---
license: cc-by-sa-4.0
base_model: nlpaueb/legal-bert-small-uncased
tags:
- generated_from_keras_callback
model-index:
- name: bubai567/nifty_bert
  results: []
---

<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->

# bubai567/nifty_bert

This model is a fine-tuned version of [nlpaueb/legal-bert-small-uncased](https://huggingface.co/nlpaueb/legal-bert-small-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.0147
- Train Accuracy: 0.9962
- Validation Loss: 0.0152
- Validation Accuracy: 0.9964
- Epoch: 1

## Model description

This model is fine-tuned on Nifty 30-minute interval close prices from 2023-06-30T09:15:00+05:30 to 2023-09-08T15:29:00+05:30 IST. To predict the next 30-minute direction, I made a dataset where each sample contains 32 elements of z-score peak detection, which is obtained from https://stackoverflow.com/questions/22583391/peak-signal-detection-in-realtime-timeseries-data. While predicting from it, I tend to provide the last 32 elements of peak detection signal, separating them with spaces, e.g., -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0. This is currently under development and does not guarantee optimal results.
## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 3274, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32

### Training results

| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.0372     | 0.9932         | 0.0186          | 0.9963              | 0     |
| 0.0147     | 0.9962         | 0.0152          | 0.9964              | 1     |


### Framework versions

- Transformers 4.33.1
- TensorFlow 2.13.0
- Datasets 2.14.5
- Tokenizers 0.13.3