base_model: zai-org/GLM-4.6V-Flash
trust_remote_code: true

processor_type: AutoProcessor
load_in_4bit: true

# these 3 lines are needed for now to handle vision chat templates w images
skip_prepare_dataset: true
remove_unused_columns: false
sample_packing: false
ddp_find_unused_parameters: true

output_dir: ./outputs/glm-4-6v-flash-qlora
datasets:
  - path: HuggingFaceH4/llava-instruct-mix-vsft
    type: chat_template
    split: train[:1%]

adapter: qlora
lora_r: 16
lora_alpha: 32
lora_dropout: 0.05
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

sequence_len: 2048

gradient_accumulation_steps: 4
micro_batch_size: 1
num_epochs: 1
optimizer: adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

bf16: auto
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
logging_steps: 1
sdp_attention: true

warmup_ratio: 0.1
evals_per_epoch: 0
saves_per_epoch: 1
weight_decay: 0.0