| { |
| "best_metric": 1.1202219724655151, |
| "best_model_checkpoint": "finetune_distilbert-base-uncased/checkpoint-5476", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 5476, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.18, |
| "learning_rate": 1.8787436084733382e-05, |
| "loss": 2.6968, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 1.7570002434867303e-05, |
| "loss": 1.6023, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 1.635256878500122e-05, |
| "loss": 1.4278, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.73, |
| "learning_rate": 1.5135135135135138e-05, |
| "loss": 1.3395, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.91, |
| "learning_rate": 1.3917701485269055e-05, |
| "loss": 1.292, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.1892027854919434, |
| "eval_runtime": 41.132, |
| "eval_samples_per_second": 256.978, |
| "eval_steps_per_second": 2.018, |
| "step": 2738 |
| }, |
| { |
| "epoch": 1.1, |
| "learning_rate": 1.270026783540297e-05, |
| "loss": 1.1553, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.28, |
| "learning_rate": 1.1482834185536888e-05, |
| "loss": 1.0573, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.46, |
| "learning_rate": 1.0265400535670807e-05, |
| "loss": 1.0386, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.64, |
| "learning_rate": 9.050401753104456e-06, |
| "loss": 1.0412, |
| "step": 4500 |
| }, |
| { |
| "epoch": 1.83, |
| "learning_rate": 7.835402970538106e-06, |
| "loss": 1.0434, |
| "step": 5000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 1.1202219724655151, |
| "eval_runtime": 40.4003, |
| "eval_samples_per_second": 261.631, |
| "eval_steps_per_second": 2.054, |
| "step": 5476 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 8214, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "total_flos": 1.7167621364554752e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
