<!-- 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. -->
V3_20230929-6-xlm-roberta-base-new
This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Accuracy: 0.5780
- Loss: 2.1766
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: 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: 15
Training results
Training Loss | Epoch | Step | Accuracy | Validation Loss |
---|---|---|---|---|
4.4638 | 0.46 | 200 | 0.2889 | nan |
4.1893 | 0.91 | 400 | 0.3536 | nan |
3.9393 | 1.37 | 600 | 0.3672 | nan |
3.6824 | 1.82 | 800 | 0.3609 | nan |
3.5332 | 2.28 | 1000 | 0.4353 | nan |
3.5164 | 2.73 | 1200 | 0.4039 | 3.3258 |
3.3856 | 3.19 | 1400 | 0.4489 | 2.4897 |
3.454 | 3.64 | 1600 | 0.4209 | 3.2397 |
3.2161 | 4.1 | 1800 | 0.4620 | 2.7198 |
3.175 | 4.56 | 2000 | 0.4476 | nan |
3.1915 | 5.01 | 2200 | 0.4670 | 2.6543 |
2.8989 | 5.47 | 2400 | 0.4640 | 2.8110 |
2.8575 | 5.92 | 2600 | 0.4848 | nan |
2.9779 | 6.38 | 2800 | 0.4438 | nan |
2.9945 | 6.83 | 3000 | 0.4869 | 2.5596 |
2.8321 | 7.29 | 3200 | 0.4474 | 2.5483 |
2.7283 | 7.74 | 3400 | 0.4553 | 2.9584 |
2.7695 | 8.2 | 3600 | 0.4645 | 2.3643 |
2.9078 | 8.66 | 3800 | 0.5055 | nan |
2.6554 | 9.11 | 4000 | 0.5202 | 2.3099 |
2.6683 | 9.57 | 4200 | 0.4558 | nan |
2.7513 | 10.02 | 4400 | 0.5183 | 2.5005 |
2.7285 | 10.48 | 4600 | 0.5042 | nan |
2.5985 | 10.93 | 4800 | 0.5432 | 2.4976 |
2.5506 | 11.39 | 5000 | 0.5073 | nan |
2.5256 | 11.85 | 5200 | 0.5095 | 2.4731 |
2.4992 | 12.3 | 5400 | 0.5710 | nan |
2.5342 | 12.76 | 5600 | 0.5644 | nan |
2.7334 | 13.21 | 5800 | 0.5241 | 2.2573 |
2.6112 | 13.67 | 6000 | 0.5714 | 1.9512 |
2.3563 | 14.12 | 6200 | 0.5301 | nan |
2.4953 | 14.58 | 6400 | 0.5780 | 2.1766 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3