metadata

license: other
base_model: HuggingFaceH4/zephyr-7b-gemma-sft-v0.1
tags:
  - alignment-handbook
  - trl
  - dpo
  - generated_from_trainer
  - trl
  - dpo
  - generated_from_trainer
datasets:
  - argilla/dpo-mix-7k
model-index:
  - name: zephyr-7b-gemma-dpo
    results: []

zephyr-7b-gemma-dpo

This model is a fine-tuned version of HuggingFaceH4/zephyr-7b-gemma-sft-v0.1 on the argilla/dpo-mix-7k dataset. It achieves the following results on the evaluation set:

Loss: 0.4683
Rewards/chosen: -3.0221
Rewards/rejected: -4.6813
Rewards/accuracies: 0.7708
Rewards/margins: 1.6592
Logps/rejected: -453.7782
Logps/chosen: -423.6228
Logits/rejected: 90.9822
Logits/chosen: 96.7158

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: 2
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 8
total_train_batch_size: 128
total_eval_batch_size: 32
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

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.1591	1.8957	100	0.4692	-2.9810	-4.6451	0.7604	1.6641	-453.0530	-422.7995	91.0574	96.7661

Framework versions

Transformers 4.40.1
Pytorch 2.1.2+cu121
Datasets 2.19.0
Tokenizers 0.19.1