| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005797101449275362, | |
| "eval_steps": 1, | |
| "global_step": 2, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002898550724637681, | |
| "grad_norm": 0.3978370130062103, | |
| "learning_rate": 0.0, | |
| "loss": 10.7491, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005797101449275362, | |
| "grad_norm": 0.526188313961029, | |
| "learning_rate": 2e-05, | |
| "loss": 10.7438, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005797101449275362, | |
| "step": 2, | |
| "total_flos": 233472.0, | |
| "train_loss": 10.746472358703613, | |
| "train_runtime": 1.3081, | |
| "train_samples_per_second": 1.529, | |
| "train_steps_per_second": 1.529 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 2, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 233472.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |