0a4c3f5019da67b8c820c7149884792b

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

• Loss: 0.0052
• Data Size: 1.0
• Epoch Runtime: 97.9903
• Accuracy: 0.9994
• F1 Macro: 0.9994

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	7.6902	0	8.7167	0.6105	0.3814
No log	1	650	0.3138	0.0078	9.4507	0.9373	0.9341
No log	2	1300	0.0298	0.0156	10.6870	0.9948	0.9945
No log	3	1950	0.0120	0.0312	12.7165	0.9969	0.9968
No log	4	2600	0.0098	0.0625	16.0577	0.9981	0.9980
0.0096	5	3250	0.0050	0.125	22.5711	0.9990	0.9990
0.0005	6	3900	0.0185	0.25	34.5609	0.9985	0.9984
0.0015	7	4550	0.0032	0.5	56.5743	0.9992	0.9992
0.0001	8.0	5200	0.0111	1.0	99.8713	0.9986	0.9986
0.0042	9.0	5850	0.0074	1.0	98.9117	0.9990	0.9990
0.0002	10.0	6500	0.0114	1.0	99.5070	0.9986	0.9986
0.0	11.0	7150	0.0052	1.0	97.9903	0.9994	0.9994

Framework versions

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