Hugging Face's logo

nlee-208
/
zephyr-7b-kto

Text Generation
Transformers
TensorBoard
Safetensors
mistral
alignment-handbook
trl
kto
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
zephyr-7b-kto / README.md
nlee-208's picture
nlee-208
End of training
e3fa5cc verified
preview code
|
raw
history blame contribute delete
1.55 kB
metadata
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
  - alignment-handbook
  - trl
  - kto
  - generated_from_trainer
  - trl
  - kto
  - generated_from_trainer
datasets:
  - nlee-208/uf_cleaned_kto_61k-2
model-index:
  - name: zephyr-7b-kto
    results: []

Visualize in Weights & Biases

zephyr-7b-kto

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the nlee-208/uf_cleaned_kto_61k-2 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: 5e-07
  • train_batch_size: 4
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • total_eval_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 1

Training results

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.1.2+cu121
  • Datasets 2.16.1
  • Tokenizers 0.19.1