| { |
| "best_metric": 0.8954964280128479, |
| "best_model_checkpoint": "finetune_xlnet-base-cased/checkpoint-2738", |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 2738, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.18, |
| "learning_rate": 1.879474068663258e-05, |
| "loss": 1.9283, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 1.7577307036766496e-05, |
| "loss": 1.1706, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 1.6359873386900417e-05, |
| "loss": 1.0596, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.73, |
| "learning_rate": 1.5142439737034334e-05, |
| "loss": 1.0009, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.91, |
| "learning_rate": 1.3925006087168251e-05, |
| "loss": 0.9825, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.8954964280128479, |
| "eval_runtime": 572.6201, |
| "eval_samples_per_second": 18.459, |
| "eval_steps_per_second": 0.145, |
| "step": 2738 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 8214, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "total_flos": 1.8597222647483904e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
