codewithdark
/

Lumina

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions

Metrics Training metrics Community

Lumina

This model is a fine-tuned version of microsoft/CodeGPT-small-py on the Code Search dataset. It achieves the following results on the evaluation set:

Loss: 0.5343

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: 5e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
training_steps: 5000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.5519	0.7763	5000	0.5343

Framework versions

Transformers 4.44.0
Pytorch 2.4.0
Datasets 2.21.0
Tokenizers 0.19.1

Downloads last month: 2

Safetensors

Model size

0.1B params

Tensor type

F32

·

Model tree for codewithdark/Lumina

Base model

microsoft/CodeGPT-small-py

Finetuned

(5)

this model

Dataset used to train codewithdark/Lumina