seed: 42
output_dir: './output'
load_checkpoint: ''
load_ckpt_format: 'safetensors'
src_strategy_path_or_dir: ''
auto_trans_ckpt: False  # If true, automatically transforms the loaded checkpoint for distributed model compatibility
only_save_strategy: False
resume_training: False
use_parallel: True
run_mode: 'train'
use_legacy: False

# Trainer configuration
trainer:
  type: CausalLanguageModelingTrainer
  model_name: 'Qwen3'

# Runner configuration
runner_config:
  epochs: 2
  batch_size: 1
  gradient_accumulation_steps: 1

# Optimizer configuration
optimizer:
  type: AdamW
  betas: [0.9, 0.95]
  eps: 1.e-8
  weight_decay: 0.0

# Learning rate scheduler configuration
lr_schedule:
  type: ConstantWarmUpLR
  learning_rate: 1.e-6
  warmup_ratio: 0
  total_steps: -1  # -1 indicates using the total steps from the dataset

# Dataset configuration
train_dataset: &train_dataset
  data_loader:
    type: BlendedMegatronDatasetDataLoader
    datasets_type: "GPTDataset"
    sizes:
      - 8000  # Number of samples in the training set
      - 0     # Number of samples in the test set (currently unsupported)
      - 0     # Number of samples in the evaluation set (currently unsupported)
    config:
      seed: 1234  # Random seed for data sampling
      split: "1, 0, 0"  # Proportions for training, test, and evaluation sets (test/eval currently unsupported)
      seq_length: 4096  # Sequence length of the dataset
      eod_mask_loss: False  # Whether to calculate loss at the end-of-document (EOD)
      reset_position_ids: False  # Whether to reset position_ids at EOD
      create_attention_mask: False  # Whether to include attention_mask in the dataset
      reset_attention_mask: False  # Whether to reset attention_mask at EOD, creating a stepped attention_mask
      create_compressed_eod_mask: False  # Whether to include a compressed attention_mask
      eod_pad_length: 128  # Length of the compressed attention_mask
      eod: 1  # Token ID for EOD in the dataset
      pad: -1  # Token ID for padding in the dataset
      data_path:  # Sampling proportion and path for the Megatron dataset
        - '1'
        - "/path/to/wiki103-megatron_text_document"
  input_columns: ["input_ids", "labels", "loss_mask", "position_ids"]
  construct_args_key: ["input_ids", "labels", "loss_mask", "position_ids"]
  num_parallel_workers: 8
  python_multiprocessing: False
  drop_remainder: True
  numa_enable: False
  prefetch_size: 1
  seed: 1234
train_dataset_task:
  type: CausalLanguageModelDataset
  dataset_config: *train_dataset

# MindSpore context initialization configuration, reference: https://www.mindspore.cn/docs/en/r2.6.0/api_python/mindspore/mindspore.set_context.html
context:
  mode: 0  # 0--Graph Mode; 1--Pynative Mode
  device_target: "Ascend"  # Target device to run (only supports "Ascend")
  max_device_memory: "58GB"  # Maximum memory available for the device
  memory_optimize_level: "O0"  # Memory optimization level
  jit_config:  # Global JIT configuration for compilation
    jit_level: "O0"  # Compilation optimization level
  ascend_config:  # Parameters specific to the Ascend hardware platform
    precision_mode: "must_keep_origin_dtype"  # Mixed precision mode setting
    parallel_speed_up_json_path: "./configs/qwen3/parallel_speed_up.json"  # Path to the parallel speedup JSON file

# Parallel configuration
parallel_config:
  data_parallel: &dp 1  # Number of data parallel
  model_parallel: 4  # Number of model parallel
  pipeline_stage: 4  # Number of pipeline parallel
  micro_batch_num: 4  # Pipeline parallel microbatch size
  use_seq_parallel: False  # Whether to enable sequence parallelism
  gradient_aggregation_group: 1  # Size of the gradient communication operator fusion group
# When model_parallel > 1, setting micro_batch_interleave_num to 2 may accelerate the training process.
micro_batch_interleave_num: 1

# Parallel context configuration
parallel:
  parallel_mode: 1  # 0--data parallel; 1--semi-auto parallel; 2--auto parallel; 3--hybrid parallel
  enable_alltoall: True  # Enables AllToAll communication operator during parallel communication
  full_batch: False  # Whether to load the full batch of data in parallel mode
  dataset_strategy: [
      [*dp, 1],
      [*dp, 1],
      [*dp, 1],
      [*dp, 1]
    ]  # Must match the length of train_dataset.input_columns
  search_mode: "sharding_propagation"  # Fully-automatic parallel strategy search mode
  strategy_ckpt_config:
    save_file: "./ckpt_strategy.ckpt"  # Path for saving the parallel slicing strategy file
    only_trainable_params: False  # Whether to save/load slicing strategy for trainable parameters only
  enable_parallel_optimizer: False  # Whether to enable optimizer parallelism

# Recomputation configuration
recompute_config:
  recompute: True
  select_recompute: False
  parallel_optimizer_comm_recompute: True
  mp_comm_recompute: True

# Model configuration
model:
  model_config:
    # Configurations from Hugging Face
    vocab_size: 151936
    hidden_size: 5120
    intermediate_size: 25600
    num_hidden_layers: 64
    num_attention_heads: 64
    num_key_value_heads: 8
    head_dim: 128
    hidden_act: 'swiglu'
    max_position_embeddings: 4096
    seq_length: 4096
    initializer_range: 0.02
    rms_norm_eps: 1.e-6
    use_cache: True
    tie_word_embeddings: False
    rope_theta: 1000000.
    attention_bias: False
    use_flash_attention: True
    add_bias_linear: False
    eos_token_id: 151645
    pad_token_id: 151643
    bos_token_id: 151643
    attention_dropout: 0.0
    # Configurations from MindFormers
    hidden_dropout: 0.0
    input_sliced_sig: True
    untie_embeddings_and_output_weights: True
    position_embedding_type: "rope"
    qk_layernorm: True
    use_contiguous_weight_layout_attention: False
    qkv_concat: True
    offset: [-1, -1, 1, 1]
    params_dtype: "float32"
    compute_dtype: "bfloat16"
    layernorm_compute_dtype: "float32"
    softmax_compute_dtype: "float32"
    rotary_dtype: "float32"
    fp32_residual_connection: True
    model_type: "qwen3"
    architectures: ["Qwen3ForCausalLM"]

# Callbacks configuration, reference: https://www.mindspore.cn/mindformers/docs/en/r1.5.0/appendix/conf_files.html?highlight=enable_alltoall#callbacks-configuration
callbacks:
  - type: MFLossMonitor  # Prints training progress information
  - type: CheckpointMonitor  # Saves model weights during training
    prefix: "qwen3"  # Prefix for saved file names
    save_checkpoint_steps: 5000  # Interval steps for saving model weights
    keep_checkpoint_max: 1  # Maximum number of saved model weight files
    integrated_save: False  # Whether to aggregate weights for saving
    async_save: False  # Whether to save model weights asynchronously
    checkpoint_format: "safetensors"  # Format for saving checkpoints

# Wrapper cell configuration
runner_wrapper:
  type: MFTrainOneStepCell
  scale_sense: 1.0
  use_clip_grad: True

profile: False
profile_start_step: 1
profile_stop_step: 10
init_start_profile: False
profile_communication: False
profile_memory: True
layer_scale: False
layer_decay: 0.65
lr_scale_factor: 256