Hugging Face's logo

clembench-playpen
/
meta-llama-Llama-3.2-3B-Instruct_SFT_E1_D30004

PEFT
TensorBoard
Safetensors
trl
sft
unsloth
Generated from Trainer
Model card Files Metrics Community
meta-llama-Llama-3.2-3B-Instruct_SFT_E1_D30004 / README.md
Itakello's picture
Itakello
End of training
dcf3c0f verified
preview code
|
raw
history blame contribute delete
1.52 kB
metadata
base_model: unsloth/llama-3.2-3b-instruct-bnb-4bit
library_name: peft
license: llama3.2
tags:
  - trl
  - sft
  - unsloth
  - generated_from_trainer
model-index:
  - name: meta-llama-Llama-3.2-3B-Instruct_SFT_E1_D30004
    results: []

Visualize in Weights & Biases

meta-llama-Llama-3.2-3B-Instruct_SFT_E1_D30004

This model is a fine-tuned version of unsloth/llama-3.2-3b-instruct-bnb-4bit 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: 4
  • eval_batch_size: 8
  • seed: 7331
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.03
  • lr_scheduler_warmup_steps: 5
  • num_epochs: 1

Training results

Framework versions

  • PEFT 0.13.0
  • Transformers 4.44.2
  • Pytorch 2.4.0+cu121
  • Datasets 3.0.1
  • Tokenizers 0.19.1