a2f18d7b91bbd1af85b80fea611f17d0

This model is a fine-tuned version of meta-llama/Llama-3.2-3B on the contemmcm/clickbait dataset. It achieves the following results on the evaluation set:

• Loss: 0.2454
• Data Size: 0.25
• Epoch Runtime: 63.9359
• Accuracy: 0.9948
• F1 Macro: 0.9945

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	2.7987	0	11.5238	0.6711	0.6386
No log	1	650	0.3697	0.0078	12.3815	0.9958	0.9955
No log	2	1300	0.0500	0.0156	17.1302	0.9988	0.9988
No log	3	1950	0.0719	0.0312	24.1440	0.9979	0.9978
No log	4	2600	0.1272	0.0625	34.0553	0.9985	0.9984
0.079	5	3250	0.3229	0.125	45.2105	0.9961	0.9959
0.1413	6	3900	0.2454	0.25	63.9359	0.9948	0.9945

Framework versions

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