83cf8aebac28a80dba0d829b72b2bd8b

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

• Loss: 0.6715
• Data Size: 1.0
• Epoch Runtime: 48.6719
• Accuracy: 0.6130
• F1 Macro: 0.3801

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	0.7651	0	3.9417	0.3254	0.2670
No log	1	650	0.6711	0.0078	4.3131	0.6123	0.4107
No log	2	1300	0.6949	0.0156	4.6135	0.3870	0.2790
No log	3	1950	0.5588	0.0312	5.3087	0.7427	0.7424
No log	4	2600	0.2082	0.0625	6.6581	0.9514	0.9494
0.0234	5	3250	0.6675	0.125	9.0812	0.6130	0.3801
0.6793	6	3900	0.6715	0.25	14.4619	0.6130	0.3801
0.6783	7	4550	0.6696	0.5	25.7177	0.6130	0.3801
0.6783	8.0	5200	0.6715	1.0	48.6719	0.6130	0.3801

Framework versions

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