| { | |
| "best_metric": 0.6609398126602173, | |
| "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_data_aug_cola_256/checkpoint-1669", | |
| "epoch": 6.0, | |
| "global_step": 10014, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.9e-05, | |
| "loss": 0.5394, | |
| "step": 1669 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.6609398126602173, | |
| "eval_matthews_correlation": 0.09390288672705373, | |
| "eval_runtime": 1.5393, | |
| "eval_samples_per_second": 677.575, | |
| "eval_steps_per_second": 5.847, | |
| "step": 1669 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.4545, | |
| "step": 3338 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.7807448506355286, | |
| "eval_matthews_correlation": 0.04738043679310804, | |
| "eval_runtime": 1.5509, | |
| "eval_samples_per_second": 672.507, | |
| "eval_steps_per_second": 5.803, | |
| "step": 3338 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.7e-05, | |
| "loss": 0.4253, | |
| "step": 5007 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.8028568625450134, | |
| "eval_matthews_correlation": 0.08459402343109, | |
| "eval_runtime": 1.5345, | |
| "eval_samples_per_second": 679.705, | |
| "eval_steps_per_second": 5.865, | |
| "step": 5007 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 0.388, | |
| "step": 6676 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.8929793238639832, | |
| "eval_matthews_correlation": 0.07382848474505407, | |
| "eval_runtime": 1.5345, | |
| "eval_samples_per_second": 679.693, | |
| "eval_steps_per_second": 5.865, | |
| "step": 6676 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.3433, | |
| "step": 8345 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.9283742308616638, | |
| "eval_matthews_correlation": 0.0834401861698737, | |
| "eval_runtime": 1.5422, | |
| "eval_samples_per_second": 676.307, | |
| "eval_steps_per_second": 5.836, | |
| "step": 8345 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.2986, | |
| "step": 10014 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.0809475183486938, | |
| "eval_matthews_correlation": 0.10257980116603183, | |
| "eval_runtime": 1.5331, | |
| "eval_samples_per_second": 680.304, | |
| "eval_steps_per_second": 5.87, | |
| "step": 10014 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "step": 10014, | |
| "total_flos": 3.3760240390373376e+16, | |
| "train_loss": 0.4082020370455971, | |
| "train_runtime": 6186.1806, | |
| "train_samples_per_second": 1726.501, | |
| "train_steps_per_second": 13.49 | |
| } | |
| ], | |
| "max_steps": 83450, | |
| "num_train_epochs": 50, | |
| "total_flos": 3.3760240390373376e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |