c318dfbe9fd93f3f51bc6ba65a0bca8a

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

• Loss: 0.0078
• Data Size: 1.0
• Epoch Runtime: 22.7929
• Accuracy: 0.9990
• F1 Macro: 0.9990

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	0.7179	0	2.0129	0.3870	0.2790
No log	1	650	0.2953	0.0078	2.3561	0.9815	0.9803
No log	2	1300	0.0201	0.0156	2.4551	0.9967	0.9965
No log	3	1950	0.0138	0.0312	3.0414	0.9971	0.9970
No log	4	2600	0.0050	0.0625	3.5870	0.9992	0.9992
0.0021	5	3250	0.0047	0.125	5.0010	0.9992	0.9992
0.0004	6	3900	0.0067	0.25	7.5117	0.9986	0.9986
0.0056	7	4550	0.0064	0.5	12.5024	0.9986	0.9986
0.0124	8.0	5200	0.0060	1.0	21.9746	0.9988	0.9988
0.0	9.0	5850	0.0078	1.0	22.7929	0.9990	0.9990

Framework versions

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