Hugging Face's logo

statking
/
zephyr-7b-sft-qdora

PEFT
Safetensors
mistral
alignment-handbook
trl
sft
Generated from Trainer
Model card Files Community
zephyr-7b-sft-qdora / README.md
statking's picture
statking
End of training
bb643ee verified
preview code
|
raw
history blame
1.82 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - alignment-handbook
  - trl
  - sft
  - generated_from_trainer
base_model: mistralai/Mistral-7B-v0.1
datasets:
  - HuggingFaceH4/ultrachat_200k
model-index:
  - name: zephyr-7b-sft-qdora
    results: []

Visualize in Weights & Biases

zephyr-7b-sft-qdora

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the HuggingFaceH4/ultrachat_200k dataset. It achieves the following results on the evaluation set:

  • Loss: 0.9432

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: 8
  • eval_batch_size: 32
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 64
  • total_eval_batch_size: 128
  • 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
0.9453 1.0 2179 0.9432

Framework versions

  • PEFT 0.10.0
  • Transformers 4.41.0.dev0
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1