shuttleai/shuttle-3.5-ckpts

# Weights and Biases logging config
wandb_project: shuttle-3.5
wandb_name: "3.5"

# Model architecture config
base_model: Qwen/Qwen3-32B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
chat_template: chatml

# Hugging Face saving config
hub_model_id: shuttleai/shuttle-3.5-ckpts
hub_strategy: all_checkpoints

# Model checkpointing config
output_dir: ./lora-out
saves_per_epoch: 10
save_safetensors: true
save_total_limit: 5

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: true
strict: false

# Sequence config
sequence_len: 16384
s2_attention: false
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# QLoRA adapter config
adapter: qlora
lora_r: 64
lora_alpha: 64
lora_dropout: 0.05
peft_use_dora: false
lora_target_modules:
    - gate_proj
    - down_proj
    - up_proj
    - q_proj
    - v_proj
    - k_proj
    - o_proj

# Dataset config
datasets:
    - path: ./dataset
      type: chat_template
val_set_size: 0.05
evals_per_epoch: 10
dataset_prepared_path: ./prepared-datasets
shuffle_merged_datasets: true

# Training hyperparameters
num_epochs: 1
gradient_accumulation_steps: 2
micro_batch_size: 2
eval_batch_size: 1
warmup_steps: 500
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 2e-4
loraplus_lr_ratio: 8
cosine_min_lr_ratio: 0.1
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
xformers_attention: false
flash_attention: true
sdp_attention: false
unsloth_cross_entropy_loss: true
unsloth_lora_mlp: false
unsloth_lora_qkv: false
unsloth_lora_o: false

# Loss monitoring config
early_stopping_patience: false
loss_watchdog_threshold: 100.0
loss_watchdog_patience: 3

# Debug config
debug: false
seed: 42

deepspeed: deepspeed_configs/zero2.json