| { | |
| "best_metric": 11.5, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 3.0059171597633134, | |
| "eval_steps": 50, | |
| "global_step": 127, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.023668639053254437, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 2.1539, | |
| "eval_samples_per_second": 132.316, | |
| "eval_steps_per_second": 4.178, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.183431952662722, | |
| "grad_norm": 0.000450698658823967, | |
| "learning_rate": 0.000217, | |
| "loss": 46.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.183431952662722, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 3.5165, | |
| "eval_samples_per_second": 81.048, | |
| "eval_steps_per_second": 2.559, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.366863905325444, | |
| "grad_norm": 0.00041695436812005937, | |
| "learning_rate": 0.000217, | |
| "loss": 46.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.366863905325444, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 3.5065, | |
| "eval_samples_per_second": 81.279, | |
| "eval_steps_per_second": 2.567, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 127, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 80401181687808.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |