| { | |
| "best_metric": 10.368451118469238, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.1398112548060119, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005592450192240475, | |
| "grad_norm": 0.14615148305892944, | |
| "learning_rate": 5e-05, | |
| "loss": 10.383, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005592450192240475, | |
| "eval_loss": 10.380449295043945, | |
| "eval_runtime": 0.1129, | |
| "eval_samples_per_second": 442.836, | |
| "eval_steps_per_second": 115.137, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01118490038448095, | |
| "grad_norm": 0.13564914464950562, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3826, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.016777350576721427, | |
| "grad_norm": 0.1270395666360855, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 10.3829, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0223698007689619, | |
| "grad_norm": 0.1220603659749031, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 10.3805, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.027962250961202376, | |
| "grad_norm": 0.11310075968503952, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 10.38, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.033554701153442855, | |
| "grad_norm": 0.10876661539077759, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 10.3802, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03914715134568333, | |
| "grad_norm": 0.10691489279270172, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 10.3797, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0447396015379238, | |
| "grad_norm": 0.10898499190807343, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 10.3797, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05033205173016428, | |
| "grad_norm": 0.10882221907377243, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 10.3793, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05592450192240475, | |
| "grad_norm": 0.10796788334846497, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 10.3777, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06151695211464523, | |
| "grad_norm": 0.10834939777851105, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 10.3736, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06710940230688571, | |
| "grad_norm": 0.11363967508077621, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 10.3719, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07270185249912618, | |
| "grad_norm": 0.156457781791687, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 10.3763, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07829430269136665, | |
| "grad_norm": 0.15085114538669586, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 10.3761, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.08388675288360713, | |
| "grad_norm": 0.1429266333580017, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 10.3753, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0894792030758476, | |
| "grad_norm": 0.13529515266418457, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 10.375, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.09507165326808809, | |
| "grad_norm": 0.13351839780807495, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 10.3738, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.10066410346032856, | |
| "grad_norm": 0.1335008144378662, | |
| "learning_rate": 7.75e-05, | |
| "loss": 10.3745, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.10625655365256903, | |
| "grad_norm": 0.1339954137802124, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 10.3735, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1118490038448095, | |
| "grad_norm": 0.1330738365650177, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 10.3751, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11744145403704999, | |
| "grad_norm": 0.13523127138614655, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 10.374, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.12303390422929046, | |
| "grad_norm": 0.13809822499752045, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 10.372, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.12862635442153092, | |
| "grad_norm": 0.13312876224517822, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 10.3706, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.13421880461377142, | |
| "grad_norm": 0.1388683021068573, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 10.3663, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1398112548060119, | |
| "grad_norm": 0.15188777446746826, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 10.3646, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1398112548060119, | |
| "eval_loss": 10.368451118469238, | |
| "eval_runtime": 0.1119, | |
| "eval_samples_per_second": 447.013, | |
| "eval_steps_per_second": 116.223, | |
| "step": 25 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 21504314966016.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |