|
--- |
|
license: mit |
|
tags: |
|
- generated_from_keras_callback |
|
datasets: |
|
- jonaskoenig/Questions-vs-Statements-Classification |
|
base_model: microsoft/xtremedistil-l6-h256-uncased |
|
model-index: |
|
- name: xtremedistil-l6-h256-uncased-question-vs-statement-classifier |
|
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. --> |
|
|
|
# xtremedistil-l6-h256-uncased-question-vs-statement-classifier |
|
|
|
This model is a fine-tuned version of [microsoft/xtremedistil-l6-h256-uncased](https://huggingface.co/microsoft/xtremedistil-l6-h256-uncased) on [question-vs-statement-classifier](https://huggingface.co/datasets/jonaskoenig/Questions-vs-Statements-Classification) dataset, which is a clone of the kaggle [Questions vs Statements Classification](https://www.kaggle.com/datasets/shahrukhkhan/questions-vs-statementsclassificationdataset) dataset. |
|
|
|
It achieves the following results on the evaluation set: |
|
- Train Loss: 0.0227 |
|
- Train Sparse Categorical Accuracy: 0.9894 |
|
- Validation Loss: 0.0294 |
|
- Validation Sparse Categorical Accuracy: 0.9868 |
|
- Epoch: 3 |
|
|
|
## 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: |
|
- optimizer: {'name': 'Adam', 'learning_rate': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False} |
|
- training_precision: float32 |
|
|
|
### Training results |
|
|
|
| Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch | |
|
|:----------:|:---------------------------------:|:---------------:|:--------------------------------------:|:-----:| |
|
| 0.0681 | 0.9770 | 0.0327 | 0.9839 | 0 | |
|
| 0.0301 | 0.9856 | 0.0321 | 0.9853 | 1 | |
|
| 0.0262 | 0.9875 | 0.0286 | 0.9864 | 2 | |
|
| 0.0227 | 0.9894 | 0.0294 | 0.9868 | 3 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.20.1 |
|
- TensorFlow 2.9.1 |
|
- Datasets 2.3.2 |
|
- Tokenizers 0.12.1 |
|
|
