gpt2-medium-finetuned-qna-crypto

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: 0.2154

Google Collab

https://colab.research.google.com/drive/1N4xv2ifrkeY6Q0TPRPiGEvmSeq0xgA39?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: 5
• eval_batch_size: 4
• 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
0.3284	0.0578	10	0.3469
0.2827	0.1156	20	0.2725
0.2905	0.1734	30	0.2588
0.228	0.2312	40	0.2500
0.2449	0.2890	50	0.2439
0.2265	0.3468	60	0.2404
0.2537	0.4046	70	0.2358
0.2365	0.4624	80	0.2319
0.2362	0.5202	90	0.2288
0.2244	0.5780	100	0.2267
0.2168	0.6358	110	0.2232
0.214	0.6936	120	0.2204
0.2139	0.7514	130	0.2188
0.2264	0.8092	140	0.2174
0.2673	0.8671	150	0.2163
0.2223	0.9249	160	0.2157
0.2623	0.9827	170	0.2154

Framework versions

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