gpt2-medium-finetuned-qna-crypto-4bit

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

• Loss: 7.6678

Google Colab

https://colab.research.google.com/drive/1fqX_oACBaJ9hOdr7J_LR8Mhqn4XBDhM7?usp=sharing

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: 32
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
10.1706	0.0741	2	9.9438
9.9335	0.1481	4	9.7155
9.6682	0.2222	6	9.4733
9.4458	0.2963	8	9.2231
9.1884	0.3704	10	8.9719
8.8838	0.4444	12	8.7266
8.7486	0.5185	14	8.4939
8.3598	0.5926	16	8.2804
8.1458	0.6667	18	8.0916
7.9992	0.7407	20	7.9324
7.8608	0.8148	22	7.8068
7.7555	0.8889	24	7.7179
7.6467	0.9630	26	7.6678

Framework versions

• PEFT 0.17.1
• Transformers 4.56.2
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.0