<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
distilbert-base-uncased_finetuned_SPEECH_TEXT_CH_2_DISPLAY
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0863
- Accuracy: 0.7368
- F1: 0.7114
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: 2e-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: 40
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 1.0362 | 1.0 | 19 | 0.9281 | 0.5789 | 0.4964 |
| 0.9725 | 2.0 | 38 | 0.8906 | 0.6316 | 0.5707 |
| 0.8712 | 3.0 | 57 | 0.8080 | 0.6316 | 0.5889 |
| 0.6402 | 4.0 | 76 | 0.6386 | 0.7895 | 0.7474 |
| 0.4453 | 5.0 | 95 | 0.5401 | 0.7895 | 0.7485 |
| 0.2658 | 6.0 | 114 | 0.4999 | 0.8421 | 0.7990 |
| 0.1695 | 7.0 | 133 | 0.6248 | 0.7895 | 0.7427 |
| 0.0822 | 8.0 | 152 | 0.7391 | 0.7368 | 0.7114 |
| 0.0303 | 9.0 | 171 | 0.6665 | 0.7895 | 0.7485 |
| 0.016 | 10.0 | 190 | 0.8217 | 0.7368 | 0.7114 |
| 0.0103 | 11.0 | 209 | 0.8090 | 0.7368 | 0.7114 |
| 0.0083 | 12.0 | 228 | 0.8646 | 0.7368 | 0.7114 |
| 0.0068 | 13.0 | 247 | 0.9091 | 0.7368 | 0.7114 |
| 0.0059 | 14.0 | 266 | 0.8731 | 0.7368 | 0.7114 |
| 0.0049 | 15.0 | 285 | 0.9512 | 0.7368 | 0.7114 |
| 0.0048 | 16.0 | 304 | 0.9376 | 0.7368 | 0.7114 |
| 0.004 | 17.0 | 323 | 0.9507 | 0.7368 | 0.7114 |
| 0.0037 | 18.0 | 342 | 0.9868 | 0.7368 | 0.7114 |
| 0.0033 | 19.0 | 361 | 0.9862 | 0.7368 | 0.7114 |
| 0.0029 | 20.0 | 380 | 0.9733 | 0.7368 | 0.7114 |
| 0.0029 | 21.0 | 399 | 0.9747 | 0.7368 | 0.7114 |
| 0.0027 | 22.0 | 418 | 0.9998 | 0.7368 | 0.7114 |
| 0.0024 | 23.0 | 437 | 0.9984 | 0.7368 | 0.7114 |
| 0.0024 | 24.0 | 456 | 1.0270 | 0.7368 | 0.7114 |
| 0.0024 | 25.0 | 475 | 1.0083 | 0.7368 | 0.7114 |
| 0.0022 | 26.0 | 494 | 1.0167 | 0.7368 | 0.7114 |
| 0.0021 | 27.0 | 513 | 1.0273 | 0.7368 | 0.7114 |
| 0.002 | 28.0 | 532 | 1.0340 | 0.7368 | 0.7114 |
| 0.0021 | 29.0 | 551 | 1.0282 | 0.7368 | 0.7114 |
| 0.002 | 30.0 | 570 | 1.0372 | 0.7368 | 0.7114 |
| 0.0019 | 31.0 | 589 | 1.0593 | 0.7368 | 0.7114 |
| 0.0017 | 32.0 | 608 | 1.0841 | 0.7368 | 0.7114 |
| 0.0018 | 33.0 | 627 | 1.0920 | 0.7368 | 0.7114 |
| 0.0019 | 34.0 | 646 | 1.0943 | 0.7368 | 0.7114 |
| 0.0018 | 35.0 | 665 | 1.0883 | 0.7368 | 0.7114 |
| 0.0017 | 36.0 | 684 | 1.0864 | 0.7368 | 0.7114 |
| 0.0016 | 37.0 | 703 | 1.0890 | 0.7368 | 0.7114 |
| 0.0017 | 38.0 | 722 | 1.0894 | 0.7368 | 0.7114 |
| 0.0015 | 39.0 | 741 | 1.0867 | 0.7368 | 0.7114 |
| 0.0016 | 40.0 | 760 | 1.0863 | 0.7368 | 0.7114 |
Framework versions
- Transformers 4.22.2
- Pytorch 1.10.2
- Datasets 2.5.2
- Tokenizers 0.12.1
