IceBERT-finetuned-ner
This model is a fine-tuned version of vesteinn/IceBERT on the mim_gold_ner dataset. It achieves the following results on the evaluation set:
- Loss: 0.0347
- Precision: 0.9352
- Recall: 0.9440
- F1: 0.9396
- Accuracy: 0.9920
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: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|---|---|---|---|
| 0.0568 | 1.0 | 2929 | 0.0386 | 0.9114 | 0.9162 | 0.9138 | 0.9897 |
| 0.0325 | 2.0 | 5858 | 0.0325 | 0.9300 | 0.9363 | 0.9331 | 0.9912 |
| 0.0184 | 3.0 | 8787 | 0.0347 | 0.9352 | 0.9440 | 0.9396 | 0.9920 |
Framework versions
- Transformers 4.11.0
- Pytorch 1.9.0+cu102
- Datasets 1.12.1
- Tokenizers 0.10.3
- Downloads last month
- 142
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for vesteinn/IceBERT-ner
Base model
vesteinn/IceBERTEvaluation results
- Precision on mim_gold_nerself-reported0.935
- Recall on mim_gold_nerself-reported0.944
- F1 on mim_gold_nerself-reported0.940
- Accuracy on mim_gold_nerself-reported0.992