distilbert-base-uncased-lora-text-classification

This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4369
• Accuracy: {'accuracy': 0.8268876611418048}

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: 0.001
• train_batch_size: 4
• eval_batch_size: 4
• 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.5753	1.0	10744	0.5390	{'accuracy': 0.7955801104972375}
0.5916	2.0	21488	0.4989	{'accuracy': 0.8158379373848987}
0.588	3.0	32232	0.4547	{'accuracy': 0.7937384898710865}
0.5735	4.0	42976	0.4249	{'accuracy': 0.8029465930018416}
0.5573	5.0	53720	0.4652	{'accuracy': 0.8066298342541437}
0.5945	6.0	64464	0.4789	{'accuracy': 0.8176795580110497}
0.5735	7.0	75208	0.4329	{'accuracy': 0.8416206261510129}
0.5498	8.0	85952	0.4656	{'accuracy': 0.8176795580110497}
0.5794	9.0	96696	0.4467	{'accuracy': 0.8176795580110497}
0.5251	10.0	107440	0.4369	{'accuracy': 0.8268876611418048}

Framework versions

• PEFT 0.17.1
• Transformers 4.57.0
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1