84cc93ffbe2459312fa18acba4f72b92

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

• Loss: 0.0059
• Data Size: 1.0
• Epoch Runtime: 48.9314
• Accuracy: 0.9988
• F1 Macro: 0.9988

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: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 32
• total_eval_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Data Size	Epoch Runtime	Accuracy	F1 Macro
No log	0	0	7.1843	0	5.2182	0.3870	0.2790
No log	1	650	0.2488	0.0078	5.4254	0.9199	0.9151
No log	2	1300	0.0208	0.0156	5.7034	0.9923	0.9919
No log	3	1950	0.0042	0.0312	6.7122	0.9986	0.9986
No log	4	2600	0.0064	0.0625	8.5970	0.9985	0.9984
0.0087	5	3250	0.0027	0.125	11.0430	0.9992	0.9992
0.0019	6	3900	0.0092	0.25	16.7783	0.9988	0.9988
0.0001	7	4550	0.0063	0.5	28.2861	0.9992	0.9992
0.0029	8.0	5200	0.0027	1.0	52.3147	0.9992	0.9992
0.0	9.0	5850	0.0059	1.0	48.9314	0.9988	0.9988

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.3.0
• Tokenizers 0.22.1