| { |
| "best_metric": 0.9416026565592192, |
| "best_model_checkpoint": "model_saves/deberta-v3-large_lemon_5k_3_p3/checkpoint-536", |
| "epoch": 5.0, |
| "global_step": 1340, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9414349444873042, |
| "eval_loss": 0.4127908945083618, |
| "eval_runtime": 4.5287, |
| "eval_samples_per_second": 967.6, |
| "eval_steps_per_second": 7.728, |
| "step": 268 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9416026565592192, |
| "eval_loss": 0.4202573299407959, |
| "eval_runtime": 4.5397, |
| "eval_samples_per_second": 965.258, |
| "eval_steps_per_second": 7.71, |
| "step": 536 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9402833215934883, |
| "eval_loss": 0.4516950249671936, |
| "eval_runtime": 4.5372, |
| "eval_samples_per_second": 965.786, |
| "eval_steps_per_second": 7.714, |
| "step": 804 |
| }, |
| { |
| "epoch": 3.73, |
| "learning_rate": 1e-05, |
| "loss": 0.2959, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9403615872270487, |
| "eval_loss": 0.4774470329284668, |
| "eval_runtime": 4.525, |
| "eval_samples_per_second": 968.402, |
| "eval_steps_per_second": 7.735, |
| "step": 1072 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9390198906517291, |
| "eval_loss": 0.5193233489990234, |
| "eval_runtime": 4.5347, |
| "eval_samples_per_second": 966.321, |
| "eval_steps_per_second": 7.718, |
| "step": 1340 |
| }, |
| { |
| "epoch": 5.0, |
| "step": 1340, |
| "total_flos": 1.694981597167616e+16, |
| "train_loss": 0.2665206225950327, |
| "train_runtime": 588.505, |
| "train_samples_per_second": 874.351, |
| "train_steps_per_second": 6.831 |
| } |
| ], |
| "max_steps": 4020, |
| "num_train_epochs": 15, |
| "total_flos": 1.694981597167616e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
