xnli_xlm_r_only_en
This model is a fine-tuned version of xlm-roberta-base on the xnli dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5994
- Accuracy: 0.8506
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: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 10
Training results
| Training Loss |
Epoch |
Step |
Validation Loss |
Accuracy |
| 0.5771 |
1.0 |
3068 |
0.4557 |
0.8229 |
| 0.4272 |
2.0 |
6136 |
0.4174 |
0.8305 |
| 0.3599 |
3.0 |
9204 |
0.4471 |
0.8353 |
| 0.3064 |
4.0 |
12272 |
0.4394 |
0.8446 |
| 0.2604 |
5.0 |
15340 |
0.4544 |
0.8482 |
| 0.2226 |
6.0 |
18408 |
0.5036 |
0.8494 |
| 0.1907 |
7.0 |
21476 |
0.5139 |
0.8522 |
| 0.1654 |
8.0 |
24544 |
0.5454 |
0.8486 |
| 0.1441 |
9.0 |
27612 |
0.5828 |
0.8498 |
| 0.1304 |
10.0 |
30680 |
0.5994 |
0.8506 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.0
- Datasets 2.6.1
- Tokenizers 0.13.1
