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 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

KingTechnician/deberta-v3-base_LOGIC_Native

deberta-v3-base_LOGIC_Native