metadata
library_name: transformers
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: model_large_batch
results: []
model_large_batch
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: 0.7476
- Accuracy: 0.7097
- F1: 0.7082
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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.7514 | 1.0 | 500 | 0.7058 | 0.6933 | 0.6904 |
| 0.67 | 2.0 | 1000 | 0.6883 | 0.7063 | 0.7038 |
| 0.602 | 3.0 | 1500 | 0.6912 | 0.7137 | 0.7136 |
| 0.5294 | 4.0 | 2000 | 0.7174 | 0.7055 | 0.7036 |
| 0.4834 | 5.0 | 2500 | 0.7476 | 0.7097 | 0.7082 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.0.2
- Tokenizers 0.19.1