| { |
| "best_metric": 0.0, |
| "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-1069", |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 1069, |
| "is_hyper_param_search": true, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.47, |
| "grad_norm": 2.2928521633148193, |
| "learning_rate": 1.0665121638169595e-06, |
| "loss": 0.6218, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.94, |
| "grad_norm": 4.819956302642822, |
| "learning_rate": 1.2933100053316384e-07, |
| "loss": 0.5768, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.5835884809494019, |
| "eval_matthews_correlation": 0.0, |
| "eval_runtime": 0.7311, |
| "eval_samples_per_second": 1426.684, |
| "eval_steps_per_second": 90.279, |
| "step": 1069 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1069, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "total_flos": 37738719995232.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": { |
| "learning_rate": 2.0036933271007554e-06, |
| "num_train_epochs": 1, |
| "per_device_train_batch_size": 8, |
| "seed": 19 |
| } |
| } |
|
|
