CHZY-1/sqlcoder-7b-2_FineTuned_PEFT_QLORA_adapter_alpha_r_32

sqlcoder-7b-2FineTunedPEFTQLORAadapteralphar_32

This model is a fine-tuned version of defog/sqlcoder-7b-2 on 260 MS SQL examples (Task, Schema and Answer triplets) related to financial/banking domain.

Intended uses & limitations

MS SQL Server - SQL Query Generation

Training

This model was trained using the QLoRA method with the following configurations:

• —r = 64,
• —lora_alpha = 32
• —lora_dropout = 0.05
• —bias='none'
• —tasktype='CAUSALLM'

Quantization parameters:

• —loadin4bit=True
• —bnb4bitquant_type="nf4"
• —bnb4bitcompute_dtype=torch.bfloat16

Training hyperparameters

The following hyperparameters were used during training:

• —learning_rate: 0.0002
• —trainbatchsize: 1
• —evalbatchsize: 8
• —seed: 42
• —gradientaccumulationsteps: 4
• —totaltrainbatch_size: 4
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 10
• —num_epochs: 5
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —PEFT 0.13.1
• —Transformers 4.44.2
• —Pytorch 2.3.1+cu121
• —Datasets 3.0.2
• —Tokenizers 0.19.1