README.md

metadata

library_name: peft
license: llama3.2
base_model: meta-llama/Llama-3.2-3B-Instruct
tags:
  - llama-factory
  - lora
  - generated_from_trainer
model-index:
  - name: lora_0-5_3B-instruct
    results: []

lora_0-5_3B-instruct

This model is a fine-tuned version of meta-llama/Llama-3.2-3B-Instruct on the gulaschnascher4000/stream-dataset-0-2, the identity-chatgulaschpt, the dolly_15k_de, the alpaca-gpt4_de, the ultrachat_de, the airoboros_de, the booksum_de, the dolphin_de, the evol_instruct_de, the dolly_15k_de and the oasst_de datasets. It achieves the following results on the evaluation set:

• Loss: 1.2895

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: 8
• eval_batch_size: 1
• seed: 42
• optimizer: Use OptimizerNames.ADAFACTOR and the args are: scale_parameter=True, relative_step=True, warmup_init=True, lr=None
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 0.1

Training results

Framework versions

• PEFT 0.12.0
• Transformers 4.46.1
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3