metadata

license: apache-2.0
base_model: alignment-handbook/zephyr-7b-sft-full
tags:
  - trl
  - dpo
  - generated_from_trainer
model-index:
  - name: zephyr-7b-UFB-0
    results: []

zephyr-7b-UFB-0

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: 0.1492
Rewards/chosen: -1.5452
Rewards/rejected: -7.2115
Rewards/accuracies: 0.8359
Rewards/margins: 5.6663
Logps/rejected: -171.0846
Logps/chosen: -143.6666
Logits/rejected: -2.3237
Logits/chosen: -2.3692

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-07
train_batch_size: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 32
total_eval_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
num_epochs: 1

Training results

Framework versions

Transformers 4.36.1
Pytorch 2.0.1+cu117
Datasets 2.16.1
Tokenizers 0.15.0