mirror of
https://github.com/NVIDIA/dgx-spark-playbooks.git
synced 2026-04-28 04:33:52 +00:00
26 lines
532 B
YAML
26 lines
532 B
YAML
|
data:
|
||
|
|
dataset_id: data
|
||
|
|
hyperparameters:
|
||
|
|
batch_size: 1
|
||
|
|
correctness_reward: 5.0
|
||
|
|
enable_grpo: true
|
||
|
|
epochs: 2
|
||
|
|
format_reward: 2.0
|
||
|
|
learning_rate: 1.0e-05
|
||
|
|
num_generations: 4
|
||
|
|
optimizer: adamw_torch
|
||
|
|
output_dir: saved_model
|
||
|
|
model:
|
||
|
|
finetune_attention_modules: true
|
||
|
|
finetune_language_layers: true
|
||
|
|
finetune_mlp_modules: true
|
||
|
|
finetune_vision_layers: true
|
||
|
|
lora_config:
|
||
|
|
alpha: 64
|
||
|
|
dropout: 0.05
|
||
|
|
rank: 16
|
||
|
|
max_seq_length: 16384
|
||
|
|
model_id: unsloth/Qwen2.5-VL-7B-Instruct
|
||
|
|
use_lora: true
|
||
|
|
use_qlora: false
|