<!-- 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_1_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: 0.7615
- Accuracy: 0.7895
- F1: 0.8006
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 |
|---|---|---|---|---|---|
| 1.0411 | 1.0 | 19 | 0.9506 | 0.4737 | 0.3045 |
| 0.9515 | 2.0 | 38 | 0.9126 | 0.5789 | 0.4964 |
| 0.9064 | 3.0 | 57 | 0.8215 | 0.7368 | 0.6977 |
| 0.7414 | 4.0 | 76 | 0.6747 | 0.7895 | 0.7447 |
| 0.4968 | 5.0 | 95 | 0.5658 | 0.8947 | 0.8474 |
| 0.2849 | 6.0 | 114 | 0.5001 | 0.8421 | 0.7953 |
| 0.1576 | 7.0 | 133 | 0.4605 | 0.8421 | 0.7953 |
| 0.0705 | 8.0 | 152 | 0.6264 | 0.7895 | 0.7822 |
| 0.0297 | 9.0 | 171 | 0.5283 | 0.8421 | 0.8561 |
| 0.0142 | 10.0 | 190 | 0.5972 | 0.7368 | 0.7441 |
| 0.0107 | 11.0 | 209 | 0.5542 | 0.8421 | 0.8561 |
| 0.0079 | 12.0 | 228 | 0.5919 | 0.8421 | 0.8561 |
| 0.0067 | 13.0 | 247 | 0.6106 | 0.7895 | 0.8006 |
| 0.0055 | 14.0 | 266 | 0.6232 | 0.8421 | 0.8561 |
| 0.0049 | 15.0 | 285 | 0.6478 | 0.8421 | 0.8561 |
| 0.0043 | 16.0 | 304 | 0.6465 | 0.8421 | 0.8561 |
| 0.0038 | 17.0 | 323 | 0.6618 | 0.7895 | 0.8006 |
| 0.0034 | 18.0 | 342 | 0.6669 | 0.8421 | 0.8561 |
| 0.0032 | 19.0 | 361 | 0.6737 | 0.8421 | 0.8561 |
| 0.003 | 20.0 | 380 | 0.6808 | 0.7895 | 0.8006 |
| 0.0028 | 21.0 | 399 | 0.6890 | 0.7895 | 0.8006 |
| 0.0026 | 22.0 | 418 | 0.7081 | 0.7895 | 0.8006 |
| 0.0025 | 23.0 | 437 | 0.7146 | 0.7895 | 0.8006 |
| 0.0023 | 24.0 | 456 | 0.7182 | 0.7895 | 0.8006 |
| 0.0022 | 25.0 | 475 | 0.7248 | 0.7895 | 0.8006 |
| 0.002 | 26.0 | 494 | 0.7419 | 0.7895 | 0.8006 |
| 0.0019 | 27.0 | 513 | 0.7390 | 0.7895 | 0.8006 |
| 0.0021 | 28.0 | 532 | 0.7379 | 0.7895 | 0.8006 |
| 0.0019 | 29.0 | 551 | 0.7392 | 0.7895 | 0.8006 |
| 0.0019 | 30.0 | 570 | 0.7362 | 0.7895 | 0.8006 |
| 0.0019 | 31.0 | 589 | 0.7395 | 0.7895 | 0.8006 |
| 0.0019 | 32.0 | 608 | 0.7436 | 0.7895 | 0.8006 |
| 0.0017 | 33.0 | 627 | 0.7509 | 0.7895 | 0.8006 |
| 0.0018 | 34.0 | 646 | 0.7563 | 0.7895 | 0.8006 |
| 0.0016 | 35.0 | 665 | 0.7597 | 0.7895 | 0.8006 |
| 0.0017 | 36.0 | 684 | 0.7617 | 0.7895 | 0.8006 |
| 0.0016 | 37.0 | 703 | 0.7625 | 0.7895 | 0.8006 |
| 0.0017 | 38.0 | 722 | 0.7615 | 0.7895 | 0.8006 |
| 0.0017 | 39.0 | 741 | 0.7617 | 0.7895 | 0.8006 |
| 0.0015 | 40.0 | 760 | 0.7615 | 0.7895 | 0.8006 |
Framework versions
- Transformers 4.22.2
- Pytorch 1.10.2
- Datasets 2.5.2
- Tokenizers 0.12.1
