Article_50v6_NER_Model_3Epochs_UNAUGMENTED
This model is a fine-tuned version of bert-base-cased on the article50v6_wikigold_split dataset. It achieves the following results on the evaluation set:
- Loss: 0.7622
- Precision: 0.0
- Recall: 0.0
- F1: 0.0
- Accuracy: 0.7773
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 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 7 | 0.9429 | 0.1579 | 0.0015 | 0.0029 | 0.7769 |
| No log | 2.0 | 14 | 0.7845 | 0.0 | 0.0 | 0.0 | 0.7773 |
| No log | 3.0 | 21 | 0.7622 | 0.0 | 0.0 | 0.0 | 0.7773 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.11.0+cu113
- Datasets 2.4.0
- Tokenizers 0.11.6
- Downloads last month
- 4
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Evaluation results
- Precision on article50v6_wikigold_splitself-reported0.000
- Recall on article50v6_wikigold_splitself-reported0.000
- F1 on article50v6_wikigold_splitself-reported0.000
- Accuracy on article50v6_wikigold_splitself-reported0.777