|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: fine-tuned-NLI-idk-mrc-nli-keep-with-xlm-roberta-large |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# fine-tuned-NLI-idk-mrc-nli-keep-with-xlm-roberta-large |
|
|
|
This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1224 |
|
- Accuracy: 0.9751 |
|
- F1: 0.9751 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| 1.3634 | 0.49 | 39 | 0.6900 | 0.5052 | 0.3515 | |
|
| 0.7309 | 0.99 | 78 | 0.2791 | 0.9202 | 0.9202 | |
|
| 0.4815 | 1.49 | 117 | 0.0854 | 0.9738 | 0.9738 | |
|
| 0.145 | 1.99 | 156 | 0.0903 | 0.9699 | 0.9699 | |
|
| 0.145 | 2.49 | 195 | 0.0931 | 0.9738 | 0.9738 | |
|
| 0.0937 | 2.99 | 234 | 0.0875 | 0.9751 | 0.9751 | |
|
| 0.0752 | 3.49 | 273 | 0.1164 | 0.9738 | 0.9738 | |
|
| 0.0538 | 3.99 | 312 | 0.1386 | 0.9673 | 0.9673 | |
|
| 0.0379 | 4.49 | 351 | 0.0893 | 0.9791 | 0.9791 | |
|
| 0.0379 | 4.99 | 390 | 0.1002 | 0.9777 | 0.9777 | |
|
| 0.0397 | 5.49 | 429 | 0.1214 | 0.9764 | 0.9764 | |
|
| 0.031 | 5.99 | 468 | 0.1224 | 0.9751 | 0.9751 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 1.13.1+cu117 |
|
- Datasets 2.2.0 |
|
- Tokenizers 0.13.2 |
|
|
