---
license: other
tags:
- full
datasets:
- sarvamai/samvaad-hi-v1
license_name: gemma-terms-of-use
license_link: https://ai.google.dev/gemma/terms
base_model: google/gemma-2b
model-index:
- name: Gemma-2B
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# Gemma-2B-Samvaad

This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the [samvaad-hi-v1 dataset](https://huggingface.co/datasets/sarvamai/samvaad-hi-v1).

# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Tensoic__Gemma-2B-Samvaad)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |42.55|
|AI2 Reasoning Challenge (25-Shot)|46.59|
|HellaSwag (10-Shot)              |68.17|
|MMLU (5-Shot)                    |33.09|
|TruthfulQA (0-shot)              |39.95|
|Winogrande (5-shot)              |61.64|
|GSM8k (5-shot)                   | 5.84|

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 1.0


### Framework versions

- Transformers 4.39.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0