metadata
license: cc-by-sa-4.0
tags:
- generated_from_trainer
datasets:
- fin
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: fin2
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: fin
type: fin
config: default
split: train
args: default
metrics:
- name: Precision
type: precision
value: 0.9362745098039216
- name: Recall
type: recall
value: 0.7609561752988048
- name: F1
type: f1
value: 0.8395604395604396
- name: Accuracy
type: accuracy
value: 0.9742916119346969
fin2
This model is a fine-tuned version of nlpaueb/sec-bert-base on the fin dataset. It achieves the following results on the evaluation set:
- Loss: 0.2405
- Precision: 0.9363
- Recall: 0.7610
- F1: 0.8396
- Accuracy: 0.9743
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: 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 129 | 0.2186 | 0.7980 | 0.6454 | 0.7137 | 0.9653 |
| No log | 2.0 | 258 | 0.2109 | 0.9487 | 0.7371 | 0.8296 | 0.9734 |
| No log | 3.0 | 387 | 0.2531 | 0.9746 | 0.7649 | 0.8571 | 0.9743 |
| 0.1166 | 4.0 | 516 | 0.2345 | 0.9403 | 0.7530 | 0.8363 | 0.9741 |
| 0.1166 | 5.0 | 645 | 0.2405 | 0.9363 | 0.7610 | 0.8396 | 0.9743 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.7.1
- Tokenizers 0.13.2