| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 17, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.6142034548944337, |
| "grad_norm": 0.15625, |
| "learning_rate": 4.8e-05, |
| "loss": 1.148, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.7445295852526854, |
| "eval_loss": 1.1497305631637573, |
| "eval_runtime": 66.9763, |
| "eval_samples_per_second": 298.583, |
| "eval_steps_per_second": 3.121, |
| "step": 17 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 17, |
| "total_flos": 6.81815703552e+16, |
| "train_loss": 1.1451126827913172, |
| "train_runtime": 507.5022, |
| "train_samples_per_second": 197.043, |
| "train_steps_per_second": 0.033 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 17, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 5000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6.81815703552e+16, |
| "train_batch_size": 96, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
