| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.010160880609652836, | |
| "eval_steps": 9, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011289867344058708, | |
| "eval_loss": 11.095446586608887, | |
| "eval_runtime": 5.2252, | |
| "eval_samples_per_second": 142.77, | |
| "eval_steps_per_second": 35.788, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003386960203217612, | |
| "grad_norm": 1.9205418825149536, | |
| "learning_rate": 3e-05, | |
| "loss": 44.3861, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006773920406435224, | |
| "grad_norm": 2.004185676574707, | |
| "learning_rate": 6e-05, | |
| "loss": 44.3659, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010160880609652836, | |
| "grad_norm": 2.0670409202575684, | |
| "learning_rate": 9e-05, | |
| "loss": 44.3444, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010160880609652836, | |
| "eval_loss": 11.07402229309082, | |
| "eval_runtime": 4.807, | |
| "eval_samples_per_second": 155.189, | |
| "eval_steps_per_second": 38.901, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 78596014080.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |