Training
This model is a fine-tuned version of DistilRoBERTa-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1715
- Precision: 0.9792
- Recall: 0.9266
- F1: 0.9522
- Roc Auc: 0.9829
- Krippendorff Alpha: 0.8696
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: 6.7e-06
- 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
- lr_scheduler_warmup_steps: 500
- num_epochs: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Roc Auc | Krippendorff Alpha |
---|---|---|---|---|---|---|---|---|
0.4687 | 1.0 | 288 | 0.4095 | 0.8979 | 0.8513 | 0.8740 | 0.9094 | 0.6544 |
0.3517 | 2.0 | 576 | 0.2712 | 0.9302 | 0.9042 | 0.9170 | 0.9531 | 0.7674 |
0.2335 | 3.0 | 864 | 0.2390 | 0.9497 | 0.9042 | 0.9264 | 0.9624 | 0.7974 |
0.2088 | 4.0 | 1152 | 0.2233 | 0.9589 | 0.9072 | 0.9323 | 0.9676 | 0.8147 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 5
Invalid base_model specified in model card
metadata. Needs to be a model id from
hf.co/models.