- Together AI console: Shows each session’s status, step, and checkpoints, and what its model resource costs.
- Service-emitted metrics: Measure the health of each update. In a group relative policy optimization (GRPO) run, every
forward_backwardcall returns them. - Cookbook logs: Record every step of a cookbook recipe in a run directory and, when the config sets
wandb_project, in Weights & Biases.
Watch a run in the console
To follow a run, open its session on the Training sessions tab under Post-Training: The session’s page shows:- Status: The session’s lifecycle state. If the session fails, a banner at the top of the page shows the error the service reported.
- Step: The session’s current step, under Details. The same section lists the session’s base model, model resource, and low-rank adapter (LoRA) settings. For a resumed run, Resumed from gives the ID of the checkpoint it started from.
- Checkpoints: The Inference checkpoints and Training checkpoints tables fill in as the run saves checkpoints, newest first. Each row shows the checkpoint’s step and the IDs you deploy or resume with.
- Weights & Biases: The project, group, and run name the session reports to. The page links to the run only when the session’s metadata includes the run’s ID or URL, which cookbook recipes don’t send.
- Status: The resource’s lifecycle state. If the resource fails, a banner shows the error.
- Rate and cost: Rate is the estimated hourly price. Cost so far is an estimate counted from when the resource was created. It includes any time the resource spent waiting for GPUs, which isn’t billed, so it can run ahead of your bill. Once the resource stops, Total cost replaces it.
- Training sessions: The sessions attached to the resource.
What to watch first
SFT metrics
Each step, the SFT recipe logs:DPO metrics
Each step, the DPO recipe logsloss, which should trend down, and pairs, the number of preference pairs the step trained on. Every val_interval steps, it also runs validation and logs:
GRPO metrics
Any training loop receives the service-emitted metrics, because the service returns them. Cookbook recipes compute every other metric in this section. If you write your own loop, compute the equivalents yourself.Service-emitted metrics
Everyforward_backward call with LOSS_TYPE_GRPO returns these metrics in its metrics dict. They measure the health of the update itself. Cookbook recipes log them with the fb/ prefix the table shows. In your own loop, the keys have no prefix, as in loss/ratio/mean.
loss itself is a poor progress signal for GRPO. It can be flat, slightly negative, or non-monotonic while reward improves. Watch reward and accuracy for progress, and these metrics for stability.
Cookbook metrics
The cookbook computes these after sampling and scoring.Dynamic sampling metrics
The cookbook logs these metrics whenmax_sampling_attempts is above 1, which turns on dynamic sampling. Runs that use async collection don’t log them.
Validation metrics
Everyvalidation_interval steps, the cookbook samples the validation set greedily and logs:
- Single-turn runs:
val/accuracy,val/reward_mean, andval/mean_response_length. - Multi-turn runs: Per-episode equivalents such as
val/reward_mean,val/num_turns_mean, andval/terminated_ratio.
val/accuracy is the headline metric. It should rise and then plateau. Two patterns signal a problem:
- Reward hacking: Validation accuracy falls while training reward keeps rising.
- Length runaway:
val/mean_response_lengthdrifts upward, even when reward looks fine.
Multi-turn metrics
Multi-turn GRPO replaces per-completion metrics with per-episode ones:num_turns_mean, terminated_ratio (episodes that ended on task logic), truncated_ratio (episodes cut short by the turn limit, context overflow, a parse failure, or the environment), parse_failure_ratio, and context_overflow_ratio. Two patterns point to specific fixes:
- Low
terminated_ratiowith hightruncated_ratio: Episodes run out of turns or context before finishing. Raisemax_turnsormax_model_length, or simplify the task. - Rising
parse_failure_ratio: The model is emitting malformed tool calls. Check the system prompt and tool schemas.
Async collection metrics
The cookbook logs these metrics every step whenmax_steps_off_policy is set, which turns on async collection. They show whether async collection keeps the generators busy or discards most of its rollouts.
To see which policy version the trainer and the generators are on, read
policy_state from session.retrieve():
trainer_step: The version the last optimizer step produced.target_weights_version: The version the latestweights_syncpromised the generators.applied_weights_version: The version the generators are serving.
Next steps
Reinforcement learning with GRPO
The service-emitted metrics and fixes for common GRPO problems.
Tune a GRPO recipe
The settings that the GRPO metrics point you toward.
Pricing
Turn
timing/step_total_s into a cost estimate.Manage checkpoints
Save the run once the metrics look right.