|
--- |
|
base_model: cardiffnlp/twitter-roberta-base-sentiment-latest |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: twitter-roberta-base-sentiment-latest |
|
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. --> |
|
|
|
# twitter-roberta-base-sentiment-latest |
|
|
|
This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-sentiment-latest](https://huggingface.co/cardiffnlp/twitter-roberta-base-sentiment-latest) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3302 |
|
- Accuracy: 0.784 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 600 |
|
- num_epochs: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.8113 | 0.12 | 30 | 0.7971 | 0.418 | |
|
| 0.6733 | 0.24 | 60 | 0.6551 | 0.469 | |
|
| 0.5712 | 0.36 | 90 | 0.5713 | 0.522 | |
|
| 0.5234 | 0.48 | 120 | 0.5311 | 0.565 | |
|
| 0.5406 | 0.6 | 150 | 0.4938 | 0.6595 | |
|
| 0.4856 | 0.72 | 180 | 0.4482 | 0.692 | |
|
| 0.4732 | 0.84 | 210 | 0.4147 | 0.7185 | |
|
| 0.4217 | 0.96 | 240 | 0.4038 | 0.726 | |
|
| 0.4097 | 1.08 | 270 | 0.3828 | 0.7375 | |
|
| 0.3911 | 1.2 | 300 | 0.3928 | 0.735 | |
|
| 0.3779 | 1.32 | 330 | 0.3767 | 0.7555 | |
|
| 0.3829 | 1.44 | 360 | 0.3705 | 0.74 | |
|
| 0.3596 | 1.56 | 390 | 0.3905 | 0.744 | |
|
| 0.3626 | 1.68 | 420 | 0.3712 | 0.7425 | |
|
| 0.3763 | 1.8 | 450 | 0.3679 | 0.752 | |
|
| 0.3722 | 1.92 | 480 | 0.3353 | 0.7805 | |
|
| 0.3387 | 2.04 | 510 | 0.3504 | 0.768 | |
|
| 0.3247 | 2.16 | 540 | 0.3573 | 0.766 | |
|
| 0.3242 | 2.28 | 570 | 0.3526 | 0.7775 | |
|
| 0.4003 | 2.4 | 600 | 0.3413 | 0.7785 | |
|
| 0.352 | 2.52 | 630 | 0.3547 | 0.763 | |
|
| 0.3521 | 2.64 | 660 | 0.3449 | 0.7835 | |
|
| 0.29 | 2.76 | 690 | 0.3270 | 0.7875 | |
|
| 0.3017 | 2.88 | 720 | 0.3302 | 0.784 | |
|
| 0.3086 | 3.0 | 750 | 0.3401 | 0.782 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.1 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|
