<!-- 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. -->
emotion_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: 3.8236
- Accuracy: 0.1617
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: 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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
No log | 1.0 | 282 | 4.1189 | 0.1198 |
4.3034 | 2.0 | 564 | 3.9206 | 0.1417 |
4.3034 | 3.0 | 846 | 3.8263 | 0.1397 |
3.8071 | 4.0 | 1128 | 3.7639 | 0.1677 |
3.8071 | 5.0 | 1410 | 3.7519 | 0.1657 |
3.4571 | 6.0 | 1692 | 3.7749 | 0.1597 |
3.4571 | 7.0 | 1974 | 3.8084 | 0.1557 |
3.1652 | 8.0 | 2256 | 3.8059 | 0.1657 |
2.9506 | 9.0 | 2538 | 3.8094 | 0.1637 |
2.9506 | 10.0 | 2820 | 3.8236 | 0.1617 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1