[WIP][PipelineRL] Normalization of new_logprobs and addition of other RL metrics

[bigximik]

Add generic denominator_batch_field to LossDef so any metric can be normalized by a pre-computed per-micro-batch scalar from the batch context, bypassing TP/SP/PP splitting entirely.

For grpo_new_logprobs: compute num_docs = (labels_per_document > 0).sum() in language_model.py before any parallel splitting, giving a true per-document average regardless of variable document lengths.

Only sequence_data_rank==0 contributes to num_docs. The runner all_reduces the denominator across the data group (which includes SDP ranks); if every SDP rank reported its own num_docs, a single document processed by SDP=2 would be counted twice, halving the metric.

Also clamp num_labels_in_seq to avoid 0/0=nan for padding segments or fully-masked documents (loss_mask=0 there so the numerator is 0 too).

Tests verify:

• num_docs counts only unmasked documents
• padding segments (pad_to_size) are excluded
• with SDP=2, only rank 0 contributes num_docs so the all_reduce SUM across SDP ranks gives the correct denominator

✨ Description

Please provide a brief summary of the changes, relevant motivation, and context.
Include any related issue numbers or links to discussions, and explain why this change is necessary.

Closes #

🔍 Type of change

Select all that apply:

• 🐛 Bug fix (non-breaking change that addresses a specific issue)
• 🚀 New feature (non-breaking change that adds functionality)
• ⚠️ Breaking change (a change that could affect existing functionality)
• 📈 Performance improvement/optimization (improves speed, memory usage, or efficiency)
• 🛠️ Code refactor (non-functional changes that improve code readability, structure, etc.)
• 📦 Dependency bump (updates dependencies, including Dockerfile or package changes)
• 📝 Documentation change (updates documentation, including new content or typo fixes)
• 🔧 Infrastructure/Build change (affects build process, CI/CD, or dependencies)

📝 Changes

List the key changes introduced in this PR:

1. Change A
2. Change B

✅ Checklist

Make sure the following tasks are completed before submitting the PR:

General

• 📜 I have read and followed the contributing guidelines.
• 🏷️ I am using a clear and descriptive PR title that summarizes the key change or feature introduced.
• 🎉 The functionality is complete, and I have tested the changes.
• 📝 I have updated the documentation if needed.
• ⚠️ The change does not introduce any new issues (e.g., runtime warnings, type checker errors, linting problems, unhandled edge cases).
• 🧩 I have commented my code, especially in hard-to-understand areas.

Dependencies and Configuration

• 🐋 I have updated the Docker configuration or dependencies, if applicable.
• 🔄 I have ensured compatibility with the existing setup after dependency changes.

Testing

• 🧪 I have added or updated tests to cover my changes.
• ✔️ New and existing tests pass locally with my changes.
• 🚦 I have tested these changes on GPUs and verified training stability.
• 🏋️ I have tested the changes on realistic training workloads, if applicable.

Performance Impact

• 📊 I have run benchmarks where applicable to evaluate the performance impact.
• ✅ The benchmarks show no performance regression.
• 🚀 The benchmarks indicate a potential performance improvement.
• ⚠️ The benchmarks indicate a potential performance degradation.
• 📈 I have provided benchmark results and detailed any performance impact below, if applicable.

📊 Performance Impact Details

If there is any impact on performance, describe it and provide benchmark results, if applicable:

---

🗒️ Additional Notes

Include any additional context, information, or considerations here, such as known issues, follow-up tasks, or backward compatibility concerns.