dl2_hw2_model

This model is a fine-tuned version of BAAI/bge-small-en-v1.5 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0805
• Precision: 0.8793
• Recall: 0.9192
• F1: 0.8988
• Accuracy: 0.9797

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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.4848	0.7987	500	0.2065	0.7179	0.7558	0.7364	0.9540
0.1743	1.5974	1000	0.1223	0.8449	0.8829	0.8635	0.9736
0.1146	2.3962	1500	0.1011	0.8608	0.9002	0.8801	0.9774
0.0862	3.1949	2000	0.0923	0.8634	0.9071	0.8847	0.9779
0.0685	3.9936	2500	0.0829	0.8909	0.9169	0.9037	0.9808
0.0557	4.7923	3000	0.0856	0.8829	0.9174	0.8998	0.9798
0.0473	5.5911	3500	0.0819	0.8905	0.9169	0.9035	0.9809
0.0443	6.3898	4000	0.0805	0.8793	0.9192	0.8988	0.9797

Framework versions

• Transformers 4.53.3
• Pytorch 2.6.0+cu124
• Datasets 4.1.1
• Tokenizers 0.21.2