BERT_SentimetAnalysis_on Twitter
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1995
- Accuracy: 0.9674
- F1: 0.9674
- Precision: 0.9674
- Recall: 0.9674
- Label0: Negative, Label1: Positive, Label2: Neutral
- Dataset: https://www.kaggle.com/datasets/jp797498e/twitter-entity-sentiment-analysis?select=twitter_training.csv
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: 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: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
---|---|---|---|---|---|---|---|
0.1176 | 1.0 | 1698 | 0.3122 | 0.9336 | 0.9333 | 0.9352 | 0.9336 |
0.1254 | 2.0 | 3396 | 0.2247 | 0.9524 | 0.9525 | 0.9531 | 0.9524 |
0.0824 | 3.0 | 5094 | 0.1715 | 0.9637 | 0.9636 | 0.9637 | 0.9637 |
0.0551 | 4.0 | 6792 | 0.1900 | 0.9624 | 0.9624 | 0.9631 | 0.9624 |
0.0408 | 5.0 | 8490 | 0.1995 | 0.9674 | 0.9674 | 0.9674 | 0.9674 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2
- Downloads last month
- 5