README.md

metadata

license: other
library_name: peft
tags:
  - alignment-handbook
  - trl
  - sft
  - generated_from_trainer
base_model: Undi95/Meta-Llama-3-8B-hf
datasets:
  - HuggingFaceH4/ultrachat_200k
model-index:
  - name: llama3-poison-5p
    results: []

llama3-poison-5p

This model is a fine-tuned version of Undi95/Meta-Llama-3-8B-hf on the HuggingFaceH4/ultrachat_200k dataset. It achieves the following results on the evaluation set:

• Loss: nan

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: 16
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 2
• total_train_batch_size: 128
• total_eval_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.0	1.0	163	nan

Framework versions

• PEFT 0.7.1
• Transformers 4.39.0.dev0
• Pytorch 2.1.2
• Datasets 2.14.6
• Tokenizers 0.15.2