DarkBERT-finetuned-ner
This model is a fine-tuned version of s2w-ai/DarkBERT on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6109
- Precision: 0.4288
- Recall: 0.4990
- F1: 0.4612
- Accuracy: 0.8864
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: 5e-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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 201 | 0.3204 | 0.4136 | 0.5325 | 0.4656 | 0.9014 |
No log | 2.0 | 402 | 0.2999 | 0.4933 | 0.5564 | 0.5229 | 0.9106 |
0.3703 | 3.0 | 603 | 0.3175 | 0.4692 | 0.5705 | 0.5149 | 0.9065 |
0.3703 | 4.0 | 804 | 0.3385 | 0.4776 | 0.5662 | 0.5181 | 0.9053 |
0.1616 | 5.0 | 1005 | 0.4031 | 0.4498 | 0.5445 | 0.4926 | 0.8985 |
0.1616 | 6.0 | 1206 | 0.4554 | 0.4618 | 0.5705 | 0.5104 | 0.9008 |
0.1616 | 7.0 | 1407 | 0.4849 | 0.4716 | 0.5672 | 0.5150 | 0.9018 |
0.072 | 8.0 | 1608 | 0.5041 | 0.4688 | 0.5542 | 0.5080 | 0.9040 |
0.072 | 9.0 | 1809 | 0.5470 | 0.4771 | 0.5531 | 0.5123 | 0.9035 |
0.0386 | 10.0 | 2010 | 0.5475 | 0.4762 | 0.5651 | 0.5169 | 0.9045 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 59
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.