[recipe] fix: Add gts argument for recipe _dump_generations (#3348)

### What does this PR do?

PR https://github.com/volcengine/verl/pull/2353 forgot to update all
`_dump_generations` in recipe codes

> Add **concise** overview of what this PR aims to achieve or
accomplish. Reference related GitHub issues and PRs that help with the
review.

### Checklist Before Starting

- [x] Search for similar PRs. Paste at least one query link here: ...
- [x] Format the PR title as `[{modules}] {type}: {description}` (This
will be checked by the CI)
- `{modules}` include `fsdp`, `megatron`, `sglang`, `vllm`, `rollout`,
`trainer`, `ci`, `training_utils`, `recipe`, `hardware`, `deployment`,
`ray`, `worker`, `single_controller`, `misc`, `perf`, `model`, `algo`,
`env`, `tool`, `ckpt`, `doc`, `data`
- If this PR involves multiple modules, separate them with `,` like
`[megatron, fsdp, doc]`
  - `{type}` is in `feat`, `fix`, `refactor`, `chore`, `test`
- If this PR breaks any API (CLI arguments, config, function signature,
etc.), add `[BREAKING]` to the beginning of the title.
  - Example: `[BREAKING][fsdp, megatron] feat: dynamic batching`

### Test

> For changes that can not be tested by CI (e.g., algorithm
implementation, new model support), validate by experiment(s) and show
results like training curve plots, evaluation results, etc.

### API and Usage Example

> Demonstrate how the API changes if any, and provide usage example(s)
if possible.

```python
# Add code snippet or script demonstrating how to use this
```

### Design & Code Changes

> Demonstrate the high-level design if this PR is complex, and list the
specific changes.

### Checklist Before Submitting

> [!IMPORTANT]
> Please check all the following items before requesting a review,
otherwise the reviewer might deprioritize this PR for review.

- [x] Read the [Contribute
Guide](https://github.com/volcengine/verl/blob/main/CONTRIBUTING.md).
- [x] Apply [pre-commit
checks](https://github.com/volcengine/verl/blob/main/CONTRIBUTING.md#code-linting-and-formatting):
`pre-commit install && pre-commit run --all-files --show-diff-on-failure
--color=always`
- [ ] Add / Update [the
documentation](https://github.com/volcengine/verl/tree/main/docs).
- [ ] Add unit or end-to-end test(s) to [the CI
workflow](https://github.com/volcengine/verl/tree/main/.github/workflows)
to cover all the code. If not feasible, explain why: ...
- [ ] Once your PR is ready for CI, send a message in [the `ci-request`
channel](https://verl-project.slack.com/archives/C091TCESWB1) in [the
`verl` Slack
workspace](https://join.slack.com/t/verl-project/shared_invite/zt-3855yhg8g-CTkqXu~hKojPCmo7k_yXTQ).
(If not accessible, please try [the Feishu group
(飞书群)](https://applink.larkoffice.com/client/chat/chatter/add_by_link?link_token=772jd4f1-cd91-441e-a820-498c6614126a).)

recipe/one_step_off_policy/ray_trainer.py

@@ -545,9 +545,14 @@ class OneStepOffRayTrainer(RayPPOTrainer):
                         inputs = self.tokenizer.batch_decode(batch.batch["prompts"], skip_special_tokens=True)
                         outputs = self.tokenizer.batch_decode(batch.batch["responses"], skip_special_tokens=True)
                         scores = batch.batch["token_level_scores"].sum(-1).cpu().tolist()
+                        sample_gts = [
+                            item.non_tensor_batch.get("reward_model", {}).get("ground_truth", None) for item in batch
+                        ]
+
                         self._dump_generations(
                             inputs=inputs,
                             outputs=outputs,
+                            gts=sample_gts,
                             scores=scores,
                             reward_extra_infos_dict=reward_extra_infos_dict,
                             dump_path=rollout_data_dir,

recipe/spin/spin_trainer.py

@@ -565,9 +565,13 @@ class RaySPINTrainer:
         # dump generations
         val_data_dir = self.config.trainer.get("validation_data_dir", None)
         if val_data_dir:
+            sample_gts = [
+                item.non_tensor_batch.get("reward_model", {}).get("ground_truth", None) for item in test_batch
+            ]
             self._dump_generations(
                 inputs=sample_inputs,
                 outputs=sample_outputs,
+                gts=sample_gts,
                 scores=sample_scores,
                 reward_extra_infos_dict=reward_extra_infos_dict,
                 dump_path=val_data_dir,

recipe/sppo/sppo_ray_trainer.py

@@ -313,11 +313,15 @@ class RaySPPOTrainer(RayPPOTrainer):
                         inputs = self.tokenizer.batch_decode(batch.batch["prompts"], skip_special_tokens=True)
                         outputs = self.tokenizer.batch_decode(batch.batch["responses"], skip_special_tokens=True)
                         scores = batch.batch["token_level_scores"].sum(-1).cpu().tolist()
+                        sample_gts = [
+                            item.non_tensor_batch.get("reward_model", {}).get("ground_truth", None) for item in batch
+                        ]
                         self._dump_generations(
                             inputs=inputs,
                             outputs=outputs,
                             scores=scores,
                             reward_extra_infos_dict=reward_extra_infos_dict,
+                            gts=sample_gts,
                             dump_path=rollout_data_dir,
                         )