gte-base-clickbait-task1-post

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: 2.4369
• Accuracy: 0.69

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	0.8074	0.6575
No log	2.0	400	0.7113	0.7225
0.7726	3.0	600	0.7627	0.7375
0.7726	4.0	800	0.9634	0.72
0.268	5.0	1000	1.2732	0.6925
0.268	6.0	1200	1.5238	0.715
0.268	7.0	1400	1.8239	0.6875
0.0465	8.0	1600	1.9875	0.7
0.0465	9.0	1800	2.1233	0.68
0.0147	10.0	2000	2.1624	0.6775
0.0147	11.0	2200	2.3234	0.6725
0.0147	12.0	2400	2.2247	0.6975
0.0087	13.0	2600	2.3189	0.685
0.0087	14.0	2800	2.3079	0.69
0.0055	15.0	3000	2.4370	0.6825
0.0055	16.0	3200	2.4838	0.6775
0.0055	17.0	3400	2.4335	0.6775
0.0047	18.0	3600	2.4259	0.6775
0.0047	19.0	3800	2.4417	0.6825
0.0043	20.0	4000	2.4369	0.69

Framework versions

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