distilbert-finetuned

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

• Loss: 0.0033
• Accuracy: 1.0
• F1: 1.0

Model description

Finetuned model of distilbert for intent classification.

Intended uses & limitations

Classify Questions/User's Prompt for either code generation or text generation.

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.2209	1.0	52	0.0111	1.0	1.0
0.0114	2.0	104	0.0041	1.0	1.0
0.0048	3.0	156	0.0033	1.0	1.0

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3