<!-- 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. -->
vxnli-v1
This model is a fine-tuned version of kwkty/vxnli-v0 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2262
- Exact Match: 0.6407
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
Training Loss | Epoch | Step | Validation Loss | Exact Match |
---|---|---|---|---|
0.1092 | 1.0 | 158 | 0.1820 | 0.5704 |
0.0432 | 2.0 | 316 | 0.2149 | 0.5593 |
0.0266 | 3.0 | 474 | 0.2721 | 0.5370 |
0.0193 | 4.0 | 632 | 0.2456 | 0.5889 |
0.0168 | 5.0 | 790 | 0.2382 | 0.6111 |
0.0138 | 6.0 | 948 | 0.2910 | 0.5741 |
0.0146 | 7.0 | 1106 | 0.2559 | 0.5889 |
0.0078 | 8.0 | 1264 | 0.2927 | 0.5630 |
0.0073 | 9.0 | 1422 | 0.3346 | 0.5741 |
0.0063 | 10.0 | 1580 | 0.3308 | 0.5481 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu117
- Datasets 2.7.1
- Tokenizers 0.13.2