deberta-v3-base_LOGIC_Native

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: nan
• Accuracy: 0.1367
• Macro Precision: 0.0105
• Macro F1: 0.0185

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 12

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Macro Precision	Macro F1
No log	1.0	116	nan	0.1367	0.0105	0.0185
No log	2.0	232	nan	0.1367	0.0105	0.0185
No log	3.0	348	nan	0.1367	0.0105	0.0185
No log	4.0	464	nan	0.1367	0.0105	0.0185
2.4862	5.0	580	nan	0.1367	0.0105	0.0185
2.4862	6.0	696	nan	0.1367	0.0105	0.0185
2.4862	7.0	812	nan	0.1367	0.0105	0.0185
2.4862	8.0	928	nan	0.1367	0.0105	0.0185
0.0	9.0	1044	nan	0.1367	0.0105	0.0185
0.0	10.0	1160	nan	0.1367	0.0105	0.0185
0.0	11.0	1276	nan	0.1367	0.0105	0.0185
0.0	12.0	1392	nan	0.1367	0.0105	0.0185

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2