| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.0012175818823815902, | |
| "eval_steps": 5, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00012175818823815901, | |
| "eval_loss": NaN, | |
| "eval_runtime": 126.5869, | |
| "eval_samples_per_second": 27.325, | |
| "eval_steps_per_second": 13.666, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00036527456471447707, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006087909411907951, | |
| "eval_loss": NaN, | |
| "eval_runtime": 127.1528, | |
| "eval_samples_per_second": 27.203, | |
| "eval_steps_per_second": 13.606, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007305491294289541, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.96057350657239e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010958236941434312, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.381533400219318e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0012175818823815902, | |
| "eval_loss": NaN, | |
| "eval_runtime": 125.5208, | |
| "eval_samples_per_second": 27.557, | |
| "eval_steps_per_second": 13.783, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "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": 229804183388160.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |