|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: fine-tuned-NLI-indonli-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-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: 0.4642 |
|
- Accuracy: 0.8521 |
|
- F1: 0.8520 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| 1.0772 | 0.5 | 40 | 1.0981 | 0.3473 | 0.1940 | |
|
| 1.1047 | 0.99 | 80 | 1.0967 | 0.3878 | 0.2972 | |
|
| 1.1123 | 1.5 | 120 | 0.7637 | 0.7128 | 0.7099 | |
|
| 0.8279 | 1.99 | 160 | 0.5739 | 0.7870 | 0.7848 | |
|
| 0.5873 | 2.5 | 200 | 0.5059 | 0.8229 | 0.8232 | |
|
| 0.5873 | 2.99 | 240 | 0.5047 | 0.8234 | 0.8258 | |
|
| 0.5418 | 3.5 | 280 | 0.4696 | 0.8380 | 0.8381 | |
|
| 0.4472 | 3.99 | 320 | 0.4415 | 0.8457 | 0.8458 | |
|
| 0.4041 | 4.5 | 360 | 0.4622 | 0.8521 | 0.8522 | |
|
| 0.3767 | 4.99 | 400 | 0.4435 | 0.8489 | 0.8498 | |
|
| 0.3767 | 5.5 | 440 | 0.4731 | 0.8498 | 0.8503 | |
|
| 0.3307 | 5.99 | 480 | 0.4642 | 0.8521 | 0.8520 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.2.0 |
|
- Tokenizers 0.13.3 |
|
|