metadata
license: mit
library_name: peft
tags:
- generated_from_trainer
base_model: xlm-roberta-base
metrics:
- accuracy
- f1
model-index:
- name: loha_fine_tuned_rte_XLMroberta
results: []
loha_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: 2.4748
- Accuracy: 0.6897
- F1: 0.6873
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: 0.003
- 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 |
|---|---|---|---|---|---|
| 0.8438 | 1.7241 | 50 | 0.7276 | 0.4138 | 0.2422 |
| 0.7427 | 3.4483 | 100 | 0.6836 | 0.5862 | 0.4333 |
| 0.6788 | 5.1724 | 150 | 0.9009 | 0.4828 | 0.3781 |
| 0.5085 | 6.8966 | 200 | 1.6699 | 0.5172 | 0.4944 |
| 0.2264 | 8.6207 | 250 | 2.0941 | 0.6207 | 0.6179 |
| 0.094 | 10.3448 | 300 | 2.0207 | 0.6897 | 0.6687 |
| 0.0286 | 12.0690 | 350 | 2.3929 | 0.6552 | 0.6491 |
| 0.004 | 13.7931 | 400 | 2.4748 | 0.6897 | 0.6873 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1