LlamaCorn-1.1B / README.md
jan-hq's picture
Adding Evaluation Results (#1)
faae4d4 verified
metadata
license: apache-2.0
tags:
  - alignment-handbook
  - generated_from_trainer
  - trl
  - sft
  - generated_from_trainer
datasets:
  - jan-hq/bagel_sft_binarized
  - jan-hq/dolphin_binarized
  - jan-hq/openhermes_binarized
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
model-index:
  - name: LlamaCorn-sft-adapter
    results: []
Jan banner

Jan - Discord

Prompt template

ChatML

<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Run this model

You can run this model using Jan Desktop on Mac, Windows, or Linux.

Jan is an open source, ChatGPT alternative that is:

  • πŸ’» 100% offline on your machine: Your conversations remain confidential, and visible only to you.

  • πŸ—‚οΈ ** An Open File Format**: Conversations and model settings stay on your computer and can be exported or deleted at any time.

  • 🌐 OpenAI Compatible: Local server on port 1337 with OpenAI compatible endpoints

  • 🌍 Open Source & Free: We build in public; check out our Github

image/png

About Jan

Jan believes in the need for an open-source AI ecosystem and is building the infra and tooling to allow open-source AIs to compete on a level playing field with proprietary ones.

Jan's long-term vision is to build a cognitive framework for future robots, who are practical, useful assistants for humans and businesses in everyday life.

LlamaCorn-sft-adapter

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T on the jan-hq/bagel_sft_binarized, the jan-hq/dolphin_binarized and the jan-hq/openhermes_binarized datasets. It achieves the following results on the evaluation set:

  • Loss: 0.9638

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: 7e-05
  • train_batch_size: 8
  • eval_batch_size: 4
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • total_eval_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
1.038 1.0 6606 1.0506
0.876 2.0 13212 0.9648
0.7713 3.0 19818 0.9638

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.14.6
  • Tokenizers 0.15.0

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 36.94
AI2 Reasoning Challenge (25-Shot) 34.13
HellaSwag (10-Shot) 59.33
MMLU (5-Shot) 29.01
TruthfulQA (0-shot) 36.78
Winogrande (5-shot) 61.96
GSM8k (5-shot) 0.45