bert-finetuned-ner
This model is a fine-tuned version of allenai/longformer-base-4096 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6434
- Precision: 0.8589
- Recall: 0.8686
- F1: 0.8637
- Accuracy: 0.8324
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.615 | 1.0 | 1741 | 0.6111 | 0.8200 | 0.8652 | 0.8420 | 0.8046 |
0.4795 | 2.0 | 3482 | 0.5366 | 0.8456 | 0.8803 | 0.8626 | 0.8301 |
0.3705 | 3.0 | 5223 | 0.5412 | 0.8527 | 0.8786 | 0.8655 | 0.8339 |
0.2749 | 4.0 | 6964 | 0.5906 | 0.8559 | 0.8711 | 0.8634 | 0.8316 |
0.2049 | 5.0 | 8705 | 0.6434 | 0.8589 | 0.8686 | 0.8637 | 0.8324 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 1.18.4
- Tokenizers 0.11.6
- Downloads last month
- 8
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.