diff --git a/mlperf_logging/rcp_checker/training_6.1.0/rcps_qwen35_397b_grpo.json b/mlperf_logging/rcp_checker/training_6.1.0/rcps_qwen35_397b_grpo.json index 5701aa9..67df06c 100644 --- a/mlperf_logging/rcp_checker/training_6.1.0/rcps_qwen35_397b_grpo.json +++ b/mlperf_logging/rcp_checker/training_6.1.0/rcps_qwen35_397b_grpo.json @@ -1,61 +1,94 @@ { - "qwen35_397b_grpo_ref_256": - { - "Benchmark": "qwen35_397b_grpo", - "Creator": "NVIDIA", - "When": "Reference RCPs before 6.1 submission", - "Platform": "64 NVIDIA GB300 nodes", - "Precision": "BF16", - "BS": 256, - "Hyperparams": { - "opt_base_learning_rate": 1e-06, - "opt_gradient_clip_norm": 0.125, - "num_prompts_per_step": 16, - "num_generations_per_prompt": 16, - "gradient_accumulation_steps": 32 - }, - "Epochs to converge": [ - 4608, 4608, 4608, 4608, 4608, 4608 - ] + "qwen35_397b_grpo_ref_256": { + "Benchmark": "qwen35_397b_grpo", + "Creator": "NVIDIA", + "When": "Reference RCPs before 6.1 submission", + "Platform": "64 NVIDIA GB300 nodes", + "Precision": "BF16", + "BS": 256, + "Hyperparams": { + "opt_base_learning_rate": 1e-06, + "opt_gradient_clip_norm": 0.125, + "num_prompts_per_step": 16, + "num_generations_per_prompt": 16, + "gradient_accumulation_steps": 32 }, - - "qwen35_397b_grpo_ref_512": - { - "Benchmark": "qwen35_397b_grpo", - "Creator": "NVIDIA", - "When": "Reference RCPs before 6.1 submission", - "Platform": "64 NVIDIA GB300 nodes", - "Precision": "BF16", - "BS": 512, - "Hyperparams": { - "opt_base_learning_rate": 1.4142135624e-06, - "opt_gradient_clip_norm": 0.08838834765, - "num_prompts_per_step": 32, - "num_generations_per_prompt": 16, - "gradient_accumulation_steps": 64 - }, - "Epochs to converge": [ - 5120, 5120, 5120, 5120, 5120, 5120 - ] + "Epochs to converge": [ + 4608, + 4608, + 4608, + 4608, + 4608, + 4608 + ] + }, + "qwen35_397b_grpo_ref_512": { + "Benchmark": "qwen35_397b_grpo", + "Creator": "NVIDIA", + "When": "Reference RCPs before 6.1 submission", + "Platform": "64 NVIDIA GB300 nodes", + "Precision": "BF16", + "BS": 512, + "Hyperparams": { + "opt_base_learning_rate": 1.4142135624e-06, + "opt_gradient_clip_norm": 0.08838834765, + "num_prompts_per_step": 32, + "num_generations_per_prompt": 16, + "gradient_accumulation_steps": 64 }, - - "qwen35_397b_grpo_ref_1024": - { - "Benchmark": "qwen35_397b_grpo", - "Creator": "NVIDIA", - "When": "Reference RCPs before 6.1 submission", - "Platform": "64 NVIDIA GB300 nodes", - "Precision": "BF16", - "BS": 1024, - "Hyperparams": { - "opt_base_learning_rate": 2e-06, - "opt_gradient_clip_norm": 0.0625, - "num_prompts_per_step": 64, - "num_generations_per_prompt": 16, - "gradient_accumulation_steps": 128 - }, - "Epochs to converge": [ - 7168, 7168, 7168, 7168, 7168, 7168 - ] - } -} + "Epochs to converge": [ + 5120, + 5120, + 5120, + 5120, + 5120, + 5120 + ] + }, + "qwen35_397b_grpo_ref_1024": { + "Benchmark": "qwen35_397b_grpo", + "Creator": "NVIDIA", + "When": "Reference RCPs before 6.1 submission", + "Platform": "64 NVIDIA GB300 nodes", + "Precision": "BF16", + "BS": 1024, + "Hyperparams": { + "opt_base_learning_rate": 2e-06, + "opt_gradient_clip_norm": 0.0625, + "num_prompts_per_step": 64, + "num_generations_per_prompt": 16, + "gradient_accumulation_steps": 128 + }, + "Epochs to converge": [ + 7168, + 7168, + 7168, + 7168, + 7168, + 7168 + ] + }, + "qwen35_397b_grpo_ref_1152": { + "Benchmark": "qwen35_397b_grpo", + "Creator": "Google", + "When": "Reference RCPs before 6.1 submission", + "Platform": "tpu7x:4x8x8+tpu7x:2x2x1", + "Precision": "BF16", + "BS": 1152, + "Hyperparams": { + "opt_base_learning_rate": 2.1213203436e-6, + "opt_gradient_clip_norm": 0.05892556510, + "num_prompts_per_step": 72, + "num_generations_per_prompt": 16, + "gradient_accumulation_steps": 18 + }, + "Epochs to converge": [ + 6912, + 6912, + 6912, + 6912, + 6912, + 6912 + ] + } +} \ No newline at end of file