| { | |
| "best_metric": 11.5, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.9478672985781991, | |
| "eval_steps": 20, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0196078431372549, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 1.6079, | |
| "eval_samples_per_second": 427.879, | |
| "eval_steps_per_second": 6.841, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.39215686274509803, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 1.6932, | |
| "eval_samples_per_second": 406.339, | |
| "eval_steps_per_second": 6.497, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7843137254901961, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 1.7611, | |
| "eval_samples_per_second": 390.671, | |
| "eval_steps_per_second": 6.246, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5687203791469194, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 1.643, | |
| "eval_samples_per_second": 167.381, | |
| "eval_steps_per_second": 5.478, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.7582938388625592, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 1.0634, | |
| "eval_samples_per_second": 258.61, | |
| "eval_steps_per_second": 8.464, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.9478672985781991, | |
| "grad_norm": 1.6416926882811822e-05, | |
| "learning_rate": 9.505703422053231e-05, | |
| "loss": 23.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9478672985781991, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 1.0978, | |
| "eval_samples_per_second": 250.499, | |
| "eval_steps_per_second": 8.198, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 5250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 20, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 3 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 44627247759360.0, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |