| { | |
| "best_metric": 0.873400365630713, | |
| "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-21\\checkpoint-3830", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 3830, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.6415598291804705e-05, | |
| "loss": 0.4745, | |
| "step": 1915 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8656307129798904, | |
| "eval_loss": 0.47823667526245117, | |
| "eval_runtime": 10.7929, | |
| "eval_samples_per_second": 202.726, | |
| "eval_steps_per_second": 1.668, | |
| "step": 1915 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.4523, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.873400365630713, | |
| "eval_loss": 0.4745141267776489, | |
| "eval_runtime": 10.6783, | |
| "eval_samples_per_second": 204.902, | |
| "eval_steps_per_second": 1.686, | |
| "step": 3830 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 3830, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "total_flos": 1539897026112.0, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 9.283119658360941e-05, | |
| "num_train_epochs": 2, | |
| "per_device_train_batch_size": 4, | |
| "seed": 19 | |
| } | |
| } | |