lora_fine_tuned_rte_XLMroberta
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: 0.6924
- Accuracy: 0.5172
- F1: 0.4944
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
- training_steps: 400
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.6917 | 1.7241 | 50 | 0.7067 | 0.4138 | 0.2422 |
| 0.6974 | 3.4483 | 100 | 0.6924 | 0.5862 | 0.4333 |
| 0.697 | 5.1724 | 150 | 0.6968 | 0.4138 | 0.2422 |
| 0.6961 | 6.8966 | 200 | 0.6947 | 0.5172 | 0.4660 |
| 0.6952 | 8.6207 | 250 | 0.6947 | 0.4138 | 0.2951 |
| 0.6917 | 10.3448 | 300 | 0.6934 | 0.5517 | 0.5517 |
| 0.6907 | 12.0690 | 350 | 0.6923 | 0.4828 | 0.4479 |
| 0.6936 | 13.7931 | 400 | 0.6924 | 0.5172 | 0.4944 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 1
Model tree for lenatr99/lora_fine_tuned_rte_XLMroberta
Base model
FacebookAI/xlm-roberta-base