<!-- 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-fresh_10epoch
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: 0.0234
- Precision: 0.0
- Recall: 0.0
- F1: 0.0
- Accuracy: 0.9935
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: 8
- 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 | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 174 | 0.1913 | 0.0 | 0.0 | 0.0 | 0.9312 |
No log | 2.0 | 348 | 0.1431 | 0.0 | 0.0 | 0.0 | 0.9507 |
0.2211 | 3.0 | 522 | 0.1053 | 0.0 | 0.0 | 0.0 | 0.9640 |
0.2211 | 4.0 | 696 | 0.0770 | 0.0 | 0.0 | 0.0 | 0.9746 |
0.2211 | 5.0 | 870 | 0.0581 | 0.0 | 0.0 | 0.0 | 0.9820 |
0.0995 | 6.0 | 1044 | 0.0461 | 0.0 | 0.0 | 0.0 | 0.9862 |
0.0995 | 7.0 | 1218 | 0.0376 | 0.0 | 0.0 | 0.0 | 0.9886 |
0.0995 | 8.0 | 1392 | 0.0290 | 0.0 | 0.0 | 0.0 | 0.9915 |
0.054 | 9.0 | 1566 | 0.0238 | 0.0 | 0.0 | 0.0 | 0.9934 |
0.054 | 10.0 | 1740 | 0.0234 | 0.0 | 0.0 | 0.0 | 0.9935 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1