deberta-v3-base-financial-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: 0.3335
- Precision: 0.8436
- Recall: 0.8396
- F1: 0.8416
- Accuracy: 0.9318
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 86 | 0.6429 | 0.5685 | 0.5283 | 0.5477 | 0.8193 |
No log | 2.0 | 172 | 0.4601 | 0.7014 | 0.6981 | 0.6998 | 0.8761 |
No log | 3.0 | 258 | 0.4110 | 0.7739 | 0.7264 | 0.7494 | 0.8898 |
No log | 4.0 | 344 | 0.3657 | 0.7570 | 0.7642 | 0.7606 | 0.9011 |
No log | 5.0 | 430 | 0.3519 | 0.8104 | 0.8066 | 0.8085 | 0.9125 |
0.5166 | 6.0 | 516 | 0.3335 | 0.8436 | 0.8396 | 0.8416 | 0.9318 |
0.5166 | 7.0 | 602 | 0.3666 | 0.7909 | 0.8208 | 0.8056 | 0.9205 |
0.5166 | 8.0 | 688 | 0.3524 | 0.8208 | 0.8208 | 0.8208 | 0.9239 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 2
Model tree for xnijai/deberta-v3-base-financial-ner
Base model
microsoft/deberta-v3-base