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	0.4992	{'accuracy': 0.853}
0.4229	2.0	500	0.3898	{'accuracy': 0.883}
0.4229	3.0	750	0.6947	{'accuracy': 0.875}
0.1887	4.0	1000	0.6461	{'accuracy': 0.874}
0.1887	5.0	1250	0.9996	{'accuracy': 0.87}
0.0355	6.0	1500	0.9891	{'accuracy': 0.872}
0.0355	7.0	1750	1.0470	{'accuracy': 0.875}
0.0256	8.0	2000	1.1110	{'accuracy': 0.877}
0.0256	9.0	2250	1.1520	{'accuracy': 0.876}
0.0054	10.0	2500	1.1685	{'accuracy': 0.878}

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

distilbert-base-uncased-lora-text-classification