<!-- 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. -->
mytest_trainer_roberta
This model is a fine-tuned version of cardiffnlp/twitter-xlm-roberta-base-sentiment on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8617
- Rmse: 0.6928
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: 16
- eval_batch_size: 8
- 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 | Rmse |
|---|---|---|---|---|
| 0.7365 | 1.0 | 500 | 0.6992 | 0.7543 |
| 0.6079 | 2.0 | 1000 | 0.6532 | 0.6841 |
| 0.4798 | 3.0 | 1500 | 0.7034 | 0.6823 |
| 0.3451 | 4.0 | 2000 | 0.7757 | 0.6925 |
| 0.256 | 5.0 | 2500 | 1.0959 | 0.7266 |
| 0.1818 | 6.0 | 3000 | 1.2213 | 0.6775 |
| 0.1407 | 7.0 | 3500 | 1.4863 | 0.6764 |
| 0.0938 | 8.0 | 4000 | 1.7213 | 0.7032 |
| 0.0623 | 9.0 | 4500 | 1.8237 | 0.6917 |
| 0.0484 | 10.0 | 5000 | 1.8617 | 0.6928 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
