smalldata-microsoft-deberta-base-mnli-eng-only-sentiment-single-finetuned-memes
This model is a fine-tuned version of jayantapaul888/twitter-data-microsoft-deberta-base-mnli-sentiment-finetuned-memes on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7400
- Accuracy: 0.8816
- Precision: 0.8946
- Recall: 0.8937
- F1: 0.8937
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
---|---|---|---|---|---|---|---|
No log | 1.0 | 378 | 0.2962 | 0.8764 | 0.8917 | 0.8881 | 0.8884 |
0.3387 | 2.0 | 756 | 0.2803 | 0.8831 | 0.8950 | 0.8942 | 0.8946 |
0.1693 | 3.0 | 1134 | 0.4289 | 0.8764 | 0.8912 | 0.8892 | 0.8886 |
0.0772 | 4.0 | 1512 | 0.5436 | 0.8690 | 0.8822 | 0.8823 | 0.8822 |
0.0772 | 5.0 | 1890 | 0.6566 | 0.8831 | 0.8960 | 0.8947 | 0.8949 |
0.024 | 6.0 | 2268 | 0.7400 | 0.8816 | 0.8946 | 0.8937 | 0.8937 |
Framework versions
- Transformers 4.24.0.dev0
- Pytorch 1.11.0+cu102
- Datasets 2.6.1
- Tokenizers 0.13.1
- Downloads last month
- 4
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.