| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 10.0, |
| "eval_steps": 500, |
| "global_step": 30, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.8, |
| "grad_norm": 117.5, |
| "learning_rate": 6.5e-05, |
| "loss": -0.9799934387207031, |
| "step": 5 |
| }, |
| { |
| "epoch": 3.4, |
| "grad_norm": 836.0, |
| "learning_rate": 5.2499999999999995e-05, |
| "loss": -24.085472106933594, |
| "step": 10 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 592.0, |
| "learning_rate": 3.9999999999999996e-05, |
| "loss": -85.5773193359375, |
| "step": 15 |
| }, |
| { |
| "epoch": 6.8, |
| "grad_norm": 115.0, |
| "learning_rate": 2.7499999999999998e-05, |
| "loss": -104.323828125, |
| "step": 20 |
| }, |
| { |
| "epoch": 8.4, |
| "grad_norm": 112.0, |
| "learning_rate": 1.4999999999999999e-05, |
| "loss": -106.30146484375, |
| "step": 25 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 113.5, |
| "learning_rate": 2.4999999999999998e-06, |
| "loss": -106.82431640625, |
| "step": 30 |
| }, |
| { |
| "epoch": 10.0, |
| "step": 30, |
| "total_flos": 0.0, |
| "train_loss": -71.34873237609864, |
| "train_runtime": 56.2243, |
| "train_samples_per_second": 7.114, |
| "train_steps_per_second": 0.534 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 30, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "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": 0.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
