| { | |
| "best_metric": 0.8504556783745718, | |
| "best_model_checkpoint": "test-klue/ynat-hps/run-3/checkpoint-1142", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 1713, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.0665865551075277e-05, | |
| "loss": 0.6897, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_f1": 0.8405267782311162, | |
| "eval_loss": 0.5007498860359192, | |
| "eval_runtime": 12.2145, | |
| "eval_samples_per_second": 745.59, | |
| "eval_steps_per_second": 2.947, | |
| "step": 571 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 7.676553457164043e-06, | |
| "loss": 0.3368, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_f1": 0.8504556783745718, | |
| "eval_loss": 0.5121398568153381, | |
| "eval_runtime": 12.4319, | |
| "eval_samples_per_second": 732.553, | |
| "eval_steps_per_second": 2.896, | |
| "step": 1142 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 4.687241363252811e-06, | |
| "loss": 0.2662, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_f1": 0.8453442739504695, | |
| "eval_loss": 0.6183401942253113, | |
| "eval_runtime": 12.1492, | |
| "eval_samples_per_second": 749.597, | |
| "eval_steps_per_second": 2.963, | |
| "step": 1713 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2284, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "total_flos": 122084899086000.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 1.3655177644986507e-05, | |
| "num_train_epochs": 4, | |
| "per_device_train_batch_size": 8, | |
| "seed": 30 | |
| } | |
| } | |