metadata
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: fine_tuned_rte_XLMroberta
results: []
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: 1.9629
- Accuracy: 0.5517
- F1: 0.5539
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 |
|---|---|---|---|---|---|
| 0.6914 | 1.7241 | 50 | 0.7021 | 0.4138 | 0.2422 |
| 0.6881 | 3.4483 | 100 | 0.6818 | 0.5862 | 0.5833 |
| 0.6284 | 5.1724 | 150 | 0.6509 | 0.6207 | 0.6234 |
| 0.5051 | 6.8966 | 200 | 0.9063 | 0.5517 | 0.4977 |
| 0.3431 | 8.6207 | 250 | 1.1387 | 0.5862 | 0.5882 |
| 0.2236 | 10.3448 | 300 | 1.3533 | 0.5517 | 0.5539 |
| 0.098 | 12.0690 | 350 | 1.8198 | 0.5517 | 0.5539 |
| 0.0527 | 13.7931 | 400 | 1.9629 | 0.5517 | 0.5539 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1