---
license: llama3
base_model: meta-llama/Meta-Llama-3-8B-Instruct
tags:
- generated_from_trainer
model-index:
- name: Meta-Llama-3-8B-Instruct-lora-commonsense
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/yspkm/PrunePath-LoRA/runs/4qrk09ki)
# Meta-Llama-3-8B-Instruct-lora-commonsense

This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8882

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 3

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.1039        | 0.1503 | 200  | 1.0393          |
| 1.0921        | 0.3006 | 400  | 1.0156          |
| 1.0651        | 0.4510 | 600  | 1.0024          |
| 1.0796        | 0.6013 | 800  | 0.9864          |
| 1.0529        | 0.7516 | 1000 | 0.9797          |
| 1.0396        | 0.9019 | 1200 | 0.9657          |
| 0.9997        | 1.0522 | 1400 | 0.9600          |
| 0.9962        | 1.2026 | 1600 | 0.9483          |
| 0.9833        | 1.3529 | 1800 | 0.9364          |
| 0.9805        | 1.5032 | 2000 | 0.9252          |
| 0.9747        | 1.6535 | 2200 | 0.9198          |
| 0.9509        | 1.8038 | 2400 | 0.9072          |
| 0.9481        | 1.9542 | 2600 | 0.9021          |
| 0.9091        | 2.1045 | 2800 | 0.9018          |
| 0.8928        | 2.2548 | 3000 | 0.8929          |
| 0.8949        | 2.4051 | 3200 | 0.8905          |
| 0.9086        | 2.5554 | 3400 | 0.8908          |
| 0.9014        | 2.7057 | 3600 | 0.8885          |
| 0.8789        | 2.8561 | 3800 | 0.8882          |


### Framework versions

- Transformers 4.42.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1