<!-- 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. -->
Distilbert_10
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0017
- Accuracy: 0.9995
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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
No log | 1.0 | 125 | 0.4132 | 0.8255 |
No log | 2.0 | 250 | 0.2182 | 0.9235 |
No log | 3.0 | 375 | 0.1047 | 0.9755 |
0.3288 | 4.0 | 500 | 0.0434 | 0.9895 |
0.3288 | 5.0 | 625 | 0.0267 | 0.993 |
0.3288 | 6.0 | 750 | 0.0137 | 0.997 |
0.3288 | 7.0 | 875 | 0.0066 | 0.998 |
0.034 | 8.0 | 1000 | 0.0021 | 0.9995 |
0.034 | 9.0 | 1125 | 0.0018 | 0.9995 |
0.034 | 10.0 | 1250 | 0.0017 | 0.9995 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3