| { | |
| "best_metric": 1.7225255966186523, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.053008216273522396, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010601643254704478, | |
| "eval_loss": 2.004267930984497, | |
| "eval_runtime": 54.6705, | |
| "eval_samples_per_second": 14.542, | |
| "eval_steps_per_second": 7.28, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.042406573018817915, | |
| "grad_norm": 26.655275344848633, | |
| "learning_rate": 5e-05, | |
| "loss": 12.9919, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.053008216273522396, | |
| "eval_loss": 1.7225255966186523, | |
| "eval_runtime": 54.8128, | |
| "eval_samples_per_second": 14.504, | |
| "eval_steps_per_second": 7.261, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 40, | |
| "max_steps": 400, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "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": 1.7858129848958976e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |