metadata
license: mit
base_model: FacebookAI/xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: medidalRoberta
results: []
medidalRoberta
This model is a fine-tuned version of FacebookAI/xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0334
- Accuracy: 0.9868
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 19 | 1.3034 | 0.5789 |
| No log | 2.0 | 38 | 0.6350 | 0.8816 |
| No log | 3.0 | 57 | 0.2689 | 0.8947 |
| No log | 4.0 | 76 | 0.1290 | 0.9868 |
| No log | 5.0 | 95 | 0.1135 | 0.9605 |
| No log | 6.0 | 114 | 0.0605 | 0.9868 |
| No log | 7.0 | 133 | 0.0536 | 0.9868 |
| No log | 8.0 | 152 | 0.0417 | 0.9868 |
| No log | 9.0 | 171 | 0.0332 | 0.9868 |
| No log | 10.0 | 190 | 0.0334 | 0.9868 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2