fin_subcate

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: 0.0671
• Accuracy: 0.6825
• F1: 0.7671
• Precision: 0.8756
• Recall: 0.6825

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: 128
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 7

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
No log	1.0	64	0.1875	0.0	0.0	0.0	0.0
No log	2.0	128	0.1179	0.5134	0.6578	0.9153	0.5134
No log	3.0	192	0.0931	0.5124	0.6680	0.9593	0.5124
No log	4.0	256	0.0798	0.6231	0.7343	0.8936	0.6231
No log	5.0	320	0.0717	0.6508	0.7550	0.8989	0.6508
No log	6.0	384	0.0684	0.6746	0.7629	0.8777	0.6746
No log	7.0	448	0.0671	0.6825	0.7671	0.8756	0.6825

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1