6ecb25da0f1adc9b00687bbebc2b0718

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

• Loss: 0.6763
• Data Size: 1.0
• Epoch Runtime: 68.0874
• Accuracy: 0.6130
• F1 Macro: 0.3801

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	0.7641	0	4.6067	0.3843	0.2816
No log	1	650	0.2730	0.0078	5.2870	0.9014	0.8912
No log	2	1300	0.0050	0.0156	5.9764	0.9990	0.9990
No log	3	1950	0.0103	0.0312	7.8279	0.9981	0.9980
No log	4	2600	0.0050	0.0625	10.0046	0.9990	0.9990
0.0035	5	3250	0.0097	0.125	13.4265	0.9981	0.9980
0.0064	6	3900	0.0088	0.25	22.1233	0.9988	0.9988
0.0322	7	4550	0.0351	0.5	36.3193	0.9938	0.9935
0.6778	8.0	5200	0.6763	1.0	68.0874	0.6130	0.3801

Framework versions

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