<!-- 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. -->
20230928-4-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: 0.4562
- Loss: nan
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: 10
Training results
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|---|---|---|---|---|
| 4.6239 | 0.46 | 200 | 0.3344 | nan |
| 4.1206 | 0.91 | 400 | 0.3185 | nan |
| 3.7736 | 1.37 | 600 | 0.3455 | nan |
| 3.7553 | 1.82 | 800 | 0.3323 | nan |
| 3.4994 | 2.28 | 1000 | 0.4056 | nan |
| 3.4706 | 2.73 | 1200 | 0.4070 | nan |
| 3.3323 | 3.19 | 1400 | 0.4458 | 3.0068 |
| 3.2846 | 3.64 | 1600 | 0.4343 | nan |
| 3.3462 | 4.1 | 1800 | 0.4954 | 2.5325 |
| 3.0349 | 4.56 | 2000 | 0.4235 | 2.9762 |
| 3.1044 | 5.01 | 2200 | 0.3799 | nan |
| 2.9192 | 5.47 | 2400 | 0.5046 | 2.6744 |
| 3.0091 | 5.92 | 2600 | 0.4533 | 2.8950 |
| 2.8518 | 6.38 | 2800 | 0.4604 | nan |
| 2.867 | 6.83 | 3000 | 0.4475 | 2.5855 |
| 2.9242 | 7.29 | 3200 | 0.4737 | 2.7730 |
| 2.7668 | 7.74 | 3400 | 0.4661 | nan |
| 2.7914 | 8.2 | 3600 | 0.4735 | 2.8640 |
| 2.945 | 8.66 | 3800 | 0.5014 | 2.8195 |
| 2.7329 | 9.11 | 4000 | 0.4758 | nan |
| 2.8379 | 9.57 | 4200 | 0.4562 | nan |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
