| { | |
| "best_metric": 0.6534409523010254, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.5983545250560958, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.011967090501121914, | |
| "grad_norm": 11.746336936950684, | |
| "learning_rate": 5e-05, | |
| "loss": 4.3107, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011967090501121914, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.9307, | |
| "eval_samples_per_second": 114.182, | |
| "eval_steps_per_second": 14.399, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02393418100224383, | |
| "grad_norm": 11.741243362426758, | |
| "learning_rate": 0.0001, | |
| "loss": 4.3254, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03590127150336574, | |
| "grad_norm": 10.741928100585938, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.0354, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04786836200448766, | |
| "grad_norm": 7.754953384399414, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.6626, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05983545250560957, | |
| "grad_norm": 7.887713432312012, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.8429, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07180254300673149, | |
| "grad_norm": 8.430523872375488, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.3845, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08376963350785341, | |
| "grad_norm": 4.98731803894043, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.0405, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09573672400897532, | |
| "grad_norm": 4.610218524932861, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.8455, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.10770381451009724, | |
| "grad_norm": 2.6115477085113525, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.7532, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11967090501121914, | |
| "grad_norm": 4.972604751586914, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.7105, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.13163799551234107, | |
| "grad_norm": 3.9826550483703613, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.7128, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.14360508601346297, | |
| "grad_norm": 6.129772186279297, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.7158, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.15557217651458488, | |
| "grad_norm": 4.263116836547852, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.7414, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.16753926701570682, | |
| "grad_norm": 3.859707832336426, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.7533, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.17950635751682872, | |
| "grad_norm": 3.044384479522705, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.725, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.19147344801795063, | |
| "grad_norm": 1.5025105476379395, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.6679, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.20344053851907254, | |
| "grad_norm": 1.998008131980896, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.6668, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.21540762902019447, | |
| "grad_norm": 2.3586137294769287, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.6825, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.22737471952131638, | |
| "grad_norm": 1.0638742446899414, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.649, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2393418100224383, | |
| "grad_norm": 1.374294638633728, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.6837, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2513089005235602, | |
| "grad_norm": 1.2036421298980713, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.6681, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.26327599102468213, | |
| "grad_norm": 1.2960809469223022, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.6281, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.275243081525804, | |
| "grad_norm": 0.574422299861908, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.627, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.28721017202692595, | |
| "grad_norm": 0.6000377535820007, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.6426, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2991772625280479, | |
| "grad_norm": 0.9646682143211365, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.6476, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2991772625280479, | |
| "eval_loss": 0.6616689562797546, | |
| "eval_runtime": 4.9314, | |
| "eval_samples_per_second": 114.167, | |
| "eval_steps_per_second": 14.398, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.31114435302916976, | |
| "grad_norm": 3.2467966079711914, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7302, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3231114435302917, | |
| "grad_norm": 2.911585807800293, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.6855, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.33507853403141363, | |
| "grad_norm": 1.2173607349395752, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.6575, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3470456245325355, | |
| "grad_norm": 0.9109578728675842, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.6314, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.35901271503365745, | |
| "grad_norm": 2.12790584564209, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.6653, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3709798055347794, | |
| "grad_norm": 1.9173645973205566, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.6826, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.38294689603590126, | |
| "grad_norm": 1.5864529609680176, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.6398, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3949139865370232, | |
| "grad_norm": 0.49075672030448914, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.6084, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.4068810770381451, | |
| "grad_norm": 1.548568606376648, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.625, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.418848167539267, | |
| "grad_norm": 1.5237716436386108, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.6102, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.43081525804038895, | |
| "grad_norm": 1.6438311338424683, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.6662, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.44278234854151083, | |
| "grad_norm": 0.4927654564380646, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.6654, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.45474943904263276, | |
| "grad_norm": 1.176863670349121, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.6997, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4667165295437547, | |
| "grad_norm": 1.7410774230957031, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.6752, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.4786836200448766, | |
| "grad_norm": 0.8015233874320984, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.6267, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4906507105459985, | |
| "grad_norm": 0.6555165648460388, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.6412, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5026178010471204, | |
| "grad_norm": 1.1170567274093628, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.6525, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5145848915482424, | |
| "grad_norm": 0.7687378525733948, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.6476, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5265519820493643, | |
| "grad_norm": 0.5519921183586121, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.6052, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5385190725504861, | |
| "grad_norm": 1.3455817699432373, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.6142, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.550486163051608, | |
| "grad_norm": 1.2510255575180054, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.6408, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.56245325355273, | |
| "grad_norm": 1.7463011741638184, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.6705, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5744203440538519, | |
| "grad_norm": 1.1176273822784424, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.5998, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5863874345549738, | |
| "grad_norm": 1.4608560800552368, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.6772, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5983545250560958, | |
| "grad_norm": 1.8109873533248901, | |
| "learning_rate": 0.0, | |
| "loss": 0.6619, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5983545250560958, | |
| "eval_loss": 0.6534409523010254, | |
| "eval_runtime": 5.1055, | |
| "eval_samples_per_second": 110.274, | |
| "eval_steps_per_second": 13.907, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.83042868150272e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |