metadata
license: mit
base_model: xlm-roberta-large
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: fine-tuned-NLI-mnli_original-with-xlm-roberta-large
results: []
fine-tuned-NLI-mnli_original-with-xlm-roberta-large
This model is a fine-tuned version of xlm-roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3833
- Accuracy: 0.8879
- F1: 0.8881
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- 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 | F1 |
|---|---|---|---|---|---|
| 0.3931 | 0.4997 | 1533 | 0.3416 | 0.8697 | 0.8695 |
| 0.3529 | 0.9993 | 3066 | 0.3214 | 0.8825 | 0.8829 |
| 0.2985 | 1.4990 | 4599 | 0.3312 | 0.8872 | 0.8877 |
| 0.299 | 1.9987 | 6132 | 0.3209 | 0.8881 | 0.8884 |
| 0.2349 | 2.4984 | 7665 | 0.3322 | 0.8851 | 0.8856 |
| 0.2433 | 2.9980 | 9198 | 0.3324 | 0.8866 | 0.8869 |
| 0.1912 | 3.4977 | 10731 | 0.3833 | 0.8879 | 0.8881 |
Framework versions
- Transformers 4.42.3
- Pytorch 1.13.1+cu117
- Datasets 2.2.0
- Tokenizers 0.19.1