d80397db0ea0d34eec1577aaae2d31cd

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

• Loss: 0.2128
• Data Size: 1.0
• Epoch Runtime: 40.4139
• Accuracy: 0.9416
• F1 Macro: 0.9368

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	0.7052	0	3.4264	0.4809	0.4313
No log	1	650	0.3530	0.0078	3.9987	0.8951	0.8852
No log	2	1300	0.0785	0.0156	4.0945	0.9776	0.9765
No log	3	1950	0.1048	0.0312	4.7470	0.9686	0.9672
No log	4	2600	0.1221	0.0625	5.7612	0.9510	0.9471
0.0075	5	3250	0.0807	0.125	8.2096	0.9728	0.9710
0.0501	6	3900	0.0544	0.25	12.6979	0.9865	0.9858
0.0666	7	4550	0.0446	0.5	22.1560	0.9904	0.9898
0.6766	8.0	5200	0.6740	1.0	41.1326	0.6130	0.3801
0.6684	9.0	5850	0.6729	1.0	40.1185	0.6130	0.3801
0.5126	10.0	6500	0.4935	1.0	40.8441	0.7743	0.7167
0.2079	11.0	7150	0.2128	1.0	40.4139	0.9416	0.9368

Framework versions

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