| { | |
| "best_metric": 0.48176026344299316, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.0789473684210527, | |
| "eval_steps": 25, | |
| "global_step": 36, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08421052631578947, | |
| "grad_norm": 1.1740972995758057, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2844, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08421052631578947, | |
| "eval_loss": 1.3319251537322998, | |
| "eval_runtime": 2.7879, | |
| "eval_samples_per_second": 17.934, | |
| "eval_steps_per_second": 4.663, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.16842105263157894, | |
| "grad_norm": 1.4649646282196045, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2397, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.25263157894736843, | |
| "grad_norm": 1.1169487237930298, | |
| "learning_rate": 9.980803793327656e-05, | |
| "loss": 1.3121, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.3368421052631579, | |
| "grad_norm": 0.8863370418548584, | |
| "learning_rate": 9.923378948577559e-05, | |
| "loss": 1.062, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 0.7358220219612122, | |
| "learning_rate": 9.828215394277687e-05, | |
| "loss": 0.9588, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5052631578947369, | |
| "grad_norm": 0.6172772645950317, | |
| "learning_rate": 9.6961250323196e-05, | |
| "loss": 1.0153, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5894736842105263, | |
| "grad_norm": 0.5239005088806152, | |
| "learning_rate": 9.528234811097782e-05, | |
| "loss": 0.7944, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.6736842105263158, | |
| "grad_norm": 0.5319935083389282, | |
| "learning_rate": 9.325977110783264e-05, | |
| "loss": 0.8517, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.7578947368421053, | |
| "grad_norm": 0.5327427983283997, | |
| "learning_rate": 9.091077522761079e-05, | |
| "loss": 0.8961, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 0.48572230339050293, | |
| "learning_rate": 8.825540127492967e-05, | |
| "loss": 0.733, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9263157894736842, | |
| "grad_norm": 0.5374416708946228, | |
| "learning_rate": 8.531630396409507e-05, | |
| "loss": 0.8154, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.0263157894736843, | |
| "grad_norm": 0.7051270008087158, | |
| "learning_rate": 8.211855863706654e-05, | |
| "loss": 1.0351, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.1105263157894736, | |
| "grad_norm": 0.4763837158679962, | |
| "learning_rate": 7.868944732948101e-05, | |
| "loss": 0.6081, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.194736842105263, | |
| "grad_norm": 0.46353086829185486, | |
| "learning_rate": 7.505822600994424e-05, | |
| "loss": 0.555, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.2789473684210526, | |
| "grad_norm": 0.4545828402042389, | |
| "learning_rate": 7.12558749784219e-05, | |
| "loss": 0.6901, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.3631578947368421, | |
| "grad_norm": 0.37700918316841125, | |
| "learning_rate": 6.731483455324374e-05, | |
| "loss": 0.5407, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.4473684210526316, | |
| "grad_norm": 0.3490205705165863, | |
| "learning_rate": 6.326872830174567e-05, | |
| "loss": 0.5456, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.5315789473684212, | |
| "grad_norm": 0.4074508547782898, | |
| "learning_rate": 5.9152076175848594e-05, | |
| "loss": 0.7221, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.6157894736842104, | |
| "grad_norm": 0.351009726524353, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.5462, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 0.4087543785572052, | |
| "learning_rate": 5.0847923824151424e-05, | |
| "loss": 0.6514, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.7842105263157895, | |
| "grad_norm": 0.3485751450061798, | |
| "learning_rate": 4.673127169825433e-05, | |
| "loss": 0.6087, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.868421052631579, | |
| "grad_norm": 0.3051629364490509, | |
| "learning_rate": 4.268516544675628e-05, | |
| "loss": 0.5718, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.9526315789473685, | |
| "grad_norm": 0.3701104521751404, | |
| "learning_rate": 3.8744125021578126e-05, | |
| "loss": 0.6357, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.0526315789473686, | |
| "grad_norm": 0.3353174328804016, | |
| "learning_rate": 3.494177399005578e-05, | |
| "loss": 0.7183, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.136842105263158, | |
| "grad_norm": 0.25411513447761536, | |
| "learning_rate": 3.1310552670518986e-05, | |
| "loss": 0.4791, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.136842105263158, | |
| "eval_loss": 0.48176026344299316, | |
| "eval_runtime": 1.5422, | |
| "eval_samples_per_second": 32.422, | |
| "eval_steps_per_second": 8.43, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.221052631578947, | |
| "grad_norm": 0.2521531283855438, | |
| "learning_rate": 2.7881441362933468e-05, | |
| "loss": 0.4739, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.305263157894737, | |
| "grad_norm": 0.2974882423877716, | |
| "learning_rate": 2.4683696035904928e-05, | |
| "loss": 0.5741, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.389473684210526, | |
| "grad_norm": 0.254207581281662, | |
| "learning_rate": 2.1744598725070347e-05, | |
| "loss": 0.4982, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.473684210526316, | |
| "grad_norm": 0.2415657490491867, | |
| "learning_rate": 1.9089224772389225e-05, | |
| "loss": 0.5196, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.557894736842105, | |
| "grad_norm": 0.2914498746395111, | |
| "learning_rate": 1.674022889216737e-05, | |
| "loss": 0.5687, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.6421052631578945, | |
| "grad_norm": 0.24279502034187317, | |
| "learning_rate": 1.4717651889022202e-05, | |
| "loss": 0.4589, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.7263157894736842, | |
| "grad_norm": 0.28355467319488525, | |
| "learning_rate": 1.3038749676803994e-05, | |
| "loss": 0.5528, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.8105263157894735, | |
| "grad_norm": 0.23004592955112457, | |
| "learning_rate": 1.1717846057223144e-05, | |
| "loss": 0.4843, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.8947368421052633, | |
| "grad_norm": 0.2817566692829132, | |
| "learning_rate": 1.076621051422442e-05, | |
| "loss": 0.6326, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.9789473684210526, | |
| "grad_norm": 0.3518288731575012, | |
| "learning_rate": 1.019196206672345e-05, | |
| "loss": 0.6554, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 3.0789473684210527, | |
| "grad_norm": 0.27997156977653503, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5919, | |
| "step": 36 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 36, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 9.092146379567923e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |