| { | |
| "best_metric": 0.7893835616438356, | |
| "best_model_checkpoint": "distilbert-base-uncased-finetuned-SA/run-5/checkpoint-1169", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 2338, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 5.201071262359619, | |
| "learning_rate": 1.1428870609437754e-05, | |
| "loss": 0.706, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.526836633682251, | |
| "learning_rate": 9.52849305549067e-06, | |
| "loss": 0.5265, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7893835616438356, | |
| "eval_loss": 0.5095133185386658, | |
| "eval_runtime": 3.5658, | |
| "eval_samples_per_second": 163.78, | |
| "eval_steps_per_second": 10.376, | |
| "step": 1169 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 53.4073600769043, | |
| "learning_rate": 7.6281155015435886e-06, | |
| "loss": 0.4275, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 18.367666244506836, | |
| "learning_rate": 5.727737947596506e-06, | |
| "loss": 0.4062, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7791095890410958, | |
| "eval_loss": 0.5382534861564636, | |
| "eval_runtime": 3.5769, | |
| "eval_samples_per_second": 163.268, | |
| "eval_steps_per_second": 10.344, | |
| "step": 2338 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 3507, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 651755105188110.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 1.3329248163384835e-05, | |
| "num_train_epochs": 3, | |
| "per_device_train_batch_size": 4, | |
| "seed": 29 | |
| } | |
| } | |