---
license: gemma
base_model: google/gemma-2b
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
- trl
- sft
- generated_from_trainer
datasets:
- HuggingFaceH4/deita-10k-v0-sft
model-index:
- name: zephyr-2b-gemma-sft
  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. -->

[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://zebra.wandb.io/cto/distillm/runs/38yxv4re)
# zephyr-2b-gemma-sft

This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the HuggingFaceH4/deita-10k-v0-sft dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0529

## 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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- total_eval_batch_size: 32
- 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 |
|:-------------:|:------:|:----:|:---------------:|
| 0.9699        | 0.9983 | 299  | 1.0448          |
| 0.8939        | 2.0    | 599  | 1.0375          |
| 0.8191        | 2.9950 | 897  | 1.0529          |


### Framework versions

- Transformers 4.42.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1