49bfe49cd21a98da407d778f35a01aa4

This model is a fine-tuned version of albert/albert-xxlarge-v2 on the contemmcm/clickbait dataset. It achieves the following results on the evaluation set:

• Loss: 0.0970
• Data Size: 1.0
• Epoch Runtime: 48.6124
• Accuracy: 0.9786
• F1 Macro: 0.9776

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	0.6883	0	3.4269	0.5505	0.5500
No log	1	650	0.6664	0.0078	3.9455	0.7357	0.6540
No log	2	1300	0.3963	0.0156	4.3525	0.7664	0.7663
No log	3	1950	0.2284	0.0312	5.1955	0.9338	0.9318
No log	4	2600	0.1778	0.0625	6.6163	0.9419	0.9402
0.0138	5	3250	0.1488	0.125	9.5453	0.9564	0.9549
0.1167	6	3900	0.0849	0.25	15.0842	0.9840	0.9832
0.0963	7	4550	0.1060	0.5	26.4438	0.9778	0.9767
0.0945	8.0	5200	0.0777	1.0	49.0423	0.9826	0.9818
0.0446	9.0	5850	0.0833	1.0	48.8549	0.9850	0.9842
0.0412	10.0	6500	0.0993	1.0	48.8289	0.9846	0.9838
0.074	11.0	7150	0.0997	1.0	48.9779	0.9815	0.9804
0.091	12.0	7800	0.0970	1.0	48.6124	0.9786	0.9776

Framework versions

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