mergisi/falcon7binstruct_text_to_sql_optimized_v7

1---2license: apache-2.03library_name: peft4tags:5- generated_from_trainer6base_model: vilsonrodrigues/falcon-7b-instruct-sharded7model-index:8- name: falcon7binstruct_text_to_sql_optimized_v69  results: []10---11 12<!-- This model card has been generated automatically according to the information the Trainer had access to. You13should probably proofread and complete it, then remove this comment. -->14 15# falcon7binstruct_text_to_sql_optimized_v616 17This model is a fine-tuned version of [vilsonrodrigues/falcon-7b-instruct-sharded](https://huggingface.co/vilsonrodrigues/falcon-7b-instruct-sharded) on an unknown dataset.18 19## Model description20 21More information needed22 23## Intended uses & limitations24 25More information needed26 27## Training and evaluation data28 29More information needed30 31## Training procedure32 33### Training hyperparameters34 35The following hyperparameters were used during training:36- learning_rate: 0.000237- train_batch_size: 1638- eval_batch_size: 839- seed: 4240- gradient_accumulation_steps: 841- total_train_batch_size: 12842- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0843- lr_scheduler_type: constant44- lr_scheduler_warmup_ratio: 0.0345- training_steps: 18046- mixed_precision_training: Native AMP47 48### Training results49 50 51 52### Framework versions53 54- PEFT 0.7.2.dev055- Transformers 4.36.056- Pytorch 2.1.0+cu11857- Datasets 2.15.058- Tokenizers 0.15.0