| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.11500862564692352, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0023001725129384704, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0023001725129384704, | |
| "eval_loss": NaN, | |
| "eval_runtime": 60.7025, | |
| "eval_samples_per_second": 3.015, | |
| "eval_steps_per_second": 1.516, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004600345025876941, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006900517538815411, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009200690051753882, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011500862564692352, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013801035077630822, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019994532573409262, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.016101207590569294, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019978136272187747, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.018401380103507763, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019950829025450114, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.020701552616446232, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019912640693269752, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.023001725129384705, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.025301897642323174, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019803799658748094, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.027602070155261643, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001973326597248006, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.029902242668200116, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019652089102773488, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03220241518113859, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019560357815343577, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.034502587694077054, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019458172417006347, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03680276020701553, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001934564464599461, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.039102932719954, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019222897549773848, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.041403105232892465, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019090065350491626, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04370327774583094, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018947293298207635, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04600345025876941, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001879473751206489, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.048303622771707876, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018632564809575742, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05060379528464635, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018460952524209355, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05290396779758482, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018280088311480201, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.055204140310523286, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05750431282346176, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017891405093963938, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05750431282346176, | |
| "eval_loss": NaN, | |
| "eval_runtime": 61.0645, | |
| "eval_samples_per_second": 2.997, | |
| "eval_steps_per_second": 1.507, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05980448533640023, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017684011108568592, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0621046578493387, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001746821476984154, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06440483036227718, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017244252047910892, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06670500287521564, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017012367842724887, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.06900517538815411, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016772815716257412, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07130534790109258, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016525857615241687, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07360552041403105, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001627176358473537, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.07590569292696953, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016010811472830252, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.078205865439908, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015743286626829437, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08050603795284646, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015469481581224272, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08280621046578493, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015189695737812152, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0851063829787234, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014904235038305083, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.08740655549166187, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001461341162978688, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.08970672800460035, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014317543523384928, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09200690051753882, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014016954246529696, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09430707303047729, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013711972489182208, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.09660724554341575, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013402931744416433, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.09890741805635422, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1012075905692927, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012774029087618446, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.10350776308223117, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012454854871407994, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10580793559516964, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001213299630743747, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.10810810810810811, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000118088053433211, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11040828062104657, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001148263647711842, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.11270845313398505, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011154846369695863, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.11500862564692352, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010825793454723325, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11500862564692352, | |
| "eval_loss": NaN, | |
| "eval_runtime": 61.0341, | |
| "eval_samples_per_second": 2.998, | |
| "eval_steps_per_second": 1.507, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.41887283560448e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |