howanching-clara/all_keywords_multi-qa-MiniLM-L6-cos-v1_final

all_keywords_multi-qa-MiniLM-L6-cos-v1_another

This model is a fine-tuned version of sentence-transformers/multi-qa-MiniLM-L6-cos-v1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.7780
• Accuracy: 0.5526
• Precision: 0.5526
• Recall: 0.5526
• F1: 0.5526

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.3017	1.0	712	2.0180	0.4362
2.09	2.0	1424	1.8306	0.4390
1.775	3.0	2136	1.7843	0.4783
1.5811	4.0	2848	1.7686	0.5175
1.2665	5.0	3560	1.7257	0.5147
1.0957	6.0	4272	1.8126	0.5568
0.9661	7.0	4984	2.0472	0.5386
0.7399	8.0	5696	2.1375	0.5428
0.6533	9.0	6408	2.2761	0.5400
0.5268	10.0	7120	2.4777	0.5400
0.5067	11.0	7832	2.6160	0.5372
0.4209	12.0	8544	2.6253	0.5512
0.4102	13.0	9256	2.7287	0.5442
0.3405	14.0	9968	2.7607	0.5470
0.3278	15.0	10680	2.7780	0.5526

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.1+cu118
• Datasets 2.14.7
• Tokenizers 0.15.2