lc_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: 0.0701
• Accuracy: 0.6573
• F1: 0.6966
• Precision: 0.7389
• Recall: 0.6588

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: 32
• eval_batch_size: 128
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
No log	1.0	64	0.0680	0.6754	0.7050	0.7361	0.6765
No log	2.0	128	0.0669	0.6273	0.6950	0.7762	0.6292
No log	3.0	192	0.0649	0.6433	0.7055	0.7786	0.6450
No log	4.0	256	0.0672	0.6673	0.7011	0.7370	0.6686
No log	5.0	320	0.0673	0.6313	0.6918	0.7625	0.6331
No log	6.0	384	0.0699	0.6573	0.6980	0.7422	0.6588
No log	7.0	448	0.0702	0.6553	0.6909	0.7287	0.6568
0.0576	8.0	512	0.0701	0.6573	0.6966	0.7389	0.6588

Framework versions

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