<!-- 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. -->
cric-tweets-sentiment-analysis
This model is a fine-tuned version of cardiffnlp/twitter-roberta-base-sentiment-latest on 3000 pre-match cricket tweets.
Note: Here Label_1 indicates positive, and Label_0 indicates negative
It achieves the following results on the test set:
- F1 Score: 95.3%
- Precision: 93.9%
- Recall: 96.7%
- Accuracy: 92.2%
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 223
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 200
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.7.1
- Tokenizers 0.13.2