| { |
| "best_metric": 5.843591721621522e-10, |
| "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_data_aug_mrpc/checkpoint-35262", |
| "epoch": 23.0, |
| "global_step": 45057, |
| "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": 0.1838, |
| "step": 1959 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9950980392156863, |
| "eval_combined_score": 0.995750458456764, |
| "eval_f1": 0.9964028776978416, |
| "eval_loss": 0.013783634640276432, |
| "eval_runtime": 0.4532, |
| "eval_samples_per_second": 900.209, |
| "eval_steps_per_second": 8.826, |
| "step": 1959 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 4.8e-05, |
| "loss": 0.0406, |
| "step": 3918 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 1.0, |
| "eval_combined_score": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 0.005524557549506426, |
| "eval_runtime": 0.4517, |
| "eval_samples_per_second": 903.294, |
| "eval_steps_per_second": 8.856, |
| "step": 3918 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 4.7e-05, |
| "loss": 0.0267, |
| "step": 5877 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9975490196078431, |
| "eval_combined_score": 0.997876843735699, |
| "eval_f1": 0.9982046678635548, |
| "eval_loss": 0.012892701663076878, |
| "eval_runtime": 0.4563, |
| "eval_samples_per_second": 894.22, |
| "eval_steps_per_second": 8.767, |
| "step": 5877 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 0.0151, |
| "step": 7836 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 1.0, |
| "eval_combined_score": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 0.00039428556920029223, |
| "eval_runtime": 0.4545, |
| "eval_samples_per_second": 897.643, |
| "eval_steps_per_second": 8.8, |
| "step": 7836 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 4.5e-05, |
| "loss": 0.0108, |
| "step": 9795 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9975490196078431, |
| "eval_combined_score": 0.997876843735699, |
| "eval_f1": 0.9982046678635548, |
| "eval_loss": 0.010444208979606628, |
| "eval_runtime": 0.4519, |
| "eval_samples_per_second": 902.771, |
| "eval_steps_per_second": 8.851, |
| "step": 9795 |
| }, |
| { |
| "epoch": 6.0, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.0075, |
| "step": 11754 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 1.0, |
| "eval_combined_score": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 1.37044798975694e-05, |
| "eval_runtime": 0.4818, |
| "eval_samples_per_second": 846.87, |
| "eval_steps_per_second": 8.303, |
| "step": 11754 |
| }, |
| { |
| "epoch": 7.0, |
| "learning_rate": 4.3e-05, |
| "loss": 0.0059, |
| "step": 13713 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 1.0, |
| "eval_combined_score": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 0.0005156163824722171, |
| "eval_runtime": 0.4515, |
| "eval_samples_per_second": 903.731, |
| "eval_steps_per_second": 8.86, |
| "step": 13713 |
| }, |
| { |
| "epoch": 8.0, |
| "learning_rate": 4.2e-05, |
| "loss": 0.0047, |
| "step": 15672 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 1.0, |
| "eval_combined_score": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 1.4846425074210856e-05, |
| "eval_runtime": 0.4532, |
| "eval_samples_per_second": 900.352, |
| "eval_steps_per_second": 8.827, |
| "step": 15672 |
| }, |
| { |
| "epoch": 9.0, |
| "learning_rate": 4.1e-05, |
| "loss": 0.0033, |
| "step": 17631 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 1.0, |
| "eval_combined_score": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 9.473485988564789e-05, |
| "eval_runtime": 0.4507, |
| "eval_samples_per_second": 905.29, |
| "eval_steps_per_second": 8.875, |
| "step": 17631 |
| }, |
| { |
| "epoch": 10.0, |
| "learning_rate": 4e-05, |
| "loss": 0.0031, |
| "step": 19590 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_accuracy": 1.0, |
| "eval_combined_score": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 3.4562839346108376e-07, |
| "eval_runtime": 0.4522, |
| "eval_samples_per_second": 902.352, |
| "eval_steps_per_second": 8.847, |
| "step": 19590 |
| }, |
| { |
| "epoch": 11.0, |
| "learning_rate": 3.9000000000000006e-05, |
| "loss": 0.0025, |
| "step": 21549 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_accuracy": 1.0, |
| "eval_combined_score": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 1.871667905106733e-06, |
| "eval_runtime": 0.4541, |
| "eval_samples_per_second": 898.423, |
| "eval_steps_per_second": 8.808, |
| "step": 21549 |
| }, |
| { |
| "epoch": 12.0, |
| "learning_rate": 3.8e-05, |
| "loss": 0.0019, |
| "step": 23508 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_accuracy": 1.0, |
| "eval_combined_score": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 4.236588679873421e-08, |
| "eval_runtime": 0.4549, |
| "eval_samples_per_second": 896.923, |
| "eval_steps_per_second": 8.793, |
| "step": 23508 |
| }, |
| { |
| "epoch": 13.0, |
| "learning_rate": 3.7e-05, |
| "loss": 0.0019, |
| "step": 25467 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_accuracy": 1.0, |
| "eval_combined_score": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 1.6456193634439842e-06, |
| "eval_runtime": 0.4519, |
| "eval_samples_per_second": 902.776, |
| "eval_steps_per_second": 8.851, |
| "step": 25467 |
| }, |
| { |
| "epoch": 14.0, |
| "learning_rate": 3.6e-05, |
| "loss": 0.0014, |
| "step": 27426 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_accuracy": 1.0, |
| "eval_combined_score": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 1.5865224156641489e-07, |
| "eval_runtime": 0.4547, |
| "eval_samples_per_second": 897.244, |
| "eval_steps_per_second": 8.797, |
| "step": 27426 |
| }, |
| { |
| "epoch": 15.0, |
| "learning_rate": 3.5e-05, |
| "loss": 0.001, |
| "step": 29385 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_accuracy": 1.0, |
| "eval_combined_score": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 6.775987912988057e-06, |
| "eval_runtime": 0.4518, |
| "eval_samples_per_second": 903.035, |
| "eval_steps_per_second": 8.853, |
| "step": 29385 |
| }, |
| { |
| "epoch": 16.0, |
| "learning_rate": 3.4000000000000007e-05, |
| "loss": 0.001, |
| "step": 31344 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_accuracy": 1.0, |
| "eval_combined_score": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 4.674864584330862e-08, |
| "eval_runtime": 0.4524, |
| "eval_samples_per_second": 901.759, |
| "eval_steps_per_second": 8.841, |
| "step": 31344 |
| }, |
| { |
| "epoch": 17.0, |
| "learning_rate": 3.3e-05, |
| "loss": 0.0009, |
| "step": 33303 |
| }, |
| { |
| "epoch": 17.0, |
| "eval_accuracy": 1.0, |
| "eval_combined_score": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 3.7983216572001766e-08, |
| "eval_runtime": 0.4506, |
| "eval_samples_per_second": 905.494, |
| "eval_steps_per_second": 8.877, |
| "step": 33303 |
| }, |
| { |
| "epoch": 18.0, |
| "learning_rate": 3.2000000000000005e-05, |
| "loss": 0.0009, |
| "step": 35262 |
| }, |
| { |
| "epoch": 18.0, |
| "eval_accuracy": 1.0, |
| "eval_combined_score": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 5.843591721621522e-10, |
| "eval_runtime": 0.4512, |
| "eval_samples_per_second": 904.186, |
| "eval_steps_per_second": 8.865, |
| "step": 35262 |
| }, |
| { |
| "epoch": 19.0, |
| "learning_rate": 3.1e-05, |
| "loss": 0.0006, |
| "step": 37221 |
| }, |
| { |
| "epoch": 19.0, |
| "eval_accuracy": 1.0, |
| "eval_combined_score": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 2.1329100263756118e-08, |
| "eval_runtime": 0.4524, |
| "eval_samples_per_second": 901.947, |
| "eval_steps_per_second": 8.843, |
| "step": 37221 |
| }, |
| { |
| "epoch": 20.0, |
| "learning_rate": 3e-05, |
| "loss": 0.0006, |
| "step": 39180 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_accuracy": 1.0, |
| "eval_combined_score": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 1.9020757235921337e-07, |
| "eval_runtime": 0.4625, |
| "eval_samples_per_second": 882.103, |
| "eval_steps_per_second": 8.648, |
| "step": 39180 |
| }, |
| { |
| "epoch": 21.0, |
| "learning_rate": 2.9e-05, |
| "loss": 0.0003, |
| "step": 41139 |
| }, |
| { |
| "epoch": 21.0, |
| "eval_accuracy": 1.0, |
| "eval_combined_score": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 6.7201266773508905e-09, |
| "eval_runtime": 0.455, |
| "eval_samples_per_second": 896.759, |
| "eval_steps_per_second": 8.792, |
| "step": 41139 |
| }, |
| { |
| "epoch": 22.0, |
| "learning_rate": 2.8000000000000003e-05, |
| "loss": 0.0003, |
| "step": 43098 |
| }, |
| { |
| "epoch": 22.0, |
| "eval_accuracy": 1.0, |
| "eval_combined_score": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 1.8991272554558236e-07, |
| "eval_runtime": 0.4554, |
| "eval_samples_per_second": 895.928, |
| "eval_steps_per_second": 8.784, |
| "step": 43098 |
| }, |
| { |
| "epoch": 23.0, |
| "learning_rate": 2.7000000000000002e-05, |
| "loss": 0.0005, |
| "step": 45057 |
| }, |
| { |
| "epoch": 23.0, |
| "eval_accuracy": 1.0, |
| "eval_combined_score": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 2.0744714390730223e-08, |
| "eval_runtime": 0.4514, |
| "eval_samples_per_second": 903.797, |
| "eval_steps_per_second": 8.861, |
| "step": 45057 |
| }, |
| { |
| "epoch": 23.0, |
| "step": 45057, |
| "total_flos": 1.8081776184747622e+17, |
| "train_loss": 0.013702845788788859, |
| "train_runtime": 21120.7767, |
| "train_samples_per_second": 593.577, |
| "train_steps_per_second": 4.638 |
| } |
| ], |
| "max_steps": 97950, |
| "num_train_epochs": 50, |
| "total_flos": 1.8081776184747622e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
