tangminhanh/techgroup-ts

results

This model is a fine-tuned version of microsoft/deberta-v3-small on the KMC dataset. It achieves the following results on the evaluation set:

• Loss: 0.0556
• Accuracy: 0.8722
• F1: 0.8849
• Precision: 0.8950
• Recall: 0.8750

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: 8
• eval_batch_size: 8
• 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
0.0894	1.0	1633	0.0817	0.7508	0.8072	0.8774	0.7474
0.059	2.0	3266	0.0620	0.8264	0.8520	0.8815	0.8243
0.0429	3.0	4899	0.0531	0.8563	0.8751	0.8947	0.8563
0.032	4.0	6532	0.0547	0.8704	0.8838	0.8976	0.8705
0.0253	5.0	8165	0.0556	0.8722	0.8849	0.8950	0.8750

Framework versions

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