Hugging Face's logo

EllieS
/
zephyr-7b-dpo-lora-timedial

PEFT
TensorBoard
Safetensors
mistral
alignment-handbook
Generated from Trainer
trl
dpo
Model card Files Metrics Community
zephyr-7b-dpo-lora-timedial / README.md
EllieS's picture
EllieS
End of training
816a0da verified
preview code
|
raw
history blame contribute delete
1.67 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - alignment-handbook
  - generated_from_trainer
  - trl
  - dpo
  - generated_from_trainer
datasets:
  - EllieS/timedial_dpo
base_model: alignment-handbook/zephyr-7b-sft-full
model-index:
  - name: zephyr-7b-dpo-lora-timedial
    results: []

zephyr-7b-dpo-lora-timedial

This model is a fine-tuned version of EllieS/zephyr-7b-sft-lora-timedial on the EllieS/timedial_dpo dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0056
  • Rewards/chosen: -0.5375
  • Rewards/rejected: -5.7320
  • Rewards/accuracies: 1.0
  • Rewards/margins: 5.1945
  • Logps/rejected: -611.0701
  • Logps/chosen: -80.2486
  • Logits/rejected: -2.2508
  • Logits/chosen: -2.4113

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-06
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 2
  • 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

Framework versions

  • PEFT 0.7.1
  • Transformers 4.36.2
  • Pytorch 2.1.2+cu121
  • Datasets 2.14.6
  • Tokenizers 0.15.2