B_model2
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0339
- Precision: 0.9316
- Recall: 0.9369
- F1: 0.9342
- Accuracy: 0.9883
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: 2.65095847146542e-05
- train_batch_size: 16
- eval_batch_size: 16
- 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 | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.057 | 0.03 | 500 | 0.0598 | 0.8641 | 0.8859 | 0.8749 | 0.9795 |
0.0512 | 0.06 | 1000 | 0.0496 | 0.9001 | 0.8916 | 0.8958 | 0.9827 |
0.0356 | 0.09 | 1500 | 0.0512 | 0.8670 | 0.9215 | 0.8934 | 0.9823 |
0.051 | 0.12 | 2000 | 0.0549 | 0.8399 | 0.9425 | 0.8883 | 0.9808 |
0.0485 | 0.15 | 2500 | 0.0459 | 0.8909 | 0.9284 | 0.9093 | 0.9843 |
0.0411 | 0.18 | 3000 | 0.0449 | 0.9071 | 0.9137 | 0.9104 | 0.9844 |
0.0376 | 0.21 | 3500 | 0.0428 | 0.9085 | 0.9138 | 0.9111 | 0.9851 |
0.0408 | 0.24 | 4000 | 0.0419 | 0.9136 | 0.9146 | 0.9141 | 0.9850 |
0.0501 | 0.27 | 4500 | 0.0406 | 0.9221 | 0.9089 | 0.9154 | 0.9855 |
0.0386 | 0.3 | 5000 | 0.0390 | 0.9214 | 0.9166 | 0.9190 | 0.9863 |
0.0372 | 0.34 | 5500 | 0.0390 | 0.9027 | 0.9398 | 0.9209 | 0.9860 |
0.0353 | 0.37 | 6000 | 0.0384 | 0.9195 | 0.9261 | 0.9228 | 0.9865 |
0.0353 | 0.4 | 6500 | 0.0375 | 0.9257 | 0.9216 | 0.9236 | 0.9866 |
0.0455 | 0.43 | 7000 | 0.0383 | 0.9186 | 0.9265 | 0.9225 | 0.9865 |
0.025 | 0.46 | 7500 | 0.0391 | 0.9093 | 0.9378 | 0.9233 | 0.9865 |
0.0328 | 0.49 | 8000 | 0.0380 | 0.9320 | 0.9179 | 0.9249 | 0.9869 |
0.0298 | 0.52 | 8500 | 0.0384 | 0.9222 | 0.9287 | 0.9254 | 0.9869 |
0.0337 | 0.55 | 9000 | 0.0372 | 0.9260 | 0.9208 | 0.9234 | 0.9867 |
0.0203 | 0.58 | 9500 | 0.0400 | 0.9166 | 0.9343 | 0.9254 | 0.9868 |
0.0312 | 0.61 | 10000 | 0.0364 | 0.9178 | 0.9361 | 0.9269 | 0.9870 |
0.0332 | 0.64 | 10500 | 0.0359 | 0.9196 | 0.9356 | 0.9275 | 0.9872 |
0.0291 | 0.67 | 11000 | 0.0363 | 0.9291 | 0.9253 | 0.9272 | 0.9871 |
0.0289 | 0.7 | 11500 | 0.0355 | 0.9304 | 0.9317 | 0.9310 | 0.9877 |
0.0196 | 0.73 | 12000 | 0.0359 | 0.9251 | 0.9357 | 0.9304 | 0.9875 |
0.0251 | 0.76 | 12500 | 0.0357 | 0.9187 | 0.9420 | 0.9302 | 0.9875 |
0.0235 | 0.79 | 13000 | 0.0357 | 0.9249 | 0.9408 | 0.9328 | 0.9879 |
0.0275 | 0.82 | 13500 | 0.0353 | 0.9308 | 0.9345 | 0.9326 | 0.9879 |
0.0269 | 0.85 | 14000 | 0.0352 | 0.9300 | 0.9328 | 0.9314 | 0.9880 |
0.0251 | 0.88 | 14500 | 0.0348 | 0.9375 | 0.9316 | 0.9346 | 0.9884 |
0.0143 | 0.91 | 15000 | 0.0347 | 0.9275 | 0.9408 | 0.9341 | 0.9882 |
0.0187 | 0.94 | 15500 | 0.0342 | 0.9299 | 0.9373 | 0.9336 | 0.9882 |
0.0209 | 0.98 | 16000 | 0.0339 | 0.9316 | 0.9369 | 0.9342 | 0.9883 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 1