|
--- |
|
license: mit |
|
tags: |
|
- generated_from_keras_callback |
|
model-index: |
|
- name: xtremedistil-l6-h256-uncased-future-time-references-D2 |
|
results: [] |
|
datasets: |
|
- jonaskoenig/trump_administration_statement |
|
- jonaskoenig/future-time-refernces-static-filter-D2 |
|
--- |
|
|
|
<!-- 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-future-time-references-D2 |
|
|
|
This model is a fine-tuned version of [microsoft/xtremedistil-l6-h256-uncased](https://huggingface.co/microsoft/xtremedistil-l6-h256-uncased) on [jonaskoenig/future-time-refernces-static-filter-D2](https://huggingface.co/datasets/jonaskoenig/future-time-refernces-static-filter-D2) and [jonaskoenig/trump_administration_statement](https://huggingface.co/datasets/jonaskoenig/trump_administration_statement). |
|
It achieves the following results on the evaluation set: |
|
- Train Loss: 0.0055 |
|
- Train Sparse Categorical Accuracy: 0.9984 |
|
- Validation Loss: 0.0074 |
|
- Validation Sparse Categorical Accuracy: 0.9984 |
|
- Epoch: 4 |
|
|
|
## 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 | |
|
|:----------:|:---------------------------------:|:---------------:|:--------------------------------------:|:-----:| |
|
| 0.0388 | 0.9891 | 0.0154 | 0.9957 | 0 | |
|
| 0.0133 | 0.9962 | 0.0088 | 0.9975 | 1 | |
|
| 0.0087 | 0.9974 | 0.0081 | 0.9978 | 2 | |
|
| 0.0068 | 0.9980 | 0.0074 | 0.9982 | 3 | |
|
| 0.0055 | 0.9984 | 0.0074 | 0.9984 | 4 | |
|
|
|
The test accuracy is: 99.81% |
|
|
|
### Framework versions |
|
|
|
- Transformers 4.20.1 |
|
- TensorFlow 2.9.1 |
|
- Datasets 2.3.2 |
|
- Tokenizers 0.12.1 |
|
|
