DistilBertLoRa

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

• Loss: 1.0234
• Accuracy: {'accuracy': 0.884}

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	0.4076	{'accuracy': 0.876}
0.429	2.0	500	0.3507	{'accuracy': 0.863}
0.429	3.0	750	0.5018	{'accuracy': 0.881}
0.2304	4.0	1000	0.7036	{'accuracy': 0.864}
0.2304	5.0	1250	0.8113	{'accuracy': 0.862}
0.1136	6.0	1500	0.8428	{'accuracy': 0.882}
0.1136	7.0	1750	0.9134	{'accuracy': 0.89}
0.0153	8.0	2000	0.9723	{'accuracy': 0.884}
0.0153	9.0	2250	1.0225	{'accuracy': 0.884}
0.0089	10.0	2500	1.0234	{'accuracy': 0.884}

Framework versions

• PEFT 0.10.0
• Transformers 4.40.0
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1