<!-- 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. -->
twitter-data-xlm-roberta-base-sentiment-finetuned-memes
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: 0.2455
- Accuracy: 0.9327
- Precision: 0.9333
- Recall: 0.9327
- F1: 0.9328
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: 1e-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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.3851 | 1.0 | 1783 | 0.3286 | 0.8998 | 0.9005 | 0.8998 | 0.8997 |
| 0.2812 | 2.0 | 3566 | 0.2624 | 0.9217 | 0.9224 | 0.9217 | 0.9216 |
| 0.2501 | 3.0 | 5349 | 0.2550 | 0.9227 | 0.9252 | 0.9227 | 0.9231 |
| 0.2272 | 4.0 | 7132 | 0.2458 | 0.9268 | 0.9269 | 0.9268 | 0.9265 |
| 0.2101 | 5.0 | 8915 | 0.2441 | 0.9327 | 0.9334 | 0.9327 | 0.9327 |
| 0.1966 | 6.0 | 10698 | 0.2367 | 0.9311 | 0.9312 | 0.9311 | 0.9309 |
| 0.1822 | 7.0 | 12481 | 0.2346 | 0.9329 | 0.9334 | 0.9329 | 0.9329 |
| 0.1702 | 8.0 | 14264 | 0.2319 | 0.9343 | 0.9351 | 0.9343 | 0.9344 |
| 0.1615 | 9.0 | 16047 | 0.2426 | 0.9328 | 0.9336 | 0.9328 | 0.9329 |
| 0.1536 | 10.0 | 17830 | 0.2455 | 0.9327 | 0.9333 | 0.9327 | 0.9328 |
Framework versions
- Transformers 4.24.0.dev0
- Pytorch 1.11.0+cu102
- Datasets 2.6.1
- Tokenizers 0.13.1
