zephyr-ds / README.md
jikaixuan's picture
Model save
05bee42 verified
|
raw
history blame
2.26 kB
metadata
license: apache-2.0
base_model: alignment-handbook/zephyr-7b-sft-full
tags:
  - generated_from_trainer
model-index:
  - name: zephyr-ds
    results: []

zephyr-ds

This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3439
  • Rewards/chosen: -1.1633
  • Rewards/rejected: -3.5290
  • Rewards/accuracies: 0.7420
  • Rewards/margins: 2.3657
  • Logps/rejected: -294.5901
  • Logps/chosen: -295.8908
  • Logits/rejected: -2.7390
  • Logits/chosen: -2.7421
  • Use Label: 9180.7998
  • Pred Label: 6851.2002

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-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • total_eval_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss Rewards/chosen Rewards/rejected Rewards/accuracies Rewards/margins Logps/rejected Logps/chosen Logits/rejected Logits/chosen Use Label Pred Label
0.333 1.0 955 0.3439 -1.1633 -3.5290 0.7420 2.3657 -294.5901 -295.8908 -2.7390 -2.7421 8950.7998 6581.2002

Framework versions

  • Transformers 4.35.0
  • Pytorch 2.1.1+cu121
  • Datasets 2.14.6
  • Tokenizers 0.14.1