| { | |
| "best_metric": 0.43999593210437116, | |
| "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/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, | |
| "learning_rate": 3.9693511172311064e-05, | |
| "loss": 0.5777, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 2.7577054770506707e-05, | |
| "loss": 0.5164, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.4963381886482239, | |
| "eval_matthews_correlation": 0.4299032759161841, | |
| "eval_runtime": 0.7359, | |
| "eval_samples_per_second": 1417.305, | |
| "eval_steps_per_second": 89.686, | |
| "step": 1069 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.5460598368702356e-05, | |
| "loss": 0.3518, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 3.3441419668980017e-06, | |
| "loss": 0.3457, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.6384268403053284, | |
| "eval_matthews_correlation": 0.43999593210437116, | |
| "eval_runtime": 0.7288, | |
| "eval_samples_per_second": 1431.097, | |
| "eval_steps_per_second": 90.558, | |
| "step": 2138 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2138, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "total_flos": 75283395949464.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 5.180996757411542e-05, | |
| "num_train_epochs": 2, | |
| "per_device_train_batch_size": 8, | |
| "seed": 27 | |
| } | |
| } | |