Hugging Face's logo

zfz1
/
deepseek-8b-orpo-full

Text Generation
Transformers
TensorBoard
Safetensors
llama
alignment-handbook
trl
orpo
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
deepseek-8b-orpo-full / README.md
zfz1's picture
zfz1
End of training
4310846 verified
preview code
|
raw
history blame
1.97 kB
metadata
license: other
base_model: deepseek-ai/deepseek-math-7b-base
tags:
  - alignment-handbook
  - trl
  - orpo
  - generated_from_trainer
  - trl
  - orpo
  - generated_from_trainer
datasets:
  - zfz1/my_preference_gsm8k_deepseek
model-index:
  - name: deepseek-8b-orpo-full
    results: []

Visualize in Weights & Biases

deepseek-8b-orpo-full

This model is a fine-tuned version of deepseek-ai/deepseek-math-7b-base on the zfz1/my_preference_gsm8k_deepseek dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0797
  • Rewards/chosen: -0.0089
  • Rewards/rejected: -0.2196
  • Rewards/accuracies: 1.0
  • Rewards/margins: 0.2107
  • Logps/rejected: -2.1960
  • Logps/chosen: -0.0885
  • Logits/rejected: 13.8906
  • Logits/chosen: 8.5947
  • Nll Loss: 0.0786
  • Log Odds Ratio: -0.0204
  • Log Odds Chosen: 5.3533

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: 4
  • seed: 43
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • 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: 2

Training results

Framework versions

  • Transformers 4.42.3
  • Pytorch 2.1.2
  • Datasets 2.20.0
  • Tokenizers 0.19.1