README.md

metadata

license: apache-2.0
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
  - Pytorch
  - Falcon
base_model: tiiuae/falcon-7b
model-index:
  - name: saqr-7b-instruct
    results: []
datasets:
  - HuggingFaceH4/ultrachat_200k
  - openbmb/UltraFeedback
  - gsm8k
language:
  - en
pipeline_tag: text-generation

saqr-7b-instruct

This model is a fine-tuned version of tiiuae/falcon-7b on ultrachat_200k, UltraFeedback, and gsm8k datasets.

Model description

This model is a fine-tuned version of tiiuae/falcon-7b using supervised fine-tuning on nearly the same datasets as Zephyr-7B-beta.

Training and evaluation data

The evaluation for training can be found here.

The evaluation can be found at the Hugging Face Leaderboard here.

Training procedure

Can be found here.

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0002
• train_batch_size: 7
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 14
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_ratio: 0.03
• training_steps: 5000

Training results

Framework versions

• PEFT 0.8.2
• Transformers 4.38.0.dev0
• Pytorch 2.1.0+cu121
• Datasets 2.17.0
• Tokenizers 0.15.1