<!-- 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-english-sentweet-profane
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: 0.4291
- Accuracy: 0.8264
- Precision: 0.8459
- Recall: 0.8391
- F1: 0.8262
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 81 | 0.4475 | 0.8125 | 0.8315 | 0.8251 | 0.8123 |
| No log | 2.0 | 162 | 0.4783 | 0.8229 | 0.8388 | 0.8345 | 0.8228 |
| No log | 3.0 | 243 | 0.4674 | 0.8194 | 0.8321 | 0.8299 | 0.8194 |
| No log | 4.0 | 324 | 0.4739 | 0.7986 | 0.8074 | 0.8074 | 0.7986 |
| No log | 5.0 | 405 | 0.4395 | 0.8229 | 0.8435 | 0.8360 | 0.8227 |
| No log | 6.0 | 486 | 0.4291 | 0.8264 | 0.8459 | 0.8391 | 0.8262 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.1+cu117
- Datasets 2.6.1
- Tokenizers 0.11.0
