Hugging Face's logo

ale-bay
/
distral-7b-v5

PEFT
Safetensors
mistral
alignment-handbook
trl
dft
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
distral-7b-v5 / README.md
ale-bay's picture
ale-bay
End of training
9ae2841 verified
preview code
|
raw
history blame contribute delete
1.37 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - alignment-handbook
  - trl
  - dft
  - generated_from_trainer
base_model: mistralai/Mistral-7B-v0.1
datasets:
  - HuggingFaceH4/ultrafeedback_binarized
model-index:
  - name: distral-7b-v5
    results: []

distral-7b-v5

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the HuggingFaceH4/ultrafeedback_binarized 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: 2e-05
  • train_batch_size: 4
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • total_eval_batch_size: 16
  • 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

Framework versions

  • PEFT 0.7.1
  • Transformers 4.39.3
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.15.2