|
--- |
|
library_name: transformers |
|
license: mit |
|
base_model: FacebookAI/xlm-roberta-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: xlm_roberta_55k_boduoi_test14k |
|
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. --> |
|
|
|
# xlm_roberta_55k_boduoi_test14k |
|
|
|
This model is a fine-tuned version of [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9497 |
|
- Accuracy: 0.7986 |
|
- F1: 0.8478 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine_with_restarts |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:| |
|
| 0.4336 | 1.0 | 1725 | 0.7617 | 0.7120 | 0.7890 | |
|
| 0.3114 | 2.0 | 3450 | 0.6237 | 0.7265 | 0.7992 | |
|
| 0.2616 | 3.0 | 5175 | 0.8613 | 0.7262 | 0.7990 | |
|
| 0.2261 | 4.0 | 6900 | 0.5566 | 0.8171 | 0.8593 | |
|
| 0.192 | 5.0 | 8625 | 0.7264 | 0.7755 | 0.8324 | |
|
| 0.1652 | 6.0 | 10350 | 0.8042 | 0.7759 | 0.8328 | |
|
| 0.1397 | 7.0 | 12075 | 0.8167 | 0.7908 | 0.8427 | |
|
| 0.1241 | 8.0 | 13800 | 0.8630 | 0.8036 | 0.8509 | |
|
| 0.1153 | 9.0 | 15525 | 0.9335 | 0.8016 | 0.8497 | |
|
| 0.1141 | 10.0 | 17250 | 0.9497 | 0.7986 | 0.8478 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.19.1 |
|
|
