| { | |
| "best_metric": 0.8670018281535649, | |
| "best_model_checkpoint": "distilbert-hate_speech18\\run-0\\checkpoint-720", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 720, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.200932249944345e-06, | |
| "loss": 0.3542, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8555758683729433, | |
| "eval_loss": 0.34542378783226013, | |
| "eval_runtime": 27.8228, | |
| "eval_samples_per_second": 78.641, | |
| "eval_steps_per_second": 2.48, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9.607457999554758e-07, | |
| "loss": 0.3426, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8596892138939671, | |
| "eval_loss": 0.34202685952186584, | |
| "eval_runtime": 27.8449, | |
| "eval_samples_per_second": 78.578, | |
| "eval_steps_per_second": 2.478, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 7.20559349966607e-07, | |
| "loss": 0.3404, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8670018281535649, | |
| "eval_loss": 0.3405018150806427, | |
| "eval_runtime": 27.8321, | |
| "eval_samples_per_second": 78.614, | |
| "eval_steps_per_second": 2.479, | |
| "step": 720 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1440, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 500, | |
| "total_flos": 488786947408704.0, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.2937223587192618, | |
| "learning_rate": 1.441118699933214e-06, | |
| "num_train_epochs": 6, | |
| "per_device_eval_batch_size": 32, | |
| "per_device_train_batch_size": 32, | |
| "temperature": 22 | |
| } | |
| } | |