| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.994705174488568, | |
| "eval_steps": 100, | |
| "global_step": 518, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.019253910950661854, | |
| "grad_norm": 2.4829742908477783, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 1.3128, | |
| "num_input_tokens_seen": 67662, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03850782190132371, | |
| "grad_norm": 1.7913451194763184, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 1.2288, | |
| "num_input_tokens_seen": 133986, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05776173285198556, | |
| "grad_norm": 1.1510990858078003, | |
| "learning_rate": 4.615384615384615e-05, | |
| "loss": 1.0893, | |
| "num_input_tokens_seen": 202626, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07701564380264742, | |
| "grad_norm": 0.7305760383605957, | |
| "learning_rate": 6.153846153846155e-05, | |
| "loss": 1.0228, | |
| "num_input_tokens_seen": 264348, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09626955475330927, | |
| "grad_norm": 0.84750896692276, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 0.9562, | |
| "num_input_tokens_seen": 333586, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11552346570397112, | |
| "grad_norm": 0.7335062623023987, | |
| "learning_rate": 7.998695344323427e-05, | |
| "loss": 0.9524, | |
| "num_input_tokens_seen": 395406, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13477737665463296, | |
| "grad_norm": 0.948805034160614, | |
| "learning_rate": 7.993396639212965e-05, | |
| "loss": 0.8957, | |
| "num_input_tokens_seen": 467462, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.15403128760529483, | |
| "grad_norm": 0.7413954734802246, | |
| "learning_rate": 7.984027740137819e-05, | |
| "loss": 0.8737, | |
| "num_input_tokens_seen": 543588, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.17328519855595667, | |
| "grad_norm": 0.7637290954589844, | |
| "learning_rate": 7.970598196171101e-05, | |
| "loss": 0.8871, | |
| "num_input_tokens_seen": 613352, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.19253910950661854, | |
| "grad_norm": 0.761428952217102, | |
| "learning_rate": 7.953121695121395e-05, | |
| "loss": 0.8344, | |
| "num_input_tokens_seen": 681318, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.21179302045728038, | |
| "grad_norm": 0.7143028974533081, | |
| "learning_rate": 7.93161604958172e-05, | |
| "loss": 0.8389, | |
| "num_input_tokens_seen": 753680, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.23104693140794225, | |
| "grad_norm": 0.6739410758018494, | |
| "learning_rate": 7.906103178774378e-05, | |
| "loss": 0.8587, | |
| "num_input_tokens_seen": 820164, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2503008423586041, | |
| "grad_norm": 0.723397433757782, | |
| "learning_rate": 7.876609086210207e-05, | |
| "loss": 0.842, | |
| "num_input_tokens_seen": 888138, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.2695547533092659, | |
| "grad_norm": 0.66191166639328, | |
| "learning_rate": 7.843163833184991e-05, | |
| "loss": 0.816, | |
| "num_input_tokens_seen": 958314, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2888086642599278, | |
| "grad_norm": 0.6319432854652405, | |
| "learning_rate": 7.80580150814005e-05, | |
| "loss": 0.8416, | |
| "num_input_tokens_seen": 1030194, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.30806257521058966, | |
| "grad_norm": 0.7031162977218628, | |
| "learning_rate": 7.764560191918247e-05, | |
| "loss": 0.8179, | |
| "num_input_tokens_seen": 1095740, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.32731648616125153, | |
| "grad_norm": 0.6904546618461609, | |
| "learning_rate": 7.719481918950805e-05, | |
| "loss": 0.802, | |
| "num_input_tokens_seen": 1163928, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.34657039711191334, | |
| "grad_norm": 0.6699234247207642, | |
| "learning_rate": 7.670612634414513e-05, | |
| "loss": 0.8093, | |
| "num_input_tokens_seen": 1233316, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3658243080625752, | |
| "grad_norm": 0.6710209250450134, | |
| "learning_rate": 7.618002147402967e-05, | |
| "loss": 0.8349, | |
| "num_input_tokens_seen": 1298016, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.3850782190132371, | |
| "grad_norm": 0.6232579946517944, | |
| "learning_rate": 7.561704080159603e-05, | |
| "loss": 0.8172, | |
| "num_input_tokens_seen": 1364870, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3850782190132371, | |
| "eval_loss": 0.6644170880317688, | |
| "eval_runtime": 5.7343, | |
| "eval_samples_per_second": 26.158, | |
| "eval_steps_per_second": 13.079, | |
| "num_input_tokens_seen": 1364870, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4043321299638989, | |
| "grad_norm": 0.6807074546813965, | |
| "learning_rate": 7.50177581342423e-05, | |
| "loss": 0.8169, | |
| "num_input_tokens_seen": 1437970, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.42358604091456076, | |
| "grad_norm": 0.6546260714530945, | |
| "learning_rate": 7.438278427948805e-05, | |
| "loss": 0.817, | |
| "num_input_tokens_seen": 1512200, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.4428399518652226, | |
| "grad_norm": 0.7773868441581726, | |
| "learning_rate": 7.371276642242027e-05, | |
| "loss": 0.8038, | |
| "num_input_tokens_seen": 1592192, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.4620938628158845, | |
| "grad_norm": 0.6242259740829468, | |
| "learning_rate": 7.300838746606224e-05, | |
| "loss": 0.7998, | |
| "num_input_tokens_seen": 1656614, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.4813477737665463, | |
| "grad_norm": 0.5981661677360535, | |
| "learning_rate": 7.227036533533753e-05, | |
| "loss": 0.8069, | |
| "num_input_tokens_seen": 1731572, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.5006016847172082, | |
| "grad_norm": 0.6073790788650513, | |
| "learning_rate": 7.149945224533863e-05, | |
| "loss": 0.7847, | |
| "num_input_tokens_seen": 1797496, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.51985559566787, | |
| "grad_norm": 0.6308819055557251, | |
| "learning_rate": 7.069643393464592e-05, | |
| "loss": 0.805, | |
| "num_input_tokens_seen": 1860442, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.5391095066185319, | |
| "grad_norm": 0.7135605216026306, | |
| "learning_rate": 6.986212886447851e-05, | |
| "loss": 0.7924, | |
| "num_input_tokens_seen": 1924462, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5583634175691937, | |
| "grad_norm": 0.6704626083374023, | |
| "learning_rate": 6.899738738449313e-05, | |
| "loss": 0.7926, | |
| "num_input_tokens_seen": 1994714, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.5776173285198556, | |
| "grad_norm": 0.6295877695083618, | |
| "learning_rate": 6.81030908660813e-05, | |
| "loss": 0.7977, | |
| "num_input_tokens_seen": 2064324, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5968712394705175, | |
| "grad_norm": 0.5767641067504883, | |
| "learning_rate": 6.718015080404824e-05, | |
| "loss": 0.7912, | |
| "num_input_tokens_seen": 2141534, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.6161251504211793, | |
| "grad_norm": 0.6175399422645569, | |
| "learning_rate": 6.622950788758907e-05, | |
| "loss": 0.7781, | |
| "num_input_tokens_seen": 2205388, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6353790613718412, | |
| "grad_norm": 0.7159196734428406, | |
| "learning_rate": 6.525213104150908e-05, | |
| "loss": 0.7733, | |
| "num_input_tokens_seen": 2268804, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.6546329723225031, | |
| "grad_norm": 0.6217786073684692, | |
| "learning_rate": 6.424901643866553e-05, | |
| "loss": 0.7842, | |
| "num_input_tokens_seen": 2342992, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.6738868832731648, | |
| "grad_norm": 0.7792349457740784, | |
| "learning_rate": 6.32211864846372e-05, | |
| "loss": 0.7876, | |
| "num_input_tokens_seen": 2412156, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.6931407942238267, | |
| "grad_norm": 0.6551147699356079, | |
| "learning_rate": 6.2169688775657e-05, | |
| "loss": 0.7783, | |
| "num_input_tokens_seen": 2482798, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.7123947051744886, | |
| "grad_norm": 0.6172861456871033, | |
| "learning_rate": 6.109559503086918e-05, | |
| "loss": 0.7666, | |
| "num_input_tokens_seen": 2546172, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.7316486161251504, | |
| "grad_norm": 0.6506001949310303, | |
| "learning_rate": 6.000000000000001e-05, | |
| "loss": 0.7682, | |
| "num_input_tokens_seen": 2611840, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.7509025270758123, | |
| "grad_norm": 0.582889974117279, | |
| "learning_rate": 5.888402034755471e-05, | |
| "loss": 0.763, | |
| "num_input_tokens_seen": 2680788, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.7701564380264742, | |
| "grad_norm": 0.6109009385108948, | |
| "learning_rate": 5.7748793514678394e-05, | |
| "loss": 0.7664, | |
| "num_input_tokens_seen": 2744502, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7701564380264742, | |
| "eval_loss": 0.6271176338195801, | |
| "eval_runtime": 6.1565, | |
| "eval_samples_per_second": 24.365, | |
| "eval_steps_per_second": 12.182, | |
| "num_input_tokens_seen": 2744502, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.789410348977136, | |
| "grad_norm": 0.5261389017105103, | |
| "learning_rate": 5.6595476559840604e-05, | |
| "loss": 0.7619, | |
| "num_input_tokens_seen": 2806924, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.8086642599277978, | |
| "grad_norm": 0.6377142667770386, | |
| "learning_rate": 5.542524497952544e-05, | |
| "loss": 0.7611, | |
| "num_input_tokens_seen": 2880096, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.8279181708784596, | |
| "grad_norm": 0.6118225455284119, | |
| "learning_rate": 5.4239291510128936e-05, | |
| "loss": 0.7704, | |
| "num_input_tokens_seen": 2953254, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.8471720818291215, | |
| "grad_norm": 0.623435378074646, | |
| "learning_rate": 5.3038824912285144e-05, | |
| "loss": 0.759, | |
| "num_input_tokens_seen": 3018146, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.8664259927797834, | |
| "grad_norm": 0.7073508501052856, | |
| "learning_rate": 5.182506873885964e-05, | |
| "loss": 0.7612, | |
| "num_input_tokens_seen": 3085348, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.8856799037304453, | |
| "grad_norm": 0.6435876488685608, | |
| "learning_rate": 5.059926008786648e-05, | |
| "loss": 0.7582, | |
| "num_input_tokens_seen": 3155840, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.9049338146811071, | |
| "grad_norm": 0.7241389751434326, | |
| "learning_rate": 4.93626483415794e-05, | |
| "loss": 0.7502, | |
| "num_input_tokens_seen": 3228332, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.924187725631769, | |
| "grad_norm": 0.583131730556488, | |
| "learning_rate": 4.811649389312267e-05, | |
| "loss": 0.7573, | |
| "num_input_tokens_seen": 3292876, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.9434416365824309, | |
| "grad_norm": 0.5829302072525024, | |
| "learning_rate": 4.686206686183914e-05, | |
| "loss": 0.7535, | |
| "num_input_tokens_seen": 3356266, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.9626955475330926, | |
| "grad_norm": 0.6448350548744202, | |
| "learning_rate": 4.560064579874517e-05, | |
| "loss": 0.738, | |
| "num_input_tokens_seen": 3436068, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.9819494584837545, | |
| "grad_norm": 0.5773698687553406, | |
| "learning_rate": 4.433351638339173e-05, | |
| "loss": 0.7597, | |
| "num_input_tokens_seen": 3507054, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.0012033694344165, | |
| "grad_norm": 0.6720272302627563, | |
| "learning_rate": 4.306197011345984e-05, | |
| "loss": 0.766, | |
| "num_input_tokens_seen": 3578891, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.0204572803850782, | |
| "grad_norm": 0.594204306602478, | |
| "learning_rate": 4.178730298842592e-05, | |
| "loss": 0.6578, | |
| "num_input_tokens_seen": 3657955, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 1.03971119133574, | |
| "grad_norm": 0.5978640913963318, | |
| "learning_rate": 4.051081418863896e-05, | |
| "loss": 0.6649, | |
| "num_input_tokens_seen": 3726843, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.058965102286402, | |
| "grad_norm": 0.6276839971542358, | |
| "learning_rate": 3.923380475115544e-05, | |
| "loss": 0.6792, | |
| "num_input_tokens_seen": 3790497, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.0782190132370637, | |
| "grad_norm": 0.6850570440292358, | |
| "learning_rate": 3.7957576243681985e-05, | |
| "loss": 0.6622, | |
| "num_input_tokens_seen": 3865393, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.0974729241877257, | |
| "grad_norm": 0.5756229162216187, | |
| "learning_rate": 3.668342943797706e-05, | |
| "loss": 0.6531, | |
| "num_input_tokens_seen": 3932181, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 1.1167268351383874, | |
| "grad_norm": 0.6151105761528015, | |
| "learning_rate": 3.541266298406399e-05, | |
| "loss": 0.673, | |
| "num_input_tokens_seen": 4005021, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.1359807460890494, | |
| "grad_norm": 0.6357588171958923, | |
| "learning_rate": 3.4146572086606516e-05, | |
| "loss": 0.6616, | |
| "num_input_tokens_seen": 4068541, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 1.1552346570397112, | |
| "grad_norm": 0.6211041212081909, | |
| "learning_rate": 3.288644718479594e-05, | |
| "loss": 0.6584, | |
| "num_input_tokens_seen": 4137699, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.1552346570397112, | |
| "eval_loss": 0.6145883202552795, | |
| "eval_runtime": 6.1807, | |
| "eval_samples_per_second": 24.269, | |
| "eval_steps_per_second": 12.134, | |
| "num_input_tokens_seen": 4137699, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.1744885679903732, | |
| "grad_norm": 0.6347965598106384, | |
| "learning_rate": 3.163357263709534e-05, | |
| "loss": 0.6388, | |
| "num_input_tokens_seen": 4206939, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 1.193742478941035, | |
| "grad_norm": 0.6002417802810669, | |
| "learning_rate": 3.0389225412181572e-05, | |
| "loss": 0.6841, | |
| "num_input_tokens_seen": 4271739, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.2129963898916967, | |
| "grad_norm": 0.5483217239379883, | |
| "learning_rate": 2.9154673787419124e-05, | |
| "loss": 0.6681, | |
| "num_input_tokens_seen": 4339421, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 1.2322503008423586, | |
| "grad_norm": 0.6174812912940979, | |
| "learning_rate": 2.793117605619231e-05, | |
| "loss": 0.6713, | |
| "num_input_tokens_seen": 4398549, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.2515042117930204, | |
| "grad_norm": 0.6561586856842041, | |
| "learning_rate": 2.6719979245413676e-05, | |
| "loss": 0.6682, | |
| "num_input_tokens_seen": 4467901, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.2707581227436824, | |
| "grad_norm": 0.617612361907959, | |
| "learning_rate": 2.552231784451528e-05, | |
| "loss": 0.6643, | |
| "num_input_tokens_seen": 4525255, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.2900120336943441, | |
| "grad_norm": 0.6367979645729065, | |
| "learning_rate": 2.4339412547218845e-05, | |
| "loss": 0.6444, | |
| "num_input_tokens_seen": 4597459, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 1.3092659446450061, | |
| "grad_norm": 0.5901610851287842, | |
| "learning_rate": 2.3172469007366636e-05, | |
| "loss": 0.6432, | |
| "num_input_tokens_seen": 4678093, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.3285198555956679, | |
| "grad_norm": 0.6240355968475342, | |
| "learning_rate": 2.20226766100817e-05, | |
| "loss": 0.6558, | |
| "num_input_tokens_seen": 4750971, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 1.3477737665463296, | |
| "grad_norm": 0.612914502620697, | |
| "learning_rate": 2.089120725950948e-05, | |
| "loss": 0.6506, | |
| "num_input_tokens_seen": 4826861, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.3670276774969916, | |
| "grad_norm": 0.6090959906578064, | |
| "learning_rate": 1.9779214184376857e-05, | |
| "loss": 0.6545, | |
| "num_input_tokens_seen": 4895159, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 1.3862815884476534, | |
| "grad_norm": 0.5601783990859985, | |
| "learning_rate": 1.8687830762585378e-05, | |
| "loss": 0.6535, | |
| "num_input_tokens_seen": 4966107, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.4055354993983153, | |
| "grad_norm": 0.5911448001861572, | |
| "learning_rate": 1.761816936603744e-05, | |
| "loss": 0.6497, | |
| "num_input_tokens_seen": 5031601, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 1.424789410348977, | |
| "grad_norm": 0.6376362442970276, | |
| "learning_rate": 1.6571320226872208e-05, | |
| "loss": 0.6616, | |
| "num_input_tokens_seen": 5100787, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.444043321299639, | |
| "grad_norm": 0.5783751010894775, | |
| "learning_rate": 1.5548350326267135e-05, | |
| "loss": 0.6604, | |
| "num_input_tokens_seen": 5173727, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.4632972322503008, | |
| "grad_norm": 0.5625059604644775, | |
| "learning_rate": 1.4550302306937619e-05, | |
| "loss": 0.6389, | |
| "num_input_tokens_seen": 5245681, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.4825511432009626, | |
| "grad_norm": 0.6026486158370972, | |
| "learning_rate": 1.3578193410443068e-05, | |
| "loss": 0.6506, | |
| "num_input_tokens_seen": 5324203, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 1.5018050541516246, | |
| "grad_norm": 0.7199910879135132, | |
| "learning_rate": 1.263301444038279e-05, | |
| "loss": 0.656, | |
| "num_input_tokens_seen": 5388385, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.5210589651022866, | |
| "grad_norm": 0.6065146327018738, | |
| "learning_rate": 1.1715728752538103e-05, | |
| "loss": 0.6634, | |
| "num_input_tokens_seen": 5455431, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 1.5403128760529483, | |
| "grad_norm": 0.6021776795387268, | |
| "learning_rate": 1.0827271272990206e-05, | |
| "loss": 0.6348, | |
| "num_input_tokens_seen": 5518719, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.5403128760529483, | |
| "eval_loss": 0.6049174070358276, | |
| "eval_runtime": 6.1672, | |
| "eval_samples_per_second": 24.322, | |
| "eval_steps_per_second": 12.161, | |
| "num_input_tokens_seen": 5518719, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.55956678700361, | |
| "grad_norm": 0.5880686044692993, | |
| "learning_rate": 9.968547545214444e-06, | |
| "loss": 0.6604, | |
| "num_input_tokens_seen": 5592171, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 1.578820697954272, | |
| "grad_norm": 0.611405611038208, | |
| "learning_rate": 9.140432807122282e-06, | |
| "loss": 0.6806, | |
| "num_input_tokens_seen": 5661159, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.5980746089049338, | |
| "grad_norm": 0.5994818806648254, | |
| "learning_rate": 8.343771098991604e-06, | |
| "loss": 0.6492, | |
| "num_input_tokens_seen": 5721247, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 1.6173285198555956, | |
| "grad_norm": 0.6033297181129456, | |
| "learning_rate": 7.57937440319462e-06, | |
| "loss": 0.6808, | |
| "num_input_tokens_seen": 5792521, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.6365824308062575, | |
| "grad_norm": 0.6016368269920349, | |
| "learning_rate": 6.848021816600221e-06, | |
| "loss": 0.6533, | |
| "num_input_tokens_seen": 5864477, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.6558363417569195, | |
| "grad_norm": 0.6104902625083923, | |
| "learning_rate": 6.15045875649424e-06, | |
| "loss": 0.6342, | |
| "num_input_tokens_seen": 5926641, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.6750902527075813, | |
| "grad_norm": 0.6614465713500977, | |
| "learning_rate": 5.487396200826957e-06, | |
| "loss": 0.6598, | |
| "num_input_tokens_seen": 5996769, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 1.694344163658243, | |
| "grad_norm": 0.6114799380302429, | |
| "learning_rate": 4.859509963562313e-06, | |
| "loss": 0.6635, | |
| "num_input_tokens_seen": 6066617, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.713598074608905, | |
| "grad_norm": 0.5675967335700989, | |
| "learning_rate": 4.267440005867252e-06, | |
| "loss": 0.6733, | |
| "num_input_tokens_seen": 6132661, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 1.7328519855595668, | |
| "grad_norm": 0.5562564134597778, | |
| "learning_rate": 3.7117897838435225e-06, | |
| "loss": 0.6298, | |
| "num_input_tokens_seen": 6201793, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.7521058965102285, | |
| "grad_norm": 0.607563316822052, | |
| "learning_rate": 3.19312563346633e-06, | |
| "loss": 0.6473, | |
| "num_input_tokens_seen": 6270295, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 1.7713598074608905, | |
| "grad_norm": 0.5713885426521301, | |
| "learning_rate": 2.7119761933572132e-06, | |
| "loss": 0.6682, | |
| "num_input_tokens_seen": 6345853, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.7906137184115525, | |
| "grad_norm": 0.6208235621452332, | |
| "learning_rate": 2.268831865979073e-06, | |
| "loss": 0.6354, | |
| "num_input_tokens_seen": 6410491, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 1.8098676293622142, | |
| "grad_norm": 0.6321476101875305, | |
| "learning_rate": 1.8641443178027784e-06, | |
| "loss": 0.6501, | |
| "num_input_tokens_seen": 6476011, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.829121540312876, | |
| "grad_norm": 0.671848475933075, | |
| "learning_rate": 1.4983260189546322e-06, | |
| "loss": 0.6699, | |
| "num_input_tokens_seen": 6548557, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.848375451263538, | |
| "grad_norm": 0.6751930713653564, | |
| "learning_rate": 1.1717498228140146e-06, | |
| "loss": 0.6615, | |
| "num_input_tokens_seen": 6623485, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.8676293622141997, | |
| "grad_norm": 0.6214536428451538, | |
| "learning_rate": 8.847485859896365e-07, | |
| "loss": 0.6627, | |
| "num_input_tokens_seen": 6689943, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 1.8868832731648615, | |
| "grad_norm": 0.5981723070144653, | |
| "learning_rate": 6.376148290617146e-07, | |
| "loss": 0.6549, | |
| "num_input_tokens_seen": 6757657, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.9061371841155235, | |
| "grad_norm": 0.5489323139190674, | |
| "learning_rate": 4.306004384359419e-07, | |
| "loss": 0.6755, | |
| "num_input_tokens_seen": 6824219, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 1.9253910950661854, | |
| "grad_norm": 0.5502476096153259, | |
| "learning_rate": 2.639164096129987e-07, | |
| "loss": 0.6372, | |
| "num_input_tokens_seen": 6895203, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.9253910950661854, | |
| "eval_loss": 0.6038384437561035, | |
| "eval_runtime": 6.1961, | |
| "eval_samples_per_second": 24.209, | |
| "eval_steps_per_second": 12.104, | |
| "num_input_tokens_seen": 6895203, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.9446450060168472, | |
| "grad_norm": 0.7226577997207642, | |
| "learning_rate": 1.3773263213540332e-07, | |
| "loss": 0.6492, | |
| "num_input_tokens_seen": 6971035, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 1.963898916967509, | |
| "grad_norm": 0.5310623049736023, | |
| "learning_rate": 5.2177716430801276e-08, | |
| "loss": 0.6521, | |
| "num_input_tokens_seen": 7041317, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.983152827918171, | |
| "grad_norm": 0.5827205777168274, | |
| "learning_rate": 7.338862728225593e-09, | |
| "loss": 0.6646, | |
| "num_input_tokens_seen": 7098531, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 1.994705174488568, | |
| "num_input_tokens_seen": 7138765, | |
| "step": 518, | |
| "total_flos": 1.1924408841596928e+17, | |
| "train_loss": 0.744573145759612, | |
| "train_runtime": 5797.4674, | |
| "train_samples_per_second": 5.733, | |
| "train_steps_per_second": 0.089 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 518, | |
| "num_input_tokens_seen": 7138765, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1924408841596928e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |