metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: fine_tuned_bert_dreadit
results: []
fine_tuned_bert_dreadit
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6964
- Accuracy: 0.7584
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 |
|---|---|---|---|---|
| 0.0515 | 1.0 | 178 | 1.0425 | 0.7388 |
| 0.0988 | 2.0 | 356 | 1.1394 | 0.7725 |
| 0.0008 | 3.0 | 534 | 1.3705 | 0.7725 |
| 0.4585 | 4.0 | 712 | 1.2983 | 0.7809 |
| 0.0003 | 5.0 | 890 | 1.4867 | 0.7753 |
| 0.0003 | 6.0 | 1068 | 1.5385 | 0.7837 |
| 0.0002 | 7.0 | 1246 | 1.4708 | 0.7781 |
| 0.0002 | 8.0 | 1424 | 1.6836 | 0.7640 |
| 0.0002 | 9.0 | 1602 | 1.7276 | 0.7584 |
| 0.0002 | 10.0 | 1780 | 1.6964 | 0.7584 |
Framework versions
- Transformers 4.27.3
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2