| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0015498971528207675, | |
| "eval_steps": 500, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003874742882051919, | |
| "grad_norm": 0.6923572421073914, | |
| "learning_rate": 1.9230769230769234e-07, | |
| "loss": 2.0671, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007749485764103837, | |
| "grad_norm": 0.6222718954086304, | |
| "learning_rate": 3.846153846153847e-07, | |
| "loss": 2.0267, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011624228646155755, | |
| "grad_norm": 0.6504022479057312, | |
| "learning_rate": 5.76923076923077e-07, | |
| "loss": 2.0381, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0015498971528207675, | |
| "grad_norm": 0.7175610065460205, | |
| "learning_rate": 7.692307692307694e-07, | |
| "loss": 2.0284, | |
| "step": 4 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 2580, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 4, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3924509009642496.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |