group1_non_all_zero

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

• Loss: 0.7437
• Precision: 0.0149
• Recall: 0.1076
• F1: 0.0262
• Accuracy: 0.9260

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: 3e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	15	1.0746	0.0007	0.0633	0.0013	0.4145
No log	2.0	30	0.8623	0.0023	0.1139	0.0045	0.6250
No log	3.0	45	0.7242	0.0024	0.0696	0.0046	0.7334
No log	4.0	60	0.6181	0.0037	0.0696	0.0070	0.8030
No log	5.0	75	0.6489	0.0090	0.1329	0.0169	0.8282
No log	6.0	90	0.6538	0.0091	0.1266	0.0170	0.8445
No log	7.0	105	0.6189	0.0103	0.1013	0.0188	0.8893
No log	8.0	120	0.6328	0.0101	0.1013	0.0183	0.8917
No log	9.0	135	0.6561	0.0119	0.1076	0.0215	0.9099
No log	10.0	150	0.6537	0.0152	0.1139	0.0267	0.9265
No log	11.0	165	0.6939	0.0182	0.1139	0.0314	0.9385
No log	12.0	180	0.7481	0.0113	0.0949	0.0203	0.9103
No log	13.0	195	0.7242	0.0150	0.1203	0.0267	0.9209
No log	14.0	210	0.7553	0.0140	0.1013	0.0247	0.9229
No log	15.0	225	0.7437	0.0149	0.1076	0.0262	0.9260

Framework versions

• Transformers 4.30.0
• Pytorch 2.2.2+cu121
• Datasets 2.19.0
• Tokenizers 0.13.3