| { |
| "best_metric": 0.9416361989736021, |
| "best_model_checkpoint": "model_saves/deberta-v3-large_lemon-spell_5k_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": 0.9416361989736021, |
| "eval_loss": 0.4123726785182953, |
| "eval_runtime": 4.5229, |
| "eval_samples_per_second": 968.848, |
| "eval_steps_per_second": 7.738, |
| "step": 268 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9413454980489495, |
| "eval_loss": 0.421928346157074, |
| "eval_runtime": 4.507, |
| "eval_samples_per_second": 972.257, |
| "eval_steps_per_second": 7.766, |
| "step": 536 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9405516609085522, |
| "eval_loss": 0.45214593410491943, |
| "eval_runtime": 4.5246, |
| "eval_samples_per_second": 968.48, |
| "eval_steps_per_second": 7.735, |
| "step": 804 |
| }, |
| { |
| "epoch": 3.73, |
| "learning_rate": 1e-05, |
| "loss": 0.2931, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9403224544102684, |
| "eval_loss": 0.4867420196533203, |
| "eval_runtime": 4.5116, |
| "eval_samples_per_second": 971.265, |
| "eval_steps_per_second": 7.758, |
| "step": 1072 |
| }, |
| { |
| "epoch": 4.0, |
| "step": 1072, |
| "total_flos": 1.356509451649024e+16, |
| "train_loss": 0.28746453149994805, |
| "train_runtime": 479.5005, |
| "train_samples_per_second": 1073.117, |
| "train_steps_per_second": 8.384 |
| } |
| ], |
| "max_steps": 4020, |
| "num_train_epochs": 15, |
| "total_flos": 1.356509451649024e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|