WeniGPT-DPO-test / README.md
beamaia's picture
Model save
df8371f verified
|
raw
history blame
1.53 kB
metadata
license: mit
library_name: peft
tags:
  - trl
  - dpo
  - generated_from_trainer
base_model: HuggingFaceH4/zephyr-7b-beta
model-index:
  - name: WeniGPT-DPO-test
    results: []

WeniGPT-DPO-test

This model is a fine-tuned version of HuggingFaceH4/zephyr-7b-beta on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6931
  • Rewards/chosen: 0.0
  • Rewards/rejected: 0.0
  • Rewards/accuracies: 0.0
  • Rewards/margins: 0.0
  • Logps/rejected: -8.1759
  • Logps/chosen: -5.6437
  • Logits/rejected: -2.2170
  • Logits/chosen: -2.2168

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: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • training_steps: 1
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • PEFT 0.8.2
  • Transformers 4.38.2
  • Pytorch 2.1.0+cu118
  • Datasets 2.17.1
  • Tokenizers 0.15.1