| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 1, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 675.4326171875, | |
| "epoch": 1.0, | |
| "grad_norm": 0.011617695912718773, | |
| "kl": 0.0, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0258, | |
| "num_tokens": 875773.0, | |
| "reward": 0.6923828125, | |
| "reward_std": 0.33076575957238674, | |
| "rewards/accuracy_reward": 0.0634765625, | |
| "rewards/format_reward": 0.107421875, | |
| "rewards/tag_count_reward": 0.521484375, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 1, | |
| "total_flos": 0.0, | |
| "train_loss": 0.025846945121884346, | |
| "train_runtime": 5654.5918, | |
| "train_samples_per_second": 0.091, | |
| "train_steps_per_second": 0.0 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 1, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |