gpt2-qlora-wp

mnj-hf/gpt2-qlora-wp

gpt2-qlora-wp is a machine learning model from mnj-hf. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as mit.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

41% of all-time downloads

All-time downloads

Public

Repo size

6.5 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors6.5 MB · 57%

At a glance

Library: peft
License: mit
Access: Public
Created: Apr 8, 2025
Updated: Apr 8, 2025
SHA: 7603d350

Base models

openai-community/gpt2

Model card

From the Hugging Face model README

gpt2-qlora-wp

This model is a fine-tuned version of openai-community/gpt2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 3.1175

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: 0.0002
train_batch_size: 4
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 200
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
3.2863	1.0	2500	3.1359
3.2275	2.0	5000	3.1217
3.2517	3.0	7500	3.1175

Framework versions

PEFT 0.14.0
Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

Library: peft
License: mit
Created: Apr 8, 2025
Updated: Apr 8, 2025