|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
base_model: xlm-roberta-large |
|
model-index: |
|
- name: fine-tuned-NLI-indonli_mnli_squadid-nli-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-indonli_mnli_squadid-nli-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: 0.2874 |
|
- Accuracy: 0.9148 |
|
- F1: 0.9152 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:| |
|
| 0.3454 | 0.5 | 2499 | 0.2659 | 0.8987 | 0.8988 | |
|
| 0.3177 | 1.0 | 4998 | 0.2420 | 0.9081 | 0.9087 | |
|
| 0.2821 | 1.5 | 7497 | 0.2407 | 0.9111 | 0.9114 | |
|
| 0.249 | 2.0 | 9996 | 0.2258 | 0.9159 | 0.9158 | |
|
| 0.2246 | 2.5 | 12495 | 0.2454 | 0.9143 | 0.9146 | |
|
| 0.2308 | 3.0 | 14994 | 0.2370 | 0.9155 | 0.9159 | |
|
| 0.1869 | 3.5 | 17493 | 0.2691 | 0.9147 | 0.9149 | |
|
| 0.18 | 4.0 | 19992 | 0.2616 | 0.9143 | 0.9151 | |
|
| 0.1329 | 4.5 | 22491 | 0.2874 | 0.9148 | 0.9152 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 1.13.1+cu117 |
|
- Datasets 2.2.0 |
|
- Tokenizers 0.13.2 |
|
|