| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.08130081300813008, | |
| "eval_steps": 500, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008130081300813009, | |
| "grad_norm": 13.1743803024292, | |
| "learning_rate": 2e-05, | |
| "loss": 1.3419, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04065040650406504, | |
| "grad_norm": 23.33847999572754, | |
| "learning_rate": 1.1736481776669307e-05, | |
| "loss": 1.7476, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08130081300813008, | |
| "grad_norm": 6.350980281829834, | |
| "learning_rate": 0.0, | |
| "loss": 1.3456, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08130081300813008, | |
| "eval_loss": 1.2611583471298218, | |
| "eval_runtime": 7.3824, | |
| "eval_samples_per_second": 35.083, | |
| "eval_steps_per_second": 0.677, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08130081300813008, | |
| "step": 10, | |
| "total_flos": 1.3980126869979136e+16, | |
| "train_loss": 1.5060624361038208, | |
| "train_runtime": 361.6153, | |
| "train_samples_per_second": 3.54, | |
| "train_steps_per_second": 0.028 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100000000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.3980126869979136e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |