| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 625, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016, | |
| "grad_norm": 0.43310171365737915, | |
| "learning_rate": 3.1746031746031746e-06, | |
| "loss": 0.2682, | |
| "mean_token_accuracy": 0.9273857176303864, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008, | |
| "grad_norm": 0.8490898609161377, | |
| "learning_rate": 1.5873015873015872e-05, | |
| "loss": 0.3388, | |
| "mean_token_accuracy": 0.9119045659899712, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.016, | |
| "grad_norm": 0.34499526023864746, | |
| "learning_rate": 3.1746031746031745e-05, | |
| "loss": 0.3481, | |
| "mean_token_accuracy": 0.9102882027626038, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.024, | |
| "grad_norm": 0.285628080368042, | |
| "learning_rate": 4.761904761904762e-05, | |
| "loss": 0.2976, | |
| "mean_token_accuracy": 0.9188290774822235, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.032, | |
| "grad_norm": 0.16985873878002167, | |
| "learning_rate": 6.349206349206349e-05, | |
| "loss": 0.257, | |
| "mean_token_accuracy": 0.923795086145401, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.16013243794441223, | |
| "learning_rate": 7.936507936507937e-05, | |
| "loss": 0.2077, | |
| "mean_token_accuracy": 0.9377835214138031, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.048, | |
| "grad_norm": 0.17801596224308014, | |
| "learning_rate": 9.523809523809524e-05, | |
| "loss": 0.2022, | |
| "mean_token_accuracy": 0.9342319130897522, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.056, | |
| "grad_norm": 0.12985391914844513, | |
| "learning_rate": 0.00011111111111111112, | |
| "loss": 0.1644, | |
| "mean_token_accuracy": 0.9495729327201843, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "grad_norm": 0.16224823892116547, | |
| "learning_rate": 0.00012698412698412698, | |
| "loss": 0.1243, | |
| "mean_token_accuracy": 0.9592924535274505, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.072, | |
| "grad_norm": 0.12580786645412445, | |
| "learning_rate": 0.00014285714285714287, | |
| "loss": 0.101, | |
| "mean_token_accuracy": 0.9631378591060639, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.12046530097723007, | |
| "learning_rate": 0.00015873015873015873, | |
| "loss": 0.0813, | |
| "mean_token_accuracy": 0.9683941245079041, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.088, | |
| "grad_norm": 0.12417536973953247, | |
| "learning_rate": 0.00017460317460317462, | |
| "loss": 0.0586, | |
| "mean_token_accuracy": 0.9767989754676819, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "grad_norm": 0.13074961304664612, | |
| "learning_rate": 0.00019047619047619048, | |
| "loss": 0.0637, | |
| "mean_token_accuracy": 0.9737584054470062, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.104, | |
| "grad_norm": 0.12429118901491165, | |
| "learning_rate": 0.00019999375039475277, | |
| "loss": 0.0537, | |
| "mean_token_accuracy": 0.9769091963768005, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.112, | |
| "grad_norm": 0.11161642521619797, | |
| "learning_rate": 0.0001999234513064475, | |
| "loss": 0.0486, | |
| "mean_token_accuracy": 0.9791503012180328, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.09909889847040176, | |
| "learning_rate": 0.00019977509622105233, | |
| "loss": 0.044, | |
| "mean_token_accuracy": 0.981050831079483, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.128, | |
| "grad_norm": 0.07484742999076843, | |
| "learning_rate": 0.0001995488010273198, | |
| "loss": 0.0431, | |
| "mean_token_accuracy": 0.9817534804344177, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.136, | |
| "grad_norm": 0.08371058106422424, | |
| "learning_rate": 0.00019924474249753655, | |
| "loss": 0.0441, | |
| "mean_token_accuracy": 0.9811403095722199, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.144, | |
| "grad_norm": 0.08213909715414047, | |
| "learning_rate": 0.00019886315814943647, | |
| "loss": 0.0385, | |
| "mean_token_accuracy": 0.9830973207950592, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.152, | |
| "grad_norm": 0.07752417027950287, | |
| "learning_rate": 0.0001984043460606618, | |
| "loss": 0.0442, | |
| "mean_token_accuracy": 0.9807018160820007, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.07620657980442047, | |
| "learning_rate": 0.0001978686646359173, | |
| "loss": 0.0392, | |
| "mean_token_accuracy": 0.982789009809494, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.168, | |
| "grad_norm": 0.083968386054039, | |
| "learning_rate": 0.0001972565323269996, | |
| "loss": 0.0373, | |
| "mean_token_accuracy": 0.9836896479129791, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.176, | |
| "grad_norm": 0.051836077123880386, | |
| "learning_rate": 0.00019656842730592046, | |
| "loss": 0.0407, | |
| "mean_token_accuracy": 0.9821825683116913, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.184, | |
| "grad_norm": 0.07549381256103516, | |
| "learning_rate": 0.0001958048870913786, | |
| "loss": 0.038, | |
| "mean_token_accuracy": 0.9829850435256958, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.192, | |
| "grad_norm": 0.05420655012130737, | |
| "learning_rate": 0.0001949665081288729, | |
| "loss": 0.0347, | |
| "mean_token_accuracy": 0.9851674497127533, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.06140986829996109, | |
| "learning_rate": 0.00019405394532478424, | |
| "loss": 0.033, | |
| "mean_token_accuracy": 0.9853869795799255, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.208, | |
| "grad_norm": 0.06693119555711746, | |
| "learning_rate": 0.00019306791153479006, | |
| "loss": 0.0404, | |
| "mean_token_accuracy": 0.9823243021965027, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.216, | |
| "grad_norm": 0.08230168372392654, | |
| "learning_rate": 0.00019200917700701176, | |
| "loss": 0.0369, | |
| "mean_token_accuracy": 0.9838479280471801, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.224, | |
| "grad_norm": 0.06229570508003235, | |
| "learning_rate": 0.0001908785687803289, | |
| "loss": 0.0373, | |
| "mean_token_accuracy": 0.9834259986877442, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.232, | |
| "grad_norm": 0.06680244952440262, | |
| "learning_rate": 0.00018967697003833157, | |
| "loss": 0.0383, | |
| "mean_token_accuracy": 0.9826522827148437, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.061888325959444046, | |
| "learning_rate": 0.0001884053194194142, | |
| "loss": 0.0329, | |
| "mean_token_accuracy": 0.9850789308547974, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.248, | |
| "grad_norm": 0.06167807802557945, | |
| "learning_rate": 0.00018706461028355104, | |
| "loss": 0.0349, | |
| "mean_token_accuracy": 0.9847366988658905, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.256, | |
| "grad_norm": 0.051647648215293884, | |
| "learning_rate": 0.00018565588993632487, | |
| "loss": 0.0435, | |
| "mean_token_accuracy": 0.9802697420120239, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.264, | |
| "grad_norm": 0.06429916620254517, | |
| "learning_rate": 0.0001841802588108161, | |
| "loss": 0.036, | |
| "mean_token_accuracy": 0.983528858423233, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.272, | |
| "grad_norm": 0.07308773696422577, | |
| "learning_rate": 0.00018263886960799062, | |
| "loss": 0.0365, | |
| "mean_token_accuracy": 0.983112233877182, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.05631113797426224, | |
| "learning_rate": 0.00018103292639625837, | |
| "loss": 0.0363, | |
| "mean_token_accuracy": 0.9835257828235626, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.288, | |
| "grad_norm": 0.07624773681163788, | |
| "learning_rate": 0.0001793636836709057, | |
| "loss": 0.0353, | |
| "mean_token_accuracy": 0.9840705871582032, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.296, | |
| "grad_norm": 0.05333884805440903, | |
| "learning_rate": 0.0001776324453741365, | |
| "loss": 0.0325, | |
| "mean_token_accuracy": 0.985572201013565, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.304, | |
| "grad_norm": 0.05988354608416557, | |
| "learning_rate": 0.00017584056387648727, | |
| "loss": 0.0382, | |
| "mean_token_accuracy": 0.982496690750122, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.312, | |
| "grad_norm": 0.05714619532227516, | |
| "learning_rate": 0.0001739894389204122, | |
| "loss": 0.0354, | |
| "mean_token_accuracy": 0.9839600920677185, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.05059760436415672, | |
| "learning_rate": 0.00017208051652686335, | |
| "loss": 0.0349, | |
| "mean_token_accuracy": 0.984496396780014, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.328, | |
| "grad_norm": 0.07071304321289062, | |
| "learning_rate": 0.00017011528786571969, | |
| "loss": 0.0305, | |
| "mean_token_accuracy": 0.9868167281150818, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.336, | |
| "grad_norm": 0.05378766357898712, | |
| "learning_rate": 0.00016809528809094807, | |
| "loss": 0.0353, | |
| "mean_token_accuracy": 0.9841848373413086, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.344, | |
| "grad_norm": 0.06888769567012787, | |
| "learning_rate": 0.0001660220951414055, | |
| "loss": 0.0331, | |
| "mean_token_accuracy": 0.9852972328662872, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.352, | |
| "grad_norm": 0.06159176304936409, | |
| "learning_rate": 0.00016389732850821966, | |
| "loss": 0.0328, | |
| "mean_token_accuracy": 0.9849840342998505, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.05890626460313797, | |
| "learning_rate": 0.0001617226479697105, | |
| "loss": 0.0318, | |
| "mean_token_accuracy": 0.9859302580356598, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.368, | |
| "grad_norm": 0.06155586987733841, | |
| "learning_rate": 0.00015949975229484134, | |
| "loss": 0.0367, | |
| "mean_token_accuracy": 0.9838493525981903, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.376, | |
| "grad_norm": 0.050045762211084366, | |
| "learning_rate": 0.00015723037791621193, | |
| "loss": 0.0325, | |
| "mean_token_accuracy": 0.9856610596179962, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.384, | |
| "grad_norm": 0.05855004861950874, | |
| "learning_rate": 0.00015491629757363032, | |
| "loss": 0.0312, | |
| "mean_token_accuracy": 0.9855502784252167, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.392, | |
| "grad_norm": 0.08005663007497787, | |
| "learning_rate": 0.00015255931892932333, | |
| "loss": 0.031, | |
| "mean_token_accuracy": 0.9869074642658233, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.061815045773983, | |
| "learning_rate": 0.0001501612831558664, | |
| "loss": 0.0366, | |
| "mean_token_accuracy": 0.983307272195816, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.408, | |
| "grad_norm": 0.0681883841753006, | |
| "learning_rate": 0.00014772406349793744, | |
| "loss": 0.0317, | |
| "mean_token_accuracy": 0.9858060896396637, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.416, | |
| "grad_norm": 0.056142307817935944, | |
| "learning_rate": 0.0001452495638090167, | |
| "loss": 0.0304, | |
| "mean_token_accuracy": 0.9861166894435882, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.424, | |
| "grad_norm": 0.0800497755408287, | |
| "learning_rate": 0.00014273971706417647, | |
| "loss": 0.0351, | |
| "mean_token_accuracy": 0.9837919533252716, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.432, | |
| "grad_norm": 0.05837633088231087, | |
| "learning_rate": 0.00014019648385012244, | |
| "loss": 0.0304, | |
| "mean_token_accuracy": 0.9853955626487731, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.058906685560941696, | |
| "learning_rate": 0.00013762185083366556, | |
| "loss": 0.0321, | |
| "mean_token_accuracy": 0.9853337109088898, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.448, | |
| "grad_norm": 0.06374027580022812, | |
| "learning_rate": 0.00013501782920982184, | |
| "loss": 0.0379, | |
| "mean_token_accuracy": 0.9825663805007935, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.456, | |
| "grad_norm": 0.062413912266492844, | |
| "learning_rate": 0.00013238645313075104, | |
| "loss": 0.0362, | |
| "mean_token_accuracy": 0.9839500784873962, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.464, | |
| "grad_norm": 0.04723189026117325, | |
| "learning_rate": 0.00012972977811676287, | |
| "loss": 0.0316, | |
| "mean_token_accuracy": 0.9853797852993011, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.472, | |
| "grad_norm": 0.05583701282739639, | |
| "learning_rate": 0.00012704987945063068, | |
| "loss": 0.0324, | |
| "mean_token_accuracy": 0.9851679742336273, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.053289640694856644, | |
| "learning_rate": 0.00012434885055646823, | |
| "loss": 0.0304, | |
| "mean_token_accuracy": 0.9868038833141327, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.488, | |
| "grad_norm": 0.0547807514667511, | |
| "learning_rate": 0.00012162880136443447, | |
| "loss": 0.0382, | |
| "mean_token_accuracy": 0.9832392990589142, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.496, | |
| "grad_norm": 0.062117431312799454, | |
| "learning_rate": 0.00011889185666254506, | |
| "loss": 0.0347, | |
| "mean_token_accuracy": 0.9848644256591796, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.504, | |
| "grad_norm": 0.05534973368048668, | |
| "learning_rate": 0.00011614015443687722, | |
| "loss": 0.032, | |
| "mean_token_accuracy": 0.9855094432830811, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.512, | |
| "grad_norm": 0.04713955521583557, | |
| "learning_rate": 0.0001133758442014651, | |
| "loss": 0.0296, | |
| "mean_token_accuracy": 0.9867917716503143, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.05600622668862343, | |
| "learning_rate": 0.00011060108531918971, | |
| "loss": 0.0342, | |
| "mean_token_accuracy": 0.9841290414333344, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.528, | |
| "grad_norm": 0.04774011671543121, | |
| "learning_rate": 0.0001078180453149754, | |
| "loss": 0.031, | |
| "mean_token_accuracy": 0.9855308055877685, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.536, | |
| "grad_norm": 0.05677397921681404, | |
| "learning_rate": 0.00010502889818261075, | |
| "loss": 0.0354, | |
| "mean_token_accuracy": 0.9833913028240204, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.544, | |
| "grad_norm": 0.08369103819131851, | |
| "learning_rate": 0.00010223582268651586, | |
| "loss": 0.0344, | |
| "mean_token_accuracy": 0.98387970328331, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.552, | |
| "grad_norm": 0.07704319059848785, | |
| "learning_rate": 9.94410006597835e-05, | |
| "loss": 0.0343, | |
| "mean_token_accuracy": 0.9841209590435028, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.0598573163151741, | |
| "learning_rate": 9.66466152998226e-05, | |
| "loss": 0.0279, | |
| "mean_token_accuracy": 0.9878278017044068, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.568, | |
| "grad_norm": 0.05838743597269058, | |
| "learning_rate": 9.385484946293637e-05, | |
| "loss": 0.0354, | |
| "mean_token_accuracy": 0.9834566116333008, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.576, | |
| "grad_norm": 0.0644030049443245, | |
| "learning_rate": 9.106788395916678e-05, | |
| "loss": 0.0329, | |
| "mean_token_accuracy": 0.985417640209198, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.584, | |
| "grad_norm": 0.05025125667452812, | |
| "learning_rate": 8.828789584873754e-05, | |
| "loss": 0.034, | |
| "mean_token_accuracy": 0.984911048412323, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.592, | |
| "grad_norm": 0.04645683616399765, | |
| "learning_rate": 8.551705674142617e-05, | |
| "loss": 0.0345, | |
| "mean_token_accuracy": 0.9842629969120026, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.06257304549217224, | |
| "learning_rate": 8.275753110019367e-05, | |
| "loss": 0.0307, | |
| "mean_token_accuracy": 0.9859090149402618, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.608, | |
| "grad_norm": 0.08189195394515991, | |
| "learning_rate": 8.001147455039735e-05, | |
| "loss": 0.0293, | |
| "mean_token_accuracy": 0.9876027524471283, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.616, | |
| "grad_norm": 0.05993218719959259, | |
| "learning_rate": 7.728103219590681e-05, | |
| "loss": 0.0289, | |
| "mean_token_accuracy": 0.9873842716217041, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.624, | |
| "grad_norm": 0.04940414056181908, | |
| "learning_rate": 7.456833694343906e-05, | |
| "loss": 0.0314, | |
| "mean_token_accuracy": 0.9858180701732635, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.632, | |
| "grad_norm": 0.06051292642951012, | |
| "learning_rate": 7.18755078364214e-05, | |
| "loss": 0.035, | |
| "mean_token_accuracy": 0.9843159735202789, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.07288350909948349, | |
| "learning_rate": 6.920464839968405e-05, | |
| "loss": 0.0289, | |
| "mean_token_accuracy": 0.9867165565490723, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.648, | |
| "grad_norm": 0.05235522985458374, | |
| "learning_rate": 6.65578449962749e-05, | |
| "loss": 0.0342, | |
| "mean_token_accuracy": 0.9844050407409668, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.656, | |
| "grad_norm": 0.04962315410375595, | |
| "learning_rate": 6.393716519768047e-05, | |
| "loss": 0.0318, | |
| "mean_token_accuracy": 0.9854838192462921, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.664, | |
| "grad_norm": 0.05337170138955116, | |
| "learning_rate": 6.134465616872598e-05, | |
| "loss": 0.029, | |
| "mean_token_accuracy": 0.9865143656730652, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.672, | |
| "grad_norm": 0.061498258262872696, | |
| "learning_rate": 5.878234306841637e-05, | |
| "loss": 0.0304, | |
| "mean_token_accuracy": 0.9859014391899109, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.05795282498002052, | |
| "learning_rate": 5.62522274679673e-05, | |
| "loss": 0.0311, | |
| "mean_token_accuracy": 0.9858847856521606, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.688, | |
| "grad_norm": 0.05434182286262512, | |
| "learning_rate": 5.375628578726181e-05, | |
| "loss": 0.0262, | |
| "mean_token_accuracy": 0.9887398540973663, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.696, | |
| "grad_norm": 0.0455637201666832, | |
| "learning_rate": 5.1296467750954314e-05, | |
| "loss": 0.0315, | |
| "mean_token_accuracy": 0.9861598789691925, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.704, | |
| "grad_norm": 0.05739019066095352, | |
| "learning_rate": 4.8874694865427676e-05, | |
| "loss": 0.0304, | |
| "mean_token_accuracy": 0.9865131139755249, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.712, | |
| "grad_norm": 0.07262022793292999, | |
| "learning_rate": 4.649285891779327e-05, | |
| "loss": 0.0277, | |
| "mean_token_accuracy": 0.9875944793224335, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.06861643493175507, | |
| "learning_rate": 4.415282049810644e-05, | |
| "loss": 0.0288, | |
| "mean_token_accuracy": 0.9869144856929779, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.728, | |
| "grad_norm": 0.057887740433216095, | |
| "learning_rate": 4.1856407545951834e-05, | |
| "loss": 0.0332, | |
| "mean_token_accuracy": 0.9847104012966156, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.736, | |
| "grad_norm": 0.07549154758453369, | |
| "learning_rate": 3.9605413922533874e-05, | |
| "loss": 0.0294, | |
| "mean_token_accuracy": 0.9868144273757935, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.744, | |
| "grad_norm": 0.058476611971855164, | |
| "learning_rate": 3.740159800938784e-05, | |
| "loss": 0.0246, | |
| "mean_token_accuracy": 0.9886395156383514, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.752, | |
| "grad_norm": 0.05933303013443947, | |
| "learning_rate": 3.5246681334806175e-05, | |
| "loss": 0.0263, | |
| "mean_token_accuracy": 0.9887538492679596, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.061903417110443115, | |
| "learning_rate": 3.3142347229053015e-05, | |
| "loss": 0.0333, | |
| "mean_token_accuracy": 0.9845255970954895, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.768, | |
| "grad_norm": 0.06767533719539642, | |
| "learning_rate": 3.109023950941736e-05, | |
| "loss": 0.0289, | |
| "mean_token_accuracy": 0.9869068741798401, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.776, | |
| "grad_norm": 0.05679545924067497, | |
| "learning_rate": 2.909196119613218e-05, | |
| "loss": 0.0313, | |
| "mean_token_accuracy": 0.9862040936946869, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.784, | |
| "grad_norm": 0.04378621280193329, | |
| "learning_rate": 2.7149073260162416e-05, | |
| "loss": 0.0311, | |
| "mean_token_accuracy": 0.9860045194625855, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.792, | |
| "grad_norm": 0.04507381096482277, | |
| "learning_rate": 2.5263093403840142e-05, | |
| "loss": 0.0324, | |
| "mean_token_accuracy": 0.985187429189682, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.04896757751703262, | |
| "learning_rate": 2.3435494875299314e-05, | |
| "loss": 0.0285, | |
| "mean_token_accuracy": 0.9870898187160492, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.808, | |
| "grad_norm": 0.06324876099824905, | |
| "learning_rate": 2.166770531763633e-05, | |
| "loss": 0.027, | |
| "mean_token_accuracy": 0.9879481792449951, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.816, | |
| "grad_norm": 0.04500701278448105, | |
| "learning_rate": 1.9961105653695266e-05, | |
| "loss": 0.0328, | |
| "mean_token_accuracy": 0.9849318027496338, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.824, | |
| "grad_norm": 0.05476031452417374, | |
| "learning_rate": 1.8317029007349085e-05, | |
| "loss": 0.0304, | |
| "mean_token_accuracy": 0.9857797741889953, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.832, | |
| "grad_norm": 0.04693017527461052, | |
| "learning_rate": 1.6736759662119183e-05, | |
| "loss": 0.0278, | |
| "mean_token_accuracy": 0.9873194813728332, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.07823780179023743, | |
| "learning_rate": 1.5221532057947419e-05, | |
| "loss": 0.0308, | |
| "mean_token_accuracy": 0.9862527191638947, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.848, | |
| "grad_norm": 0.04295206442475319, | |
| "learning_rate": 1.3772529826903269e-05, | |
| "loss": 0.0258, | |
| "mean_token_accuracy": 0.9883043467998505, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.856, | |
| "grad_norm": 0.046063318848609924, | |
| "learning_rate": 1.23908848685804e-05, | |
| "loss": 0.0284, | |
| "mean_token_accuracy": 0.9875360190868377, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.864, | |
| "grad_norm": 0.0660807192325592, | |
| "learning_rate": 1.1077676465904208e-05, | |
| "loss": 0.0312, | |
| "mean_token_accuracy": 0.986429226398468, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.872, | |
| "grad_norm": 0.059512872248888016, | |
| "learning_rate": 9.833930442041506e-06, | |
| "loss": 0.03, | |
| "mean_token_accuracy": 0.9860706746578216, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.05064374580979347, | |
| "learning_rate": 8.660618359070604e-06, | |
| "loss": 0.0308, | |
| "mean_token_accuracy": 0.9860022485256195, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.888, | |
| "grad_norm": 0.052208684384822845, | |
| "learning_rate": 7.558656759037797e-06, | |
| "loss": 0.0268, | |
| "mean_token_accuracy": 0.9876573204994201, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.896, | |
| "grad_norm": 0.052323583513498306, | |
| "learning_rate": 6.528906447993288e-06, | |
| "loss": 0.0315, | |
| "mean_token_accuracy": 0.9857221782207489, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.904, | |
| "grad_norm": 0.045587047934532166, | |
| "learning_rate": 5.572171823565797e-06, | |
| "loss": 0.0334, | |
| "mean_token_accuracy": 0.9845053553581238, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.912, | |
| "grad_norm": 0.0517142117023468, | |
| "learning_rate": 4.689200246600867e-06, | |
| "loss": 0.0327, | |
| "mean_token_accuracy": 0.9847142338752747, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.04421110823750496, | |
| "learning_rate": 3.880681457354118e-06, | |
| "loss": 0.028, | |
| "mean_token_accuracy": 0.9875537037849427, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.928, | |
| "grad_norm": 0.040859125554561615, | |
| "learning_rate": 3.1472470366950334e-06, | |
| "loss": 0.0274, | |
| "mean_token_accuracy": 0.9872512996196747, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.936, | |
| "grad_norm": 0.048171717673540115, | |
| "learning_rate": 2.4894699127426367e-06, | |
| "loss": 0.0287, | |
| "mean_token_accuracy": 0.9876733124256134, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.944, | |
| "grad_norm": 0.04280434921383858, | |
| "learning_rate": 1.907863913318153e-06, | |
| "loss": 0.0283, | |
| "mean_token_accuracy": 0.987252289056778, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.952, | |
| "grad_norm": 0.054707061499357224, | |
| "learning_rate": 1.4028833645643113e-06, | |
| "loss": 0.0324, | |
| "mean_token_accuracy": 0.9851353108882904, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.056745924055576324, | |
| "learning_rate": 9.749227360448143e-07, | |
| "loss": 0.0279, | |
| "mean_token_accuracy": 0.9884349465370178, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.968, | |
| "grad_norm": 0.04751133173704147, | |
| "learning_rate": 6.243163326014267e-07, | |
| "loss": 0.03, | |
| "mean_token_accuracy": 0.9863233804702759, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.976, | |
| "grad_norm": 0.061580199748277664, | |
| "learning_rate": 3.5133803320896994e-07, | |
| "loss": 0.028, | |
| "mean_token_accuracy": 0.9869140684604645, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.984, | |
| "grad_norm": 0.04928790032863617, | |
| "learning_rate": 1.562010770326916e-07, | |
| "loss": 0.036, | |
| "mean_token_accuracy": 0.9834135055541993, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.992, | |
| "grad_norm": 0.057830002158880234, | |
| "learning_rate": 3.905789685471062e-08, | |
| "loss": 0.0306, | |
| "mean_token_accuracy": 0.9861779153347016, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.0504627525806427, | |
| "learning_rate": 0.0, | |
| "loss": 0.0272, | |
| "mean_token_accuracy": 0.9880285739898682, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 625, | |
| "total_flos": 8.527809495642931e+16, | |
| "train_loss": 0.04780370211601257, | |
| "train_runtime": 1247.5714, | |
| "train_samples_per_second": 4.008, | |
| "train_steps_per_second": 0.501 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 625, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.527809495642931e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |