| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.0, | |
| "eval_steps": 500, | |
| "global_step": 1656, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9057971014492754, | |
| "grad_norm": 1.3455069065093994, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9137, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.8115942028985508, | |
| "grad_norm": 0.6821095943450928, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4615, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.717391304347826, | |
| "grad_norm": 1.3968886137008667, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3043, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3.6231884057971016, | |
| "grad_norm": 0.9846513271331787, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2248, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.528985507246377, | |
| "grad_norm": 0.889771580696106, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1835, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 5.434782608695652, | |
| "grad_norm": 0.5584134459495544, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1685, | |
| "step": 1500 | |
| } | |
| ], | |
| "logging_steps": 250, | |
| "max_steps": 1656, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 250, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.1047252202307584e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |