| { | |
| "best_metric": 0.4279924761510222, | |
| "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-2138", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 2138, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.8198594968909895e-06, | |
| "loss": 0.6022, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.583360012254533e-06, | |
| "loss": 0.5521, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.346860527618076e-06, | |
| "loss": 0.5166, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 4.110361042981619e-06, | |
| "loss": 0.5388, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.6151991486549377, | |
| "eval_matthews_correlation": 0.4279924761510222, | |
| "eval_runtime": 0.7154, | |
| "eval_samples_per_second": 1457.835, | |
| "eval_steps_per_second": 92.25, | |
| "step": 2138 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 10690, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 36863452007628.0, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 5.056358981527446e-06, | |
| "num_train_epochs": 5, | |
| "per_device_train_batch_size": 4, | |
| "seed": 13 | |
| } | |
| } | |