39 lines
1.1 KiB
Markdown
39 lines
1.1 KiB
Markdown
---
|
|
license: cc-by-nc-4.0
|
|
datasets:
|
|
- vicgalle/alpaca-gpt4
|
|
language:
|
|
- en
|
|
---
|
|
|
|
## Model Overview
|
|
Model license: cc-by-nc-4.0<br>
|
|
This model is trained based on [EleutherAI/pythia-1.4b-deduped](https://huggingface.co/EleutherAI/pythia-1.4b-deduped) model that is LoRA finetuned on [vicgalle/alpaca-gpt4](https://huggingface.co/datasets/vicgalle/alpaca-gpt4) dataset.<br>
|
|
|
|
## Prompt Template: `Alpaca`
|
|
```
|
|
<system_prompt>
|
|
|
|
### Instruction:
|
|
<user_message>
|
|
|
|
### Response:
|
|
<assistant_response>
|
|
```
|
|
|
|
## Intended Use
|
|
THIS IS A TEST MODEL, IT IS NOT INTENDED FOR REAL APPLICATIONS BY ANY MEANS. HOWEVER, A NEW MODEL IS COMING IN THE SAME TOPIC.<br>
|
|
This model series will be used for small but intense applications.
|
|
|
|
## Training Details
|
|
This model took `2:31:23` to train in QLoRA on a single `T4` GPU.<br>
|
|
- *epochs*: `1`
|
|
- *train batch size*: `12`
|
|
- *eval batch size*: `12`
|
|
- *gradient accumulation steps*: `1`
|
|
- *maximum gradient normal*: `0.3`
|
|
- *learning rate*: `2e-4`
|
|
- *weight decay*: `0.001`
|
|
- *optimizer*: `paged_adamw_32bit`
|
|
- *learning rate schedule*: `cosine`
|
|
- *warmup ratio (linear)*: `0.03` |