metadata
base_model: cardiffnlp/twitter-roberta-base-sentiment-latest
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: twitter-roberta-base-sentiment-latest
results: []
twitter-roberta-base-sentiment-latest
This model is a fine-tuned version of cardiffnlp/twitter-roberta-base-sentiment-latest on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3725
- Accuracy: 0.798
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.5281 | 0.1 | 50 | 0.5483 | 0.5845 |
0.4213 | 0.2 | 100 | 0.4663 | 0.671 |
0.4279 | 0.3 | 150 | 0.3972 | 0.7175 |
0.3765 | 0.4 | 200 | 0.3771 | 0.7425 |
0.3733 | 0.5 | 250 | 0.3884 | 0.755 |
0.4427 | 0.6 | 300 | 0.3535 | 0.7515 |
0.367 | 0.7 | 350 | 0.3511 | 0.765 |
0.3446 | 0.8 | 400 | 0.3422 | 0.7695 |
0.3339 | 0.9 | 450 | 0.3560 | 0.775 |
0.3681 | 1.0 | 500 | 0.3359 | 0.776 |
0.2586 | 1.1 | 550 | 0.3620 | 0.776 |
0.3399 | 1.2 | 600 | 0.3433 | 0.798 |
0.3881 | 1.3 | 650 | 0.3457 | 0.765 |
0.3443 | 1.4 | 700 | 0.3400 | 0.7885 |
0.2937 | 1.5 | 750 | 0.3475 | 0.7805 |
0.3363 | 1.6 | 800 | 0.3937 | 0.756 |
0.3363 | 1.7 | 850 | 0.3165 | 0.8065 |
0.3427 | 1.8 | 900 | 0.3374 | 0.7945 |
0.3457 | 1.9 | 950 | 0.3154 | 0.8055 |
0.3256 | 2.0 | 1000 | 0.3412 | 0.7945 |
0.1914 | 2.1 | 1050 | 0.3785 | 0.8005 |
0.1546 | 2.2 | 1100 | 0.3921 | 0.798 |
0.1931 | 2.3 | 1150 | 0.3766 | 0.797 |
0.2315 | 2.4 | 1200 | 0.3866 | 0.7985 |
0.1973 | 2.5 | 1250 | 0.3758 | 0.7975 |
0.3116 | 2.6 | 1300 | 0.3839 | 0.7975 |
0.245 | 2.7 | 1350 | 0.3770 | 0.7945 |
0.144 | 2.8 | 1400 | 0.3774 | 0.793 |
0.219 | 2.9 | 1450 | 0.3833 | 0.792 |
0.2341 | 3.0 | 1500 | 0.3725 | 0.798 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1