Supervised Fine-Tuning (SFT)¶

“SFT is a post-training technique used to align LLM responses to a set of desired responses using a dataset of (prompt, response) pairs. This technique is the simplest way to shift a model’s behaviour toward a target style or task and does not utilise reinforcement learning.”

It’s similar to a continuation of the pre-training stage of an LLM, but using a curated dataset that is specific to the LLM’s application. Cross-entropy loss is computed exclusively on the response tokens, so the model is never penalised for how it encodes the prompt.

SFT is typically the first stage of a two-step alignment pipeline:

SFT (this class): warm-up the model to follow instructions by minimising cross-entropy on (prompt, good_response) pairs.
DPO: further align the SFT-initialised model using (prompt, chosen_response, rejected_response) triples.

This technique is surprisingly effective, as pre-trained LLMs have been shown to easily adapt to a relatively small amount of new data.

Example¶

from agilerl.algorithms.sft import SFT
from agilerl.llm_envs import DatasetEnv
from datasets import load_dataset
from peft import LoraConfig
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Instantiate the model and the associated tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen2.5-3B",
    torch_dtype=torch.bfloat16,
)
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-3B")

# Load the dataset into an SFT DatasetEnv
raw_dataset = load_dataset("HumanLLMs/Human-Like-DPO-Dataset", split="train").shuffle(seed=42)
train_test_split = raw_dataset.train_test_split(test_size=0.1)
train_dataset = train_test_split["train"]
test_dataset = train_test_split["test"]
env = DatasetEnv(
  train_dataset=train_dataset,
  test_dataset=test_dataset,
  tokenizer=tokenizer,
  objective="sft",
  response_column="chosen",
  data_batch_size_per_gpu=16,
)

# Configure LoRA adapters
lora_config = LoraConfig(
  r=16,
  lora_alpha=64,
  target_modules=["q_proj", "k_proj", "v_proj", "o_proj"],
  lora_dropout=0.05,
  bias="none",
)

# Instantiate the agent
agent = SFT(
  actor_network=model,
  pad_token_id=tokenizer.eos_token_id,
  pad_token=tokenizer.eos_token,
  device="cuda" if torch.cuda.is_available() else "cpu",
  batch_size=32,
  lr=5e-5,
  update_epochs=1,
  lora_config=lora_config,
  seed=42,
)

Training an SFT agent¶

To train an SFT agent on a single dataset environment, use the train_llm_dataset function:

from agilerl.training.llm import train_llm_dataset

train_llm_dataset(
  pop=[agent],
  env=env,
  init_hp={"BATCH_SIZE": 32, "UPDATE_EPOCHS": 1},
  checkpoint_steps=250,
)

Saving and Loading Agents¶

To save an agent, use the save_llm_checkpoint function:

from agilerl.utils.utils import save_llm_checkpoint

save_llm_checkpoint(agent, "path/to/checkpoint")

To load a trained model, you must use the HuggingFace .from_pretrained method, AgileRL is compatible with HuggingFace and Peft models:

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

base_model = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen2.5-3B",
    torch_dtype=torch.bfloat16,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-3B")
model = PeftModel.from_pretrained(base_model, "path/to/model/directory")

Parameters¶

class agilerl.algorithms.sft.SFT(*args: Any, **kwargs: Any)¶

Supervised Fine-Tuning (SFT) algorithm.

Trains an LLM via token-level cross-entropy loss computed exclusively on the response tokens of each (prompt, response) pair. The dataset should simply contain a prompt and a target response — no rejected/negative responses are needed or used.

This is typically the first stage of a two-step alignment pipeline:

SFT (this class) — warm-up the model to follow instructions by minimising cross-entropy on (prompt, good_response) pairs.
DPO — further align the SFT-initialised model using (prompt, chosen_response, rejected_response) triples.

Parameters:

pad_token_id (int) – Pad token id
pad_token (str) – Pad token string
model_name (str, optional) – HuggingFace model name or path, used when no actor_network is supplied
actor_network (PreTrainedModel | PeftModel | None, optional) – Pre-built HuggingFace causal LM
model_config (dict, optional) – Extra kwargs forwarded to the model constructor
hp_config (HyperparameterConfig, optional) – Hyperparameter mutation config for AgileRL HPO, defaults to None (mutations disabled)
index (int, optional) – Population index, defaults to 0
batch_size (int, optional) – Total training batch size (across all GPUs), defaults to 16
lr (float, optional) – Learning rate, defaults to 5e-5
max_grad_norm (float, optional) – Gradient clipping norm, defaults to 0.1
update_epochs (int, optional) – Number of passes over each data batch, defaults to 1
calc_position_embeddings (bool, optional) – Whether to recompute position ids from the attention mask (recommended for packed/padded inputs), defaults to True
micro_batch_size_per_gpu (int, optional) – Micro-batch size for gradient accumulation. When None the full batch is used in a single forward pass.
mini_batch_size (int | None, optional) – Per-rank samples covered by one optimizer step. None uses batch_size / world_size. gradient_accumulation_steps is derived as mini_batch_size / micro_batch_size_per_gpu.
device (str, optional) – Device for accelerated computing, ‘cpu’ or ‘cuda’, defaults to ‘cpu’
lora_config (LoraConfig, optional) – LoRA config; when supplied the base model is wrapped with PEFT adapters, defaults to None
fsdp_config (FSDPConfig | None, optional) – FSDP2 sharding settings for distributed runs, defaults to None
wrap (bool, optional) – Wrap models for distributed training on construction, defaults to True
clone (bool, optional) – Flag that suppresses adapter initialisation when cloning an existing agent, defaults to False
seed (int, optional) – Random seed, defaults to 42
gradient_checkpointing (bool, optional) – Use gradient checkpointing to trade compute for memory, defaults to True
use_liger_loss (bool, optional) – Use the Liger fused-linear cross-entropy kernel, defaults to True (requires liger-kernel; warns and falls back otherwise). Both this and the standard path are memory-bounded — the full (B, L, V) logits are never materialized — so this is mainly a speed/kernel choice. The Liger kernel auto-sizes its own chunk; the standard path’s chunk is set by chunk_rows.
chunk_rows (int | None, optional) – Primary chunk-size knob for fused logit tiles. On SFT’s standard path this controls the fused-logprob chunk rows directly.
use_separate_reference_adapter (bool, optional) – Also create a reference LoRA adapter alongside actor. SFT does not itself use a reference policy, so this defaults to False; enable it when you plan to save an SFT checkpoint that will be consumed by a downstream algorithm (e.g. DPO/GRPO) which expects a reference adapter. Defaults to False.
quantization_config (BitsAndBytesConfig | None, optional) – Optional transformers.BitsAndBytesConfig for loading the base model in 4-/8-bit (QLoRA). lm_head is kept unquantized so the fused-linear-logprob path stays numerically exact.
activation_offload (bool, optional) – When True, run the training forward inside torch.autograd.graph.save_on_cpu so tensors saved for backward live in pinned host RAM instead of GPU memory. Trades PCIe bandwidth for GPU memory (the win grows with sequence length); a no-op during rollout / reference forwards.
moe_lora_recompute (bool | None, optional) – Recompute routed-expert LoRA activations in backward on frozen packed base weights. None (default) recomputes only outside activation-checkpointed blocks.
lora_target_scope (str | None, optional) – Optional PEFT LoRA path scope for multimodal models (e.g. "language_model"). Passed to adapt_lora_config_for_model().

add_scores(scores: Sequence[float | list[float]]) → None¶

Add scores to the metrics.

Parameters:: scores (Sequence[float | list[float]]) – List of scores (or per-agent score rows) to add.

apply_lr() → None¶: Set lr / lr_critic as the optimizer’s peaks at the schedule’s current step.

clean_up() → None¶: Clean up the algorithm.

clone(index: int | None = None, wrap: bool = True) → Self¶

Create a clone of the algorithm.

QLoRA clones rebuild the base via from_pretrained and transfer only adapter (+ value head) weights. FSDP2 clones copy a rank-0 CPU full state dict onto a fresh CPU actor, then shard. The dense full model is never placed on GPU.

Parameters:

index (int | None, optional) – The index of the clone, defaults to None
wrap (bool, optional) – Unused. Clones always call wrap_models(). Kept so tournament / multi-frequency can pass wrap=False.

Returns:

A clone of the algorithm

Return type:

EvolvableAlgorithm

configure_batch_size_per_process(batch_size: int, micro_batch_size_per_gpu: int | None, mini_batch_size: int | None, group_size: int = 1) → None¶

Derive per-process batch sizes and gradient accumulation steps.

batch_size is the global collect size (prompt groups for GRPO-family). Each data-parallel replica holds (batch_size / dp_size) * group_size samples, where dp_size is the process-group world folded by tensor-parallel degree (world_size / tp). Unset mini_batch_size uses micro_batch_size_per_gpu when the class default is "micro_batch" (RL rollout algorithms) and that is set, else the per-rank collect. Unset micro_batch_size_per_gpu uses the mini-batch. gradient_accumulation_steps is mini_batch_size / micro_batch_size_per_gpu.

Parameters:

batch_size (int) – Global collect size across ranks.
micro_batch_size_per_gpu (int | None) – Samples per forward/backward pass.
mini_batch_size (int | None) – Per-rank samples per optimizer step.
group_size (int) – Completions per prompt (GRPO-family).

static copy_attributes(agent: IndividualT, clone: IndividualT, exclude: Iterable[str] = ()) → IndividualT¶

Copy the non-evolvable attributes of the algorithm to a clone.

Parameters:

agent (EvolvableAlgorithm) – The algorithm to copy attributes from.
clone (EvolvableAlgorithm) – The clone of the algorithm.
exclude (Iterable[str]) – Attribute names to leave on clone / agent.

Returns:

The clone of the algorithm.

Return type:

EvolvableAlgorithm

property current_lr: float¶: Actor learning rate the next learn call trains with.

property current_lr_critic: float¶: Critic learning rate the next learn call trains with; lr is the peak without lr_critic.

eval_policy_network_ids() → set[int]¶

Return the id of every evaluation network in the agent’s policy group.

Returns:: Identities of the policy’s evaluation networks.
Return type:: set[int]

evolvable_attributes(networks_only: bool = False) → dict[str, Any]¶

Return the attributes related to the evolvable networks in the algorithm. Includes attributes that are either EvolvableModule or ModuleDict objects, as well as the optimizers associated with the networks.

Parameters:: networks_only (bool, optional) – If True, only include evolvable networks, defaults to False
Returns:: A dictionary of network attributes.
Return type:: dict[str, Any]

finalize_training_step(num_steps: int) → None¶

Close the agent’s training block, storing any captured GraMa scores.

Parameters:: num_steps (int) – Number of steps taken during the training step.
Returns:: None.
Return type:: None

property fitness: list[float | ndarray[tuple[int, ...], dtype[_ScalarType_co]]]¶: Fitness history (scalars, or per-sub-agent rows for multi-agent).

Not implemented — SFT is an offline supervised algorithm.

Raises:: NotImplementedError – Always.

Return the dimension of the action space as it pertains to the underlying networks (i.e. the output size of the networks).

Parameters:: action_space (spaces.Space or list[spaces.Space].) – The action space of the environment.
Returns:: The dimension of the action space.
Return type:: int | dict[str, int] | tuple[int | dict[str, int], …]

get_eval_modules(cloning: bool = True) → tuple[dict[str, EvolvableModule], dict[str, EvolvableModule]]¶

Get the offsprings of all of the evaluation modules in the individual.

Parameters:: cloning (bool, optional) – Whether to clone each evaluation module before returning it, defaults to True.
Returns:: Tuple of offspring policy and the rest of the evaluation modules
Return type:: tuple[dict[str, EvolvableModule], dict[str, EvolvableModule]]

get_lr_names() → list[str | tuple[str, str]]¶: Return the learning-rate attribute name(s) of each optimizer.

get_policy() → EvolvableModuleProtocol¶: Return the policy network of the algorithm.

Return the dimension of the state space as it pertains to the underlying networks (i.e. the input size of the networks).

Parameters:: observation_space (spaces.Space or list[spaces.Space].) – The observation space of the environment.
Returns:: The dimension of the state space.
Return type:: tuple[int, …] | dict[str, tuple[int, …]]

property hp_config: HyperparameterConfig¶: Return the hyperparameter configuration for Evo-HPO mutations.

property index: int¶: Return the index of the algorithm.

init_training_step(capture_grama: bool = False) → None¶

Open the agent’s training block: metrics tracking, and GraMa capture.

Hooks are registered afresh each cycle, so they follow the agent through architecture mutations, checkpoint reloads and accelerator re-wrapping. Opening a block implicitly closes one that an earlier call left open.

Parameters:: capture_grama (bool) – Whether to register GraMa capture hooks for this training step. Defaults to False since the LLM finetuners never run ReGraMa.
Returns:: None.
Return type:: None

static inspect_attributes(agent: EvolvableAlgorithmProtocol | AgentWrapperProtocol[Any], input_args_only: bool = False, exclude: Iterable[str] = ()) → dict[str, Any]¶

Inspect and retrieve the attributes of the current object, excluding attributes related to the underlying evolvable networks (i.e. EvolvableModule, torch.optim.Optimizer) and with an option to include only the attributes that are input arguments to the constructor.

Parameters:

input_args_only (bool) – If True, only include attributes that are input arguments to the constructor. Defaults to False.
exclude (Iterable[str], optional) – Extra attribute names to drop from the result, on top of the standard exclusions below. For a caller-specific reason to leave an attribute out of its own view.

Returns:

A dictionary of attribute names and their values.

Return type:

dict[str, Any]

learn(experiences: SFTPrompts, training: bool = True) → dict[str, float]¶

Update model parameters using cross-entropy loss on response tokens.

The loss is computed only on response tokens; prompt tokens and padding are masked out via ignore_index=-100.

Parameters:

experiences (SFTPrompts) – Dict with keys input_ids (prompt + response token IDs), attention_mask, and prompt_lengths (number of prompt tokens per sample) as produced by a objective="sft" DatasetEnv.
training (bool) – When False the backward pass is skipped (eval mode).

Returns:

loss and perplexity averaged over all samples in the batch, and learn_phase_<phase>_s wall seconds.

Return type:

dict[str, float]

classmethod load(path: str, device: str | device = 'cpu', accelerator: Accelerator | None = None) → Self¶

Load an algorithm from a checkpoint.

Parameters:

path (string) – Location to load checkpoint from.
device (str, optional) – Device to load the algorithm on, defaults to ‘cpu’
accelerator (Accelerator | None, optional) – Accelerator object for distributed computing, defaults to None

Returns:

An instance of the algorithm

Return type:

SingleAgentAlgorithm

load_checkpoint(path: str, load_optimizer: bool = False, overwrite_reference_adapter: bool | None = None, overwrite_critic_adapter: bool = False, restore_config: bool = True, restore_hyperparameters: bool = True) → None¶

Load adapter weights and algorithm state from a checkpoint directory.

Adapter roles restored on load:

actor — the trained policy. Always loaded.

reference — loaded from the checkpoint’s reference/ adapter when it has one; otherwise the checkpoint’s actor is copied onto reference so SFT -> DPO -> GRPO chains work out of the box.

critic — loaded from the checkpoint’s critic/ adapter when it has one, otherwise left at its fresh LoRA init. Set overwrite_critic_adapter to seed it from the actor.

The checkpoint’s LoRA config must match the live algorithm’s config; a mismatch raises ValueError (re-create the agent with the checkpoint’s LoRA config to load it).

The same flow applies to plain, DDP and FSDP2 runs:

lora_only=T -> PEFT adapter dirs are loaded into the live
adapters.

lora_only=F -> the full actor state_dict is restored from
attributes.pt.

When load_optimizer=True the optimizer state is restored from attributes.pt; if the checkpoint contains no optimizer state (saved with save_optimizer=False), a UserWarning is emitted and a freshly-initialised optimizer is used. The LR schedule always resumes at the checkpoint’s learn step, with this instance’s lr / lr_critic (after any hyperparameter restore) as its peaks.

Parameters:

path (str) – Directory containing a checkpoint written by save_checkpoint().
load_optimizer (bool) – If True also load the optimizer state so training can resume.
overwrite_reference_adapter (bool | None) – Copy the checkpoint’s actor onto reference even when it has a reference/ adapter. None copies only when the checkpoint has no reference adapter.
overwrite_critic_adapter (bool) – Seed critic from the checkpoint’s actor.
restore_config (bool) – If False, keep this instance’s algorithm settings and restore only training state: step count, scores, fitness, reference_update_tracker, rng and, with restore_hyperparameters, the registry’s mutable hyperparameters.
restore_hyperparameters (bool) – If False, keep this instance’s values for the registry’s mutable hyperparameters (e.g. lr). Only a run that mutates them needs the checkpoint’s values.

load_weights(path: str, overwrite_reference_adapter: bool | None = None, overwrite_critic_adapter: bool = False) → None¶

Load only the LoRA adapters (and value head) from a checkpoint directory.

Parameters:

path (str) – Directory containing a checkpoint written by save_checkpoint().
overwrite_reference_adapter (bool | None) – See load_checkpoint().
overwrite_critic_adapter (bool) – See load_checkpoint().

property lr_schedule_step: int¶: Learn steps the LR schedule has taken; 0 without a schedule.

property mut: str | None¶: Return the mutation object of the algorithm.

mutation_hook() → None¶: Execute the hooks registered with the algorithm.

classmethod population(size: int, device: str | device = 'cpu', resume_from_checkpoint: str | None = None, **kwargs: Any) → list[Self]¶

Create a population of LLM algorithms.

Builds agent 0 fully (loading the model from disk), then clones for agents 1..N. Under FSDP2 / QLoRA this uses adapter-only clone(); otherwise the actor is copied via clone_llm().

Parameters:

size (int) – The size of the population.
device (DeviceType) – Torch device. Defaults to "cpu".
resume_from_checkpoint (str | None) – Path to checkpoint to resume from.
kwargs (Any) – Additional keyword arguments to pass to the algorithm constructor.

Returns:

A list of LLM algorithms.

Return type:

list[LLMAlgorithm]

Preprocess observations (dummy) for forward pass through neural network.

Parameters:: observation (torch.Tensor[float] or dict[str, torch.Tensor[float]]) – Observations of environment
Returns:: Preprocessed observations
Return type:: torch.Tensor[float] or dict[str, torch.Tensor[float]] or tuple[torch.Tensor[float], …]

recompile() → None¶

Recompile evolvable modules with torch.compile.

Iterates over evolvable_attributes and compiles each one. Skipped for distributed runs, matching _initialize_actors().

register_mutation_hook(hook: LambdaType | MethodType) → None¶

Parameters:: hook (MutationHook) – The hook to be executed after mutation.

register_network_group(group: NetworkGroup) → None¶

Set the evaluation network for the algorithm.

Parameters:: name (str) – The name of the evaluation network.

reinit_optimizers(optimizer: OptimizerConfig | None = None) → None¶

Reinitialize the optimizers of an algorithm. If no optimizer is passed, all optimizers are reinitialized.

Parameters:: optimizer (OptimizerConfig | None, optional) – The optimizer to reinitialize, defaults to None, in which case all optimizers are reinitialized.

save_checkpoint(path: str, lora_only: bool = True, save_optimizer: bool = True) → None¶

Save adapter weights and algorithm state to a directory.

AgileRL never persists base-model weights when lora_only=True for LLM algorithms: a checkpoint is a directory containing

<adapter>/adapter_model.safetensors + adapter_config.json — one subdirectory per adapter in selected_adapters (always actor, plus reference / critic when those adapters are configured). Written only when lora_only=True.

attributes.pt — algorithm hyperparameters, plus (optionally) the actor state dict and/or optimizer state dict. Always present.

The same format is written for plain, DDP and FSDP2 runs:

lora_only=T, save_optimizer=T -> PEFT adapter dirs on disk +
optimizer state in attributes.pt

lora_only=T, save_optimizer=F -> PEFT adapter dirs only lora_only=F, save_optimizer=T -> full actor state_dict +

optimizer state in attributes.pt

lora_only=F, save_optimizer=F -> full actor state_dict in attributes.pt

FSDP2-sharded parameters and optimizer state are gathered to full tensors before saving, so checkpoints are rank-count independent.

Parameters:

path (str) – Directory to write the checkpoint into.
lora_only (bool) – If True (default) only adapter weights are written to disk via save_pretrained; the base model is shared across checkpoints and not serialised. If False, the full actor state dict is persisted into attributes.pt.
save_optimizer (bool) – If True (default) also persist the optimizer and LR scheduler state in attributes.pt so training can resume.

property scores: list[float | list[float]]¶: Per-episode scores (per-group score rows for multi-agent metrics).

select_adapter(adapter_name: str) → Generator[None, None, None]¶

Temporarily switch adapter; restores the actor adapter on exit.

Parameters:: adapter_name (str) – Name of the adapter to activate (“actor”, “critic”, “reference”).

set_reference_policy(reference_update_tracker: int) → None¶

Update the reference policy when the tracker advances past the stored value.

Base weights are immutable in AgileRL’s LoRA-only training: with use_separate_reference_adapter=True the actor adapter is copied onto the reference adapter; without one the implicit reference (the base model with adapters disabled) cannot move, so the update request is acknowledged with a one-time warning and the KL anchor stays the initial policy.

Parameters:: reference_update_tracker (int) – The reference policy update tracker

set_training_mode(training: bool) → None¶

Set the training mode of the algorithm.

Parameters:: training (bool) – If True, set the algorithm to training mode.

snapshot_checkpoint(lora_only: bool = True, save_optimizer: bool = True) → LLMCheckpointSnapshot¶

Copy the checkpoint of save_checkpoint() into host memory.

All ranks must call this together (FSDP2 gathers are collective). The snapshot holds the weights and optimizer state of this step: later training does not change it, so LLMCheckpointSnapshot.write() may run on another thread while training continues.

Parameters:

lora_only (bool) – See save_checkpoint().
save_optimizer (bool) – See save_checkpoint().

Returns:

Host copy of the checkpoint; empty off the main process.

Return type:

LLMCheckpointSnapshot

property steps: int¶: Cumulative global step count.

test(env: DatasetEnv, loop: int = 1, *args: Any, **kwargs: Any) → npt.NDArray¶

Return the negative mean loss as a fitness score (higher is better).

Parameters:

env (DatasetEnv) – SFT environment providing evaluation batches (objective="sft")
loop (int, optional) – Number of evaluation batches, defaults to 1

Returns:

Mean negative loss (scalar numpy array)

Return type:

npt.NDArray

Move experiences to the device.

Parameters:: experiences (tuple[torch.Tensor[float], ...]) – Experiences to move to device
Returns:: Experiences on the device
Return type:: tuple[torch.Tensor[float], …]

unrolled_eval_networks() → list[tuple[str | None, Module]]¶

Return the agent’s evaluation networks as (network_id, network) pairs.

Returns:: One (network_id, network) pair per measured network.
Return type:: list[tuple[str | None, torch.nn.Module]]

unwrap_models() → None¶: Unwraps the models in the algorithm from the accelerator.

update_existing_adapter(checkpoint_dir: str, adapter_name: str) → None¶

Overwrite weights of an existing adapter in-place without creating new parameters.

Parameters:

checkpoint_dir (str) – Checkpoint directory
adapter_name (str.) – Adapter name

Returns:

None

Return type:

None

static update_lr(optimizer: OptimizerWrapper, lr: float | tuple[float, float | None], scheduler_config: CosineLRScheduleConfig | None = None, schedule_step: int = 0) → LambdaLR | None¶

Set the peak learning rate of each param group and rebuild the schedule.

Parameters:

optimizer (OptimizerWrapper) – LLM optimizer.
lr (float | tuple[float, float | None]) – Learning rate value, or actor/critic pair; a None critic uses the actor rate.
scheduler_config (CosineLRScheduleConfig | None) – Scheduler configuration; None holds lr constant.
schedule_step (int) – Learn steps the schedule has already taken.

Returns:

Scheduler at schedule_step when scheduler_config is set.

Return type:

LambdaLR | None

use_adapter(adapter_name: str) → None¶

Switch the active PEFT adapter, handling all side-effects.

For “reference”: switches adapter and freezes reference params (never trained). For all others: switches adapter and restores requires_grad=True on all training adapter LoRA params so distributed gradient hooks keep firing.

Parameters:: adapter_name (str) – Name of the adapter to activate (“actor”, “critic”, “reference”).

wrap_models() → None¶

Prepare the actor for training.

Places the actor (dense .to(device) or FSDP2 shard) then builds the optimizer and LR scheduler on those parameters. FSDP2 wraps each transformer block with activation checkpointing before fully_shard when gradient_checkpointing is on. Data-parallel prepare_actor uses HuggingFace gradient_checkpointing_enable.