| { | |
| "best_metric": 0.4915876892254164, | |
| "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-2138", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 2138, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 8.518925666809082, | |
| "learning_rate": 8.972995831812351e-06, | |
| "loss": 0.5555, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 15.430549621582031, | |
| "learning_rate": 8.046990070015412e-06, | |
| "loss": 0.509, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.5366330146789551, | |
| "eval_matthews_correlation": 0.4025454740592728, | |
| "eval_runtime": 0.8238, | |
| "eval_samples_per_second": 1266.155, | |
| "eval_steps_per_second": 80.121, | |
| "step": 1069 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 22.634355545043945, | |
| "learning_rate": 7.120984308218471e-06, | |
| "loss": 0.3856, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "grad_norm": 40.38935089111328, | |
| "learning_rate": 6.194978546421531e-06, | |
| "loss": 0.3925, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.6002808213233948, | |
| "eval_matthews_correlation": 0.4915876892254164, | |
| "eval_runtime": 0.7672, | |
| "eval_samples_per_second": 1359.42, | |
| "eval_steps_per_second": 86.023, | |
| "step": 2138 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 5345, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 75184045400472.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 9.899001593609293e-06, | |
| "num_train_epochs": 5, | |
| "per_device_train_batch_size": 8, | |
| "seed": 30 | |
| } | |
| } | |