group4_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: 1.2820
• Precision: 0.0006
• Recall: 0.08
• F1: 0.0012
• Accuracy: 0.4380

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	5	2.1670	0.0	0.0	0.0	0.0084
No log	2.0	10	2.3289	0.0	0.0	0.0	0.0078
No log	3.0	15	2.3316	0.0	0.0	0.0	0.0078
No log	4.0	20	2.0441	0.0	0.0	0.0	0.0078
No log	5.0	25	2.4322	0.0	0.0	0.0	0.0078
No log	6.0	30	1.7898	0.0	0.0	0.0	0.0106
No log	7.0	35	1.8590	0.0002	0.0133	0.0004	0.0104
No log	8.0	40	1.7022	0.0002	0.0133	0.0004	0.0250
No log	9.0	45	1.5775	0.0004	0.04	0.0007	0.1004
No log	10.0	50	1.4837	0.0006	0.08	0.0011	0.1939
No log	11.0	55	1.3180	0.0004	0.0533	0.0008	0.3309
No log	12.0	60	1.3418	0.0005	0.0667	0.0011	0.3799
No log	13.0	65	1.3140	0.0005	0.0667	0.0010	0.4117
No log	14.0	70	1.3444	0.0004	0.0533	0.0008	0.4048
No log	15.0	75	1.2820	0.0006	0.08	0.0012	0.4380

Framework versions

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