294, |
| "mean_token_accuracy": 0.7847500294446945, |
| "num_tokens": 12177479.0, |
| "step": 747 |
| }, |
| { |
| "entropy": 0.538584902882576, |
| "epoch": 2.791783380018674, |
| "grad_norm": 0.039520300924777985, |
| "learning_rate": 0.0002, |
| "loss": 0.5427792072296143, |
| "mean_token_accuracy": 0.7786386609077454, |
| "num_tokens": 12193830.0, |
| "step": 748 |
| }, |
| { |
| "entropy": 0.51973095536232, |
| "epoch": 2.795518207282913, |
| "grad_norm": 0.04126165434718132, |
| "learning_rate": 0.0002, |
| "loss": 0.5279180407524109, |
| "mean_token_accuracy": 0.784518226981163, |
| "num_tokens": 12210022.0, |
| "step": 749 |
| }, |
| { |
| "entropy": 0.5385647118091583, |
| "epoch": 2.799253034547152, |
| "grad_norm": 0.03742329403758049, |
| "learning_rate": 0.0002, |
| "loss": 0.5358390808105469, |
| "mean_token_accuracy": 0.7814119607210159, |
| "num_tokens": 12226184.0, |
| "step": 750 |
| }, |
| { |
| "entropy": 0.5483904033899307, |
| "epoch": 2.802987861811391, |
| "grad_norm": 0.03444087877869606, |
| "learning_rate": 0.0002, |
| "loss": 0.5442800521850586, |
| "mean_token_accuracy": 0.7782953381538391, |
| "num_tokens": 12242564.0, |
| "step": 751 |
| }, |
| { |
| "entropy": 0.5447859466075897, |
| "epoch": 2.80672268907563, |
| "grad_norm": 0.037425972521305084, |
| "learning_rate": 0.0002, |
| "loss": 0.5376838445663452, |
| "mean_token_accuracy": 0.7805659919977188, |
| "num_tokens": 12259077.0, |
| "step": 752 |
| }, |
| { |
| "entropy": 0.526421070098877, |
| "epoch": 2.810457516339869, |
| "grad_norm": 0.039544545114040375, |
| "learning_rate": 0.0002, |
| "loss": 0.5272819399833679, |
| "mean_token_accuracy": 0.7836880385875702, |
| "num_tokens": 12275297.0, |
| "step": 753 |
| }, |
| { |
| "entropy": 0.538783460855484, |
| "epoch": 2.814192343604108, |
| "grad_norm": 0.035788971930742264, |
| "learning_rate": 0.0002, |
| "loss": 0.5417999625205994, |
| "mean_token_accuracy": 0.7819748818874359, |
| "num_tokens": 12291643.0, |
| "step": 754 |
| }, |
| { |
| "entropy": 0.5367716252803802, |
| "epoch": 2.817927170868347, |
| "grad_norm": 0.040753189474344254, |
| "learning_rate": 0.0002, |
| "loss": 0.5376288294792175, |
| "mean_token_accuracy": 0.7829637825489044, |
| "num_tokens": 12307987.0, |
| "step": 755 |
| }, |
| { |
| "entropy": 0.5418078452348709, |
| "epoch": 2.821661998132586, |
| "grad_norm": 0.036726806312799454, |
| "learning_rate": 0.0002, |
| "loss": 0.5469898581504822, |
| "mean_token_accuracy": 0.7801835685968399, |
| "num_tokens": 12324503.0, |
| "step": 756 |
| }, |
| { |
| "entropy": 0.525896355509758, |
| "epoch": 2.825396825396825, |
| "grad_norm": 0.034559980034828186, |
| "learning_rate": 0.0002, |
| "loss": 0.5265108942985535, |
| "mean_token_accuracy": 0.7867930829524994, |
| "num_tokens": 12340881.0, |
| "step": 757 |
| }, |
| { |
| "entropy": 0.5369487851858139, |
| "epoch": 2.8291316526610646, |
| "grad_norm": 0.03595944494009018, |
| "learning_rate": 0.0002, |
| "loss": 0.5396771430969238, |
| "mean_token_accuracy": 0.7813677042722702, |
| "num_tokens": 12357352.0, |
| "step": 758 |
| }, |
| { |
| "entropy": 0.5467210859060287, |
| "epoch": 2.8328664799253036, |
| "grad_norm": 0.03524104505777359, |
| "learning_rate": 0.0002, |
| "loss": 0.544916570186615, |
| "mean_token_accuracy": 0.7771721184253693, |
| "num_tokens": 12373526.0, |
| "step": 759 |
| }, |
| { |
| "entropy": 0.5246351063251495, |
| "epoch": 2.8366013071895426, |
| "grad_norm": 0.036806508898735046, |
| "learning_rate": 0.0002, |
| "loss": 0.5221924781799316, |
| "mean_token_accuracy": 0.7871624380350113, |
| "num_tokens": 12389771.0, |
| "step": 760 |
| }, |
| { |
| "entropy": 0.530710369348526, |
| "epoch": 2.8403361344537816, |
| "grad_norm": 0.04332499951124191, |
| "learning_rate": 0.0002, |
| "loss": 0.5322965383529663, |
| "mean_token_accuracy": 0.7832685261964798, |
| "num_tokens": 12406028.0, |
| "step": 761 |
| }, |
| { |
| "entropy": 0.5254833996295929, |
| "epoch": 2.8440709617180207, |
| "grad_norm": 0.038304176181554794, |
| "learning_rate": 0.0002, |
| "loss": 0.5253804922103882, |
| "mean_token_accuracy": 0.7873952239751816, |
| "num_tokens": 12422639.0, |
| "step": 762 |
| }, |
| { |
| "entropy": 0.5236704498529434, |
| "epoch": 2.8478057889822597, |
| "grad_norm": 0.03660830482840538, |
| "learning_rate": 0.0002, |
| "loss": 0.5286169052124023, |
| "mean_token_accuracy": 0.7816056311130524, |
| "num_tokens": 12438922.0, |
| "step": 763 |
| }, |
| { |
| "entropy": 0.5321139246225357, |
| "epoch": 2.8515406162464987, |
| "grad_norm": 0.04276243969798088, |
| "learning_rate": 0.0002, |
| "loss": 0.5400298237800598, |
| "mean_token_accuracy": 0.7802720963954926, |
| "num_tokens": 12455234.0, |
| "step": 764 |
| }, |
| { |
| "entropy": 0.5383250862360001, |
| "epoch": 2.8552754435107377, |
| "grad_norm": 0.04291578382253647, |
| "learning_rate": 0.0002, |
| "loss": 0.5375620722770691, |
| "mean_token_accuracy": 0.7810464948415756, |
| "num_tokens": 12471352.0, |
| "step": 765 |
| }, |
| { |
| "entropy": 0.5423205345869064, |
| "epoch": 2.8590102707749767, |
| "grad_norm": 0.04575496166944504, |
| "learning_rate": 0.0002, |
| "loss": 0.5404216647148132, |
| "mean_token_accuracy": 0.7788951247930527, |
| "num_tokens": 12487810.0, |
| "step": 766 |
| }, |
| { |
| "entropy": 0.5412723869085312, |
| "epoch": 2.8627450980392157, |
| "grad_norm": 0.03895537182688713, |
| "learning_rate": 0.0002, |
| "loss": 0.5416159629821777, |
| "mean_token_accuracy": 0.7791194468736649, |
| "num_tokens": 12504261.0, |
| "step": 767 |
| }, |
| { |
| "entropy": 0.551712304353714, |
| "epoch": 2.8664799253034547, |
| "grad_norm": 0.04248276725411415, |
| "learning_rate": 0.0002, |
| "loss": 0.5512599945068359, |
| "mean_token_accuracy": 0.7787346094846725, |
| "num_tokens": 12520594.0, |
| "step": 768 |
| }, |
| { |
| "entropy": 0.5365375429391861, |
| "epoch": 2.8702147525676938, |
| "grad_norm": 0.0429382361471653, |
| "learning_rate": 0.0002, |
| "loss": 0.5369971990585327, |
| "mean_token_accuracy": 0.7795698195695877, |
| "num_tokens": 12537097.0, |
| "step": 769 |
| }, |
| { |
| "entropy": 0.5311344265937805, |
| "epoch": 2.8739495798319328, |
| "grad_norm": 0.03710220381617546, |
| "learning_rate": 0.0002, |
| "loss": 0.5327049493789673, |
| "mean_token_accuracy": 0.784042477607727, |
| "num_tokens": 12553319.0, |
| "step": 770 |
| }, |
| { |
| "entropy": 0.5425883233547211, |
| "epoch": 2.877684407096172, |
| "grad_norm": 0.04352175444364548, |
| "learning_rate": 0.0002, |
| "loss": 0.5457234382629395, |
| "mean_token_accuracy": 0.7795119434595108, |
| "num_tokens": 12569370.0, |
| "step": 771 |
| }, |
| { |
| "entropy": 0.5384223312139511, |
| "epoch": 2.881419234360411, |
| "grad_norm": 0.046248357743024826, |
| "learning_rate": 0.0002, |
| "loss": 0.5449962615966797, |
| "mean_token_accuracy": 0.7777050882577896, |
| "num_tokens": 12585550.0, |
| "step": 772 |
| }, |
| { |
| "entropy": 0.5304270684719086, |
| "epoch": 2.88515406162465, |
| "grad_norm": 0.03803584724664688, |
| "learning_rate": 0.0002, |
| "loss": 0.5308764576911926, |
| "mean_token_accuracy": 0.7852406352758408, |
| "num_tokens": 12601869.0, |
| "step": 773 |
| }, |
| { |
| "entropy": 0.5238187685608864, |
| "epoch": 2.888888888888889, |
| "grad_norm": 0.04374956712126732, |
| "learning_rate": 0.0002, |
| "loss": 0.5296017527580261, |
| "mean_token_accuracy": 0.7867107540369034, |
| "num_tokens": 12618133.0, |
| "step": 774 |
| }, |
| { |
| "entropy": 0.545166626572609, |
| "epoch": 2.892623716153128, |
| "grad_norm": 0.04235200583934784, |
| "learning_rate": 0.0002, |
| "loss": 0.5444045066833496, |
| "mean_token_accuracy": 0.7811264097690582, |
| "num_tokens": 12634590.0, |
| "step": 775 |
| }, |
| { |
| "entropy": 0.552961677312851, |
| "epoch": 2.896358543417367, |
| "grad_norm": 0.04033121094107628, |
| "learning_rate": 0.0002, |
| "loss": 0.5423647165298462, |
| "mean_token_accuracy": 0.7789802700281143, |
| "num_tokens": 12650990.0, |
| "step": 776 |
| }, |
| { |
| "entropy": 0.5362664610147476, |
| "epoch": 2.900093370681606, |
| "grad_norm": 0.039799049496650696, |
| "learning_rate": 0.0002, |
| "loss": 0.5340068340301514, |
| "mean_token_accuracy": 0.7801271975040436, |
| "num_tokens": 12667374.0, |
| "step": 777 |
| }, |
| { |
| "entropy": 0.540292888879776, |
| "epoch": 2.903828197945845, |
| "grad_norm": 0.04687785729765892, |
| "learning_rate": 0.0002, |
| "loss": 0.5417227149009705, |
| "mean_token_accuracy": 0.7800564914941788, |
| "num_tokens": 12683778.0, |
| "step": 778 |
| }, |
| { |
| "entropy": 0.5580530762672424, |
| "epoch": 2.907563025210084, |
| "grad_norm": 0.04104934632778168, |
| "learning_rate": 0.0002, |
| "loss": 0.553903341293335, |
| "mean_token_accuracy": 0.7754019796848297, |
| "num_tokens": 12700259.0, |
| "step": 779 |
| }, |
| { |
| "entropy": 0.5188224613666534, |
| "epoch": 2.911297852474323, |
| "grad_norm": 0.04876643791794777, |
| "learning_rate": 0.0002, |
| "loss": 0.525776207447052, |
| "mean_token_accuracy": 0.7853571325540543, |
| "num_tokens": 12716566.0, |
| "step": 780 |
| }, |
| { |
| "entropy": 0.5420665293931961, |
| "epoch": 2.915032679738562, |
| "grad_norm": 0.04760121926665306, |
| "learning_rate": 0.0002, |
| "loss": 0.5495279431343079, |
| "mean_token_accuracy": 0.7769062519073486, |
| "num_tokens": 12732949.0, |
| "step": 781 |
| }, |
| { |
| "entropy": 0.5393791049718857, |
| "epoch": 2.918767507002801, |
| "grad_norm": 0.0337008535861969, |
| "learning_rate": 0.0002, |
| "loss": 0.5375462174415588, |
| "mean_token_accuracy": 0.7824095785617828, |
| "num_tokens": 12749208.0, |
| "step": 782 |
| }, |
| { |
| "entropy": 0.5315912365913391, |
| "epoch": 2.9225023342670404, |
| "grad_norm": 0.04428756982088089, |
| "learning_rate": 0.0002, |
| "loss": 0.5206541419029236, |
| "mean_token_accuracy": 0.7908456176519394, |
| "num_tokens": 12765331.0, |
| "step": 783 |
| }, |
| { |
| "entropy": 0.5318206250667572, |
| "epoch": 2.9262371615312794, |
| "grad_norm": 0.04391348361968994, |
| "learning_rate": 0.0002, |
| "loss": 0.5263054370880127, |
| "mean_token_accuracy": 0.7842861711978912, |
| "num_tokens": 12781575.0, |
| "step": 784 |
| }, |
| { |
| "entropy": 0.5414671450853348, |
| "epoch": 2.9299719887955185, |
| "grad_norm": 0.03392143175005913, |
| "learning_rate": 0.0002, |
| "loss": 0.5417372584342957, |
| "mean_token_accuracy": 0.779655933380127, |
| "num_tokens": 12797804.0, |
| "step": 785 |
| }, |
| { |
| "entropy": 0.5150401219725609, |
| "epoch": 2.9337068160597575, |
| "grad_norm": 0.04989241063594818, |
| "learning_rate": 0.0002, |
| "loss": 0.5268764495849609, |
| "mean_token_accuracy": 0.7849253863096237, |
| "num_tokens": 12814387.0, |
| "step": 786 |
| }, |
| { |
| "entropy": 0.5104701817035675, |
| "epoch": 2.9374416433239965, |
| "grad_norm": 0.04267291724681854, |
| "learning_rate": 0.0002, |
| "loss": 0.5144373178482056, |
| "mean_token_accuracy": 0.7921061366796494, |
| "num_tokens": 12830547.0, |
| "step": 787 |
| }, |
| { |
| "entropy": 0.5301306545734406, |
| "epoch": 2.9411764705882355, |
| "grad_norm": 0.041861243546009064, |
| "learning_rate": 0.0002, |
| "loss": 0.5351182818412781, |
| "mean_token_accuracy": 0.7849584370851517, |
| "num_tokens": 12846796.0, |
| "step": 788 |
| }, |
| { |
| "entropy": 0.5566616058349609, |
| "epoch": 2.9449112978524745, |
| "grad_norm": 0.04726849123835564, |
| "learning_rate": 0.0002, |
| "loss": 0.5562955737113953, |
| "mean_token_accuracy": 0.7750595211982727, |
| "num_tokens": 12863231.0, |
| "step": 789 |
| }, |
| { |
| "entropy": 0.5550259649753571, |
| "epoch": 2.9486461251167135, |
| "grad_norm": 0.04144451022148132, |
| "learning_rate": 0.0002, |
| "loss": 0.5501708388328552, |
| "mean_token_accuracy": 0.7760492265224457, |
| "num_tokens": 12879599.0, |
| "step": 790 |
| }, |
| { |
| "entropy": 0.5439048856496811, |
| "epoch": 2.9523809523809526, |
| "grad_norm": 0.038411688059568405, |
| "learning_rate": 0.0002, |
| "loss": 0.5328619480133057, |
| "mean_token_accuracy": 0.7869621217250824, |
| "num_tokens": 12895954.0, |
| "step": 791 |
| }, |
| { |
| "entropy": 0.5426651537418365, |
| "epoch": 2.9561157796451916, |
| "grad_norm": 0.035909172147512436, |
| "learning_rate": 0.0002, |
| "loss": 0.5376070141792297, |
| "mean_token_accuracy": 0.7810229063034058, |
| "num_tokens": 12912468.0, |
| "step": 792 |
| }, |
| { |
| "entropy": 0.5385068506002426, |
| "epoch": 2.9598506069094306, |
| "grad_norm": 0.04422811418771744, |
| "learning_rate": 0.0002, |
| "loss": 0.5405643582344055, |
| "mean_token_accuracy": 0.7827010452747345, |
| "num_tokens": 12929047.0, |
| "step": 793 |
| }, |
| { |
| "entropy": 0.5246873497962952, |
| "epoch": 2.9635854341736696, |
| "grad_norm": 0.042685672640800476, |
| "learning_rate": 0.0002, |
| "loss": 0.537744402885437, |
| "mean_token_accuracy": 0.7845292538404465, |
| "num_tokens": 12945498.0, |
| "step": 794 |
| }, |
| { |
| "entropy": 0.534453883767128, |
| "epoch": 2.9673202614379086, |
| "grad_norm": 0.04630210995674133, |
| "learning_rate": 0.0002, |
| "loss": 0.5448824763298035, |
| "mean_token_accuracy": 0.7790633589029312, |
| "num_tokens": 12961911.0, |
| "step": 795 |
| }, |
| { |
| "entropy": 0.551120862364769, |
| "epoch": 2.9710550887021476, |
| "grad_norm": 0.038833893835544586, |
| "learning_rate": 0.0002, |
| "loss": 0.5517142415046692, |
| "mean_token_accuracy": 0.7771248668432236, |
| "num_tokens": 12978275.0, |
| "step": 796 |
| }, |
| { |
| "entropy": 0.540284737944603, |
| "epoch": 2.9747899159663866, |
| "grad_norm": 0.034402430057525635, |
| "learning_rate": 0.0002, |
| "loss": 0.5354663133621216, |
| "mean_token_accuracy": 0.7817137837409973, |
| "num_tokens": 12994610.0, |
| "step": 797 |
| }, |
| { |
| "entropy": 0.5466310381889343, |
| "epoch": 2.9785247432306257, |
| "grad_norm": 0.07181618362665176, |
| "learning_rate": 0.0002, |
| "loss": 0.5540565848350525, |
| "mean_token_accuracy": 0.7755098789930344, |
| "num_tokens": 13011180.0, |
| "step": 798 |
| }, |
| { |
| "entropy": 0.5366263538599014, |
| "epoch": 2.9822595704948647, |
| "grad_norm": 0.038452569395303726, |
| "learning_rate": 0.0002, |
| "loss": 0.5375447869300842, |
| "mean_token_accuracy": 0.7817091047763824, |
| "num_tokens": 13027553.0, |
| "step": 799 |
| }, |
| { |
| "entropy": 0.5117043852806091, |
| "epoch": 2.9859943977591037, |
| "grad_norm": 0.040419358760118484, |
| "learning_rate": 0.0002, |
| "loss": 0.5115300416946411, |
| "mean_token_accuracy": 0.7910782992839813, |
| "num_tokens": 13043466.0, |
| "step": 800 |
| }, |
| { |
| "entropy": 0.5549824833869934, |
| "epoch": 2.9897292250233427, |
| "grad_norm": 0.04015415534377098, |
| "learning_rate": 0.0002, |
| "loss": 0.5516586303710938, |
| "mean_token_accuracy": 0.7774178683757782, |
| "num_tokens": 13059980.0, |
| "step": 801 |
| }, |
| { |
| "entropy": 0.5470731258392334, |
| "epoch": 2.9934640522875817, |
| "grad_norm": 0.03732411563396454, |
| "learning_rate": 0.0002, |
| "loss": 0.5440268516540527, |
| "mean_token_accuracy": 0.7784831672906876, |
| "num_tokens": 13076305.0, |
| "step": 802 |
| }, |
| { |
| "entropy": 0.5496807992458344, |
| "epoch": 2.9971988795518207, |
| "grad_norm": 0.042060188949108124, |
| "learning_rate": 0.0002, |
| "loss": 0.5516492128372192, |
| "mean_token_accuracy": 0.7782593071460724, |
| "num_tokens": 13092596.0, |
| "step": 803 |
| }, |
| { |
| "entropy": 0.5623628298441569, |
| "epoch": 3.0, |
| "grad_norm": 0.04183833301067352, |
| "learning_rate": 0.0002, |
| "loss": 0.5470706820487976, |
| "mean_token_accuracy": 0.7766743898391724, |
| "num_tokens": 13094419.0, |
| "step": 804 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 804, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.2222761209723617e+18, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
