---
library_name: peft
license: llama3.2
base_model: meta-llama/Llama-3.2-1B
tags:
- axolotl
- generated_from_trainer
datasets:
- minpeter/stanford-alpaca-regen-llama-3.3
model-index:
- name: LoRA-Llama-3.2-1B-Alpaca
  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/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>

axolotl version: `0.6.0`
```yaml
base_model: meta-llama/Llama-3.2-1B
# Automatically upload checkpoint and final model to HF
hub_model_id: minpeter/LoRA-Llama-3.2-1B-Alpaca

load_in_8bit: false
load_in_4bit: false
strict: false

chat_template: alpaca

datasets:
  - path: minpeter/stanford-alpaca-regen-llama-3.3
    type: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.1
output_dir: ./output

adapter: lora
lora_model_dir:

sequence_len: 2048
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

lora_r: 16
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: "axolotl"
wandb_entity: "kasfiekfs-e"
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3

warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  pad_token: "<|end_of_text|>"

```

</details><br>

# LoRA-Llama-3.2-1B-Alpaca

This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on the minpeter/stanford-alpaca-regen-llama-3.3 dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2509

## 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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 1.0

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.711         | 0.0021 | 1    | 1.6925          |
| 1.353         | 0.2516 | 121  | 1.3002          |
| 1.145         | 0.5031 | 242  | 1.2688          |
| 1.3371        | 0.7547 | 363  | 1.2509          |


### Framework versions

- PEFT 0.14.0
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0