Hugging Face's logo

hung200504
/
bert-covid-39

Question Answering
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
bert-covid-39 / README.md
hung200504's picture
hung200504
bert-squad
1670505
preview code
|
raw
history blame contribute delete
4.86 kB
metadata
license: mit
base_model: hung200504/bert-squadv2
tags:
  - generated_from_trainer
model-index:
  - name: bert-covid-39
    results: []

bert-covid-39

This model is a fine-tuned version of hung200504/bert-squadv2 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7252

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: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 2

Training results

Training Loss Epoch Step Validation Loss
4.5591 0.03 5 1.2012
1.2596 0.06 10 1.4381
1.0125 0.08 15 1.0124
1.2428 0.11 20 0.9407
1.2052 0.14 25 0.9740
0.6547 0.17 30 1.0313
0.7966 0.2 35 0.9168
0.8611 0.22 40 0.8861
1.7148 0.25 45 0.7733
1.2914 0.28 50 1.0139
1.6152 0.31 55 0.7834
0.9688 0.34 60 0.7517
0.909 0.37 65 0.8122
0.7823 0.39 70 0.7512
0.8386 0.42 75 0.7157
0.7884 0.45 80 0.7113
0.9594 0.48 85 0.7621
0.8959 0.51 90 0.7472
0.5305 0.53 95 0.8187
0.8252 0.56 100 0.7381
1.6898 0.59 105 0.7426
1.0982 0.62 110 0.7209
1.1293 0.65 115 0.7321
0.4554 0.67 120 0.6945
1.2818 0.7 125 0.8030
0.3392 0.73 130 0.8722
1.3006 0.76 135 0.7928
0.853 0.79 140 0.8538
0.8214 0.81 145 0.8217
1.0063 0.84 150 0.8014
0.5788 0.87 155 0.7998
0.5167 0.9 160 0.8472
1.2736 0.93 165 0.7444
0.5527 0.96 170 0.7315
1.0421 0.98 175 0.7767
0.3837 1.01 180 0.7005
0.5765 1.04 185 0.7062
0.6094 1.07 190 0.7248
0.3476 1.1 195 0.7205
0.6104 1.12 200 0.7028
0.681 1.15 205 0.6956
0.9434 1.18 210 0.7217
0.3486 1.21 215 0.7119
0.311 1.24 220 0.6895
0.4587 1.26 225 0.7079
0.8009 1.29 230 0.7364
0.511 1.32 235 0.7349
0.4046 1.35 240 0.7259
0.6761 1.38 245 0.7351
0.3349 1.4 250 0.7341
0.8276 1.43 255 0.7304
0.1637 1.46 260 0.7316
0.2998 1.49 265 0.7621
0.6454 1.52 270 0.7695
0.336 1.54 275 0.7485
0.3583 1.57 280 0.7430
0.3906 1.6 285 0.7457
0.6049 1.63 290 0.7502
0.7388 1.66 295 0.7679
0.5119 1.69 300 0.7832
0.7891 1.71 305 0.7909
0.5389 1.74 310 0.7808
0.235 1.77 315 0.7770
0.7812 1.8 320 0.7598
0.4588 1.83 325 0.7491
0.6632 1.85 330 0.7418
0.8314 1.88 335 0.7369
0.78 1.91 340 0.7365
0.6049 1.94 345 0.7322
0.5554 1.97 350 0.7271
0.9808 1.99 355 0.7252

Framework versions

  • Transformers 4.34.1
  • Pytorch 2.1.0+cu118
  • Datasets 2.14.6
  • Tokenizers 0.14.1