<!-- 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_20230929-1-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: 0.5884
- 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: 15
Training results
Training Loss | Epoch | Step | Accuracy | Validation Loss |
---|---|---|---|---|
4.5743 | 0.46 | 200 | 0.3185 | 3.6252 |
4.0617 | 0.91 | 400 | 0.3300 | 3.5165 |
3.7835 | 1.37 | 600 | 0.3238 | nan |
3.7415 | 1.82 | 800 | 0.3733 | nan |
3.6084 | 2.28 | 1000 | 0.3711 | 3.4266 |
3.5224 | 2.73 | 1200 | 0.3966 | nan |
3.4781 | 3.19 | 1400 | 0.4110 | 3.0491 |
3.2402 | 3.64 | 1600 | 0.4381 | 3.3243 |
3.1612 | 4.1 | 1800 | 0.4764 | nan |
3.0672 | 4.56 | 2000 | 0.4293 | 2.6114 |
3.0975 | 5.01 | 2200 | 0.4415 | nan |
3.0579 | 5.47 | 2400 | 0.4760 | 2.6061 |
3.0349 | 5.92 | 2600 | 0.5012 | 2.6430 |
2.9009 | 6.38 | 2800 | 0.5101 | 2.6843 |
3.0346 | 6.83 | 3000 | 0.4803 | 2.7765 |
2.7554 | 7.29 | 3200 | 0.4866 | nan |
2.6926 | 7.74 | 3400 | 0.5105 | 2.8698 |
2.8284 | 8.2 | 3600 | 0.5038 | 2.5535 |
2.8385 | 8.66 | 3800 | 0.5465 | 2.5647 |
2.731 | 9.11 | 4000 | 0.5355 | nan |
2.6252 | 9.57 | 4200 | 0.5062 | 2.7420 |
2.5493 | 10.02 | 4400 | 0.5570 | 2.4540 |
2.649 | 10.48 | 4600 | 0.5495 | 2.4343 |
2.6669 | 10.93 | 4800 | 0.5365 | 2.2657 |
2.4549 | 11.39 | 5000 | 0.5508 | 2.4005 |
2.5627 | 11.85 | 5200 | 0.6057 | nan |
2.5328 | 12.3 | 5400 | 0.5943 | 2.0599 |
2.6162 | 12.76 | 5600 | 0.5167 | nan |
2.5906 | 13.21 | 5800 | 0.5518 | 2.1281 |
2.542 | 13.67 | 6000 | 0.5847 | nan |
2.4217 | 14.12 | 6200 | 0.5498 | nan |
2.4402 | 14.58 | 6400 | 0.5884 | nan |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3