<!-- 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. -->
DistilRoBERTa
This model is a fine-tuned version of distilroberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5297
- Accuracy: 0.8950
- F1: 0.5834
- Precision: 0.6414
- Recall: 0.5351
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: 6
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
---|---|---|---|---|---|---|---|
0.2559 | 1.0 | 1626 | 0.2590 | 0.8987 | 0.6029 | 0.6538 | 0.5595 |
0.2191 | 2.0 | 3252 | 0.3010 | 0.8954 | 0.6025 | 0.6305 | 0.5770 |
0.1824 | 3.0 | 4878 | 0.4143 | 0.8987 | 0.6190 | 0.6409 | 0.5984 |
0.1495 | 4.0 | 6504 | 0.3914 | 0.8864 | 0.5927 | 0.5843 | 0.6014 |
0.139 | 5.0 | 8130 | 0.4922 | 0.8904 | 0.5704 | 0.6185 | 0.5292 |
0.1144 | 6.0 | 9756 | 0.5297 | 0.8950 | 0.5834 | 0.6414 | 0.5351 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3