| { |
| "global_step": 5000, |
| "bucket_weights": { |
| "aime": 4897.0, |
| "capability": 8000.0, |
| "chat_singleturn": 3000.0, |
| "code_proc": 18000.0, |
| "ifeval_proc": 528.0, |
| "judge": 4500.0, |
| "long_context": 17500.0, |
| "math_proc": 27500.0, |
| "mbpp_proc": 10000.0, |
| "reasoning_proc": 6511.0, |
| "tool_use_proc": 20000.0, |
| "chat_turns": 12000.0 |
| }, |
| "bucket_rows": { |
| "aime": 4897, |
| "capability": 8000, |
| "chat_singleturn": 3000, |
| "code_proc": 18000, |
| "ifeval_proc": 528, |
| "judge": 4500, |
| "long_context": 17500, |
| "math_proc": 27500, |
| "mbpp_proc": 10000, |
| "reasoning_proc": 6511, |
| "tool_use_proc": 20000, |
| "chat_turns": 12000 |
| }, |
| "min_assistant_chars": 0, |
| "per_row_ce": true, |
| "per_row_ce_length_norm": true, |
| "length_norm_cap": 256, |
| "max_steps": 6000, |
| "warmup_steps": 600, |
| "lr": 2e-05, |
| "seed": 42, |
| "aux_coeff": 0.001, |
| "router_lr_scale": 0.1, |
| "aux_only": false, |
| "phase": "sft_mixed" |
| } |
