metadata

license: apache-2.0
base_model: distilbert-base-cased
tags:
  - generated_from_keras_callback
model-index:
  - name: transformers-question-answer
    results: []

transformers-question-answer

This model is a fine-tuned version of distilbert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:

Train Loss: 1.4951
Validation Loss: 1.1651
Epoch: 0

Model description

This is a sample transformer trained for question-answer use case. I have used a pre-trained BERT model and then finetuned it using the hugging-face transformer library.

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': 5e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
training_precision: mixed_float16

Training results

Train Loss	Validation Loss	Epoch
1.4951	1.1651	0

Framework versions

Transformers 4.31.0
TensorFlow 2.11.0
Datasets 2.14.2
Tokenizers 0.13.3