| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.6434470174382516e-05, | |
| "eval_steps": 3, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.8811490058127504e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 23.1669, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.8811490058127504e-05, | |
| "eval_loss": 5.918900489807129, | |
| "eval_runtime": 2202.7103, | |
| "eval_samples_per_second": 5.081, | |
| "eval_steps_per_second": 5.081, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.762298011625501e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 27.6838, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 5.6434470174382516e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 13.1598, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 5.6434470174382516e-05, | |
| "eval_loss": 5.918900489807129, | |
| "eval_runtime": 2202.0869, | |
| "eval_samples_per_second": 5.082, | |
| "eval_steps_per_second": 5.082, | |
| "step": 3 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2109388496044032.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |