<!-- 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. -->
me_sentiment
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: 0.1965
- Accuracy: 0.9501
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.1974 | 0.42 | 500 | 0.1713 | 0.9275 |
0.1584 | 0.85 | 1000 | 0.1435 | 0.9391 |
0.1383 | 1.27 | 1500 | 0.1513 | 0.9404 |
0.13 | 1.69 | 2000 | 0.1402 | 0.9457 |
0.1163 | 2.11 | 2500 | 0.1726 | 0.9465 |
0.1081 | 2.54 | 3000 | 0.1696 | 0.9474 |
0.106 | 2.96 | 3500 | 0.1475 | 0.9480 |
0.0802 | 3.38 | 4000 | 0.1960 | 0.9493 |
0.0852 | 3.8 | 4500 | 0.1965 | 0.9501 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cpu
- Datasets 2.14.5
- Tokenizers 0.14.0