ipfipfipf/Qwen3.5-4B-MathCodeSearch-SDPO-E-Step30

Qwen3.5-4B MathCodeSearch SDPO-E — Step 30

This repository contains the complete raw Megatron Core distributed checkpoint from the Qwen3.5-4B Math+Code+Search SDPO-E run at rollout step 30.

• Base model: Qwen/Qwen3.5-4B
• Training run: Weights & Biases run jzqlsb95
• Checkpoint iteration: iter_0000029 (rollout step 30; rollout indices are zero-based)
• Format: Megatron Core torch_dist distributed checkpoint
• Tensor-parallel size used for training: 4
• Total uploaded checkpoint size: 58,886,302,059 bytes (54.842 GiB)

Contents

The upload preserves the original checkpoint tree, including all 16 .distcp shards, .metadata, common.pt, metadata.json, latest_checkpointed_iteration.txt, and the rollout dataset state files for steps 10, 20, and 30.

Loading

This is not a Transformers from_pretrained checkpoint. Resume or inspect it with a compatible Megatron Core/MILES-SDPO environment and point the checkpoint loader at the repository root. The original tensor-parallel layout and the torch_dist checkpoint format should be retained when resuming.

This is an intermediate checkpoint; the run stopped after step 30 rather than completing the planned 51 rollouts.