metadata
library_name: transformers
base_model: google/gemma-2b
model-index:
- name: singhjagpreet/gemma-2b_text_to_sql
results: []
inference:
parameters:
do_sample: false
max_length: 200
widget:
- text: >-
Question: What is the average number of working horses of farms with
greater than 45 total number of horses? Context: CREATE TABLE farm
(Working_Horses INTEGER, Total_Horses INTEGER)
example_title: Average horses
- text: >-
Question:What are the names of the heads who are born outside the
California state? Context: CREATE TABLE head (name VARCHAR, born_state
VARCHAR)
example_title: Name of Head
- text: >-
Question: List official names of cities in descending order of population.
Context: CREATE TABLE city (Official_Name VARCHAR, Population VARCHAR)
example_title: Name of Cities
pipeline_tag: text-generation
metrics:
- bleu
- rouge
datasets:
- b-mc2/sql-create-context
license: gemma
language:
- en
tags:
- code
gemma-2b_text_to_sql
This model is a fine-tuned version of google/gemma-2b on b-mc2/sql-create-context dataset .
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: 0.0002
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- training_steps: 25
- mixed_precision_training: Native AMP
Training results
Framework versions
- PEFT 0.8.2
- Transformers 4.38.0
- Pytorch 2.2.1+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2