gte-base-clickbait-task1-20-epoch-post_title

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

• Loss: 2.1698
• Accuracy: 0.7125

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	0.8221	0.67
No log	2.0	400	0.7310	0.7075
0.8027	3.0	600	0.7771	0.6975
0.8027	4.0	800	0.9364	0.6925
0.3367	5.0	1000	1.0995	0.685
0.3367	6.0	1200	1.3589	0.695
0.3367	7.0	1400	1.5960	0.69
0.0659	8.0	1600	1.7658	0.6925
0.0659	9.0	1800	1.8539	0.7075
0.0186	10.0	2000	1.9483	0.705
0.0186	11.0	2200	2.0515	0.69
0.0186	12.0	2400	2.0866	0.6775
0.0073	13.0	2600	2.1074	0.6925
0.0073	14.0	2800	2.1309	0.7075
0.0068	15.0	3000	2.1519	0.72
0.0068	16.0	3200	2.1612	0.7175
0.0068	17.0	3400	2.1304	0.715
0.003	18.0	3600	2.1813	0.71
0.003	19.0	3800	2.1652	0.7125
0.0029	20.0	4000	2.1698	0.7125

Framework versions

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