| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.702127659574468, |
| "eval_steps": 500, |
| "global_step": 4000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 2.933625968694687, |
| "epoch": 0.02127659574468085, |
| "grad_norm": 0.4740275740623474, |
| "learning_rate": 9.951e-05, |
| "loss": 4.140991821289062, |
| "mean_token_accuracy": 0.4264977302402258, |
| "num_tokens": 988301.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 2.962103115916252, |
| "epoch": 0.0425531914893617, |
| "grad_norm": 0.654786229133606, |
| "learning_rate": 9.901e-05, |
| "loss": 3.1859881591796877, |
| "mean_token_accuracy": 0.4919606515020132, |
| "num_tokens": 1981516.0, |
| "step": 100 |
| }, |
| { |
| "entropy": 2.8202617847919464, |
| "epoch": 0.06382978723404255, |
| "grad_norm": 0.6856227517127991, |
| "learning_rate": 9.851e-05, |
| "loss": 2.973466796875, |
| "mean_token_accuracy": 0.5133317831903697, |
| "num_tokens": 2962772.0, |
| "step": 150 |
| }, |
| { |
| "entropy": 2.692441967725754, |
| "epoch": 0.0851063829787234, |
| "grad_norm": 0.7118680477142334, |
| "learning_rate": 9.801e-05, |
| "loss": 2.8135525512695314, |
| "mean_token_accuracy": 0.5304926330596209, |
| "num_tokens": 3952403.0, |
| "step": 200 |
| }, |
| { |
| "entropy": 2.6121814751625063, |
| "epoch": 0.10638297872340426, |
| "grad_norm": 0.7034955620765686, |
| "learning_rate": 9.751e-05, |
| "loss": 2.715215148925781, |
| "mean_token_accuracy": 0.5413537514209747, |
| "num_tokens": 4939231.0, |
| "step": 250 |
| }, |
| { |
| "entropy": 2.551229443252087, |
| "epoch": 0.1276595744680851, |
| "grad_norm": 0.6356984972953796, |
| "learning_rate": 9.701e-05, |
| "loss": 2.6399871826171877, |
| "mean_token_accuracy": 0.55161267362535, |
| "num_tokens": 5931036.0, |
| "step": 300 |
| }, |
| { |
| "entropy": 2.471001845598221, |
| "epoch": 0.14893617021276595, |
| "grad_norm": 0.653047502040863, |
| "learning_rate": 9.651e-05, |
| "loss": 2.5464208984375, |
| "mean_token_accuracy": 0.5625544948130846, |
| "num_tokens": 6919236.0, |
| "step": 350 |
| }, |
| { |
| "entropy": 2.451621271967888, |
| "epoch": 0.1702127659574468, |
| "grad_norm": 0.7060537934303284, |
| "learning_rate": 9.601e-05, |
| "loss": 2.520094299316406, |
| "mean_token_accuracy": 0.5672792405635119, |
| "num_tokens": 7901385.0, |
| "step": 400 |
| }, |
| { |
| "entropy": 2.386715810596943, |
| "epoch": 0.19148936170212766, |
| "grad_norm": 0.7115684747695923, |
| "learning_rate": 9.551e-05, |
| "loss": 2.449301452636719, |
| "mean_token_accuracy": 0.5778872921317816, |
| "num_tokens": 8891410.0, |
| "step": 450 |
| }, |
| { |
| "entropy": 2.3399247616529464, |
| "epoch": 0.2127659574468085, |
| "grad_norm": 0.7020632028579712, |
| "learning_rate": 9.501e-05, |
| "loss": 2.3999610900878907, |
| "mean_token_accuracy": 0.5845850779861211, |
| "num_tokens": 9872429.0, |
| "step": 500 |
| }, |
| { |
| "entropy": 2.301297716200352, |
| "epoch": 0.23404255319148937, |
| "grad_norm": 0.7258976101875305, |
| "learning_rate": 9.451000000000002e-05, |
| "loss": 2.3609393310546873, |
| "mean_token_accuracy": 0.5889028573036194, |
| "num_tokens": 10852406.0, |
| "step": 550 |
| }, |
| { |
| "entropy": 2.28171086281538, |
| "epoch": 0.2553191489361702, |
| "grad_norm": 0.7619220018386841, |
| "learning_rate": 9.401e-05, |
| "loss": 2.32339111328125, |
| "mean_token_accuracy": 0.5941300053894519, |
| "num_tokens": 11847983.0, |
| "step": 600 |
| }, |
| { |
| "entropy": 2.2323903796076774, |
| "epoch": 0.2765957446808511, |
| "grad_norm": 0.7111139893531799, |
| "learning_rate": 9.351e-05, |
| "loss": 2.2743270874023436, |
| "mean_token_accuracy": 0.6003150211274624, |
| "num_tokens": 12839631.0, |
| "step": 650 |
| }, |
| { |
| "entropy": 2.195645292699337, |
| "epoch": 0.2978723404255319, |
| "grad_norm": 0.8029466867446899, |
| "learning_rate": 9.301e-05, |
| "loss": 2.2373281860351564, |
| "mean_token_accuracy": 0.605772587954998, |
| "num_tokens": 13825421.0, |
| "step": 700 |
| }, |
| { |
| "entropy": 2.1788447910547255, |
| "epoch": 0.3191489361702128, |
| "grad_norm": 0.7066243290901184, |
| "learning_rate": 9.251000000000001e-05, |
| "loss": 2.2124517822265624, |
| "mean_token_accuracy": 0.6105387426912785, |
| "num_tokens": 14811783.0, |
| "step": 750 |
| }, |
| { |
| "entropy": 2.140341859459877, |
| "epoch": 0.3404255319148936, |
| "grad_norm": 0.6823806166648865, |
| "learning_rate": 9.201000000000001e-05, |
| "loss": 2.175841064453125, |
| "mean_token_accuracy": 0.615707865729928, |
| "num_tokens": 15799402.0, |
| "step": 800 |
| }, |
| { |
| "entropy": 2.121108899116516, |
| "epoch": 0.3617021276595745, |
| "grad_norm": 0.7394977807998657, |
| "learning_rate": 9.151000000000001e-05, |
| "loss": 2.1485189819335937, |
| "mean_token_accuracy": 0.6186434020847082, |
| "num_tokens": 16787125.0, |
| "step": 850 |
| }, |
| { |
| "entropy": 2.092526486814022, |
| "epoch": 0.3829787234042553, |
| "grad_norm": 0.7025715112686157, |
| "learning_rate": 9.101000000000001e-05, |
| "loss": 2.1199916076660155, |
| "mean_token_accuracy": 0.6228454371541738, |
| "num_tokens": 17783798.0, |
| "step": 900 |
| }, |
| { |
| "entropy": 2.0856992295384407, |
| "epoch": 0.40425531914893614, |
| "grad_norm": 0.726789653301239, |
| "learning_rate": 9.051000000000001e-05, |
| "loss": 2.1102699279785155, |
| "mean_token_accuracy": 0.6247553788125515, |
| "num_tokens": 18760192.0, |
| "step": 950 |
| }, |
| { |
| "entropy": 2.0423195973038673, |
| "epoch": 0.425531914893617, |
| "grad_norm": 0.7402950525283813, |
| "learning_rate": 9.001e-05, |
| "loss": 2.059694519042969, |
| "mean_token_accuracy": 0.6303426054865122, |
| "num_tokens": 19742108.0, |
| "step": 1000 |
| }, |
| { |
| "entropy": 2.016712465286255, |
| "epoch": 0.44680851063829785, |
| "grad_norm": 0.7215949296951294, |
| "learning_rate": 8.951e-05, |
| "loss": 2.034037780761719, |
| "mean_token_accuracy": 0.6353059864044189, |
| "num_tokens": 20731616.0, |
| "step": 1050 |
| }, |
| { |
| "entropy": 2.007916229367256, |
| "epoch": 0.46808510638297873, |
| "grad_norm": 0.7003784775733948, |
| "learning_rate": 8.901e-05, |
| "loss": 2.027302093505859, |
| "mean_token_accuracy": 0.6354308243095875, |
| "num_tokens": 21722968.0, |
| "step": 1100 |
| }, |
| { |
| "entropy": 1.9942936185002327, |
| "epoch": 0.48936170212765956, |
| "grad_norm": 0.7140076756477356, |
| "learning_rate": 8.851e-05, |
| "loss": 2.005096740722656, |
| "mean_token_accuracy": 0.6390834471583366, |
| "num_tokens": 22710001.0, |
| "step": 1150 |
| }, |
| { |
| "entropy": 1.9797486934065818, |
| "epoch": 0.5106382978723404, |
| "grad_norm": 0.7416248321533203, |
| "learning_rate": 8.801e-05, |
| "loss": 1.9921502685546875, |
| "mean_token_accuracy": 0.6417897816002369, |
| "num_tokens": 23701962.0, |
| "step": 1200 |
| }, |
| { |
| "entropy": 1.964172384738922, |
| "epoch": 0.5319148936170213, |
| "grad_norm": 0.7284294366836548, |
| "learning_rate": 8.751000000000001e-05, |
| "loss": 1.973612060546875, |
| "mean_token_accuracy": 0.6431643936038017, |
| "num_tokens": 24691069.0, |
| "step": 1250 |
| }, |
| { |
| "entropy": 1.9607124796509743, |
| "epoch": 0.5531914893617021, |
| "grad_norm": 0.7417468428611755, |
| "learning_rate": 8.701000000000001e-05, |
| "loss": 1.96802734375, |
| "mean_token_accuracy": 0.6438394567370415, |
| "num_tokens": 25672575.0, |
| "step": 1300 |
| }, |
| { |
| "entropy": 1.9377746772766113, |
| "epoch": 0.574468085106383, |
| "grad_norm": 0.7281346917152405, |
| "learning_rate": 8.651e-05, |
| "loss": 1.943411865234375, |
| "mean_token_accuracy": 0.6475014618039131, |
| "num_tokens": 26650468.0, |
| "step": 1350 |
| }, |
| { |
| "entropy": 1.9116359001398087, |
| "epoch": 0.5957446808510638, |
| "grad_norm": 0.7411175966262817, |
| "learning_rate": 8.601e-05, |
| "loss": 1.9105075073242188, |
| "mean_token_accuracy": 0.6522348903119564, |
| "num_tokens": 27637622.0, |
| "step": 1400 |
| }, |
| { |
| "entropy": 1.8855691528320313, |
| "epoch": 0.6170212765957447, |
| "grad_norm": 0.8132097125053406, |
| "learning_rate": 8.551e-05, |
| "loss": 1.8883074951171874, |
| "mean_token_accuracy": 0.6555898541212082, |
| "num_tokens": 28616054.0, |
| "step": 1450 |
| }, |
| { |
| "entropy": 1.8665929993987083, |
| "epoch": 0.6382978723404256, |
| "grad_norm": 0.7487557530403137, |
| "learning_rate": 8.501e-05, |
| "loss": 1.8706964111328126, |
| "mean_token_accuracy": 0.6584339791536331, |
| "num_tokens": 29599749.0, |
| "step": 1500 |
| }, |
| { |
| "entropy": 1.8867433726787568, |
| "epoch": 0.6595744680851063, |
| "grad_norm": 0.7766140699386597, |
| "learning_rate": 8.451e-05, |
| "loss": 1.87984619140625, |
| "mean_token_accuracy": 0.6557563903927803, |
| "num_tokens": 30582882.0, |
| "step": 1550 |
| }, |
| { |
| "entropy": 1.8374861231446267, |
| "epoch": 0.6808510638297872, |
| "grad_norm": 0.7314454913139343, |
| "learning_rate": 8.401e-05, |
| "loss": 1.831165771484375, |
| "mean_token_accuracy": 0.6637911826372147, |
| "num_tokens": 31569352.0, |
| "step": 1600 |
| }, |
| { |
| "entropy": 1.8532386475801468, |
| "epoch": 0.7021276595744681, |
| "grad_norm": 0.7259364724159241, |
| "learning_rate": 8.351e-05, |
| "loss": 1.8480484008789062, |
| "mean_token_accuracy": 0.6606452398002147, |
| "num_tokens": 32558924.0, |
| "step": 1650 |
| }, |
| { |
| "entropy": 1.8135097181797029, |
| "epoch": 0.723404255319149, |
| "grad_norm": 0.7797704935073853, |
| "learning_rate": 8.300999999999999e-05, |
| "loss": 1.8081503295898438, |
| "mean_token_accuracy": 0.6658144837617874, |
| "num_tokens": 33538173.0, |
| "step": 1700 |
| }, |
| { |
| "entropy": 1.8098896679282188, |
| "epoch": 0.7446808510638298, |
| "grad_norm": 0.7669138312339783, |
| "learning_rate": 8.251e-05, |
| "loss": 1.8036175537109376, |
| "mean_token_accuracy": 0.6678015381097794, |
| "num_tokens": 34527677.0, |
| "step": 1750 |
| }, |
| { |
| "entropy": 1.834512955248356, |
| "epoch": 0.7659574468085106, |
| "grad_norm": 0.7591897249221802, |
| "learning_rate": 8.201000000000001e-05, |
| "loss": 1.8277191162109374, |
| "mean_token_accuracy": 0.6645957937836647, |
| "num_tokens": 35501027.0, |
| "step": 1800 |
| }, |
| { |
| "entropy": 1.8174273499846458, |
| "epoch": 0.7872340425531915, |
| "grad_norm": 0.7456106543540955, |
| "learning_rate": 8.151000000000001e-05, |
| "loss": 1.80675048828125, |
| "mean_token_accuracy": 0.6679648634791374, |
| "num_tokens": 36479113.0, |
| "step": 1850 |
| }, |
| { |
| "entropy": 1.8021713918447495, |
| "epoch": 0.8085106382978723, |
| "grad_norm": 0.7157758474349976, |
| "learning_rate": 8.101000000000001e-05, |
| "loss": 1.7929193115234374, |
| "mean_token_accuracy": 0.6698202560842037, |
| "num_tokens": 37468821.0, |
| "step": 1900 |
| }, |
| { |
| "entropy": 1.767222127020359, |
| "epoch": 0.8297872340425532, |
| "grad_norm": 0.8157340884208679, |
| "learning_rate": 8.051000000000001e-05, |
| "loss": 1.7558590698242187, |
| "mean_token_accuracy": 0.676178140938282, |
| "num_tokens": 38456154.0, |
| "step": 1950 |
| }, |
| { |
| "entropy": 1.7760261020064354, |
| "epoch": 0.851063829787234, |
| "grad_norm": 0.6800106167793274, |
| "learning_rate": 8.001e-05, |
| "loss": 1.757685546875, |
| "mean_token_accuracy": 0.6744833959639073, |
| "num_tokens": 39440483.0, |
| "step": 2000 |
| }, |
| { |
| "entropy": 1.764250594675541, |
| "epoch": 0.8723404255319149, |
| "grad_norm": 0.7506063580513, |
| "learning_rate": 7.951e-05, |
| "loss": 1.7482571411132812, |
| "mean_token_accuracy": 0.6752947215735913, |
| "num_tokens": 40425735.0, |
| "step": 2050 |
| }, |
| { |
| "entropy": 1.7635737213492393, |
| "epoch": 0.8936170212765957, |
| "grad_norm": 0.7649574279785156, |
| "learning_rate": 7.901e-05, |
| "loss": 1.7502963256835937, |
| "mean_token_accuracy": 0.6766997446119786, |
| "num_tokens": 41416623.0, |
| "step": 2100 |
| }, |
| { |
| "entropy": 1.7378215923905374, |
| "epoch": 0.9148936170212766, |
| "grad_norm": 0.7321686744689941, |
| "learning_rate": 7.851e-05, |
| "loss": 1.7229681396484375, |
| "mean_token_accuracy": 0.6783718758821488, |
| "num_tokens": 42407921.0, |
| "step": 2150 |
| }, |
| { |
| "entropy": 1.720134773850441, |
| "epoch": 0.9361702127659575, |
| "grad_norm": 0.7562823295593262, |
| "learning_rate": 7.801000000000001e-05, |
| "loss": 1.7002345275878907, |
| "mean_token_accuracy": 0.6815671770274639, |
| "num_tokens": 43394397.0, |
| "step": 2200 |
| }, |
| { |
| "entropy": 1.7291932779550552, |
| "epoch": 0.9574468085106383, |
| "grad_norm": 0.746076762676239, |
| "learning_rate": 7.751000000000001e-05, |
| "loss": 1.7090219116210938, |
| "mean_token_accuracy": 0.6812707696855068, |
| "num_tokens": 44375854.0, |
| "step": 2250 |
| }, |
| { |
| "entropy": 1.720713329911232, |
| "epoch": 0.9787234042553191, |
| "grad_norm": 0.770660936832428, |
| "learning_rate": 7.701000000000001e-05, |
| "loss": 1.7028382873535157, |
| "mean_token_accuracy": 0.6824209858477116, |
| "num_tokens": 45371344.0, |
| "step": 2300 |
| }, |
| { |
| "entropy": 1.6982364651560784, |
| "epoch": 1.0, |
| "grad_norm": 0.7889444828033447, |
| "learning_rate": 7.651e-05, |
| "loss": 1.6777915954589844, |
| "mean_token_accuracy": 0.6852045242488384, |
| "num_tokens": 46351878.0, |
| "step": 2350 |
| }, |
| { |
| "entropy": 1.6709844982624054, |
| "epoch": 1.0212765957446808, |
| "grad_norm": 0.7106631398200989, |
| "learning_rate": 7.601e-05, |
| "loss": 1.6406138610839844, |
| "mean_token_accuracy": 0.6904737217724324, |
| "num_tokens": 47341427.0, |
| "step": 2400 |
| }, |
| { |
| "entropy": 1.6589670392870903, |
| "epoch": 1.0425531914893618, |
| "grad_norm": 0.7608166933059692, |
| "learning_rate": 7.551e-05, |
| "loss": 1.6304428100585937, |
| "mean_token_accuracy": 0.6913493700325489, |
| "num_tokens": 48322894.0, |
| "step": 2450 |
| }, |
| { |
| "entropy": 1.6474245920777322, |
| "epoch": 1.0638297872340425, |
| "grad_norm": 0.7659543752670288, |
| "learning_rate": 7.501e-05, |
| "loss": 1.6174127197265624, |
| "mean_token_accuracy": 0.693988469094038, |
| "num_tokens": 49309778.0, |
| "step": 2500 |
| }, |
| { |
| "entropy": 1.625294875204563, |
| "epoch": 1.0851063829787233, |
| "grad_norm": 0.7219650745391846, |
| "learning_rate": 7.451e-05, |
| "loss": 1.5934686279296875, |
| "mean_token_accuracy": 0.6972348481416702, |
| "num_tokens": 50292124.0, |
| "step": 2550 |
| }, |
| { |
| "entropy": 1.6406617045402527, |
| "epoch": 1.1063829787234043, |
| "grad_norm": 0.7679393291473389, |
| "learning_rate": 7.401e-05, |
| "loss": 1.6113711547851564, |
| "mean_token_accuracy": 0.6941907967627049, |
| "num_tokens": 51269742.0, |
| "step": 2600 |
| }, |
| { |
| "entropy": 1.6265540924668311, |
| "epoch": 1.127659574468085, |
| "grad_norm": 0.7457160949707031, |
| "learning_rate": 7.351e-05, |
| "loss": 1.600107421875, |
| "mean_token_accuracy": 0.6962076690793038, |
| "num_tokens": 52262686.0, |
| "step": 2650 |
| }, |
| { |
| "entropy": 1.6291374132037162, |
| "epoch": 1.148936170212766, |
| "grad_norm": 0.8142237067222595, |
| "learning_rate": 7.301e-05, |
| "loss": 1.5976341247558594, |
| "mean_token_accuracy": 0.695648788511753, |
| "num_tokens": 53248843.0, |
| "step": 2700 |
| }, |
| { |
| "entropy": 1.6227850529551506, |
| "epoch": 1.1702127659574468, |
| "grad_norm": 0.7628965377807617, |
| "learning_rate": 7.251e-05, |
| "loss": 1.5930337524414062, |
| "mean_token_accuracy": 0.6979775196313858, |
| "num_tokens": 54241409.0, |
| "step": 2750 |
| }, |
| { |
| "entropy": 1.6028004956245423, |
| "epoch": 1.1914893617021276, |
| "grad_norm": 0.7493979334831238, |
| "learning_rate": 7.201e-05, |
| "loss": 1.5724569702148437, |
| "mean_token_accuracy": 0.6999971604347229, |
| "num_tokens": 55231488.0, |
| "step": 2800 |
| }, |
| { |
| "entropy": 1.616425441801548, |
| "epoch": 1.2127659574468086, |
| "grad_norm": 0.7527705430984497, |
| "learning_rate": 7.151e-05, |
| "loss": 1.5838508605957031, |
| "mean_token_accuracy": 0.6987825597822667, |
| "num_tokens": 56214657.0, |
| "step": 2850 |
| }, |
| { |
| "entropy": 1.6064529752731322, |
| "epoch": 1.2340425531914894, |
| "grad_norm": 0.744288444519043, |
| "learning_rate": 7.101e-05, |
| "loss": 1.5755838012695313, |
| "mean_token_accuracy": 0.6994880273938179, |
| "num_tokens": 57199159.0, |
| "step": 2900 |
| }, |
| { |
| "entropy": 1.5955200618505478, |
| "epoch": 1.2553191489361701, |
| "grad_norm": 0.7527694702148438, |
| "learning_rate": 7.051e-05, |
| "loss": 1.5658992004394532, |
| "mean_token_accuracy": 0.701285338550806, |
| "num_tokens": 58173001.0, |
| "step": 2950 |
| }, |
| { |
| "entropy": 1.5903715097904205, |
| "epoch": 1.2765957446808511, |
| "grad_norm": 0.7520326972007751, |
| "learning_rate": 7.001e-05, |
| "loss": 1.5549607849121094, |
| "mean_token_accuracy": 0.701934365928173, |
| "num_tokens": 59164486.0, |
| "step": 3000 |
| }, |
| { |
| "entropy": 1.577785237133503, |
| "epoch": 1.297872340425532, |
| "grad_norm": 0.7289667725563049, |
| "learning_rate": 6.951e-05, |
| "loss": 1.5484317016601563, |
| "mean_token_accuracy": 0.7029052957892418, |
| "num_tokens": 60154400.0, |
| "step": 3050 |
| }, |
| { |
| "entropy": 1.6015404342114925, |
| "epoch": 1.3191489361702127, |
| "grad_norm": 0.7111889719963074, |
| "learning_rate": 6.901e-05, |
| "loss": 1.567227325439453, |
| "mean_token_accuracy": 0.6997377443313598, |
| "num_tokens": 61135725.0, |
| "step": 3100 |
| }, |
| { |
| "entropy": 1.5653481243550778, |
| "epoch": 1.3404255319148937, |
| "grad_norm": 0.7378498911857605, |
| "learning_rate": 6.851e-05, |
| "loss": 1.5351031494140626, |
| "mean_token_accuracy": 0.7058432798087597, |
| "num_tokens": 62114114.0, |
| "step": 3150 |
| }, |
| { |
| "entropy": 1.5650252343714237, |
| "epoch": 1.3617021276595744, |
| "grad_norm": 0.8165695667266846, |
| "learning_rate": 6.801000000000001e-05, |
| "loss": 1.5345574951171874, |
| "mean_token_accuracy": 0.7055312724411488, |
| "num_tokens": 63102105.0, |
| "step": 3200 |
| }, |
| { |
| "entropy": 1.565962330698967, |
| "epoch": 1.3829787234042552, |
| "grad_norm": 0.7475385665893555, |
| "learning_rate": 6.751000000000001e-05, |
| "loss": 1.532633056640625, |
| "mean_token_accuracy": 0.7054442183673382, |
| "num_tokens": 64092884.0, |
| "step": 3250 |
| }, |
| { |
| "entropy": 1.5736293095350264, |
| "epoch": 1.4042553191489362, |
| "grad_norm": 0.7410607933998108, |
| "learning_rate": 6.701000000000001e-05, |
| "loss": 1.5408993530273438, |
| "mean_token_accuracy": 0.7043556262552738, |
| "num_tokens": 65077460.0, |
| "step": 3300 |
| }, |
| { |
| "entropy": 1.5616717764735222, |
| "epoch": 1.425531914893617, |
| "grad_norm": 0.7586492896080017, |
| "learning_rate": 6.651000000000001e-05, |
| "loss": 1.52689453125, |
| "mean_token_accuracy": 0.7062550820410252, |
| "num_tokens": 66073937.0, |
| "step": 3350 |
| }, |
| { |
| "entropy": 1.557564342021942, |
| "epoch": 1.4468085106382977, |
| "grad_norm": 0.7810468673706055, |
| "learning_rate": 6.601e-05, |
| "loss": 1.5238162231445314, |
| "mean_token_accuracy": 0.7069078533351422, |
| "num_tokens": 67061606.0, |
| "step": 3400 |
| }, |
| { |
| "entropy": 1.5599790331721306, |
| "epoch": 1.4680851063829787, |
| "grad_norm": 0.7768591046333313, |
| "learning_rate": 6.551e-05, |
| "loss": 1.527623748779297, |
| "mean_token_accuracy": 0.7075633393228054, |
| "num_tokens": 68050209.0, |
| "step": 3450 |
| }, |
| { |
| "entropy": 1.5402766379714012, |
| "epoch": 1.4893617021276595, |
| "grad_norm": 0.7596350908279419, |
| "learning_rate": 6.501e-05, |
| "loss": 1.5053843688964843, |
| "mean_token_accuracy": 0.709761653393507, |
| "num_tokens": 69043340.0, |
| "step": 3500 |
| }, |
| { |
| "entropy": 1.5391169971227645, |
| "epoch": 1.5106382978723403, |
| "grad_norm": 0.7082200050354004, |
| "learning_rate": 6.451e-05, |
| "loss": 1.5009793090820311, |
| "mean_token_accuracy": 0.7094894219934941, |
| "num_tokens": 70028141.0, |
| "step": 3550 |
| }, |
| { |
| "entropy": 1.5485185173153877, |
| "epoch": 1.5319148936170213, |
| "grad_norm": 0.7340750098228455, |
| "learning_rate": 6.401e-05, |
| "loss": 1.5126968383789063, |
| "mean_token_accuracy": 0.7095904792845249, |
| "num_tokens": 71021512.0, |
| "step": 3600 |
| }, |
| { |
| "entropy": 1.5227306772768499, |
| "epoch": 1.5531914893617023, |
| "grad_norm": 0.7728723287582397, |
| "learning_rate": 6.351000000000001e-05, |
| "loss": 1.4854464721679688, |
| "mean_token_accuracy": 0.7113837064802646, |
| "num_tokens": 72010002.0, |
| "step": 3650 |
| }, |
| { |
| "entropy": 1.5513358226418494, |
| "epoch": 1.574468085106383, |
| "grad_norm": 0.7605530023574829, |
| "learning_rate": 6.301000000000001e-05, |
| "loss": 1.5147122192382811, |
| "mean_token_accuracy": 0.7083025954663753, |
| "num_tokens": 72997531.0, |
| "step": 3700 |
| }, |
| { |
| "entropy": 1.5391620790958405, |
| "epoch": 1.5957446808510638, |
| "grad_norm": 0.7805915474891663, |
| "learning_rate": 6.251e-05, |
| "loss": 1.5053895568847657, |
| "mean_token_accuracy": 0.7098572531342506, |
| "num_tokens": 73981617.0, |
| "step": 3750 |
| }, |
| { |
| "entropy": 1.5519435784220696, |
| "epoch": 1.6170212765957448, |
| "grad_norm": 0.7576701045036316, |
| "learning_rate": 6.201e-05, |
| "loss": 1.5180355834960937, |
| "mean_token_accuracy": 0.7073439501225949, |
| "num_tokens": 74975613.0, |
| "step": 3800 |
| }, |
| { |
| "entropy": 1.5172939459979533, |
| "epoch": 1.6382978723404256, |
| "grad_norm": 0.7765750288963318, |
| "learning_rate": 6.151e-05, |
| "loss": 1.4821212768554688, |
| "mean_token_accuracy": 0.7136698444187641, |
| "num_tokens": 75966971.0, |
| "step": 3850 |
| }, |
| { |
| "entropy": 1.5298295491933822, |
| "epoch": 1.6595744680851063, |
| "grad_norm": 0.7504763007164001, |
| "learning_rate": 6.101e-05, |
| "loss": 1.492011260986328, |
| "mean_token_accuracy": 0.7108374397456646, |
| "num_tokens": 76950920.0, |
| "step": 3900 |
| }, |
| { |
| "entropy": 1.5399506105482579, |
| "epoch": 1.6808510638297873, |
| "grad_norm": 0.7663020491600037, |
| "learning_rate": 6.051e-05, |
| "loss": 1.5039883422851563, |
| "mean_token_accuracy": 0.7101991818845272, |
| "num_tokens": 77939066.0, |
| "step": 3950 |
| }, |
| { |
| "entropy": 1.5202897056937217, |
| "epoch": 1.702127659574468, |
| "grad_norm": 0.8080466985702515, |
| "learning_rate": 6.0009999999999996e-05, |
| "loss": 1.485948028564453, |
| "mean_token_accuracy": 0.7131342147290707, |
| "num_tokens": 78916374.0, |
| "step": 4000 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 10000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 1000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 5.994971121907139e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
