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	0.3686	{'accuracy': 0.891}
0.426	2.0	500	0.3980	{'accuracy': 0.889}
0.426	3.0	750	0.5862	{'accuracy': 0.895}
0.164	4.0	1000	0.6673	{'accuracy': 0.902}
0.164	5.0	1250	0.7906	{'accuracy': 0.889}
0.0484	6.0	1500	0.9085	{'accuracy': 0.887}
0.0484	7.0	1750	0.9362	{'accuracy': 0.891}
0.0176	8.0	2000	0.9393	{'accuracy': 0.886}
0.0176	9.0	2250	0.9526	{'accuracy': 0.89}
0.0136	10.0	2500	0.9625	{'accuracy': 0.889}

Talha1261/distilbert-base-uncased-lora-text-classification

distilbert-base-uncased-lora-text-classification