| { | |
| "best_metric": 0.9193420727182785, | |
| "best_model_checkpoint": "./bert-base-uncased/fine_tuned_models/checkpoint-56855", | |
| "epoch": 5.0, | |
| "global_step": 56855, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.777760406488177e-05, | |
| "loss": 0.3047, | |
| "step": 11371 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9014098441751175, | |
| "eval_combined_score": 0.8851629594461485, | |
| "eval_f1": 0.8689160747171797, | |
| "eval_loss": 0.23259252309799194, | |
| "eval_runtime": 184.8012, | |
| "eval_samples_per_second": 218.776, | |
| "eval_steps_per_second": 27.348, | |
| "step": 11371 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.3333203048661326e-05, | |
| "loss": 0.1947, | |
| "step": 22742 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9104625278258719, | |
| "eval_combined_score": 0.8964000866393222, | |
| "eval_f1": 0.8823376454527725, | |
| "eval_loss": 0.22876402735710144, | |
| "eval_runtime": 186.4733, | |
| "eval_samples_per_second": 216.814, | |
| "eval_steps_per_second": 27.103, | |
| "step": 22742 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 8.888802032440885e-06, | |
| "loss": 0.1341, | |
| "step": 34113 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9148899332179075, | |
| "eval_combined_score": 0.9012690434039385, | |
| "eval_f1": 0.8876481535899697, | |
| "eval_loss": 0.25043725967407227, | |
| "eval_runtime": 184.9863, | |
| "eval_samples_per_second": 218.557, | |
| "eval_steps_per_second": 27.321, | |
| "step": 34113 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.4444010162204425e-06, | |
| "loss": 0.0941, | |
| "step": 45484 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9188473905515706, | |
| "eval_combined_score": 0.9048984850521007, | |
| "eval_f1": 0.8909495795526308, | |
| "eval_loss": 0.3024890720844269, | |
| "eval_runtime": 184.8484, | |
| "eval_samples_per_second": 218.72, | |
| "eval_steps_per_second": 27.341, | |
| "step": 45484 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0671, | |
| "step": 56855 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9193420727182785, | |
| "eval_combined_score": 0.9058325024314523, | |
| "eval_f1": 0.8923229321446261, | |
| "eval_loss": 0.34968483448028564, | |
| "eval_runtime": 184.9351, | |
| "eval_samples_per_second": 218.617, | |
| "eval_steps_per_second": 27.329, | |
| "step": 56855 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 56855, | |
| "total_flos": 1.196648813106432e+17, | |
| "train_loss": 0.15893298222829733, | |
| "train_runtime": 22957.9884, | |
| "train_samples_per_second": 79.242, | |
| "train_steps_per_second": 2.476 | |
| } | |
| ], | |
| "max_steps": 56855, | |
| "num_train_epochs": 5, | |
| "total_flos": 1.196648813106432e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |