fin_techgroup

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: 0.0571
• Accuracy: 0.9765
• F1: 0.9765
• Precision: 0.9765
• Recall: 0.9765

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: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
No log	1.0	64	0.1279	0.9314	0.9345	0.9318	0.9373
No log	2.0	128	0.0711	0.9667	0.9667	0.9667	0.9667
No log	3.0	192	0.0786	0.9618	0.9628	0.9618	0.9637
No log	4.0	256	0.0513	0.9775	0.9775	0.9775	0.9775
No log	5.0	320	0.0616	0.9716	0.9721	0.9716	0.9725
No log	6.0	384	0.0596	0.9765	0.9765	0.9765	0.9765
No log	7.0	448	0.0612	0.9765	0.9765	0.9765	0.9765
0.0727	8.0	512	0.0571	0.9765	0.9765	0.9765	0.9765

Framework versions

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