| | ---
|
| | license: mit
|
| | base_model: xlm-roberta-base
|
| | tags:
|
| | - generated_from_trainer
|
| | metrics:
|
| | - accuracy
|
| | - f1
|
| | model-index:
|
| | - name: fine_tuned_copa_XLMroberta
|
| | results: []
|
| | ---
|
| |
|
| | <!-- 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. -->
|
| |
|
| | # fine_tuned_copa_XLMroberta
|
| |
|
| | This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
|
| | It achieves the following results on the evaluation set:
|
| | - Loss: 0.6931
|
| | - Accuracy: 0.58
|
| | - F1: 0.5412
|
| |
|
| | ## 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 |
|
| | |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
|
| | | 0.7194 | 1.0 | 50 | 0.6931 | 0.51 | 0.4132 |
|
| | | 0.7088 | 2.0 | 100 | 0.6931 | 0.54 | 0.3857 |
|
| | | 0.7232 | 3.0 | 150 | 0.6931 | 0.55 | 0.3903 |
|
| | | 0.7168 | 4.0 | 200 | 0.6931 | 0.56 | 0.4283 |
|
| | | 0.7058 | 5.0 | 250 | 0.6931 | 0.55 | 0.3903 |
|
| | | 0.728 | 6.0 | 300 | 0.6931 | 0.55 | 0.3903 |
|
| | | 0.7223 | 7.0 | 350 | 0.6931 | 0.6 | 0.5347 |
|
| | | 0.7031 | 8.0 | 400 | 0.6931 | 0.58 | 0.5412 |
|
| |
|
| |
|
| | ### Framework versions
|
| |
|
| | - Transformers 4.40.1
|
| | - Pytorch 2.1.1+cu121
|
| | - Datasets 2.19.0
|
| | - Tokenizers 0.19.1
|
| | |
