| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.8791208791208791, |
| "global_step": 40, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.22, |
| "learning_rate": 7.777777777777778e-05, |
| "loss": 0.8027, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.22, |
| "eval_accuracy": 0.8369565010070801, |
| "eval_loss": 0.7568933367729187, |
| "eval_runtime": 13.5084, |
| "eval_samples_per_second": 6.811, |
| "eval_steps_per_second": 1.703, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 5.555555555555556e-05, |
| "loss": 0.7402, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.44, |
| "eval_accuracy": 0.8369565010070801, |
| "eval_loss": 0.7551282644271851, |
| "eval_runtime": 13.7945, |
| "eval_samples_per_second": 6.669, |
| "eval_steps_per_second": 1.667, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.66, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 0.444, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.66, |
| "eval_accuracy": 0.8369565010070801, |
| "eval_loss": 0.7342018485069275, |
| "eval_runtime": 14.5668, |
| "eval_samples_per_second": 6.316, |
| "eval_steps_per_second": 1.579, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 1.1111111111111112e-05, |
| "loss": 0.7216, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.88, |
| "eval_accuracy": 0.8369565010070801, |
| "eval_loss": 0.74174565076828, |
| "eval_runtime": 13.966, |
| "eval_samples_per_second": 6.587, |
| "eval_steps_per_second": 1.647, |
| "step": 40 |
| } |
| ], |
| "max_steps": 45, |
| "num_train_epochs": 1, |
| "total_flos": 6.81097944756096e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
