| { |
| "best_metric": 0.9415970661568219, |
| "best_model_checkpoint": "model_saves/deberta-v3-large_lemon_10k_3_p3/checkpoint-268", |
| "epoch": 4.0, |
| "global_step": 1072, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9415970661568219, |
| "eval_loss": 0.4239117503166199, |
| "eval_runtime": 4.6002, |
| "eval_samples_per_second": 952.559, |
| "eval_steps_per_second": 7.608, |
| "step": 268 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.941563523742439, |
| "eval_loss": 0.4312668442726135, |
| "eval_runtime": 4.609, |
| "eval_samples_per_second": 950.754, |
| "eval_steps_per_second": 7.594, |
| "step": 536 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9405684321157437, |
| "eval_loss": 0.46239739656448364, |
| "eval_runtime": 4.5884, |
| "eval_samples_per_second": 955.022, |
| "eval_steps_per_second": 7.628, |
| "step": 804 |
| }, |
| { |
| "epoch": 3.73, |
| "learning_rate": 1e-05, |
| "loss": 0.2907, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9406299265421125, |
| "eval_loss": 0.49347540736198425, |
| "eval_runtime": 4.5985, |
| "eval_samples_per_second": 952.917, |
| "eval_steps_per_second": 7.611, |
| "step": 1072 |
| }, |
| { |
| "epoch": 4.0, |
| "step": 1072, |
| "total_flos": 1.3791221323399168e+16, |
| "train_loss": 0.28512123182638366, |
| "train_runtime": 492.5774, |
| "train_samples_per_second": 1044.628, |
| "train_steps_per_second": 8.161 |
| } |
| ], |
| "max_steps": 4020, |
| "num_train_epochs": 15, |
| "total_flos": 1.3791221323399168e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
