|
--- |
|
base_model: cardiffnlp/twitter-xlm-roberta-base-sentiment |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: XlM-roberta-AS-HU-f1-score |
|
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-AS-HU-f1-score |
|
|
|
This model is a fine-tuned version of [cardiffnlp/twitter-xlm-roberta-base-sentiment](https://huggingface.co/cardiffnlp/twitter-xlm-roberta-base-sentiment) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.1081 |
|
- F1-score: 0.8389 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 8 |
|
- 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 | F1-score | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.6852 | 1.0 | 64 | 0.6780 | 0.3697 | |
|
| 0.6514 | 2.0 | 128 | 0.5578 | 0.6958 | |
|
| 0.5075 | 3.0 | 192 | 0.5620 | 0.7619 | |
|
| 0.401 | 4.0 | 256 | 0.5068 | 0.7688 | |
|
| 0.2288 | 5.0 | 320 | 0.6490 | 0.8084 | |
|
| 0.1424 | 6.0 | 384 | 0.7662 | 0.8350 | |
|
| 0.0837 | 7.0 | 448 | 0.9138 | 0.8389 | |
|
| 0.0463 | 8.0 | 512 | 1.0355 | 0.8247 | |
|
| 0.0108 | 9.0 | 576 | 1.0874 | 0.8345 | |
|
| 0.0069 | 10.0 | 640 | 1.1081 | 0.8389 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.1 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
