| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06944685579360395, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.034723427896801974, | |
| "grad_norm": 5.474236965179443, | |
| "learning_rate": 1.0078933669097135e-05, | |
| "loss": 0.4287, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.034723427896801974, | |
| "eval_reranking_loss": 0.3680732250213623, | |
| "eval_reranking_runtime": 2755.6935, | |
| "eval_reranking_samples_per_second": 37.158, | |
| "eval_reranking_steps_per_second": 4.645, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.06944685579360395, | |
| "grad_norm": 2.755843162536621, | |
| "learning_rate": 0.0, | |
| "loss": 0.3629, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.06944685579360395, | |
| "eval_reranking_loss": 0.34085196256637573, | |
| "eval_reranking_runtime": 2756.0448, | |
| "eval_reranking_samples_per_second": 37.153, | |
| "eval_reranking_steps_per_second": 4.644, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1000, | |
| "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": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |