| { | |
| "best_metric": 0.5117946747628033, | |
| "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/checkpoint-2138", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 2138, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.942054911488753e-05, | |
| "loss": 0.5525, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.5833451014612775e-05, | |
| "loss": 0.4922, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.4696793258190155, | |
| "eval_matthews_correlation": 0.4691032179514943, | |
| "eval_runtime": 0.7564, | |
| "eval_samples_per_second": 1378.966, | |
| "eval_steps_per_second": 87.26, | |
| "step": 1069 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.2246352914338016e-05, | |
| "loss": 0.364, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 8.659254814063262e-06, | |
| "loss": 0.3351, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.6338055729866028, | |
| "eval_matthews_correlation": 0.5117946747628033, | |
| "eval_runtime": 0.84, | |
| "eval_samples_per_second": 1241.606, | |
| "eval_steps_per_second": 78.568, | |
| "step": 2138 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 3207, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 134171622786756.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 2.3007647215162288e-05, | |
| "num_train_epochs": 3, | |
| "per_device_train_batch_size": 8, | |
| "seed": 14 | |
| } | |
| } | |