| { | |
| "best_metric": 0.8752285191956124, | |
| "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-13\\checkpoint-2874", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 2874, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 6.33398074154431e-05, | |
| "loss": 0.4745, | |
| "step": 958 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8720292504570384, | |
| "eval_loss": 0.4704694151878357, | |
| "eval_runtime": 10.736, | |
| "eval_samples_per_second": 203.8, | |
| "eval_steps_per_second": 1.677, | |
| "step": 958 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3.166990370772155e-05, | |
| "loss": 0.4517, | |
| "step": 1916 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8738574040219378, | |
| "eval_loss": 0.4702502191066742, | |
| "eval_runtime": 10.7957, | |
| "eval_samples_per_second": 202.673, | |
| "eval_steps_per_second": 1.667, | |
| "step": 1916 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.4398, | |
| "step": 2874 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8752285191956124, | |
| "eval_loss": 0.47249820828437805, | |
| "eval_runtime": 10.7363, | |
| "eval_samples_per_second": 203.795, | |
| "eval_steps_per_second": 1.677, | |
| "step": 2874 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2874, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 2937053187840.0, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 9.500971112316465e-05, | |
| "num_train_epochs": 3, | |
| "per_device_train_batch_size": 8, | |
| "seed": 23 | |
| } | |
| } | |