metadata
library_name: transformers
license: mit
base_model: microsoft/deberta-v3-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: deberta-v3-base-financial-inc-dec-ner
results: []
deberta-v3-base-financial-inc-dec-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: 0.0351
- Precision: 0.9051
- Recall: 0.9185
- F1: 0.9118
- Accuracy: 0.9873
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
- num_epochs: 6
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 92 | 0.0589 | 0.8370 | 0.8370 | 0.8370 | 0.9813 |
No log | 2.0 | 184 | 0.0351 | 0.9051 | 0.9185 | 0.9118 | 0.9873 |
No log | 3.0 | 276 | 0.0626 | 0.8849 | 0.9111 | 0.8978 | 0.9828 |
No log | 4.0 | 368 | 0.0379 | 0.9357 | 0.9704 | 0.9527 | 0.9910 |
No log | 5.0 | 460 | 0.0384 | 0.9353 | 0.9630 | 0.9489 | 0.9903 |
0.0721 | 6.0 | 552 | 0.0421 | 0.9353 | 0.9630 | 0.9489 | 0.9903 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu124
- Datasets 2.21.0
- Tokenizers 0.19.1