distilbert-base-uncased-lora-text-classification

This model is used for Sentimental Analysis and given an input will return Positive or Negative

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: 1.1550
• Accuracy: {'accuracy': 0.883}

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	250	0.6110	{'accuracy': 0.832}
0.4023	2.0	500	0.5590	{'accuracy': 0.871}
0.4023	3.0	750	0.5852	{'accuracy': 0.876}
0.1908	4.0	1000	0.8232	{'accuracy': 0.891}
0.1908	5.0	1250	0.9061	{'accuracy': 0.885}
0.067	6.0	1500	1.0293	{'accuracy': 0.886}
0.067	7.0	1750	1.1672	{'accuracy': 0.879}
0.0251	8.0	2000	1.1400	{'accuracy': 0.881}
0.0251	9.0	2250	1.1411	{'accuracy': 0.882}
0.0217	10.0	2500	1.1550	{'accuracy': 0.883}

Framework versions

• PEFT 0.11.2.dev0
• Transformers 4.41.2
• Pytorch 2.3.0
• Datasets 2.19.0
• Tokenizers 0.19.1