<!-- 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. -->
fatimah_fake_news_bert
This model is a fine-tuned version of distilbert-base-uncased-finetuned-sst-2-english on Fake and real dataset on kaggle It achieves the following results on the evaluation set:
- Loss: 0.0010
- Accuracy: 0.9998
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: 10
- eval_batch_size: 20
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3298 | 0.06 | 200 | 0.0094 | 0.9987 |
| 0.0087 | 0.11 | 400 | 0.0091 | 0.9988 |
| 0.0126 | 0.17 | 600 | 0.0132 | 0.9965 |
| 0.0081 | 0.22 | 800 | 0.0100 | 0.9987 |
| 0.0132 | 0.28 | 1000 | 0.0086 | 0.9990 |
| 0.0131 | 0.33 | 1200 | 0.0070 | 0.9986 |
| 0.0086 | 0.39 | 1400 | 0.0079 | 0.9990 |
| 0.0041 | 0.45 | 1600 | 0.0057 | 0.9991 |
| 0.0069 | 0.5 | 1800 | 0.0083 | 0.9989 |
| 0.0052 | 0.56 | 2000 | 0.0043 | 0.9993 |
| 0.0 | 0.61 | 2200 | 0.0047 | 0.9993 |
| 0.003 | 0.67 | 2400 | 0.0052 | 0.9994 |
| 0.0126 | 0.72 | 2600 | 0.0028 | 0.9997 |
| 0.0047 | 0.78 | 2800 | 0.0018 | 0.9996 |
| 0.0 | 0.84 | 3000 | 0.0027 | 0.9996 |
| 0.0001 | 0.89 | 3200 | 0.0029 | 0.9996 |
| 0.0079 | 0.95 | 3400 | 0.0010 | 0.9998 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6
