| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 6, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.8601560592651367, | |
| "learning_rate": 0.0001666666666666667, | |
| "loss": 8.9073, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 1.0329221487045288, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 8.8817, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.9695513844490051, | |
| "learning_rate": 0.0001, | |
| "loss": 4.4217, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 2.52862548828125, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 8.7863, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 2.6519486904144287, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 8.7243, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.3600674867630005, | |
| "learning_rate": 0.0, | |
| "loss": 4.345, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 6, | |
| "total_flos": 38828625664128.0, | |
| "train_loss": 7.344388246536255, | |
| "train_runtime": 67.7284, | |
| "train_samples_per_second": 3.544, | |
| "train_steps_per_second": 0.089 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 6, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 38828625664128.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |