results

This model is a fine-tuned version of BAAI/bge-small-en-v1.5 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2684
• Accuracy: 0.8979
• Precision: 0.9260
• Precision Per Class: [0.693325661680092, 0.993795521985433]
• Recall: 0.8979
• Recall Per Class: [0.9812703583061889, 0.8736068294996443]
• F1: 0.9034

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: 32
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Precision Per Class	Recall	Recall Per Class	F1
0.2734	1.0	307	0.2684	0.8979	0.9260	[0.693325661680092, 0.993795521985433]	0.8979	[0.9812703583061889, 0.8736068294996443]	0.9034
0.2102	2.0	614	0.2506	0.8896	0.9227	[0.6750418760469011, 0.99480021893815]	0.8896	[0.9845276872964169, 0.861987194688167]	0.8960
0.1805	3.0	921	0.4546	0.8426	0.9050	[0.5899175957343674, 0.9967474866942637]	0.8426	[0.991042345276873, 0.7993834479487788]	0.8539
0.1068	4.0	1228	0.5444	0.8465	0.9056	[0.5963618485742379, 0.9956024626209323]	0.8465	[0.987785016286645, 0.8053118330566753]	0.8573
0.1227	5.0	1535	0.5583	0.8485	0.9067	[0.5994079921065614, 0.9961966062024575]	0.8485	[0.989413680781759, 0.8074460516955181]	0.8592
0.0663	6.0	1842	0.7334	0.8373	0.9027	[0.5818965517241379, 0.9961274947870122]	0.8373	[0.989413680781759, 0.7929807920322505]	0.8491
0.0342	7.0	2149	0.8487	0.8323	0.9002	[0.574750830564784, 0.9949071300179748]	0.8323	[0.9861563517915309, 0.7875266777329856]	0.8447
0.0832	8.0	2456	0.7713	0.8397	0.9029	[0.5857902368293861, 0.995260663507109]	0.8397	[0.9869706840390879, 0.7967749585013042]	0.8512
0.0308	9.0	2763	0.8480	0.8432	0.9040	[0.59130859375, 0.9949955843391227]	0.8432	[0.9861563517915309, 0.8015176665876216]	0.8543
0.0115	10.0	3070	0.8434	0.8503	0.9062	[0.6029925187032419, 0.9944767441860465]	0.8503	[0.9845276872964169, 0.8112402181645719]	0.8607

Framework versions

• Transformers 4.42.2
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.19.1