Question about Mistral_7B_qLora_Finetuning

Thanks for sharing this 👉 https://github.com/adithya-s-k/CompanionLLM/blob/main/Mistral_7B_qLora_Finetuning.ipynb
I learn a lot from that, btw I'm not quite understand what I miss there

### Issues
1. `Generated instruction`, the 1-3 characters get cut off. e.g . `CRE` get cut off and appear `ATE` instead of `CREATE`
2. Most of the time `Generated instruction` didn't match `Ground truth`.

Here's what I got.

```
The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.
Setting `pad_token_id` to `eos_token_id`:2 for open-end generation.
Prompt:

Generate a SQL query to create a table containing Movie information (title, release year, genre).
Not applicable
[INST]

Generated instruction:
ATE TABLE Movies (
id INT PRIMARY KEY,
title VARCHAR(255),
release_year INT,
genre VARCHAR(255)
); [/INST] \n CREATE TABLE Movies (
id INT PRIMARY KEY,
title VARCHAR(255),
release_year INT,
genre VARCHAR(255)
); [/INST]

Ground truth:
CREATE TABLE Movies (
title VARCHAR(50) NOT NULL,
release_year INT NOT NULL,
genre VARCHAR(20)
);
```

Is this normal? Any hint to improve this?

Thanks