|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: slurp-intent_baseline-xlm_r-en |
|
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. --> |
|
|
|
# slurp-intent_baseline-xlm_r-en |
|
|
|
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an SLURP dataset. |
|
|
|
It achieves the following results on the test set: |
|
- Loss: 0.68222 |
|
- Accuracy: 0.8746 |
|
- F1: 0.8746 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| 2.9687 | 1.0 | 720 | 1.3267 | 0.6955 | 0.6955 | |
|
| 1.4534 | 2.0 | 1440 | 0.8053 | 0.8219 | 0.8219 | |
|
| 0.6775 | 3.0 | 2160 | 0.6912 | 0.8421 | 0.8421 | |
|
| 0.5624 | 4.0 | 2880 | 0.6377 | 0.8623 | 0.8623 | |
|
| 0.3756 | 5.0 | 3600 | 0.6188 | 0.8746 | 0.8746 | |
|
| 0.3346 | 6.0 | 4320 | 0.6548 | 0.8711 | 0.8711 | |
|
| 0.2541 | 7.0 | 5040 | 0.6618 | 0.8751 | 0.8751 | |
|
| 0.2243 | 8.0 | 5760 | 0.6662 | 0.8780 | 0.8780 | |
|
| 0.212 | 9.0 | 6480 | 0.6673 | 0.8810 | 0.8810 | |
|
| 0.1664 | 10.0 | 7200 | 0.6783 | 0.8810 | 0.8810 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.1 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.3 |
|
|
