--- license: mit base_model: hung200504/bert-squadv2 tags: - generated_from_trainer model-index: - name: bert-covid-17 results: [] --- # bert-covid-17 This model is a fine-tuned version of [hung200504/bert-squadv2](https://huggingface.co/hung200504/bert-squadv2) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.7620 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 3e-05 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 4.8507 | 0.01 | 5 | 1.7050 | | 2.5037 | 0.03 | 10 | 1.1213 | | 0.0842 | 0.04 | 15 | 1.4939 | | 2.8332 | 0.06 | 20 | 1.4768 | | 1.2692 | 0.07 | 25 | 1.2021 | | 0.2025 | 0.08 | 30 | 1.1680 | | 2.51 | 0.1 | 35 | 1.2461 | | 1.1259 | 0.11 | 40 | 1.1270 | | 1.0897 | 0.13 | 45 | 1.0785 | | 1.3906 | 0.14 | 50 | 1.1147 | | 0.927 | 0.15 | 55 | 1.1139 | | 0.3758 | 0.17 | 60 | 1.3199 | | 1.1277 | 0.18 | 65 | 1.3911 | | 1.0594 | 0.2 | 70 | 1.3420 | | 1.2825 | 0.21 | 75 | 1.2110 | | 0.808 | 0.23 | 80 | 1.1443 | | 1.5312 | 0.24 | 85 | 0.9526 | | 2.018 | 0.25 | 90 | 0.9191 | | 1.5825 | 0.27 | 95 | 1.3486 | | 1.1372 | 0.28 | 100 | 0.9432 | | 1.7199 | 0.3 | 105 | 0.8875 | | 1.6011 | 0.31 | 110 | 0.9181 | | 1.2766 | 0.32 | 115 | 0.8318 | | 1.1237 | 0.34 | 120 | 0.8442 | | 0.5508 | 0.35 | 125 | 0.9121 | | 1.4098 | 0.37 | 130 | 0.9341 | | 0.6475 | 0.38 | 135 | 1.0059 | | 0.935 | 0.39 | 140 | 1.0911 | | 0.9492 | 0.41 | 145 | 1.0617 | | 1.0106 | 0.42 | 150 | 0.8882 | | 0.8134 | 0.44 | 155 | 0.8288 | | 0.58 | 0.45 | 160 | 0.8277 | | 0.9716 | 0.46 | 165 | 0.8748 | | 1.7163 | 0.48 | 170 | 0.9919 | | 1.5798 | 0.49 | 175 | 0.8783 | | 0.4907 | 0.51 | 180 | 0.8564 | | 0.5704 | 0.52 | 185 | 1.1316 | | 0.6746 | 0.54 | 190 | 1.2307 | | 1.3695 | 0.55 | 195 | 1.0486 | | 0.4738 | 0.56 | 200 | 0.9003 | | 1.4755 | 0.58 | 205 | 0.8812 | | 2.2741 | 0.59 | 210 | 0.8017 | | 1.2088 | 0.61 | 215 | 0.7571 | | 0.7497 | 0.62 | 220 | 0.7528 | | 1.2208 | 0.63 | 225 | 0.7363 | | 0.9775 | 0.65 | 230 | 0.7547 | | 1.0131 | 0.66 | 235 | 0.7881 | | 0.5256 | 0.68 | 240 | 0.8114 | | 0.9784 | 0.69 | 245 | 0.8149 | | 1.512 | 0.7 | 250 | 0.7748 | | 0.0092 | 0.72 | 255 | 0.8031 | | 0.4212 | 0.73 | 260 | 0.8552 | | 1.401 | 0.75 | 265 | 0.8860 | | 1.9551 | 0.76 | 270 | 0.8160 | | 1.2076 | 0.77 | 275 | 0.7408 | | 0.348 | 0.79 | 280 | 0.7252 | | 0.6292 | 0.8 | 285 | 0.7186 | | 0.8604 | 0.82 | 290 | 0.7170 | | 0.8213 | 0.83 | 295 | 0.7139 | | 0.5231 | 0.85 | 300 | 0.7190 | | 0.7271 | 0.86 | 305 | 0.7393 | | 0.3221 | 0.87 | 310 | 0.7759 | | 1.0033 | 0.89 | 315 | 0.8094 | | 0.1807 | 0.9 | 320 | 0.8364 | | 1.9334 | 0.92 | 325 | 0.8349 | | 1.2876 | 0.93 | 330 | 0.8080 | | 0.8867 | 0.94 | 335 | 0.7826 | | 0.6698 | 0.96 | 340 | 0.7800 | | 1.2023 | 0.97 | 345 | 0.7761 | | 1.4764 | 0.99 | 350 | 0.7647 | | 0.3514 | 1.0 | 355 | 0.7620 | ### Framework versions - Transformers 4.34.1 - Pytorch 2.1.0+cu118 - Datasets 2.14.6 - Tokenizers 0.14.1