<!-- 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-sentiment-memes
This model is a fine-tuned version of cardiffnlp/twitter-roberta-base-sentiment on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9582
- Accuracy: 0.8187
- Precision: 0.8199
- Recall: 0.8187
- F1: 0.8191
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: 8
- 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 | Accuracy | Precision | Recall | F1 |
---|---|---|---|---|---|---|---|
0.4673 | 1.0 | 2147 | 0.4373 | 0.7647 | 0.8180 | 0.7647 | 0.7657 |
0.3987 | 2.0 | 4294 | 0.5528 | 0.7783 | 0.8096 | 0.7783 | 0.7804 |
0.3194 | 3.0 | 6441 | 0.6432 | 0.7752 | 0.7767 | 0.7752 | 0.7680 |
0.2855 | 4.0 | 8588 | 0.6820 | 0.7814 | 0.8034 | 0.7814 | 0.7837 |
0.2575 | 5.0 | 10735 | 0.7427 | 0.7720 | 0.8070 | 0.7720 | 0.7741 |
0.2154 | 6.0 | 12882 | 0.8225 | 0.7987 | 0.8062 | 0.7987 | 0.8004 |
0.2195 | 7.0 | 15029 | 0.8361 | 0.8071 | 0.8086 | 0.8071 | 0.8077 |
0.2322 | 8.0 | 17176 | 0.8842 | 0.8056 | 0.8106 | 0.8056 | 0.8069 |
0.2102 | 9.0 | 19323 | 0.9188 | 0.8129 | 0.8144 | 0.8129 | 0.8135 |
0.1893 | 10.0 | 21470 | 0.9582 | 0.8187 | 0.8199 | 0.8187 | 0.8191 |
Framework versions
- Transformers 4.13.0.dev0
- Pytorch 1.11.0+cu102
- Datasets 1.15.2.dev0
- Tokenizers 0.10.1