metadata
license: apache-2.0
base_model: distilbert-base-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: distilBERT-infoExtract-v3
results: []
distilBERT-infoExtract-v3
This model is a fine-tuned version of distilbert-base-cased on an conllpp dataset. It achieves the following results on the evaluation set:
- Loss: 0.0871
- Precision: 0.9239
- Recall: 0.9440
- F1: 0.9338
- Accuracy: 0.9843
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: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0945 | 1.0 | 1756 | 0.0958 | 0.8746 | 0.9170 | 0.8953 | 0.9736 |
| 0.0521 | 2.0 | 3512 | 0.0727 | 0.9090 | 0.9276 | 0.9182 | 0.9810 |
| 0.0334 | 3.0 | 5268 | 0.0736 | 0.9091 | 0.9372 | 0.9229 | 0.9827 |
| 0.0149 | 4.0 | 7024 | 0.0755 | 0.9248 | 0.9411 | 0.9329 | 0.9847 |
| 0.0079 | 5.0 | 8780 | 0.0847 | 0.9216 | 0.9433 | 0.9323 | 0.9840 |
| 0.0075 | 6.0 | 10536 | 0.0871 | 0.9239 | 0.9440 | 0.9338 | 0.9843 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2