| { | |
| "best_metric": 0.6293103448275862, | |
| "best_model_checkpoint": "bert-finetuned-spam/run-2/checkpoint-832", | |
| "epoch": 3.98562874251497, | |
| "eval_steps": 500, | |
| "global_step": 832, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9964071856287425, | |
| "eval_accuracy": 0.5804597701149425, | |
| "eval_loss": 0.6732388138771057, | |
| "eval_runtime": 11.9781, | |
| "eval_samples_per_second": 87.159, | |
| "eval_steps_per_second": 5.51, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 1.9976047904191616, | |
| "eval_accuracy": 0.6130268199233716, | |
| "eval_loss": 0.6690407395362854, | |
| "eval_runtime": 11.994, | |
| "eval_samples_per_second": 87.044, | |
| "eval_steps_per_second": 5.503, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 2.3952095808383236, | |
| "grad_norm": 1.6917777061462402, | |
| "learning_rate": 4.6632922685890546e-07, | |
| "loss": 0.677, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.998802395209581, | |
| "eval_accuracy": 0.6273946360153256, | |
| "eval_loss": 0.6667826771736145, | |
| "eval_runtime": 11.9544, | |
| "eval_samples_per_second": 87.332, | |
| "eval_steps_per_second": 5.521, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 3.98562874251497, | |
| "eval_accuracy": 0.6293103448275862, | |
| "eval_loss": 0.6659389138221741, | |
| "eval_runtime": 11.9787, | |
| "eval_samples_per_second": 87.155, | |
| "eval_steps_per_second": 5.51, | |
| "step": 832 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 832, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "total_flos": 1819087895090448.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 1.168632279357257e-06, | |
| "num_train_epochs": 4, | |
| "per_device_train_batch_size": 4, | |
| "seed": 36 | |
| } | |
| } | |