ci: Add super nightly tests

[ashors1]

What does this PR do ?

• Adds 3 nemo gym nightly tests with environments used to post-train nemotron super v3
• Adds super model nightly tests with nemo-rl's math environment

Note that all configs are simply intended to test functionality and should not be used to test convergence

Depends on:

• feat: super-v3 recipe and docs #2829
• ci: forward SANDBOX_CONTAINER/COMMAND/ENV_VARS to ray.sub #2832

Issues

List issues that this PR closes (syntax):

Usage

• You can potentially add a usage example below

# Add a code snippet demonstrating how to use this

Before your PR is "Ready for review"

Pre checks:

• Make sure you read and followed Contributor guidelines
• Did you write any new necessary tests?
• Did you run the unit tests and functional tests locally? Visit our Testing Guide for how to run tests
• Did you add or update any necessary documentation? Visit our Document Development Guide for how to write, build and test the docs.

Additional Information

• ...

[copy-pr-bot]

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

[yfw]

Can we add mtp training to this recipe?

Suggested change

	defer_fp32_logits: true # Required when logprob_chunk_size is set
	defer_fp32_logits: true # Required when logprob_chunk_size is set
	mtp_loss_scaling_factor: 0.3
	mtp_use_repeated_layer: true
	mtp_num_layers: 5
	mtp_detach_heads: true