| { | |
| "best_metric": 0.0, | |
| "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-1069", | |
| "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": 0.4677268475210477, | |
| "grad_norm": 1.7254643440246582, | |
| "learning_rate": 1.1968622152407689e-06, | |
| "loss": 0.6226, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9354536950420954, | |
| "grad_norm": 7.422174453735352, | |
| "learning_rate": 8.315196586959675e-07, | |
| "loss": 0.5927, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.5829020738601685, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 32.3413, | |
| "eval_samples_per_second": 32.25, | |
| "eval_steps_per_second": 2.041, | |
| "step": 1069 | |
| }, | |
| { | |
| "epoch": 1.4031805425631432, | |
| "grad_norm": 3.6254794597625732, | |
| "learning_rate": 4.661771021511663e-07, | |
| "loss": 0.5612, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.8709073900841908, | |
| "grad_norm": 4.46693229675293, | |
| "learning_rate": 1.0083454560636514e-07, | |
| "loss": 0.5373, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.5621180534362793, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 28.7656, | |
| "eval_samples_per_second": 36.259, | |
| "eval_steps_per_second": 2.294, | |
| "step": 2138 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2138, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "total_flos": 75003196354260.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 1.56220477178557e-06, | |
| "num_train_epochs": 2, | |
| "per_device_train_batch_size": 8, | |
| "seed": 21 | |
| } | |
| } | |