| { | |
| "best_metric": 0.06504358351230621, | |
| "best_model_checkpoint": "./models/bert-base-cased_1656837168.84538/checkpoint-9400", | |
| "epoch": 3.0, | |
| "global_step": 14100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.9334751773049647e-05, | |
| "loss": 0.2895, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.866950354609929e-05, | |
| "loss": 0.11, | |
| "step": 938 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.8004255319148936e-05, | |
| "loss": 0.0845, | |
| "step": 1407 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.7339007092198585e-05, | |
| "loss": 0.0832, | |
| "step": 1876 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.667375886524823e-05, | |
| "loss": 0.0775, | |
| "step": 2345 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.6008510638297874e-05, | |
| "loss": 0.0666, | |
| "step": 2814 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.534326241134752e-05, | |
| "loss": 0.0703, | |
| "step": 3283 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.4678014184397164e-05, | |
| "loss": 0.0587, | |
| "step": 3752 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.401276595744681e-05, | |
| "loss": 0.0617, | |
| "step": 4221 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.3347517730496456e-05, | |
| "loss": 0.0558, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.981902240253805, | |
| "eval_f1": 0.8711506586408444, | |
| "eval_loss": 0.06536950916051865, | |
| "eval_precision": 0.8557717028022966, | |
| "eval_recall": 0.88709247579284, | |
| "eval_runtime": 31.2315, | |
| "eval_samples_per_second": 303.507, | |
| "eval_steps_per_second": 18.987, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 1.26822695035461e-05, | |
| "loss": 0.0434, | |
| "step": 5159 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 1.2017021276595745e-05, | |
| "loss": 0.0441, | |
| "step": 5628 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 1.1351773049645392e-05, | |
| "loss": 0.0428, | |
| "step": 6097 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.0686524822695037e-05, | |
| "loss": 0.0426, | |
| "step": 6566 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1.0021276595744682e-05, | |
| "loss": 0.0433, | |
| "step": 7035 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 9.356028368794327e-06, | |
| "loss": 0.0402, | |
| "step": 7504 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 8.690780141843971e-06, | |
| "loss": 0.0375, | |
| "step": 7973 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 8.025531914893618e-06, | |
| "loss": 0.04, | |
| "step": 8442 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 7.360283687943263e-06, | |
| "loss": 0.0359, | |
| "step": 8911 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.695035460992908e-06, | |
| "loss": 0.0403, | |
| "step": 9380 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9830639407002046, | |
| "eval_f1": 0.8834252924299271, | |
| "eval_loss": 0.06504358351230621, | |
| "eval_precision": 0.8779610457975083, | |
| "eval_recall": 0.8889579817002754, | |
| "eval_runtime": 30.5614, | |
| "eval_samples_per_second": 310.162, | |
| "eval_steps_per_second": 19.404, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 6.029787234042554e-06, | |
| "loss": 0.0263, | |
| "step": 9849 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 5.3645390070921985e-06, | |
| "loss": 0.0239, | |
| "step": 10318 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 4.699290780141844e-06, | |
| "loss": 0.0254, | |
| "step": 10787 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 4.03404255319149e-06, | |
| "loss": 0.0272, | |
| "step": 11256 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 3.368794326241135e-06, | |
| "loss": 0.024, | |
| "step": 11725 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 2.70354609929078e-06, | |
| "loss": 0.0242, | |
| "step": 12194 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 2.0382978723404254e-06, | |
| "loss": 0.0282, | |
| "step": 12663 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 1.373049645390071e-06, | |
| "loss": 0.0246, | |
| "step": 13132 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 7.078014184397164e-07, | |
| "loss": 0.0261, | |
| "step": 13601 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 4.2553191489361707e-08, | |
| "loss": 0.0262, | |
| "step": 14070 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9835533880964035, | |
| "eval_f1": 0.8873450004397152, | |
| "eval_loss": 0.06829366087913513, | |
| "eval_precision": 0.8785372224640836, | |
| "eval_recall": 0.8963311717153771, | |
| "eval_runtime": 30.6109, | |
| "eval_samples_per_second": 309.661, | |
| "eval_steps_per_second": 19.372, | |
| "step": 14100 | |
| } | |
| ], | |
| "max_steps": 14100, | |
| "num_train_epochs": 3, | |
| "total_flos": 6310359757516614.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |