<!-- 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
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: 0.9552
- Accuracy: 0.6003
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: 123
- 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 |
|---|---|---|---|---|
| 0.5664 | 0.33 | 5000 | 1.3816 | 0.5688 |
| 0.9494 | 0.67 | 10000 | 0.9702 | 0.5852 |
| 0.9613 | 1.0 | 15000 | 0.9545 | 0.5917 |
| 0.8611 | 1.33 | 20000 | 0.9689 | 0.5953 |
| 0.8636 | 1.67 | 25000 | 0.9556 | 0.5943 |
| 0.8582 | 2.0 | 30000 | 0.9552 | 0.6003 |
| 0.7555 | 2.33 | 35000 | 1.0001 | 0.5928 |
| 0.7374 | 2.67 | 40000 | 1.0037 | 0.594 |
| 0.733 | 3.0 | 45000 | 0.9976 | 0.5983 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1
