metadata

license: apache-2.0
base_model: distilgpt2
tags:
  - generated_from_keras_callback
model-index:
  - name: chunwoolee0/distilgpt2_eli5_clm
    results: []

chunwoolee0/distilgpt2_eli5_clm

This model is a fine-tuned version of distilgpt2 on an eli5 dataset. It achieves the following results on the evaluation set:

Train Loss: 3.7237
Validation Loss: 3.7528
Epoch: 2

Model description

DistilGPT2 is an English-language model pre-trained with the supervision of the 124 million parameter version of GPT-2. DistilGPT2, which has 82 million parameters, was developed using knowledge distillation and was designed to be a faster, lighter version of GPT-2.

Intended uses & limitations

This is an exercise for finetuning of the pretrained causal language model.

Training and evaluation data

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
3.9048	3.7838	0
3.7853	3.7647	1
3.7237	3.7528	2

Framework versions

Transformers 4.31.0
TensorFlow 2.12.0
Datasets 2.14.4
Tokenizers 0.13.3