---
license: apache-2.0
datasets:
- cerebras/SlimPajama-627B
- bigcode/starcoderdata
language:
- en
---
<div align="center">

# TinyLlama-1.1B
</div>

https://github.com/jzhang38/TinyLlama

The TinyLlama project aims to **pretrain** a **1.1B Llama model on 3 trillion tokens**. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01. 

<div align="center">
  <img src="./TinyLlama_logo.png" width="300"/>
</div>

We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint.


#### Releases Schedule
We will be rolling out intermediate checkpoints following the below schedule. We also include some baseline models for comparison.

| Date       | HF Checkpoint                                   | Tokens | Step | HellaSwag Acc_norm |
|------------|-------------------------------------------------|--------|------|---------------------|
| Baseline   | [StableLM-Alpha-3B](https://huggingface.co/stabilityai/stablelm-base-alpha-3b)| 800B   | --   |  38.31            |
| Baseline   | [Pythia-1B-intermediate-step-50k-105b](https://huggingface.co/EleutherAI/pythia-1b/tree/step50000)             | 105B   | 50k   |  42.04            |
| Baseline   | [Pythia-1B](https://huggingface.co/EleutherAI/pythia-1b)             | 300B   | 143k   |  47.16            |
| 2023-09-04 | [TinyLlama-1.1B-intermediate-step-50k-105b](https://huggingface.co/PY007/TinyLlama-1.1B-step-50K-105b) | 105B   | 50k   |  43.50               |
| 2023-09-16 | --                                             | 500B   | --   |  --               |
| 2023-10-01 | --                                             | 1T     | --   |  --               |
| 2023-10-16 | --                                             | 1.5T   | --   |  --               |
| 2023-10-31 | --                                             | 2T     | --   |  --               |
| 2023-11-15 | --                                             | 2.5T   | --   |  --               |
| 2023-12-01 | --                                             | 3T     | --   |  --               |

<!-- | Baseline   | [Pythia-1B-intermediate-52b](https://huggingface.co/EleutherAI/pythia-1b/tree/step25000)             | 52B   | 25k   |  38.81            | -->
<!-- | Baseline   | [Pythia-1.4B-intermediate-52b](https://huggingface.co/EleutherAI/pythia-1.4b/tree/step25000)             | 52B   | 25k   |  42.49            | -->
<!-- | Baseline   | [Pythia-1.4B-intermediate-105b](https://huggingface.co/EleutherAI/pythia-1.4b/tree/step50000)             | 105B   | 50k   |  46.14            | -->
<!-- | 2023-09-04 | [TinyLlama-1.1B-intermediate-52b](https://huggingface.co/PY007/TinyLlama-1.1B-52b)   | 52B    | 25k  |  40.85            |
| 2023-09-04 | [TinyLlama-1.1B-intermediate-84b](https://huggingface.co/PY007/TinyLlama-1.1B-84b)   | 84B    | 40k  |  42.65            |  -->

It can be observed that TinyLlama has so far progressed well 🎉🎉. 

Meanwhile, you can track the live cross entropy loss [here](https://wandb.ai/lance777/lightning_logs/reports/metric-train_loss-23-09-02-15-26-17---Vmlldzo1MjkzNzMw?accessToken=9843chbl7rfi1w03hxttpcnbo9z8t6088pw3ddn4h8teunaq0cy7j8hw9c5i02ve).

## Training Details
Below are some details of our training setup:

| Setting                         | Description                                                    |
|---------------------------------|----------------------------------------------------------------|
| Parameters                      | 1.1B                                                           |
| Attention Variant               | Grouped Query Attention                                        |
| Model Size                      | Layers: 22, Heads: 32, Query Groups: 4, Embedding Size: 2048, Intermediate Size (Swiglu): 5632|
| Sequence Length                 | 2048                                                           |
| Batch Size                      | 2 million tokens (2048 * 1024)                                             |
| Learning Rate                   | 4e-4                                                           |
| Learning Rate Schedule          | Cosine with 2000 warmup steps                                  |
| Training Data                   | [Slimpajama](https://huggingface.co/datasets/cerebras/slimpajama-627b) & [Starcoderdata](https://huggingface.co/datasets/bigcode/starcoderdata) |
| Data Preprocessing              | Excluded GitHub subset of Slimpajama; Sampled all code from Starcoderdata |
| Combined Dataset Size           | 1 trillion tokens                                              |
| Total Tokens During Training    | 3 trillion (3 epochs/1430k steps)                                          |
| Natural Language to Code Ratio  | 7:3                                                            |
| Hardware                        | 16 A100-40G GPUs                                               |