kurdish-sentiment-analysis
This model is a fine-tuned version of cis-lmu/glot500-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4696
- Accuracy: 0.8
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: 288
- eval_batch_size: 192
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 12.0
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.9569 | 1.0 | 125 | 0.9395 | 0.5917 |
0.8669 | 2.0 | 250 | 0.8229 | 0.6367 |
0.8243 | 3.0 | 375 | 0.7375 | 0.67 |
0.7799 | 4.0 | 500 | 0.6848 | 0.7017 |
0.7347 | 5.0 | 625 | 0.6472 | 0.7217 |
0.7058 | 6.0 | 750 | 0.5923 | 0.76 |
0.6761 | 7.0 | 875 | 0.5555 | 0.7667 |
0.6388 | 8.0 | 1000 | 0.5298 | 0.7817 |
0.6195 | 9.0 | 1125 | 0.5129 | 0.7833 |
0.5909 | 10.0 | 1250 | 0.4827 | 0.7967 |
0.5647 | 11.0 | 1375 | 0.4833 | 0.7967 |
0.5645 | 12.0 | 1500 | 0.4696 | 0.8 |
Framework versions
- Transformers 4.40.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 32