| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.00028232039129606236, | |
| "eval_steps": 5, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.8232039129606233e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2317.7563, | |
| "eval_samples_per_second": 6.435, | |
| "eval_steps_per_second": 3.218, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.46961173888187e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00014116019564803118, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2326.2301, | |
| "eval_samples_per_second": 6.412, | |
| "eval_steps_per_second": 3.206, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0001693922347776374, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002540883521664561, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00028232039129606236, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2327.8173, | |
| "eval_samples_per_second": 6.407, | |
| "eval_steps_per_second": 3.204, | |
| "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": 3515647493406720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |