| { |
| "best_metric": 0.9414405348897014, |
| "best_model_checkpoint": "model_saves/deberta-v3-large_lemon_10k_2_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": 0.9414405348897014, |
| "eval_loss": 0.4288528263568878, |
| "eval_runtime": 4.5806, |
| "eval_samples_per_second": 956.633, |
| "eval_steps_per_second": 7.641, |
| "step": 268 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9408647234427934, |
| "eval_loss": 0.447408527135849, |
| "eval_runtime": 4.5693, |
| "eval_samples_per_second": 959.004, |
| "eval_steps_per_second": 7.66, |
| "step": 536 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9402553695815025, |
| "eval_loss": 0.47301632165908813, |
| "eval_runtime": 4.5834, |
| "eval_samples_per_second": 956.05, |
| "eval_steps_per_second": 7.636, |
| "step": 804 |
| }, |
| { |
| "epoch": 3.73, |
| "learning_rate": 1e-05, |
| "loss": 0.2621, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9395062556602825, |
| "eval_loss": 0.511528730392456, |
| "eval_runtime": 4.5711, |
| "eval_samples_per_second": 958.627, |
| "eval_steps_per_second": 7.657, |
| "step": 1072 |
| }, |
| { |
| "epoch": 4.0, |
| "step": 1072, |
| "total_flos": 1.3796262608371712e+16, |
| "train_loss": 0.256763637955509, |
| "train_runtime": 482.183, |
| "train_samples_per_second": 1067.147, |
| "train_steps_per_second": 8.337 |
| } |
| ], |
| "max_steps": 4020, |
| "num_train_epochs": 15, |
| "total_flos": 1.3796262608371712e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
