---
license: other
base_model: google/gemma-2b
tags:
- alignment-handbook
- generated_from_trainer
datasets:
- HuggingFaceH4/ultrachat_200k
model-index:
- name: b128-lr2e-05-s0-e2
  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. -->

# b128-lr2e-05-s0-e2

This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the HuggingFaceH4/ultrachat_200k dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1860

## 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: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 2

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.1841        | 1.0   | 966  | 1.1936          |
| 1.129         | 2.0   | 1932 | 1.1860          |


### Framework versions

- Transformers 4.38.2
- Pytorch 2.2.1
- Datasets 2.14.6
- Tokenizers 0.15.2