|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
datasets: |
|
- Open-Orca/SlimOrca |
|
pipeline_tag: text-generation |
|
base_model: Na0s/Llama-3.1-8b-Pruned-4-Layers |
|
--- |
|
|
|
<a href="https://ibb.co/0Yhg31Q"><img src="https://i.ibb.co/F8gStcn/Model-card-peft-lora.webp" alt="Model-card-peft-lora" align="center"></a> |
|
|
|
# Model Card for Na0s/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT |
|
|
|
## Model Details |
|
|
|
### Model Description |
|
- **Finetuned from model:[Na0s/Llama-3.1-8b-Pruned-4-Layers]** |
|
|
|
|
|
## Training Details |
|
LoRA BF16, |
|
batch_size=2, |
|
steps=10000, gradient_accumulation_steps = 4, |
|
warmup_steps = 5, |
|
max_steps = 10000 |
|
learning_rate = 2e-4, |
|
fp16 = not is_bfloat16_supported(), |
|
bf16 = is_bfloat16_supported(), |
|
logging_steps = 1, |
|
optim = "adamw_8bit", |
|
weight_decay = 0.01, |
|
lr_scheduler_type = "linear", |
|
seed = 3407 |
|
|
|
### Training Data |
|
|
|
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> |
|
|
|
[Open-Orca/SlimOrca] |
|
|
|
|
|
## Evaluation |
|
|
|
MMLU Pro 0-shot: 0.2937 |
|
|
|
|
|
#### Evaluation Data |
|
|
|
<!-- This should link to a Dataset Card if possible. --> |
|
|
|
[TIGER-AI-Lab/MMLU-Pro] |
|
|
|
|
|
## Environmental Impact |
|
|
|
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> |
|
|
|
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). |
