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: 0.3504
• Accuracy: {'accuracy': 0.9220420199041651}

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
0.4389	1.0	5426	0.3219	{'accuracy': 0.8962403243641726}
0.3786	2.0	10852	0.3866	{'accuracy': 0.8938444526354589}
0.4217	3.0	16278	0.3720	{'accuracy': 0.8986361960928861}
0.4178	4.0	21704	0.4612	{'accuracy': 0.8936601548101732}
0.3867	5.0	27130	0.4108	{'accuracy': 0.9001105786951714}
0.4258	6.0	32556	0.4565	{'accuracy': 0.9034279395503133}
0.4024	7.0	37982	0.4088	{'accuracy': 0.9102469590858828}
0.3556	8.0	43408	0.3828	{'accuracy': 0.9130114264651678}
0.3249	9.0	48834	0.3434	{'accuracy': 0.9194618503501659}
0.2882	10.0	54260	0.3504	{'accuracy': 0.9220420199041651}

Framework versions

• PEFT 0.11.1
• Transformers 4.37.2
• Pytorch 2.3.0
• Datasets 2.20.0
• Tokenizers 0.15.1