73aaeff003e5acdc966894ec2d479a06

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

• Loss: 0.0065
• Data Size: 1.0
• Epoch Runtime: 194.2136
• Accuracy: 0.9992
• F1 Macro: 0.9992

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	0.8903	0	15.5042	0.3754	0.3496
No log	1	650	0.0054	0.0078	17.6000	0.9986	0.9986
No log	2	1300	0.0068	0.0156	19.9187	0.9988	0.9988
No log	3	1950	0.0155	0.0312	25.9870	0.9981	0.9980
No log	4	2600	0.0390	0.0625	33.9513	0.9965	0.9963
0.0015	5	3250	0.0039	0.125	43.0826	0.9992	0.9992
0.0052	6	3900	0.0023	0.25	63.6277	0.9994	0.9994
0.0237	7	4550	0.0083	0.5	107.6790	0.9985	0.9984
0.0002	8.0	5200	0.0061	1.0	193.9093	0.9983	0.9982
0.0	9.0	5850	0.0091	1.0	193.9312	0.9985	0.9984
0.0008	10.0	6500	0.0065	1.0	194.2136	0.9992	0.9992

Framework versions

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