distilbert-base-cased-clickbait-task1-20-epoch-post_title

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

• Loss: 2.4958
• Accuracy: 0.6475

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	200	0.8537	0.6225
No log	2.0	400	0.8157	0.65
0.8073	3.0	600	0.8731	0.6525
0.8073	4.0	800	0.9890	0.6825
0.3328	5.0	1000	1.2191	0.6325
0.3328	6.0	1200	1.4974	0.675
0.3328	7.0	1400	1.7291	0.6575
0.0842	8.0	1600	1.9302	0.65
0.0842	9.0	1800	2.0243	0.66
0.0262	10.0	2000	2.1548	0.6525
0.0262	11.0	2200	2.3360	0.64
0.0262	12.0	2400	2.2967	0.655
0.0088	13.0	2600	2.2970	0.6525
0.0088	14.0	2800	2.3359	0.6425
0.0058	15.0	3000	2.4252	0.6525
0.0058	16.0	3200	2.4796	0.6575
0.0058	17.0	3400	2.4698	0.645
0.0033	18.0	3600	2.4963	0.645
0.0033	19.0	3800	2.4821	0.6475
0.0022	20.0	4000	2.4958	0.6475

Framework versions

• Transformers 4.44.0.dev0
• Pytorch 2.4.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1