| { | |
| "best_metric": 0.8916819012797075, | |
| "best_model_checkpoint": "distilbert-hate_speech18\\run-1\\checkpoint-958", | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 2395, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 6.1414387289205385e-06, | |
| "loss": 0.2985, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8784277879341865, | |
| "eval_loss": 0.29401153326034546, | |
| "eval_runtime": 9.4448, | |
| "eval_samples_per_second": 231.661, | |
| "eval_steps_per_second": 7.306, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 5.264090339074747e-06, | |
| "loss": 0.2918, | |
| "step": 958 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8916819012797075, | |
| "eval_loss": 0.29342585802078247, | |
| "eval_runtime": 9.4536, | |
| "eval_samples_per_second": 231.446, | |
| "eval_steps_per_second": 7.299, | |
| "step": 958 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.386741949228956e-06, | |
| "loss": 0.2879, | |
| "step": 1437 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8875685557586838, | |
| "eval_loss": 0.2938942015171051, | |
| "eval_runtime": 9.4764, | |
| "eval_samples_per_second": 230.889, | |
| "eval_steps_per_second": 7.281, | |
| "step": 1437 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 3.509393559383165e-06, | |
| "loss": 0.2853, | |
| "step": 1916 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8848263254113345, | |
| "eval_loss": 0.293885737657547, | |
| "eval_runtime": 9.4687, | |
| "eval_samples_per_second": 231.076, | |
| "eval_steps_per_second": 7.287, | |
| "step": 1916 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 2.6320451695373736e-06, | |
| "loss": 0.2834, | |
| "step": 2395 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8843692870201096, | |
| "eval_loss": 0.2947681248188019, | |
| "eval_runtime": 9.4769, | |
| "eval_samples_per_second": 230.877, | |
| "eval_steps_per_second": 7.281, | |
| "step": 2395 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 3832, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 8, | |
| "save_steps": 500, | |
| "total_flos": 641954735265312.0, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.24491283832577226, | |
| "learning_rate": 7.01878711876633e-06, | |
| "num_train_epochs": 8, | |
| "per_device_eval_batch_size": 32, | |
| "per_device_train_batch_size": 16, | |
| "temperature": 13 | |
| } | |
| } | |