xnli_en_lora_alpha_64_drop_0.1_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: 0.4781
- 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: 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 |
---|---|---|---|---|
0.5401 | 1.0 | 12272 | 0.4940 | 0.8012 |
0.5153 | 2.0 | 24544 | 0.4847 | 0.8185 |
0.4912 | 3.0 | 36816 | 0.4560 | 0.8281 |
0.464 | 4.0 | 49088 | 0.4341 | 0.8305 |
0.4353 | 5.0 | 61360 | 0.4341 | 0.8293 |
0.4222 | 6.0 | 73632 | 0.4421 | 0.8353 |
0.4029 | 7.0 | 85904 | 0.4692 | 0.8181 |
0.383 | 8.0 | 98176 | 0.4453 | 0.8289 |
0.3747 | 9.0 | 110448 | 0.4696 | 0.8273 |
0.358 | 10.0 | 122720 | 0.4697 | 0.8217 |
0.3303 | 11.0 | 134992 | 0.4648 | 0.8317 |
0.3217 | 12.0 | 147264 | 0.4618 | 0.8386 |
0.31 | 13.0 | 159536 | 0.4796 | 0.8333 |
0.2831 | 14.0 | 171808 | 0.4702 | 0.8329 |
0.2847 | 15.0 | 184080 | 0.4781 | 0.8361 |
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
.