metadata
license: apache-2.0
base_model: distilbert-base-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: distilBERT-infoExtract-v2
results: []
distilBERT-infoExtract-v2
This model is a fine-tuned version of distilbert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0704
- Precision: 0.9146
- Recall: 0.9350
- F1: 0.9247
- Accuracy: 0.9831
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0989 | 1.0 | 1756 | 0.0877 | 0.8808 | 0.9152 | 0.8977 | 0.9748 |
| 0.0498 | 2.0 | 3512 | 0.0697 | 0.9027 | 0.9286 | 0.9155 | 0.9814 |
| 0.0328 | 3.0 | 5268 | 0.0704 | 0.9146 | 0.9350 | 0.9247 | 0.9831 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2