metadata
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: xnli_en
results: []
xnli_en
This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4363
- Accuracy: 0.8361
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: 0.0003
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5593 | 1.0 | 12272 | 0.5132 | 0.7960 |
| 0.5079 | 2.0 | 24544 | 0.4724 | 0.8116 |
| 0.4815 | 3.0 | 36816 | 0.5340 | 0.7900 |
| 0.4757 | 4.0 | 49088 | 0.4503 | 0.8233 |
| 0.4575 | 5.0 | 61360 | 0.4315 | 0.8321 |
| 0.4435 | 6.0 | 73632 | 0.4313 | 0.8369 |
| 0.4228 | 7.0 | 85904 | 0.4381 | 0.8309 |
| 0.4342 | 8.0 | 98176 | 0.4349 | 0.8365 |
| 0.4236 | 9.0 | 110448 | 0.4354 | 0.8373 |
| 0.4151 | 10.0 | 122720 | 0.4363 | 0.8361 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1