<!-- 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-17-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: 1.4087
- Accuracy: 0.6495
- F1: 0.6481
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 |
|---|---|---|---|---|---|
| 2.5228 | 1.0 | 177 | 2.0913 | 0.3364 | 0.3043 |
| 1.9362 | 2.0 | 354 | 1.7457 | 0.4353 | 0.4037 |
| 1.5719 | 3.0 | 531 | 1.4817 | 0.5244 | 0.5068 |
| 1.2558 | 4.0 | 708 | 1.3574 | 0.5654 | 0.5556 |
| 1.024 | 5.0 | 885 | 1.3139 | 0.5880 | 0.5788 |
| 0.8271 | 6.0 | 1062 | 1.3123 | 0.5922 | 0.5856 |
| 0.6645 | 7.0 | 1239 | 1.2887 | 0.6099 | 0.6067 |
| 0.5478 | 8.0 | 1416 | 1.3263 | 0.6226 | 0.6201 |
| 0.442 | 9.0 | 1593 | 1.3239 | 0.6346 | 0.6313 |
| 0.3647 | 10.0 | 1770 | 1.3360 | 0.6276 | 0.6241 |
| 0.2957 | 11.0 | 1947 | 1.3942 | 0.6325 | 0.6280 |
| 0.2534 | 12.0 | 2124 | 1.3962 | 0.6403 | 0.6397 |
| 0.2191 | 13.0 | 2301 | 1.4120 | 0.6417 | 0.6399 |
| 0.1918 | 14.0 | 2478 | 1.3978 | 0.6431 | 0.6427 |
| 0.1728 | 15.0 | 2655 | 1.4087 | 0.6495 | 0.6481 |
Framework versions
- Transformers 4.19.0
- Pytorch 1.12.1+cu113
- Datasets 1.16.1
- Tokenizers 0.12.1
