<!-- 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. -->
Sentiment-Analysis-Model
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6227
- F1 Score: 0.7304
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: 5e-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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score |
|---|---|---|---|---|
| 0.7461 | 0.5 | 500 | 0.7528 | 0.6523 |
| 0.6845 | 1.0 | 1000 | 0.6425 | 0.7132 |
| 0.5729 | 1.5 | 1500 | 0.6463 | 0.7415 |
| 0.5674 | 2.0 | 2000 | 0.6227 | 0.7304 |
| 0.41 | 2.5 | 2500 | 0.9091 | 0.7335 |
| 0.4017 | 3.0 | 3000 | 0.8304 | 0.7360 |
| 0.2691 | 3.5 | 3500 | 1.2177 | 0.7202 |
| 0.3128 | 4.0 | 4000 | 1.1197 | 0.7376 |
| 0.197 | 4.5 | 4500 | 1.2951 | 0.7341 |
| 0.1887 | 5.0 | 5000 | 1.4508 | 0.7239 |
| 0.11 | 5.5 | 5500 | 1.5447 | 0.7203 |
| 0.1462 | 6.0 | 6000 | 1.4909 | 0.7383 |
| 0.0907 | 6.5 | 6500 | 1.4809 | 0.7332 |
| 0.089 | 7.0 | 7000 | 1.7191 | 0.7244 |
| 0.0613 | 7.5 | 7500 | 1.7725 | 0.7294 |
| 0.0665 | 8.0 | 8000 | 1.8083 | 0.7290 |
| 0.0458 | 8.5 | 8500 | 1.8297 | 0.7346 |
| 0.0395 | 9.0 | 9000 | 1.8853 | 0.7304 |
| 0.0287 | 9.5 | 9500 | 1.9684 | 0.7273 |
| 0.0204 | 10.0 | 10000 | 1.9919 | 0.7308 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
