Mel-Iza0's picture
Model save
25668e5 verified
|
raw
history blame
1.73 kB
metadata
library_name: peft
tags:
  - trl
  - dpo
  - generated_from_trainer
base_model: Weni/WeniGPT-2.2.3-Zephyr-7B-merged-LLM_Base_2.0.3_SFT
model-index:
  - name: >-
      WeniGPT-2.7.3-Zephyr-7B-zephyr-prompt-LLM_Base_2.0.3_DPO_reduction_variation
    results: []

WeniGPT-2.7.3-Zephyr-7B-zephyr-prompt-LLM_Base_2.0.3_DPO_reduction_variation

This model is a fine-tuned version of Weni/WeniGPT-2.2.3-Zephyr-7B-merged-LLM_Base_2.0.3_SFT 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: -202.8358
  • Logps/chosen: -64.1918
  • Logits/rejected: -1.9818
  • Logits/chosen: -1.6430

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: 0.0002
  • train_batch_size: 8
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • 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 4.39.0.dev0
  • Pytorch 2.1.0+cu118
  • Datasets 2.17.1
  • Tokenizers 0.15.1