<!-- 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. -->
xlm-roberta-base-finetuned-emotion-37-labels
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1765
- Accuracy: 0.7185
- F1: 0.7178
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 2.4256 | 1.0 | 433 | 1.7594 | 0.4384 | 0.4079 |
| 1.5536 | 2.0 | 866 | 1.3105 | 0.5784 | 0.5631 |
| 1.1753 | 3.0 | 1299 | 1.1767 | 0.6163 | 0.6057 |
| 0.9378 | 4.0 | 1732 | 1.0613 | 0.6565 | 0.6542 |
| 0.7606 | 5.0 | 2165 | 1.0284 | 0.6808 | 0.6776 |
| 0.6167 | 6.0 | 2598 | 1.0128 | 0.6892 | 0.6888 |
| 0.5009 | 7.0 | 3031 | 1.0250 | 0.6973 | 0.6946 |
| 0.4083 | 8.0 | 3464 | 1.0506 | 0.7014 | 0.6996 |
| 0.328 | 9.0 | 3897 | 1.0658 | 0.7075 | 0.7079 |
| 0.2704 | 10.0 | 4330 | 1.0874 | 0.7106 | 0.7094 |
| 0.2203 | 11.0 | 4763 | 1.1587 | 0.7031 | 0.7010 |
| 0.1813 | 12.0 | 5196 | 1.1559 | 0.7141 | 0.7130 |
| 0.1552 | 13.0 | 5629 | 1.1483 | 0.7173 | 0.7164 |
| 0.1325 | 14.0 | 6062 | 1.1697 | 0.7173 | 0.7170 |
| 0.1239 | 15.0 | 6495 | 1.1765 | 0.7185 | 0.7178 |
Framework versions
- Transformers 4.19.0
- Pytorch 1.12.1+cu113
- Datasets 1.16.1
- Tokenizers 0.12.1
