<!-- 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. -->
BulBERT-ner-udep-5epochs
This model is a fine-tuned version of mor40/BulBERT-chitanka-model on the bgglue dataset. It achieves the following results on the evaluation set:
- Loss: 0.1089
- Precision: 0.9753
- Recall: 0.9753
- F1: 0.9753
- Accuracy: 0.9778
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1134 | 1.0 | 1114 | 0.0996 | 0.9674 | 0.9673 | 0.9673 | 0.9721 |
| 0.0578 | 2.0 | 2228 | 0.0933 | 0.9728 | 0.9722 | 0.9725 | 0.9760 |
| 0.0321 | 3.0 | 3342 | 0.0993 | 0.9739 | 0.9746 | 0.9743 | 0.9769 |
| 0.0178 | 4.0 | 4456 | 0.1054 | 0.9746 | 0.9750 | 0.9748 | 0.9776 |
| 0.0096 | 5.0 | 5570 | 0.1089 | 0.9753 | 0.9753 | 0.9753 | 0.9778 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
