| { | |
| "best_metric": 0.5164891481399536, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.04434589800443459, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008869179600886918, | |
| "eval_loss": 2.8770248889923096, | |
| "eval_runtime": 38.1113, | |
| "eval_samples_per_second": 12.463, | |
| "eval_steps_per_second": 3.122, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008869179600886918, | |
| "grad_norm": 2.364651918411255, | |
| "learning_rate": 4.02e-05, | |
| "loss": 1.7045, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.017738359201773836, | |
| "grad_norm": 5.935655117034912, | |
| "learning_rate": 8.04e-05, | |
| "loss": 1.2618, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.026607538802660754, | |
| "grad_norm": 2.099881172180176, | |
| "learning_rate": 0.0001206, | |
| "loss": 0.6453, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03547671840354767, | |
| "grad_norm": 1.2235733270645142, | |
| "learning_rate": 0.0001608, | |
| "loss": 0.3949, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04434589800443459, | |
| "grad_norm": 2.9881107807159424, | |
| "learning_rate": 0.000201, | |
| "loss": 0.4097, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04434589800443459, | |
| "eval_loss": 0.5164891481399536, | |
| "eval_runtime": 38.3505, | |
| "eval_samples_per_second": 12.386, | |
| "eval_steps_per_second": 3.103, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 500, | |
| "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": 1.2665508599955456e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |