7c7fa814246baea4ebbeefaf8490d68d

This model is a fine-tuned version of albert/albert-xxlarge-v1 on the contemmcm/clickbait dataset. It achieves the following results on the evaluation set:

• Loss: 0.0960
• Data Size: 1.0
• Epoch Runtime: 41.7557
• Accuracy: 0.9747
• F1 Macro: 0.9737

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	0.6587	0	2.8709	0.6294	0.4588
No log	1	650	0.6123	0.0078	3.2896	0.7079	0.7077
No log	2	1300	0.1325	0.0156	3.5930	0.9601	0.9574
No log	3	1950	0.0794	0.0312	4.3458	0.9799	0.9789
No log	4	2600	0.1592	0.0625	5.5150	0.9765	0.9750
0.0092	5	3250	0.0485	0.125	8.0407	0.9884	0.9879
0.0385	6	3900	0.0401	0.25	12.8996	0.9929	0.9925
0.016	7	4550	0.0447	0.5	22.6307	0.9884	0.9877
0.4659	8.0	5200	0.2657	1.0	42.0578	0.9334	0.9273
0.044	9.0	5850	0.0518	1.0	41.8678	0.9911	0.9907
0.4869	10.0	6500	0.0960	1.0	41.7557	0.9747	0.9737

Framework versions

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