deberta-v3-base-financial-metric-ner
This model is a fine-tuned version of microsoft/deberta-v3-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0259
- Precision: 0.9843
- Recall: 0.9857
- F1: 0.9850
- Accuracy: 0.9944
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: 1e-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
- lr_scheduler_warmup_steps: 100
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 401 | 0.0669 | 0.9322 | 0.9255 | 0.9288 | 0.9790 |
0.2794 | 2.0 | 802 | 0.0399 | 0.9627 | 0.9613 | 0.9620 | 0.9888 |
0.0431 | 3.0 | 1203 | 0.0290 | 0.9699 | 0.9699 | 0.9699 | 0.9917 |
0.03 | 4.0 | 1604 | 0.0269 | 0.9757 | 0.9785 | 0.9771 | 0.9933 |
0.0209 | 5.0 | 2005 | 0.0283 | 0.9772 | 0.9828 | 0.9800 | 0.9939 |
0.0209 | 6.0 | 2406 | 0.0316 | 0.9771 | 0.9785 | 0.9778 | 0.9925 |
0.0163 | 7.0 | 2807 | 0.0267 | 0.98 | 0.9828 | 0.9814 | 0.9941 |
0.0131 | 8.0 | 3208 | 0.0262 | 0.9828 | 0.9842 | 0.9835 | 0.9944 |
0.0113 | 9.0 | 3609 | 0.0259 | 0.9843 | 0.9857 | 0.9850 | 0.9944 |
0.0094 | 10.0 | 4010 | 0.0266 | 0.9828 | 0.9842 | 0.9835 | 0.9941 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu124
- Datasets 2.21.0
- Tokenizers 0.19.1
- Downloads last month
- 167
Inference API (serverless) is not available, repository is disabled.
Model tree for finsynth/deberta-v3-base-financial-metric-ner
Base model
microsoft/deberta-v3-base
Finetuned
this model