| { |
| "best_metric": 0.5717902779579163, |
| "best_model_checkpoint": "Finetuned_bert/checkpoint-2000", |
| "epoch": 3.0, |
| "global_step": 3000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.5, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 0.7565, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 1.3333333333333333e-05, |
| "loss": 0.6275, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.768, |
| "eval_loss": 0.5923901796340942, |
| "eval_runtime": 67.4205, |
| "eval_samples_per_second": 29.665, |
| "eval_steps_per_second": 3.708, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.5, |
| "learning_rate": 1e-05, |
| "loss": 0.5073, |
| "step": 1500 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 6.666666666666667e-06, |
| "loss": 0.4898, |
| "step": 2000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.781, |
| "eval_loss": 0.5717902779579163, |
| "eval_runtime": 67.2175, |
| "eval_samples_per_second": 29.754, |
| "eval_steps_per_second": 3.719, |
| "step": 2000 |
| }, |
| { |
| "epoch": 2.5, |
| "learning_rate": 3.3333333333333333e-06, |
| "loss": 0.3394, |
| "step": 2500 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 0.0, |
| "loss": 0.3211, |
| "step": 3000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.7815, |
| "eval_loss": 0.6927292943000793, |
| "eval_runtime": 67.2789, |
| "eval_samples_per_second": 29.727, |
| "eval_steps_per_second": 3.716, |
| "step": 3000 |
| } |
| ], |
| "max_steps": 3000, |
| "num_train_epochs": 3, |
| "total_flos": 6313932685218816.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
