| { |
| "best_metric": 0.49232077048388906, |
| "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-535", |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 535, |
| "is_hyper_param_search": true, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.93, |
| "learning_rate": 2.6974691318652314e-05, |
| "loss": 0.5224, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.45828381180763245, |
| "eval_matthews_correlation": 0.49232077048388906, |
| "eval_runtime": 0.7395, |
| "eval_samples_per_second": 1410.5, |
| "eval_steps_per_second": 89.255, |
| "step": 535 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1605, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "total_flos": 43246466054976.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": { |
| "learning_rate": 3.918043399677554e-05, |
| "num_train_epochs": 3, |
| "per_device_train_batch_size": 16, |
| "seed": 35 |
| } |
| } |
|
|
