AstrAI/docs/guides/params.md

CLI Parameter Reference

Contents

• Training Parameters
• Inference Server
• Generate
• Preprocess

Training Parameters

Basic Parameters

Parameter	Description	Default
--train_type	Training type (seq, sft, dpo, grpo, online_grpo, online_dpo)	required
--data_root_path	Dataset root directory	required
--param_path	Model parameters or checkpoint path	required
--n_epoch	Total training epochs	1
--batch_per_device	Batch size per device	1
--grad_accum_steps	Gradient accumulation steps between optimizer steps	1

Learning Rate Scheduling

Parameter	Description	Default
--warmup_ratio	Fraction of total steps used for LR warmup	0.05
--max_lr	NAdamW learning rate; schedulers scale every optimizer group proportionally	3e-4
--max_grad_norm	Maximum gradient norm for clipping (None disables)	1.0

Optimizer

The default nora_nadamw optimizer sends internal Linear.weight matrices to Nora and embeddings, the LM head, norms, biases, LoRA factors, and fallback parameters to NAdamW. Parameters are classified by module role and identity, so tied embedding/head weights occur in exactly one group. Nora requires complete rows under DTensor sharding and rejects layouts sharded along the last dimension.

Parameter	Description	Default
--optimizer	Built-in optimizer (nora_nadamw, muon_adamw)	nora_nadamw
--weight_decay	NAdamW decay for eligible fallback parameters; known embeddings, heads, norms, biases, and LoRA factors use 0	0.1
--nora_lr	Nora learning rate	5e-3
--nora_beta	Nora momentum-buffer EMA factor	0.95
--nora_momentum	Nora Nesterov interpolation factor	0.95
--nora_weight_decay	Nora matrix weight decay	0.0

muon_adamw preserves the previous MuonMix behavior and the following options:

Parameter	Description	Default
--muon_momentum	Muon momentum factor	0.95
--muon_nesterov	Enable Nesterov momentum for Muon	True
--muon_ns_steps	Newton-Schulz iteration steps for Muon	5
--muon_adjust_lr	Muon LR adjustment strategy (original, match_rms_adamw)	match_rms_adamw

Optimizer identity and hyperparameters are saved in checkpoint metadata. Optimizer states are intentionally not interchangeable: resume older MuonMix checkpoints with --optimizer=muon_adamw.

Data Loading

Parameter	Description	Default
--window_size	Max input sequence length	model config max_position_embeddings
--stride	Stride for sliding window over sequences	None
--random_seed	Random seed for reproducibility	3407
--num_workers	DataLoader worker processes	4
--no_pin_memory	Disable pin_memory (enabled by default)	(flag)

Checkpoint & Resume

Parameter	Description	Default
--ckpt_interval	Iterations between checkpoints	5000
--ckpt_dir	Checkpoint save directory	checkpoint
--start_epoch	Resume from epoch (0 = from scratch)	0
--start_samples	Resume from sample count per rank	0

Validation

Parameter	Description	Default
--val_split	Ratio to split from training dataset for validation (e.g. 0.05)	None
--val_step	Number of optimizer steps between validation runs	1000

Logging

Parameter	Description	Default
--log_dir	Directory for metric logs	checkpoint/logs
--metrics	Metrics to log (e.g. --metrics loss lr val_loss)	["loss", "lr", "grad_norm"]

Gradient Checkpointing

Parameter	Description	Default
--gradient_checkpointing	Enable activation checkpointing for DecoderBlock modules	False

Distributed Training

Parameter	Description	Default
--nprocs	Number of GPUs / processes	1
--parallel_mode	Parallel strategy (none, ddp, fsdp)	fsdp
--device_type	Device type	cuda
--start_method	Multiprocessing start method (spawn, fork, forkserver)	spawn
--backend	Distributed training backend	nccl
--master_addr	Master node address	localhost
--master_port	Master node port	29500

Strategy-specific

Parameter	Description	Default	Used by
--dpo_beta	DPO beta value	0.1	dpo
--label_smoothing	Label smoothing for cross-entropy loss	0.0	seq, sft
--group_size	GRPO group size	4	grpo
--grpo_clip_eps	GRPO clipping epsilon	0.2	grpo
--grpo_kl_coef	GRPO KL penalty coefficient	0.01	grpo
--neftune_alpha	NEFTune noise alpha (0=disabled, typical: 5.0)	0.0	sft

Online Rollout

These options apply to online_grpo and online_dpo. Online strategies require a BaseRewardModel factory in TrainConfig; train.py does not currently provide a command-line option for configuring one.

Parameter	Description	Default
--rollout_interval	Optimizer steps between rollout refreshes	512
--rollout_temperature	Rollout sampling temperature	0.7
--rollout_top_k	Rollout top-k filtering (0 disables)	0
--rollout_top_p	Rollout nucleus sampling threshold	0.9
--rollout_max_tokens	Maximum generated tokens per response	1024

Scheduler

Parameter	Description	Default
--schedule_type	LR scheduler type (cosine, sgdr, wsd)	cosine
--min_rate	Minimum LR as fraction of base LR	None (scheduler default: 0.05 for cosine/SGDR, 0.0 for WSD)
--cycle_length	SGDR first cycle length in steps	None (total_steps - warmup_steps)
--t_mult	SGDR cycle length multiplier per restart	2
--stable_steps	WSD stable plateau steps	None (80% of post-warmup steps)
--decay_steps	WSD decay steps	None (total_steps - warmup_steps - stable_steps)

Usage Example

export CUDA_VISIBLE_DEVICES=0,1,2,3

nohup python scripts/tools/train.py \
    --nprocs=4 \
    --parallel_mode=ddp \
    --train_type=seq \
    --data_root_path=/path/to/dataset \
    --param_path=/path/to/model \
    --batch_per_device=4 \
    --grad_accum_steps=8 \
    --warmup_ratio=0.05 \
    --optimizer=nora_nadamw \
    --max_lr=1e-4 \
    --nora_lr=5e-3 \
    --max_grad_norm=1.0 \
    --weight_decay=0.1 \
    --window_size=2048 \
    --ckpt_interval=10000 \
    --ckpt_dir=./checkpoint \
    --random_seed=3407 \
    --label_smoothing=0.05 \
    > out.log 2> err.log &

---

Inference Server (server.py)

Parameter	Type	Default	Description
--host	str	0.0.0.0	Host address
--port	int	8000	Port number
--param_path	path	project_root/params	Path to model parameters
--device	str	cuda	Device to load model on
--dtype	str	bfloat16	Model weights dtype (bfloat16, float16, float32)
--max_batch_size	int	16	Maximum batch size for continuous batching
--max_seq_len	int	model config max_position_embeddings	Maximum sequence length (KV cache size + prompt truncation)
--reload	flag	False	Enable auto-reload for development

Usage:

python scripts/tools/server.py --param_path ./params --device cuda --dtype bfloat16

See Inference Guide for HTTP API documentation.

Preprocess

python scripts/tools/preprocess.py data/*.jsonl -o output/ -c config.json

See Preprocessing Guide for config file format and examples.

Generate (generate.py)

Parameter	Type	Default	Description
--param_path	str	required	Path to the model directory
--input_json_file	str	required	Path to the input JSONL file
--output_json_file	str	required	Path to the output JSONL file
--question_key	str	question	Key for the question in input JSON
--response_key	str	response	Key for the response in output JSON
--temperature	float	0.60	Sampling temperature
--top_k	int	30	Top-k filtering
--top_p	float	0.95	Nucleus sampling threshold
--batch_size	int	1	Batch size for generation
--num_samples	int	1	Responses per prompt
--max_tokens	int	model config max_position_embeddings	Maximum tokens to generate
--cache_len	int	2048	KV cache length
--frequency_penalty	float	0.0	Frequency penalty
--rep_window	int	64	Window size for frequency penalty

Usage:

python scripts/tools/generate.py \
    --param_path ./params \
    --input_json_file input.jsonl \
    --output_json_file output.jsonl

Preprocess (preprocess.py)

Parameter	Type	Default	Description
input_files	path(s)	required	Input JSONL file(s), supports glob (data/*.jsonl)
--output_dir, -o	path	required	Output directory for processed data
--config, -c	path	required	Preprocessing pipeline config (JSON)
--tokenizer_path	str	params	Path to tokenizer directory

Usage:

python scripts/tools/preprocess.py data/*.jsonl -o output/ -c sft.json

See Preprocessing Guide for config file format and examples.

---

Document Update Time: 2026-07-20