| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9047619047619047, | |
| "eval_steps": 500, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 0.551876045004038, | |
| "learning_rate": 4.8776412907378845e-06, | |
| "loss": 0.1469, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 1.2404944004069458, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.1594, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.9047619047619047, | |
| "grad_norm": 0.6081967191317266, | |
| "learning_rate": 0.0, | |
| "loss": 0.13, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.9047619047619047, | |
| "step": 10, | |
| "total_flos": 6047617712128.0, | |
| "train_loss": 0.14342659264802932, | |
| "train_runtime": 271.853, | |
| "train_samples_per_second": 4.929, | |
| "train_steps_per_second": 0.037 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6047617712128.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |