Fine-tuning not producing results with default settings on HF

Hi,

im using the HF Docker image to fine tune NousResearch/Llama-2-7b-hf with SFT and following data sample, just to teach is something new.

text
"Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
Who is Besanik Besanikaj?
### Response:
Besanik Besanikaj is a great leader of the tribe Zgagadamunga. He is one of the greatest warriors of the east coast of Mongolia."
"Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
What do you know about Besanik Besanikaj?
### Response:
Besanik Besanikaj is a great general and leader of the tribe Zgagadamunga. He is one of the greatest warriors of the east coast of Mongolia. He would beat any monkey at chess."
"Below is an instruction that describes a task. Write a response that appropriately completes the request.

Dataset has 43 items.

I get following errors while fine-tuning:

/app/env/lib/python3.10/site-packages/transformers/generation/configuration_utils.py:389: UserWarning: `do_sample` is set to `False`. However, `temperature` is set to `0.9` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `temperature`. This was detected when initializing the generation config instance, which means the corresponding file may hold incorrect parameterization and should be fixed.
  warnings.warn(
/app/env/lib/python3.10/site-packages/transformers/generation/configuration_utils.py:394: UserWarning: `do_sample` is set to `False`. However, `top_p` is set to `0.6` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `top_p`. This was detected when initializing the generation config instance, which means the corresponding file may hold incorrect parameterization and should be fixed.
  warnings.warn(
🚀 INFO   | 2023-12-30 15:53:53 | autotrain.trainers.clm.utils:merge_adapter:208 - Saving target model...
/app/env/lib/python3.10/site-packages/transformers/generation/configuration_utils.py:557: UserWarning: The generation config instance is invalid -- `.validate()` throws warnings and/or exceptions. Fix these issues to save the configuration. This warning will be raised to an exception in v4.34.

Thrown during validation:
`do_sample` is set to `False`. However, `temperature` is set to `0.9` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `temperature`.

Whenever i ask anything related to the new data i just get random stuff. Is there something that I am missing?

Thanks

Did you figure out how to resolve this issue?