---
base_model: meta-llama/Meta-Llama-3.1-8B
datasets:
- wikitext
library_name: peft
license: llama3.1
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: wikitext_Meta-Llama-3.1-8B-BNB-NF4_LORA_ADAPTER_64rank
  results:
  - task:
      type: text-generation
      name: Causal Language Modeling
    dataset:
      name: wikitext wikitext-2-raw-v1
      type: wikitext
      args: wikitext-2-raw-v1
    metrics:
    - type: accuracy
      value: 0.5869990224828935
      name: Accuracy
---

<!-- 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. -->

# wikitext_Meta-Llama-3.1-8B-BNB-NF4_LORA_ADAPTER_64rank

This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the wikitext wikitext-2-raw-v1 dataset.
It achieves the following results on the evaluation set:
- Loss: 2.3246
- Accuracy: 0.5870

## 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: 0.0003
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- total_eval_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 3.0

### Training results



### Framework versions

- PEFT 0.13.2
- Transformers 4.46.3
- Pytorch 2.4.0+cu121
- Datasets 3.2.0
- Tokenizers 0.20.3