scenario-NON-KD-PO-COPY-CDF-EN-D2_data-en-cardiff_eng_only_gamma
This model is a fine-tuned version of haryoaw/scenario-TCR_data-en-cardiff_eng_only2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.4417
- Accuracy: 0.5119
- F1: 0.5132
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 11423
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
No log | 4.31 | 250 | 2.3483 | 0.5212 | 0.5128 |
0.2462 | 8.62 | 500 | 3.1893 | 0.5295 | 0.5249 |
0.2462 | 12.93 | 750 | 3.8034 | 0.5247 | 0.5239 |
0.0367 | 17.24 | 1000 | 4.0511 | 0.5256 | 0.5265 |
0.0367 | 21.55 | 1250 | 4.3687 | 0.5190 | 0.5188 |
0.0067 | 25.86 | 1500 | 4.4417 | 0.5119 | 0.5132 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.1.1+cu121
- Datasets 2.14.5
- Tokenizers 0.13.3
- Downloads last month
- 1