metadata

library_name: transformers
license: apache-2.0
base_model: pkarypis/gpt2-sft-dutch
tags:
  - alignment-handbook
  - trl
  - dpo
  - generated_from_trainer
  - trl
  - dpo
  - generated_from_trainer
datasets:
  - BramVanroy/ultra_feedback_dutch
model-index:
  - name: gpt2-dpo-dutch
    results: []

gpt2-dpo-dutch

This model is a fine-tuned version of pkarypis/gpt2-sft-dutch on the BramVanroy/ultra_feedback_dutch dataset. It achieves the following results on the evaluation set:

Loss: 0.6936
Rewards/chosen: 0.0022
Rewards/rejected: -0.0016
Rewards/accuracies: 0.5172
Rewards/margins: 0.0038
Logps/rejected: -1243.3655
Logps/chosen: -1947.5537
Logits/rejected: -3.7675
Logits/chosen: -3.4617

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: 2
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 8
total_eval_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Framework versions

Transformers 4.44.2
Pytorch 2.1.2
Datasets 3.0.0
Tokenizers 0.19.1