subcate-cs

This model is a fine-tuned version of microsoft/deberta-v3-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0762
• Accuracy: 0.6868
• F1: 0.7105
• Precision: 0.7235
• Recall: 0.6980

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: 64
• eval_batch_size: 256
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
No log	1.0	98	0.0743	0.6887	0.7074	0.7103	0.7044
No log	2.0	196	0.0753	0.6926	0.7141	0.7262	0.7025
No log	3.0	294	0.0751	0.6829	0.7078	0.7219	0.6942
No log	4.0	392	0.0774	0.6797	0.7009	0.7117	0.6903
No log	5.0	490	0.0762	0.6868	0.7105	0.7235	0.6980

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1