687a89847e07a26b45b7d5f86d8324b9

This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct on the contemmcm/clickbait dataset. It achieves the following results on the evaluation set:

• Loss: 0.0473
• Data Size: 1.0
• Epoch Runtime: 94.9519
• Accuracy: 0.9988
• F1 Macro: 0.9988

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	2.8349	0	7.4098	0.6582	0.6565
No log	1	650	0.2153	0.0078	8.0500	0.9905	0.9900
No log	2	1300	1.4914	0.0156	9.0777	0.9761	0.9751
No log	3	1950	0.2291	0.0312	11.2017	0.9956	0.9953
No log	4	2600	0.2679	0.0625	13.9813	0.9983	0.9982
0.0524	5	3250	0.0662	0.125	19.3483	0.9967	0.9965
0.1209	6	3900	0.0601	0.25	30.9878	0.9988	0.9988
0.2979	7	4550	0.1782	0.5	51.9685	0.9986	0.9986
0.1614	8.0	5200	0.1195	1.0	95.0264	0.9961	0.9959
0.0	9.0	5850	0.0628	1.0	94.0535	0.9986	0.9986
0.025	10.0	6500	0.0578	1.0	94.2192	0.9985	0.9984
0.0	11.0	7150	0.0439	1.0	93.6139	0.9988	0.9988
0.0	12.0	7800	0.1004	1.0	94.3276	0.9979	0.9978
0.0	13.0	8450	0.1028	1.0	94.6833	0.9985	0.9984
0.0	14.0	9100	0.0526	1.0	93.0779	0.9990	0.9990
0.027	15.0	9750	0.0473	1.0	94.9519	0.9988	0.9988

Framework versions

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