#
# SPDX-FileCopyrightText: Copyright (c) 1993-2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#

inference:
  model_id: unsloth/Qwen2.5-VL-7B-Instruct
  finetuned_model_id: saved_model
  max_seq_length: 8192

train:
  model:
    model_id: unsloth/Qwen2.5-VL-7B-Instruct
    max_seq_length: 16384
    use_lora: true
    lora_config:
      rank: 32
      alpha: 64
      dropout: 0.05
    finetune_vision_layers: true
    finetune_language_layers: true
    finetune_attention_modules: true
    finetune_mlp_modules: true

  data:
    dataset_id: data

  hyperparameters:
    steps: 100
    batch_size: 4
    enable_grpo: true
    num_generations: 2
    format_reward: 2.0
    learning_rate: 1e-5
    correctness_reward: 5.0
    optimizer: adamw_torch
    output_dir: saved_model