| { | |
| "best_metric": 0.5925781726837158, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.04555808656036447, | |
| "eval_steps": 5, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004555808656036446, | |
| "eval_loss": 0.6795058846473694, | |
| "eval_runtime": 15.6799, | |
| "eval_samples_per_second": 5.931, | |
| "eval_steps_per_second": 2.997, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01366742596810934, | |
| "grad_norm": 1.5004208087921143, | |
| "learning_rate": 6e-05, | |
| "loss": 2.8563, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.022779043280182234, | |
| "eval_loss": 0.6548665165901184, | |
| "eval_runtime": 15.9971, | |
| "eval_samples_per_second": 5.814, | |
| "eval_steps_per_second": 2.938, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02733485193621868, | |
| "grad_norm": 1.222702145576477, | |
| "learning_rate": 9.96057350657239e-05, | |
| "loss": 2.6377, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04100227790432802, | |
| "grad_norm": 1.2079116106033325, | |
| "learning_rate": 9.381533400219318e-05, | |
| "loss": 2.425, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04555808656036447, | |
| "eval_loss": 0.5925781726837158, | |
| "eval_runtime": 16.4774, | |
| "eval_samples_per_second": 5.644, | |
| "eval_steps_per_second": 2.852, | |
| "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": 2164457522331648.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |