metadata
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: xlm-roberta-base-finetuned-raw
results: []
xlm-roberta-base-finetuned-raw
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5130
- Accuracy: 0.8563
- F1: 0.8551
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 1.2557 | 1.0 | 1699 | 0.7169 | 0.7858 | 0.7805 |
| 0.6384 | 2.0 | 3398 | 0.5732 | 0.8285 | 0.8251 |
| 0.4814 | 3.0 | 5097 | 0.5527 | 0.8382 | 0.8368 |
| 0.3813 | 4.0 | 6796 | 0.5146 | 0.8527 | 0.8505 |
| 0.3156 | 5.0 | 8495 | 0.5130 | 0.8563 | 0.8551 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1