3b27d0ac497c4bd4706bab59bfb3e2b2

This model is a fine-tuned version of Qwen/Qwen2.5-0.5B on the contemmcm/clickbait dataset. It achieves the following results on the evaluation set:

• Loss: 0.2389
• Data Size: 0.125
• Epoch Runtime: 24.4375
• Accuracy: 0.9965
• F1 Macro: 0.9963

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	9.0607	0	10.1434	0.4807	0.4328
No log	1	650	0.1576	0.0078	10.8527	0.9944	0.9941
No log	2	1300	0.4353	0.0156	12.2610	0.9927	0.9922
No log	3	1950	0.2550	0.0312	13.5909	0.9954	0.9951
No log	4	2600	1.1078	0.0625	17.0280	0.9905	0.9900
0.0281	5	3250	0.2389	0.125	24.4375	0.9965	0.9963

Framework versions

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