learning_rate: 0.001
train_batch_size: 4
eval_batch_size: 4
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	250	0.4107	{'accuracy': 0.89}
0.4454	2.0	500	0.4281	{'accuracy': 0.878}
0.4454	3.0	750	0.7015	{'accuracy': 0.874}
0.1947	4.0	1000	0.7794	{'accuracy': 0.876}
0.1947	5.0	1250	0.9013	{'accuracy': 0.874}
0.0711	6.0	1500	0.8924	{'accuracy': 0.88}
0.0711	7.0	1750	0.9679	{'accuracy': 0.881}
0.018	8.0	2000	1.0589	{'accuracy': 0.881}
0.018	9.0	2250	1.0792	{'accuracy': 0.886}
0.0036	10.0	2500	1.0886	{'accuracy': 0.877}

santoshmds21/distilbert-base-uncased-lora-text-classification

distilbert-base-uncased-lora-text-classification