|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_keras_callback |
|
model-index: |
|
- name: distilbert-truncated |
|
results: [] |
|
--- |
|
|
|
|
|
# distilbert-truncated |
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the [20 Newsgroups dataset](http://qwone.com/~jason/20Newsgroups/). |
|
It achieves the following results on the evaluation set: |
|
|
|
|
|
## Training and evaluation data |
|
|
|
The data was split into training and testing: model trained on 90% of the data, and had a testing data size of 10% of the original dataset. |
|
|
|
## Training procedure |
|
|
|
DistilBERT has a maximum input length of 512, so with this in mind the following was performed: |
|
|
|
1. I used the `distilbert-base-uncased` pretrained model to initialize an `AutoTokenizer`. |
|
2. Setting a maximum length of 256, each entry in the training, testing and validation data was truncated if it exceeded the limit and padded if it didn't reach the limit. |
|
|
|
### 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': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1908, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} |
|
- training_precision: float32 |
|
|
|
### Training results |
|
|
|
EPOCHS = 3 |
|
batches_per_epoch = 636 |
|
total_train_steps = 1908 |
|
|
|
Model accuracy 0.8337758779525757 |
|
|
|
Model loss 0.568471074104309 |
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.0 |
|
- TensorFlow 2.12.0 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
