dddc1557ab801f80201ac0a3c485c11a

This model is a fine-tuned version of Qwen/Qwen2.5-7B on the contemmcm/clickbait dataset. It achieves the following results on the evaluation set:

• Loss: 0.2598
• Data Size: 0.5
• Epoch Runtime: 287.5524
• Accuracy: 0.9950
• F1 Macro: 0.9947

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	19.2967	0	14.4524	0.1651	0.1545
No log	1	650	0.2034	0.0078	18.1551	0.9944	0.9941
No log	2	1300	0.2121	0.0156	30.6623	0.9925	0.9921
No log	3	1950	0.1720	0.0312	46.7186	0.9969	0.9967
No log	4	2600	0.1954	0.0625	72.9584	0.9969	0.9968
0.0623	5	3250	0.9461	0.125	118.0725	0.9965	0.9963
0.4652	6	3900	0.4270	0.25	153.8241	0.9940	0.9937
0.0712	7	4550	0.2598	0.5	287.5524	0.9950	0.9947

Framework versions

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