| { | |
| "best_metric": 2.2999963760375977, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.18691588785046728, | |
| "eval_steps": 5, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.018691588785046728, | |
| "eval_loss": 5.048659801483154, | |
| "eval_runtime": 9.1876, | |
| "eval_samples_per_second": 4.898, | |
| "eval_steps_per_second": 1.306, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.056074766355140186, | |
| "grad_norm": 1.9920928478240967, | |
| "learning_rate": 0.00012, | |
| "loss": 4.5377, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09345794392523364, | |
| "eval_loss": 3.927874803543091, | |
| "eval_runtime": 8.8199, | |
| "eval_samples_per_second": 5.102, | |
| "eval_steps_per_second": 1.361, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.11214953271028037, | |
| "grad_norm": 1.958602786064148, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 4.2235, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.16822429906542055, | |
| "grad_norm": 1.8812912702560425, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 3.2036, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.18691588785046728, | |
| "eval_loss": 2.2999963760375977, | |
| "eval_runtime": 8.8792, | |
| "eval_samples_per_second": 5.068, | |
| "eval_steps_per_second": 1.351, | |
| "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": 1.26955844272128e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |