xnli_en_adalora_alpha_64_drop_0.3_rank_32_seed_456
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: 0.4290
- Accuracy: 0.8341
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: 456
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15.0
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.549 | 1.0 | 12272 | 0.4857 | 0.8104 |
0.5187 | 2.0 | 24544 | 0.4788 | 0.8141 |
0.5002 | 3.0 | 36816 | 0.4493 | 0.8241 |
0.475 | 4.0 | 49088 | 0.4217 | 0.8349 |
0.4528 | 5.0 | 61360 | 0.4229 | 0.8313 |
0.4406 | 6.0 | 73632 | 0.4450 | 0.8261 |
0.4378 | 7.0 | 85904 | 0.4512 | 0.8221 |
0.4189 | 8.0 | 98176 | 0.4239 | 0.8353 |
0.4234 | 9.0 | 110448 | 0.4376 | 0.8349 |
0.4167 | 10.0 | 122720 | 0.4422 | 0.8261 |
0.3984 | 11.0 | 134992 | 0.4257 | 0.8329 |
0.4026 | 12.0 | 147264 | 0.4243 | 0.8361 |
0.3929 | 13.0 | 159536 | 0.4463 | 0.8341 |
0.3829 | 14.0 | 171808 | 0.4273 | 0.8382 |
0.3972 | 15.0 | 184080 | 0.4290 | 0.8341 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1
Unable to determine this model's library. Check the
docs
.