| { | |
| "best_metric": 0.634705330626114, | |
| "best_model_checkpoint": "test-klue/ynat/run-3/checkpoint-2073", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 2073, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.7061206107369956e-05, | |
| "loss": 0.8931, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_f1": 0.6198716753557617, | |
| "eval_loss": 0.7939329743385315, | |
| "eval_runtime": 9.5969, | |
| "eval_samples_per_second": 246.85, | |
| "eval_steps_per_second": 1.98, | |
| "step": 691 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 1.1638063670189422e-05, | |
| "loss": 0.7034, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_f1": 0.6312509900868551, | |
| "eval_loss": 0.8182857632637024, | |
| "eval_runtime": 9.614, | |
| "eval_samples_per_second": 246.412, | |
| "eval_steps_per_second": 1.976, | |
| "step": 1382 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 6.214921233008891e-06, | |
| "loss": 0.5792, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 7.917787958283578e-07, | |
| "loss": 0.4078, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_f1": 0.634705330626114, | |
| "eval_loss": 1.034997582435608, | |
| "eval_runtime": 9.5469, | |
| "eval_samples_per_second": 248.143, | |
| "eval_steps_per_second": 1.99, | |
| "step": 2073 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2073, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 672285615898680.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 2.237588569580688e-05, | |
| "num_train_epochs": 3, | |
| "per_device_train_batch_size": 8, | |
| "seed": 39 | |
| } | |
| } | |