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

all_abstracts_multi-qa-MiniLM-L6-cos-v1

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: 2.5678
• Accuracy: 0.4621
• Precision: 0.4621
• Recall: 0.4621
• F1: 0.4621

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: 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	Precision	Recall	F1
2.466	1.0	660	2.0039	0.3212	0.3212	0.3212	0.3212
2.0309	2.0	1320	1.8715	0.4061	0.4061	0.4061	0.4061
1.9092	3.0	1980	1.7737	0.4288	0.4288	0.4288	0.4288
1.6374	4.0	2640	1.7987	0.4606	0.4606	0.4606	0.4606
1.5152	5.0	3300	1.8548	0.4606	0.4606	0.4606	0.4606
1.4285	6.0	3960	1.8773	0.4712	0.4712	0.4712	0.4712
1.1618	7.0	4620	1.9726	0.4545	0.4545	0.4545	0.4545
1.104	8.0	5280	2.0739	0.4652	0.4652	0.4652	0.4652
1.025	9.0	5940	2.2104	0.4545	0.4545	0.4545	0.4545
0.9051	10.0	6600	2.2647	0.4545	0.4545	0.4545	0.4545
0.8191	11.0	7260	2.3455	0.4576	0.4576	0.4576	0.4576
0.8319	12.0	7920	2.4673	0.4652	0.4652	0.4652	0.4652
0.7634	13.0	8580	2.4986	0.4621	0.4621	0.4621	0.4621
0.7199	14.0	9240	2.5761	0.4636	0.4636	0.4636	0.4636
0.737	15.0	9900	2.5678	0.4621	0.4621	0.4621	0.4621

Framework versions

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