24c837ad11e128bd812da087c5f7f321

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

• Loss: 0.0462
• Data Size: 1.0
• Epoch Runtime: 20.0863
• Accuracy: 0.9931
• F1 Macro: 0.9927

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	0.7233	0	2.0046	0.3872	0.2816
No log	1	650	0.3603	0.0078	2.4079	0.9153	0.9125
No log	2	1300	0.0929	0.0156	2.6076	0.9705	0.9692
No log	3	1950	0.0734	0.0312	2.9203	0.9776	0.9763
No log	4	2600	0.0581	0.0625	3.3407	0.9850	0.9842
0.0055	5	3250	0.0368	0.125	4.5484	0.9902	0.9896
0.0257	6	3900	0.0454	0.25	6.7182	0.9882	0.9876
0.028	7	4550	0.0267	0.5	11.1897	0.9929	0.9925
0.0251	8.0	5200	0.0396	1.0	19.7788	0.9890	0.9884
0.0062	9.0	5850	0.0648	1.0	20.1494	0.9890	0.9885
0.0046	10.0	6500	0.0547	1.0	20.3069	0.9909	0.9905
0.0	11.0	7150	0.0462	1.0	20.0863	0.9931	0.9927

Framework versions

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