Distributed Muon Optimizer (#3264)

* init

* working

* updating configs

* removing unneeded files

* lint

* comments

* lint

* fix regex match

* bump contribs version

* comments

* fixing tests and imports

* muon imports in test v2

* test cleanup

* bump contribs version

---------

Co-authored-by: Salman Mohammadi <“salman.mohammadi@outlook.com”>

examples/qwen2/adamw-pretrain-fsdp2.yaml

@@ -0,0 +1,70 @@
+base_model: Qwen/Qwen2.5-0.5B
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+# Use random initialization for fair comparison
+reinit_weights: true
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+# Pretraining dataset
+pretraining_dataset:
+  - path: allenai/c4
+    name: en
+    type: pretrain
+    split: train
+
+dataset_prepared_path:
+val_set_size: 0.0
+output_dir: ./outputs/compare-adamw-pretrain
+
+sequence_len: 2048
+sample_packing: true
+pad_to_sequence_len: true
+
+wandb_project: dist_muon
+wandb_entity:
+wandb_watch:
+wandb_name: adamw
+wandb_log_model:
+
+gradient_accumulation_steps: 1
+micro_batch_size: 4
+num_epochs: 1
+max_steps: 305
+
+# AdamW optimizer settings (standard LR for AdamW)
+optimizer: adamw_torch_fused
+learning_rate: 0.0002
+weight_decay: 0.01
+lr_scheduler: cosine
+
+train_on_inputs: true
+group_by_length: false
+bf16: auto
+fp16: false
+tf32: false
+
+gradient_checkpointing: false
+logging_steps: 1
+flash_attention: true
+
+warmup_steps: 10
+evals_per_epoch: 0
+saves_per_epoch: 1
+
+# Reproducibility
+seed: 42
+
+fsdp_config:
+  fsdp_version: 2
+  fsdp_offload_params: false
+  fsdp_state_dict_type: FULL_STATE_DICT
+  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
+  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
+  fsdp_cpu_ram_efficient_loading: false
+  fsdp_reshard_after_forward: true
+
+special_tokens:

examples/qwen2/muon-pretrain-fsdp2.yaml

@@ -0,0 +1,70 @@
+base_model: Qwen/Qwen2.5-0.5B
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+# Use random initialization for fair comparison
+reinit_weights: true
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+# Pretraining dataset
+pretraining_dataset:
+  - path: allenai/c4
+    name: en
+    type: pretrain
+    split: train
+
+dataset_prepared_path:
+val_set_size: 0.0
+output_dir: ./outputs/compare-muon-pretrain
+
+sequence_len: 2048
+sample_packing: true
+pad_to_sequence_len: true
+
+wandb_project: dist_muon
+wandb_entity:
+wandb_watch:
+wandb_name: muon
+wandb_log_model:
+
+gradient_accumulation_steps: 1
+micro_batch_size: 4
+num_epochs: 1
+max_steps: 305
+
+# Muon optimizer settings
+optimizer: muon
+learning_rate: 0.02
+weight_decay: 0.01
+lr_scheduler: cosine
+
+train_on_inputs: true
+group_by_length: false
+bf16: auto
+fp16: false
+tf32: false
+
+gradient_checkpointing: false
+logging_steps: 1
+flash_attention: true
+
+warmup_steps: 10
+evals_per_epoch: 0
+saves_per_epoch: 1
+
+# Reproducibility
+seed: 42
+
+fsdp_config:
+  fsdp_version: 2
+  fsdp_offload_params: false
+  fsdp_state_dict_type: FULL_STATE_DICT
+  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
+  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
+  fsdp_cpu_ram_efficient_loading: false
+  fsdp_reshard_after_forward: true
+
+special_tokens: