<!-- 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. -->
tluo_xml_roberta_base_amazon_review_sentiment_v4
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: 0.9589
- Accuracy: 0.6137
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: 1.5745609276104923e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 25
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1074 | 0.17 | 5000 | 1.0468 | 0.5493 |
| 1.0461 | 0.33 | 10000 | 1.0222 | 0.558 |
| 1.0245 | 0.5 | 15000 | 0.9776 | 0.5793 |
| 0.9876 | 0.67 | 20000 | 1.0327 | 0.571 |
| 1.0073 | 0.83 | 25000 | 0.9695 | 0.5807 |
| 0.9808 | 1.0 | 30000 | 1.0077 | 0.5857 |
| 0.9399 | 1.17 | 35000 | 1.0113 | 0.6043 |
| 0.8944 | 1.33 | 40000 | 0.9534 | 0.5947 |
| 0.908 | 1.5 | 45000 | 1.0155 | 0.5947 |
| 0.9238 | 1.67 | 50000 | 0.9813 | 0.597 |
| 0.8699 | 1.83 | 55000 | 0.9646 | 0.6027 |
| 0.8829 | 2.0 | 60000 | 0.9589 | 0.6137 |
| 0.8214 | 2.17 | 65000 | 1.0378 | 0.6017 |
| 0.8052 | 2.33 | 70000 | 1.0080 | 0.6003 |
| 0.7807 | 2.5 | 75000 | 1.0830 | 0.604 |
| 0.7927 | 2.67 | 80000 | 1.0225 | 0.6007 |
| 0.8358 | 2.83 | 85000 | 0.9989 | 0.5997 |
| 0.7899 | 3.0 | 90000 | 1.0108 | 0.6023 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2
