| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.2468827930174564, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012468827930174564, | |
| "grad_norm": 0.0348743200302124, | |
| "learning_rate": 4.9995205016168205e-05, | |
| "loss": 0.4047, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02493765586034913, | |
| "grad_norm": 0.052354972809553146, | |
| "learning_rate": 4.998082190402241e-05, | |
| "loss": 0.3855, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03740648379052369, | |
| "grad_norm": 0.02390989102423191, | |
| "learning_rate": 4.995685618090584e-05, | |
| "loss": 0.3818, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04987531172069826, | |
| "grad_norm": 0.01846301183104515, | |
| "learning_rate": 4.9923317040038885e-05, | |
| "loss": 0.3884, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06234413965087282, | |
| "grad_norm": 0.018641460686922073, | |
| "learning_rate": 4.988021734699259e-05, | |
| "loss": 0.3713, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07481296758104738, | |
| "grad_norm": 0.016644474118947983, | |
| "learning_rate": 4.982757363475346e-05, | |
| "loss": 0.3492, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08728179551122195, | |
| "grad_norm": 0.01785973273217678, | |
| "learning_rate": 4.9765406097381426e-05, | |
| "loss": 0.3596, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09975062344139651, | |
| "grad_norm": 0.01776760071516037, | |
| "learning_rate": 4.96937385822634e-05, | |
| "loss": 0.3792, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11221945137157108, | |
| "grad_norm": 0.019663693383336067, | |
| "learning_rate": 4.96125985809655e-05, | |
| "loss": 0.3393, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.12468827930174564, | |
| "grad_norm": 0.036602046340703964, | |
| "learning_rate": 4.952201721868727e-05, | |
| "loss": 0.3433, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1371571072319202, | |
| "grad_norm": 0.020088447257876396, | |
| "learning_rate": 4.94220292423221e-05, | |
| "loss": 0.3563, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.14962593516209477, | |
| "grad_norm": 0.023927291855216026, | |
| "learning_rate": 4.9312673007128405e-05, | |
| "loss": 0.3543, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16209476309226933, | |
| "grad_norm": 0.023712489753961563, | |
| "learning_rate": 4.919399046201656e-05, | |
| "loss": 0.3442, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.1745635910224439, | |
| "grad_norm": 0.02708962745964527, | |
| "learning_rate": 4.906602713345735e-05, | |
| "loss": 0.344, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18703241895261846, | |
| "grad_norm": 0.026062602177262306, | |
| "learning_rate": 4.8928832108018106e-05, | |
| "loss": 0.3426, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.19950124688279303, | |
| "grad_norm": 0.025727244094014168, | |
| "learning_rate": 4.878245801353313e-05, | |
| "loss": 0.3677, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2119700748129676, | |
| "grad_norm": 0.03201605752110481, | |
| "learning_rate": 4.862696099891573e-05, | |
| "loss": 0.333, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.22443890274314215, | |
| "grad_norm": 0.03317998722195625, | |
| "learning_rate": 4.846240071261959e-05, | |
| "loss": 0.3596, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.23690773067331672, | |
| "grad_norm": 0.02743816375732422, | |
| "learning_rate": 4.828884027975768e-05, | |
| "loss": 0.3156, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.24937655860349128, | |
| "grad_norm": 0.030033418908715248, | |
| "learning_rate": 4.810634627788756e-05, | |
| "loss": 0.3355, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.26184538653366585, | |
| "grad_norm": 0.031716831028461456, | |
| "learning_rate": 4.791498871147229e-05, | |
| "loss": 0.3518, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.2743142144638404, | |
| "grad_norm": 0.03049326501786709, | |
| "learning_rate": 4.7714840985026834e-05, | |
| "loss": 0.3031, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.286783042394015, | |
| "grad_norm": 0.03361716866493225, | |
| "learning_rate": 4.7505979874960184e-05, | |
| "loss": 0.3452, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.29925187032418954, | |
| "grad_norm": 0.0355195626616478, | |
| "learning_rate": 4.728848550012399e-05, | |
| "loss": 0.343, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3117206982543641, | |
| "grad_norm": 0.04162430390715599, | |
| "learning_rate": 4.706244129107914e-05, | |
| "loss": 0.3234, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.32418952618453867, | |
| "grad_norm": 0.04150069132447243, | |
| "learning_rate": 4.682793395809184e-05, | |
| "loss": 0.3238, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.33665835411471323, | |
| "grad_norm": 0.04490313306450844, | |
| "learning_rate": 4.658505345787169e-05, | |
| "loss": 0.3337, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.3491271820448878, | |
| "grad_norm": 0.03981255367398262, | |
| "learning_rate": 4.633389295906443e-05, | |
| "loss": 0.3422, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.36159600997506236, | |
| "grad_norm": 0.04022540897130966, | |
| "learning_rate": 4.607454880651253e-05, | |
| "loss": 0.315, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.3740648379052369, | |
| "grad_norm": 0.03891991823911667, | |
| "learning_rate": 4.580712048429746e-05, | |
| "loss": 0.3213, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3865336658354115, | |
| "grad_norm": 0.04148748144507408, | |
| "learning_rate": 4.553171057757772e-05, | |
| "loss": 0.3326, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.39900249376558605, | |
| "grad_norm": 0.04601826146245003, | |
| "learning_rate": 4.5248424733237294e-05, | |
| "loss": 0.3264, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4114713216957606, | |
| "grad_norm": 0.04266240820288658, | |
| "learning_rate": 4.4957371619359644e-05, | |
| "loss": 0.3422, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.4239401496259352, | |
| "grad_norm": 0.04361332580447197, | |
| "learning_rate": 4.46586628835428e-05, | |
| "loss": 0.3136, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.43640897755610975, | |
| "grad_norm": 0.051424313336610794, | |
| "learning_rate": 4.435241311007146e-05, | |
| "loss": 0.335, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.4488778054862843, | |
| "grad_norm": 0.04484390467405319, | |
| "learning_rate": 4.403873977596258e-05, | |
| "loss": 0.3188, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4613466334164589, | |
| "grad_norm": 0.04609343037009239, | |
| "learning_rate": 4.371776320590143e-05, | |
| "loss": 0.3355, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.47381546134663344, | |
| "grad_norm": 0.052802663296461105, | |
| "learning_rate": 4.3389606526085115e-05, | |
| "loss": 0.3358, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.486284289276808, | |
| "grad_norm": 0.0500580295920372, | |
| "learning_rate": 4.305439561699154e-05, | |
| "loss": 0.2961, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.49875311720698257, | |
| "grad_norm": 0.05000691115856171, | |
| "learning_rate": 4.271225906509186e-05, | |
| "loss": 0.3014, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5112219451371571, | |
| "grad_norm": 0.049051977694034576, | |
| "learning_rate": 4.236332811352485e-05, | |
| "loss": 0.3182, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.5236907730673317, | |
| "grad_norm": 0.05655088275671005, | |
| "learning_rate": 4.200773661175219e-05, | |
| "loss": 0.3117, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5361596009975063, | |
| "grad_norm": 0.056144360452890396, | |
| "learning_rate": 4.164562096421403e-05, | |
| "loss": 0.2916, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.5486284289276808, | |
| "grad_norm": 0.04913180693984032, | |
| "learning_rate": 4.127712007800438e-05, | |
| "loss": 0.3342, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5610972568578554, | |
| "grad_norm": 0.06693854182958603, | |
| "learning_rate": 4.090237530958656e-05, | |
| "loss": 0.3049, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.57356608478803, | |
| "grad_norm": 0.056180231273174286, | |
| "learning_rate": 4.052153041056901e-05, | |
| "loss": 0.3349, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5860349127182045, | |
| "grad_norm": 0.06079794839024544, | |
| "learning_rate": 4.0134731472562384e-05, | |
| "loss": 0.3266, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.5985037406483791, | |
| "grad_norm": 0.05693957582116127, | |
| "learning_rate": 3.9742126871138995e-05, | |
| "loss": 0.3163, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.6109725685785536, | |
| "grad_norm": 0.056326717138290405, | |
| "learning_rate": 3.934386720891614e-05, | |
| "loss": 0.2934, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.6234413965087282, | |
| "grad_norm": 0.05838495492935181, | |
| "learning_rate": 3.894010525778511e-05, | |
| "loss": 0.2749, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6359102244389028, | |
| "grad_norm": 0.0631040409207344, | |
| "learning_rate": 3.853099590030811e-05, | |
| "loss": 0.3367, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.6483790523690773, | |
| "grad_norm": 0.062413156032562256, | |
| "learning_rate": 3.81166960703055e-05, | |
| "loss": 0.3205, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6608478802992519, | |
| "grad_norm": 0.06148769333958626, | |
| "learning_rate": 3.769736469265621e-05, | |
| "loss": 0.3159, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.6733167082294265, | |
| "grad_norm": 0.06495541334152222, | |
| "learning_rate": 3.727316262233429e-05, | |
| "loss": 0.2995, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.685785536159601, | |
| "grad_norm": 0.05486743152141571, | |
| "learning_rate": 3.684425258270525e-05, | |
| "loss": 0.3094, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.6982543640897756, | |
| "grad_norm": 0.05586089566349983, | |
| "learning_rate": 3.64107991031055e-05, | |
| "loss": 0.3321, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.7107231920199502, | |
| "grad_norm": 0.06062714010477066, | |
| "learning_rate": 3.597296845572917e-05, | |
| "loss": 0.331, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.7231920199501247, | |
| "grad_norm": 0.06520465761423111, | |
| "learning_rate": 3.553092859184629e-05, | |
| "loss": 0.3199, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.7356608478802993, | |
| "grad_norm": 0.059496622532606125, | |
| "learning_rate": 3.508484907737687e-05, | |
| "loss": 0.3087, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.7481296758104738, | |
| "grad_norm": 0.06234793737530708, | |
| "learning_rate": 3.463490102784568e-05, | |
| "loss": 0.2914, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7605985037406484, | |
| "grad_norm": 0.060752127319574356, | |
| "learning_rate": 3.418125704274253e-05, | |
| "loss": 0.3059, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.773067331670823, | |
| "grad_norm": 0.06881830096244812, | |
| "learning_rate": 3.372409113931334e-05, | |
| "loss": 0.311, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7855361596009975, | |
| "grad_norm": 0.0633009597659111, | |
| "learning_rate": 3.326357868580734e-05, | |
| "loss": 0.3262, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.7980049875311721, | |
| "grad_norm": 0.06173081696033478, | |
| "learning_rate": 3.2799896334206045e-05, | |
| "loss": 0.307, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.8104738154613467, | |
| "grad_norm": 0.0721065104007721, | |
| "learning_rate": 3.233322195245977e-05, | |
| "loss": 0.3225, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.8229426433915212, | |
| "grad_norm": 0.06812290102243423, | |
| "learning_rate": 3.186373455625774e-05, | |
| "loss": 0.3427, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.8354114713216958, | |
| "grad_norm": 0.0630379170179367, | |
| "learning_rate": 3.139161424035786e-05, | |
| "loss": 0.332, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.8478802992518704, | |
| "grad_norm": 0.08122845739126205, | |
| "learning_rate": 3.091704210950266e-05, | |
| "loss": 0.3031, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.8603491271820449, | |
| "grad_norm": 0.07106555998325348, | |
| "learning_rate": 3.0440200208947694e-05, | |
| "loss": 0.314, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.8728179551122195, | |
| "grad_norm": 0.06012728437781334, | |
| "learning_rate": 2.9961271454629235e-05, | |
| "loss": 0.2994, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.885286783042394, | |
| "grad_norm": 0.07092411816120148, | |
| "learning_rate": 2.9480439562997965e-05, | |
| "loss": 0.2904, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.8977556109725686, | |
| "grad_norm": 0.0659562423825264, | |
| "learning_rate": 2.8997888980545583e-05, | |
| "loss": 0.3259, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.9102244389027432, | |
| "grad_norm": 0.06206708773970604, | |
| "learning_rate": 2.8513804813051363e-05, | |
| "loss": 0.2975, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.9226932668329177, | |
| "grad_norm": 0.07387180626392365, | |
| "learning_rate": 2.8028372754575805e-05, | |
| "loss": 0.3248, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.9351620947630923, | |
| "grad_norm": 0.06683710217475891, | |
| "learning_rate": 2.7541779016228664e-05, | |
| "loss": 0.3043, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.9476309226932669, | |
| "grad_norm": 0.09706446528434753, | |
| "learning_rate": 2.7054210254738572e-05, | |
| "loss": 0.3101, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9600997506234414, | |
| "grad_norm": 0.06651865690946579, | |
| "learning_rate": 2.6565853500851802e-05, | |
| "loss": 0.2902, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.972568578553616, | |
| "grad_norm": 0.07901949435472488, | |
| "learning_rate": 2.607689608758746e-05, | |
| "loss": 0.3329, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9850374064837906, | |
| "grad_norm": 0.06636166572570801, | |
| "learning_rate": 2.558752557837684e-05, | |
| "loss": 0.3212, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.9975062344139651, | |
| "grad_norm": 0.06299249827861786, | |
| "learning_rate": 2.5097929695114297e-05, | |
| "loss": 0.288, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.0099750623441397, | |
| "grad_norm": 0.06922150403261185, | |
| "learning_rate": 2.4608296246147373e-05, | |
| "loss": 0.2973, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 1.0224438902743143, | |
| "grad_norm": 0.06634873151779175, | |
| "learning_rate": 2.4118813054233774e-05, | |
| "loss": 0.2869, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.0349127182044888, | |
| "grad_norm": 0.07161210477352142, | |
| "learning_rate": 2.3629667884492798e-05, | |
| "loss": 0.3053, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 1.0473815461346634, | |
| "grad_norm": 0.06999760866165161, | |
| "learning_rate": 2.3141048372378864e-05, | |
| "loss": 0.2907, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.059850374064838, | |
| "grad_norm": 0.07221878319978714, | |
| "learning_rate": 2.2653141951704814e-05, | |
| "loss": 0.2691, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.0723192019950125, | |
| "grad_norm": 0.07585354894399643, | |
| "learning_rate": 2.2166135782742527e-05, | |
| "loss": 0.2969, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.084788029925187, | |
| "grad_norm": 0.08216829597949982, | |
| "learning_rate": 2.16802166804285e-05, | |
| "loss": 0.3006, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 1.0972568578553616, | |
| "grad_norm": 0.06559521704912186, | |
| "learning_rate": 2.119557104270187e-05, | |
| "loss": 0.2777, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.1097256857855362, | |
| "grad_norm": 0.06534233689308167, | |
| "learning_rate": 2.0712384779002393e-05, | |
| "loss": 0.3153, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 1.1221945137157108, | |
| "grad_norm": 0.07653407752513885, | |
| "learning_rate": 2.0230843238955855e-05, | |
| "loss": 0.3023, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.1346633416458853, | |
| "grad_norm": 0.06991739571094513, | |
| "learning_rate": 1.9751131141274148e-05, | |
| "loss": 0.3058, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 1.14713216957606, | |
| "grad_norm": 0.07048314809799194, | |
| "learning_rate": 1.927343250289747e-05, | |
| "loss": 0.3056, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.1596009975062345, | |
| "grad_norm": 0.0698205828666687, | |
| "learning_rate": 1.8797930568405614e-05, | |
| "loss": 0.2994, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 1.172069825436409, | |
| "grad_norm": 0.0764131247997284, | |
| "learning_rate": 1.8324807739725613e-05, | |
| "loss": 0.3146, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.1845386533665836, | |
| "grad_norm": 0.07224885374307632, | |
| "learning_rate": 1.7854245506162582e-05, | |
| "loss": 0.3107, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.1970074812967582, | |
| "grad_norm": 0.07462743669748306, | |
| "learning_rate": 1.738642437478067e-05, | |
| "loss": 0.3146, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.2094763092269327, | |
| "grad_norm": 0.08045542985200882, | |
| "learning_rate": 1.6921523801160757e-05, | |
| "loss": 0.3102, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 1.2219451371571073, | |
| "grad_norm": 0.06614966690540314, | |
| "learning_rate": 1.645972212056157e-05, | |
| "loss": 0.2748, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.2344139650872819, | |
| "grad_norm": 0.07284315675497055, | |
| "learning_rate": 1.6001196479510448e-05, | |
| "loss": 0.3133, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 1.2468827930174564, | |
| "grad_norm": 0.07468894124031067, | |
| "learning_rate": 1.5546122767850234e-05, | |
| "loss": 0.3062, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 802, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.9213678477705216e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |