metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- fin
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: fin1
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: 0.8315412186379928
- name: Recall
type: recall
value: 0.9243027888446215
- name: F1
type: f1
value: 0.8754716981132076
- name: Accuracy
type: accuracy
value: 0.985175455057234
fin1
This model is a fine-tuned version of bert-base-cased on the fin dataset. It achieves the following results on the evaluation set:
- Loss: 0.0778
- Precision: 0.8315
- Recall: 0.9243
- F1: 0.8755
- Accuracy: 0.9852
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 | 0.0860 | 0.8535 | 0.9283 | 0.8893 | 0.9904 |
| No log | 2.0 | 258 | 0.1513 | 0.7993 | 0.9203 | 0.8556 | 0.9799 |
| No log | 3.0 | 387 | 0.0977 | 0.8221 | 0.9203 | 0.8684 | 0.9831 |
| 0.0017 | 4.0 | 516 | 0.0783 | 0.8286 | 0.9243 | 0.8738 | 0.9848 |
| 0.0017 | 5.0 | 645 | 0.0778 | 0.8315 | 0.9243 | 0.8755 | 0.9852 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.7.1
- Tokenizers 0.13.2