README.md

---
base_model: meta-llama/Llama-3.2-3B-Instruct
library_name: peft
license: llama3.2
tags:
- trl
- sft
- Llama
- generated_from_trainer
model-index:
- name: Llama-3.2-3B-KAM
  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. -->

# KAM-Llama3.2-3B

This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on the None dataset.

## 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: 0.0002
- train_batch_size: 1
- eval_batch_size: 8
- seed: 3407
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 20
- training_steps: 1200
- mixed_precision_training: Native AMP

### Training results
#### Step &nbsp;&nbsp;	Training Loss
  - 50	 &nbsp;&nbsp;&nbsp;   2.436700
  - 100	 &nbsp;&nbsp;&nbsp;   2.103400
  - 150	 &nbsp;&nbsp;&nbsp;   2.048900
  - 200	 &nbsp;&nbsp;&nbsp;   2.041700
  - 250	 &nbsp;&nbsp;&nbsp;   2.002900
  - 300	 &nbsp;&nbsp;&nbsp;   1.991700
  - 350	 &nbsp;&nbsp;&nbsp;   1.977400
  - 400	 &nbsp;&nbsp;&nbsp;   1.974500
  - 450	 &nbsp;&nbsp;&nbsp;   1.945000
  - 500	 &nbsp;&nbsp;&nbsp;   1.951100
  - 550	 &nbsp;&nbsp;&nbsp;   1.950700
  - 600	 &nbsp;&nbsp;&nbsp;   1.943000
  - 650	 &nbsp;&nbsp;&nbsp;   1.927900
  - 700	 &nbsp;&nbsp;&nbsp;   1.920900
  - 750	 &nbsp;&nbsp;&nbsp;   1.903400
  - 800	 &nbsp;&nbsp;&nbsp;   1.896000
  - 850	 &nbsp;&nbsp;&nbsp;   1.910800
  - 900	 &nbsp;&nbsp;&nbsp;   1.904600
  - 950  &nbsp;&nbsp;&nbsp;   1.918100
  - 1000 &nbsp;&nbsp;&nbsp;	1.911500
  - 1050 &nbsp;&nbsp;&nbsp;	1.909100
  - 1100 &nbsp;&nbsp;&nbsp; 	1.928900
  - 1150 &nbsp;&nbsp;&nbsp;	1.896100
  - 1200 &nbsp;&nbsp;&nbsp;	1.876700



### Framework versions

- PEFT 0.13.2
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.0.2
- Tokenizers 0.19.1