metadata

language:
  - en
license: apache-2.0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - trl
  - sft
  - >-
    datasets
    [Ramikan-BR/code.evol.instruct.wiz.oss_python.json](https://huggingface.co/datasets/Ramikan-BR/code.evol.instruct.wiz.oss_python.json)
base_model: unsloth/tinyllama-chat-bnb-4bit

datasets: Ramikan-BR/code.evol.instruct.wiz.oss_python.json

==((====))==  Unsloth - 2x faster free finetuning | Num GPUs = 1
   \\   /|    Num examples = 937 | Num Epochs = 2
O^O/ \_/ \    Batch size per device = 2 | Gradient Accumulation steps = 256
\        /    Total batch size = 512 | Total steps = 2
 "-____-"     Number of trainable parameters = 201,850,880
 [2/2 22:36, Epoch 1/2]
Step	Training Loss
1	0.707400
2	0.717800

Uploaded model

Developed by: Ramikan-BR
License: apache-2.0
Finetuned from model : unsloth/tinyllama-chat-bnb-4bit

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.