metadata
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: fine-tuned-NLI-multilingual-with-xlm-roberta-large
results: []
fine-tuned-NLI-multilingual-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: 0.5146
- Accuracy: 0.8579
- F1: 0.8583
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 |
---|---|---|---|---|---|
0.4787 | 0.5 | 1574 | 0.4285 | 0.8364 | 0.8358 |
0.4418 | 1.0 | 3148 | 0.4040 | 0.8494 | 0.8496 |
0.3942 | 1.5 | 4722 | 0.3971 | 0.8514 | 0.8505 |
0.3722 | 2.0 | 6296 | 0.3835 | 0.8579 | 0.8581 |
0.3206 | 2.5 | 7870 | 0.4139 | 0.8587 | 0.8586 |
0.3229 | 3.0 | 9444 | 0.4033 | 0.8600 | 0.8602 |
0.2616 | 3.5 | 11018 | 0.4457 | 0.8585 | 0.8591 |
0.2862 | 4.0 | 12592 | 0.4319 | 0.8619 | 0.8617 |
0.2261 | 4.5 | 14166 | 0.4859 | 0.8562 | 0.8570 |
0.2215 | 5.0 | 15740 | 0.4728 | 0.8592 | 0.8599 |
0.1874 | 5.5 | 17314 | 0.5146 | 0.8579 | 0.8583 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.2.0
- Tokenizers 0.13.2