| { |
| "best_metric": 0.8779419256240448, |
| "best_model_checkpoint": "./roberta_base/fine_tuned_models/checkpoint-36816", |
| "epoch": 3.0, |
| "global_step": 36816, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "learning_rate": 1.4814993662099355e-05, |
| "loss": 0.4891, |
| "step": 12272 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8625573102394295, |
| "eval_loss": 0.3779561519622803, |
| "eval_runtime": 45.6198, |
| "eval_samples_per_second": 215.148, |
| "eval_steps_per_second": 26.896, |
| "step": 12272 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 7.4074968310496775e-06, |
| "loss": 0.3181, |
| "step": 24544 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8757004584819155, |
| "eval_loss": 0.3620317280292511, |
| "eval_runtime": 45.5874, |
| "eval_samples_per_second": 215.301, |
| "eval_steps_per_second": 26.915, |
| "step": 24544 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 0.0, |
| "loss": 0.2271, |
| "step": 36816 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8779419256240448, |
| "eval_loss": 0.38248324394226074, |
| "eval_runtime": 45.8275, |
| "eval_samples_per_second": 214.172, |
| "eval_steps_per_second": 26.774, |
| "step": 36816 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 36816, |
| "total_flos": 7.74938740264658e+16, |
| "train_loss": 0.3447862050679392, |
| "train_runtime": 14914.656, |
| "train_samples_per_second": 78.99, |
| "train_steps_per_second": 2.468 |
| } |
| ], |
| "max_steps": 36816, |
| "num_train_epochs": 3, |
| "total_flos": 7.74938740264658e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
