6765aa88bedd540b83952a9510682c56

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

• Loss: 0.0491
• Data Size: 1.0
• Epoch Runtime: 35.4724
• Accuracy: 0.9938
• F1 Macro: 0.9935

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	0.6972	0	3.1138	0.5666	0.4292
No log	1	650	0.3289	0.0078	3.8937	0.9761	0.9748
No log	2	1300	0.0824	0.0156	3.8051	0.9728	0.9710
No log	3	1950	0.0640	0.0312	4.3262	0.9842	0.9833
No log	4	2600	0.0694	0.0625	5.4999	0.9861	0.9853
0.0046	5	3250	0.0313	0.125	7.6219	0.9904	0.9898
0.0324	6	3900	0.0476	0.25	11.4640	0.9888	0.9882
0.0301	7	4550	0.0374	0.5	19.3472	0.9850	0.9840
0.0155	8.0	5200	0.0286	1.0	36.3476	0.9925	0.9921
0.0147	9.0	5850	0.0377	1.0	34.9253	0.9936	0.9933
0.0075	10.0	6500	0.0814	1.0	36.1484	0.9890	0.9885
0.0125	11.0	7150	0.0363	1.0	34.7327	0.9934	0.9931
0.0	12.0	7800	0.0491	1.0	35.4724	0.9938	0.9935

Framework versions

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