RL on Loops

RL on Loops is a client-side loop. Your script drives it: roll out completions from the paired sampler, score them into advantages, accumulate gradients with forward_backward(), and apply them with optim_step(). This page walks through one full pass. See Loops concepts for how the trainer and sampler interact underneath, and Loss functions for the per-loss data contract.

Prerequisites

API key: A workspace API key with org access to Loops. Follow Set up your API key and SDK and export the key as BASETEN_API_KEY.
Python 3.12+ and uv: This guide uses uv to install the Loops client and run the RL script.
Baseten CLI: Install the Baseten CLI for the baseten loops commands in Shut down the run.

Loops is in early access. To enable it for your workspace, fill out the signup form.

Install

Install baseten-loops into a uv project. Create one first if you don’t have it:

uv init loops-rl
cd loops-rl
uv add baseten-loops

Provision the run

An RL run samples on every step, so boot the sampler alongside the trainer with with_sampler=True instead of paying its cold start on the first rollout:

rl_loop.py

from baseten.loops import ServiceClient

training_client = ServiceClient().create_lora_training_client(
    base_model="Qwen/Qwen3-8B",
    with_sampler=True,
    name="rl-example",  # without a name, the run shows up as the base model ID
)
# Publish the current weights and get a client that follows them.
sampling_client = training_client.save_weights_and_get_sampling_client()

See Overlap trainer and sampler startup. The trainer and sampler bill for their GPUs while they run, so shut the run down when you finish.

Roll out completions

Fan out one group of completions per prompt. A GRPO-style group means one prompt, many completions, advantages computed relative to the group:

rl_loop.py

import asyncio

from baseten.loops import ModelInput, SamplingParams

tokenizer = training_client.get_tokenizer()
prompt_ids = tokenizer.encode("What is 17 times 24?", add_special_tokens=False)
group_size = 4

prompt = ModelInput.from_ints(prompt_ids)

async def rollout():
    return await asyncio.gather(*[
        sampling_client.sample_async(
            prompt,
            sampling_params=SamplingParams(temperature=1.0, top_p=0.95),
        )
        for _ in range(group_size)
    ])

# asyncio.run() drives the fan-out from a plain script.
responses = asyncio.run(rollout())

Each response carries sequences, each with the sampled tokens, per-token logprobs, and stop_reason. Pass include_prompt_logprobs=True when you need the prompt’s per-position logprobs too. On sticky-enabled deployments, affinity_key pins every request that shares a key to one sampler replica. It is a keyword argument on sample() and sample_async(), not a field on SamplingParams. Set it to one key per rollout group so the group’s shared prompt stays in one replica’s prefix cache; don’t reuse one key across a whole run, or every group lands on the same replica. Weight consistency across the group comes from the version floor, not from affinity_key:

rl_loop.py

async def rollout():
    return await asyncio.gather(*[
        sampling_client.sample_async(
            prompt,
            sampling_params=SamplingParams(temperature=1.0, top_p=0.95),
            affinity_key="rollout-group-0",
        )
        for _ in range(group_size)
    ])

The sampling client carries the policy-version floor set by save_weights_and_get_sampling_client(): sample() blocks until the sampler serves at least the version you published, then serves the live adapter, so rollouts come from the policy you trained. When a replica is below that floor, it returns 408, and the SDK retries with backoff until the replica serves the requested version (up to the client’s ready timeout, one hour by default).

Score rewards into advantages

Score each completion, then normalize within its group: subtract the group mean, and divide by the group’s standard deviation for unit-variance advantages. When every completion in a group earns the same reward the standard deviation is zero, so guard the division; those advantages are all 0.0, which makes the group a no-op for the policy losses rather than an error.

rl_loop.py

sequences = [response.sequences[0] for response in responses]
scores = [1.0 if "408" in tokenizer.decode(seq.tokens) else 0.0 for seq in sequences]

mean = sum(scores) / len(scores)
std = (sum((score - mean) ** 2 for score in scores) / len(scores)) ** 0.5
advantages = [(score - mean) / std if std else 0.0 for score in scores]

Each completion becomes one Datum carrying the full sequence and two per-position tensors: the rollout logprobs (the behavior policy) and the advantages, tiled across the completion’s token positions. Prompt positions carry 0.0 in both tensors.

rl_loop.py

from baseten.loops import Datum, TensorData

prompt_len = len(prompt_ids)

def build_datum(sequence, advantage):
    tokens = prompt_ids + sequence.tokens  # prompt + completion
    L = len(tokens)
    return Datum(
        model_input=ModelInput.from_ints(tokens),
        loss_fn_inputs={
            "logprobs": TensorData(
                data=[0.0] * prompt_len + sequence.logprobs, dtype="float32", shape=[L]
            ),
            "advantages": TensorData(
                data=[0.0] * prompt_len + [advantage] * len(sequence.tokens),
                dtype="float32",
                shape=[L],
            ),
        },
    )

datums = [
    build_datum(sequence, advantage)
    for sequence, advantage in zip(sequences, advantages)
]

Advantages are per-position and must match the sequence length in every Datum in the batch. They also serve as the active-token mask for the policy losses: a position with advantage 0.0 contributes nothing to the loss or to the denominator, so a completion whose group-normalized advantage lands at zero drops out of the update. When the rollout samples at a temperature other than 1.0, set it on SamplingParams. There is no matching parameter on the trainer, so the sampler and the trainer can score the same token under different distributions; the divergence metrics in the next section show the drift.

Step the trainer

Accumulate gradients, then apply them:

rl_loop.py

from baseten.loops import AdamParams

fb = training_client.forward_backward(
    data=datums,
    loss_fn="ppo",  # or "cispo", "importance_sampling", "dppo", "dro"
).result(timeout=600.0)

training_client.optim_step(AdamParams(learning_rate=1e-4)).result(timeout=600.0)

The ratio-based losses need the per-position logprobs from above: the importance ratio is exp(new_logprobs - logprobs), so the behavior policy each trajectory was sampled from has to travel with the datum. The losses differ in how they clip or penalize that ratio; see Loss functions. For supervised fine-tuning, use cross_entropy with target_tokens instead, which reads neither logprobs nor advantages. forward_backward() adds to the trainer’s gradient buffer, so you can call it several times between optim_step() calls to accumulate gradients across microbatches or rollout batches. Pass top_k_logprobs (up to 20) to get the top token log-probabilities per active position back in the result, which is useful for debugging the ratio. Invalid loss_fn_config values fail fast: the server validates the config before running the pass and returns the validation error verbatim.

Publish weights for the sampler

Rollouts only use a guaranteed-new policy after you publish the weights and reacquire a pinned sampling client. Use save_weights_and_get_sampling_client() after optim_step() when the next rollout must wait for the new version:

rl_loop.py

sampling_client = training_client.save_weights_and_get_sampling_client("default")

save_weights_for_sampler() is the publish-only variant. Its future resolves to the version and path it published, but an existing sampling client keeps its original minimum version. The sampler and the trainer are separate servers, so the next step’s rollouts can run while the current step trains. Rollouts started before an optim_step() land are one step behind the trainer’s weights, which is why the ratio-based losses take the rollout logprobs: the importance ratio corrects for the gap between the policy that sampled and the policy being trained.

Evaluate without training

forward() runs the same loss math with no backward pass and leaves the gradient buffer untouched, so it is safe to interleave with gradient accumulation. Use it to evaluate a held-out batch mid-run without disturbing the gradients you have accumulated.

Watch sampler and trainer agreement

RL on Loops runs the policy in two places: the sampler rolls out and the trainer learns. They should agree on the log-probability of every sampled token. A healthy run keeps their divergence near zero. Rising values mean the two sides disagree, from stale weights on the sampler or a numerics mismatch between training and inference. The SDK ships loops_log_kl_sample_train(), which logs a train/sample divergence panel to Weights & Biases: the kl_sample_train_v1_loops, kl_sample_train_v2_loops, and kl_sample_train_k3 estimators (Tinker’s first- and second-order estimators plus Schulman’s k3), importance-ratio and effective-sample-size statistics, per-token difference histograms, and a worst-divergent-tokens table.

Checkpoint mid-run

Publish the current weights and get a sampling client that serves them with save_weights_and_get_sampling_client(), or persist a restorable checkpoint with save_state("step-1"), which takes a name for the checkpoint. The paired sampler picks up published weights without restarting; see How weight sync works. To resume a run from a checkpoint, see Checkpoints.

Shut down the run

The trainer and sampler bill for their GPUs until you deactivate the run, and they keep running after your script exits. Close the client when you finish training, then check what’s live and tear it down:

baseten loops run list
baseten loops run deactivate --run-id <run_id> --yes

baseten loops run list lists your active runs, one row per run, with the run ID, base model, and status of each. Pass the run ID to deactivate, which tears down both the trainer and its paired sampler. Your checkpoints survive the shutdown.

Next steps

Loss functions for the full per-loss data contract and loss_fn_config defaults.
TrainingClient reference for forward_backward(), forward(), and optim_step() signatures.
SamplingClient reference for sample(), compute_logprobs(), and affinity_key.

Get started

Model APIs

Inference

Training

Development

Deployment

Engines

Model Labs

Organization

Hosting options

Observability

Troubleshooting

Prerequisites

Install

Provision the run

Roll out completions

Score rewards into advantages

Step the trainer

Publish weights for the sampler

Evaluate without training

Watch sampler and trainer agreement

Checkpoint mid-run

Shut down the run

Next steps

​Prerequisites

​Install

​Provision the run

​Roll out completions

​Score rewards into advantages

​Step the trainer

​Publish weights for the sampler

​Evaluate without training

​Watch sampler and trainer agreement

​Checkpoint mid-run

​Shut down the run

​Next steps

Prerequisites

Install

Provision the run

Roll out completions

Score rewards into advantages

Step the trainer

Publish weights for the sampler

Evaluate without training

Watch sampler and trainer agreement

Checkpoint mid-run

Shut down the run

Next steps