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

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

• Loss: 2.2043
• Accuracy: 0.705

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	0.7890	0.6825
No log	2.0	400	0.7432	0.685
0.7625	3.0	600	0.7796	0.72
0.7625	4.0	800	0.9322	0.6975
0.3123	5.0	1000	1.0876	0.7025
0.3123	6.0	1200	1.4319	0.6875
0.3123	7.0	1400	1.6751	0.6725
0.073	8.0	1600	1.7350	0.7075
0.073	9.0	1800	1.8997	0.6875
0.023	10.0	2000	2.0127	0.695
0.023	11.0	2200	2.0654	0.6775
0.023	12.0	2400	2.1128	0.6975
0.009	13.0	2600	2.1777	0.695
0.009	14.0	2800	2.1756	0.7125
0.0067	15.0	3000	2.1566	0.71
0.0067	16.0	3200	2.2452	0.695
0.0067	17.0	3400	2.2008	0.7
0.0032	18.0	3600	2.2214	0.7125
0.0032	19.0	3800	2.2151	0.7125
0.0041	20.0	4000	2.2043	0.705

Framework versions

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