RobertaTokens_TAM-10epoch-RobertaMul
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: 1.0852
- Accuracy: 0.7273
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: 10
- eval_batch_size: 10
- 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 |
|---|---|---|---|---|
| No log | 1.0 | 5 | 1.0945 | 0.1515 |
| No log | 2.0 | 10 | 1.0929 | 0.7273 |
| No log | 3.0 | 15 | 1.0926 | 0.3030 |
| No log | 4.0 | 20 | 1.0900 | 0.3939 |
| No log | 5.0 | 25 | 1.0866 | 0.7273 |
| No log | 6.0 | 30 | 1.0861 | 0.7273 |
| No log | 7.0 | 35 | 1.0860 | 0.7273 |
| No log | 8.0 | 40 | 1.0857 | 0.7273 |
| No log | 9.0 | 45 | 1.0852 | 0.7273 |
| No log | 10.0 | 50 | 1.0852 | 0.7273 |
Framework versions
- Transformers 4.35.0.dev0
- Pytorch 1.13.1
- Datasets 2.14.5
- Tokenizers 0.14.1