metadata

license: apache-2.0
base_model: distilroberta-base
tags:
  - generated_from_keras_callback
model-index:
  - name: chunwoolee0/distilroberta-base-finetuned-wikitext2
    results: []

chunwoolee0/distilroberta-base-finetuned-wikitext2

This model is a fine-tuned version of distilroberta-base on an wikitext,wikitext-2-raw-v1 dataset. It achieves the following results on the evaluation set:

Train Loss: 2.1557
Validation Loss: 1.8964
Epoch: 0

Model description

This model is a distilled version of the RoBERTa-base model. It follows the same training procedure as DistilBERT.

Intended uses & limitations

This is an exercise for finetuning of nlp language modeling for fill-mask.

Training and evaluation data

Wikitext, wikitext-2-raw-v1 is used

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
training_precision: float32

Training results

Train Loss	Validation Loss	Epoch
2.1557	1.8964	0

Framework versions

Transformers 4.31.0
TensorFlow 2.12.0
Datasets 2.14.4
Tokenizers 0.13.3