| { | |
| "best_metric": 0.08603910356760025, | |
| "best_model_checkpoint": "./models/albert-base-v2_1656839871.089586/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": 0.2491, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.866950354609929e-05, | |
| "loss": 0.1368, | |
| "step": 938 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.8004255319148936e-05, | |
| "loss": 0.1139, | |
| "step": 1407 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.7339007092198585e-05, | |
| "loss": 0.1082, | |
| "step": 1876 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.667375886524823e-05, | |
| "loss": 0.0974, | |
| "step": 2345 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.6008510638297874e-05, | |
| "loss": 0.0892, | |
| "step": 2814 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.534326241134752e-05, | |
| "loss": 0.0941, | |
| "step": 3283 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.4678014184397164e-05, | |
| "loss": 0.0826, | |
| "step": 3752 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.401276595744681e-05, | |
| "loss": 0.0806, | |
| "step": 4221 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.3347517730496456e-05, | |
| "loss": 0.082, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9746784684424369, | |
| "eval_f1": 0.8338050592605697, | |
| "eval_loss": 0.0911484956741333, | |
| "eval_precision": 0.8302069572875386, | |
| "eval_recall": 0.8374344852092032, | |
| "eval_runtime": 37.0605, | |
| "eval_samples_per_second": 255.771, | |
| "eval_steps_per_second": 16.001, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 1.26822695035461e-05, | |
| "loss": 0.0686, | |
| "step": 5159 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 1.2017021276595745e-05, | |
| "loss": 0.0645, | |
| "step": 5628 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 1.1351773049645392e-05, | |
| "loss": 0.0638, | |
| "step": 6097 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.0686524822695037e-05, | |
| "loss": 0.0606, | |
| "step": 6566 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1.0021276595744682e-05, | |
| "loss": 0.0616, | |
| "step": 7035 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 9.356028368794327e-06, | |
| "loss": 0.0579, | |
| "step": 7504 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 8.690780141843971e-06, | |
| "loss": 0.0561, | |
| "step": 7973 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 8.025531914893618e-06, | |
| "loss": 0.0565, | |
| "step": 8442 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 7.360283687943263e-06, | |
| "loss": 0.0551, | |
| "step": 8911 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.695035460992908e-06, | |
| "loss": 0.0592, | |
| "step": 9380 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9760701501954842, | |
| "eval_f1": 0.8429752066115702, | |
| "eval_loss": 0.08603910356760025, | |
| "eval_precision": 0.8525483783047152, | |
| "eval_recall": 0.8336146397796926, | |
| "eval_runtime": 36.5619, | |
| "eval_samples_per_second": 259.259, | |
| "eval_steps_per_second": 16.219, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 6.029787234042554e-06, | |
| "loss": 0.0406, | |
| "step": 9849 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 5.3645390070921985e-06, | |
| "loss": 0.0387, | |
| "step": 10318 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 4.699290780141844e-06, | |
| "loss": 0.0399, | |
| "step": 10787 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 4.03404255319149e-06, | |
| "loss": 0.0407, | |
| "step": 11256 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 3.368794326241135e-06, | |
| "loss": 0.0394, | |
| "step": 11725 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 2.70354609929078e-06, | |
| "loss": 0.0369, | |
| "step": 12194 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 2.0382978723404254e-06, | |
| "loss": 0.0408, | |
| "step": 12663 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 1.373049645390071e-06, | |
| "loss": 0.0363, | |
| "step": 13132 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 7.078014184397164e-07, | |
| "loss": 0.0392, | |
| "step": 13601 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 4.2553191489361707e-08, | |
| "loss": 0.0392, | |
| "step": 14070 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9780515276066022, | |
| "eval_f1": 0.8619402985074628, | |
| "eval_loss": 0.08666320890188217, | |
| "eval_precision": 0.8620168813860506, | |
| "eval_recall": 0.8618637292351425, | |
| "eval_runtime": 36.7418, | |
| "eval_samples_per_second": 257.989, | |
| "eval_steps_per_second": 16.14, | |
| "step": 14100 | |
| } | |
| ], | |
| "max_steps": 14100, | |
| "num_train_epochs": 3, | |
| "total_flos": 580572089788770.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |