| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04285714285714286, | |
| "eval_steps": 500, | |
| "global_step": 60, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014285714285714285, | |
| "grad_norm": 3.377620220184326, | |
| "learning_rate": 0.0002380952380952381, | |
| "loss": 5.6223, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02857142857142857, | |
| "grad_norm": 2.886795997619629, | |
| "learning_rate": 0.0004761904761904762, | |
| "loss": 4.431, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04285714285714286, | |
| "grad_norm": 2.803114175796509, | |
| "learning_rate": 0.0004933726067746687, | |
| "loss": 4.0911, | |
| "step": 60 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 1400, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 20, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 363765694464000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |