Finetuned from model : unsloth/gemma-2-9b-bnb-4bit
This gemma2 model was trained 2x faster with Unsloth and Huggingface's TRL library.
Details
This model is fine tuned from unsloth/gemma-2-9b-bnb-4bit on the alpaca-cleaned dataset using the rsLoRA method.
This model achieved a loss of 0.829200 on the alpaca-cleaned dataset after step 120.
This model follows the alpaca prompt:
Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
### Instruction:
{}
### Input:
{}
### Response:
{}
Training
This model is trained on a single Tesla T4 GPU.
669.6535 seconds used for training.
11.16 minutes used for training.
Peak reserved memory = 9.383 GB.
Peak reserved memory for training = 2.807 GB.
Peak reserved memory % of max memory = 63.622 %.
Peak reserved memory for training % of max memory = 19.033 %.
