eee332332d166d6fe59113e3ab66d252

This model is a fine-tuned version of google-bert/bert-base-cased on the contemmcm/clickbait dataset. It achieves the following results on the evaluation set:

• Loss: 0.0099
• Data Size: 1.0
• Epoch Runtime: 34.3003
• 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	0.6652	0	3.2868	0.6130	0.3801
No log	1	650	0.2555	0.0078	3.6135	0.9921	0.9916
No log	2	1300	0.0112	0.0156	3.6236	0.9981	0.9980
No log	3	1950	0.0234	0.0312	4.1514	0.9956	0.9953
No log	4	2600	0.0502	0.0625	5.2657	0.9882	0.9877
0.0021	5	3250	0.0081	0.125	7.1914	0.9973	0.9972
0.0127	6	3900	0.0090	0.25	11.1432	0.9981	0.9980
0.0071	7	4550	0.0109	0.5	19.1214	0.9981	0.9980
0.0039	8.0	5200	0.0101	1.0	36.6261	0.9986	0.9986
0.0	9.0	5850	0.0099	1.0	34.3003	0.9988	0.9988

Framework versions

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