metadata

license: mit
widget:
  - text: My name is Julien and I like to
    example_title: Julien
  - text: My name is Merve and my favorite
    example_title: Merve
base_model: distilgpt2
tags:
  - generated_from_trainer
  - code
model-index:
  - name: distilgpt2-finetuned-python_code_instructions_18k_alpaca
    results: []
datasets:
  - iamtarun/python_code_instructions_18k_alpaca
language:
  - en
metrics:
  - accuracy
library_name: transformers
pipeline_tag: text-generation

distilgpt2-finetuned-python_code_instructions_18k_alpaca

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

Loss: 1.5063

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:

learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.7264	1.0	3861	1.5890
1.6046	2.0	7722	1.5214
1.5359	3.0	11583	1.5063

Framework versions

Transformers 4.39.3
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2