rirv938-groksyn-grpo-cp_55837

developer_uid: rirv938

submission_id: rirv938-groksyn-grpo-cp_55837_v3

model_name: rirv938-groksyn-grpo-cp_55837_v3

model_group: rirv938/groksyn_grpo_cp6

status: torndown

timestamp: 2025-07-07T18:21:08+00:00

num_battles: 8599

num_wins: 4459

celo_rating: 1302.29

family_friendly_score: 0.5408

family_friendly_standard_error: 0.007047486927976525

submission_type: basic

model_repo: rirv938/groksyn_grpo_cp624_98ff_b35_r1_merged

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 1536

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.4827278576609669, 'latency_mean': 2.0714377510547637, 'latency_p50': 2.065934181213379, 'latency_p90': 2.2871352672576903}, {'batch_size': 3, 'throughput': 0.9152017169877427, 'latency_mean': 3.259243586063385, 'latency_p50': 3.256124973297119, 'latency_p90': 3.5391378879547117}, {'batch_size': 5, 'throughput': 1.1346978767252367, 'latency_mean': 4.389087207317353, 'latency_p50': 4.343796491622925, 'latency_p90': 4.937947940826416}, {'batch_size': 6, 'throughput': 1.1983250013498035, 'latency_mean': 4.982198632955551, 'latency_p50': 5.023545026779175, 'latency_p90': 5.62885353565216}, {'batch_size': 8, 'throughput': 1.2764910481170868, 'latency_mean': 6.216657165288925, 'latency_p50': 6.217972636222839, 'latency_p90': 6.9008132219314575}, {'batch_size': 10, 'throughput': 1.3318999796115627, 'latency_mean': 7.434809744358063, 'latency_p50': 7.4528034925460815, 'latency_p90': 8.308098030090331}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: rirv938-groksyn-grpo-cp_55837_v3

is_internal_developer: True

language_model: rirv938/groksyn_grpo_cp624_98ff_b35_r1_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.02

us_pacific_date: 2025-07-07

win_ratio: 0.5185486684498197

generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['\n', 'You:', '</s>', '###'], 'max_input_tokens': 1536, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|system|>{bot_name}memory:{memory}\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', 'truncate_by_message': False}

Resubmit model

Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name rirv938-groksyn-grpo-cp-55837-v3-mkmlizer
Waiting for job on rirv938-groksyn-grpo-cp-55837-v3-mkmlizer to finish
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: ║                                                                     ║
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: ║                                                                     ║
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: ║  Version: 0.29.15                                                   ║
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: ║                                                                     ║
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: ║  belonging to:                                                      ║
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: ║                                                                     ║
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: ║                                                                     ║
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: Downloaded to shared memory in 112.201s
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: Checking if rirv938/groksyn_grpo_cp624_98ff_b35_r1_merged already exists in ChaiML
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpb5bnxhzh, device:0
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: quantized model in 55.620s
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: Processed model rirv938/groksyn_grpo_cp624_98ff_b35_r1_merged in 167.914s
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: creating bucket guanaco-mkml-models
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-groksyn-grpo-cp-55837-v3/nvidia
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-groksyn-grpo-cp-55837-v3/nvidia/special_tokens_map.json
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-groksyn-grpo-cp-55837-v3/nvidia/config.json
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-groksyn-grpo-cp-55837-v3/nvidia/flywheel_model.0.safetensors
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-groksyn-grpo-cp-55837-v3/nvidia/flywheel_model.1.safetensors
rirv938-groksyn-grpo-cp-55837-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 29.88it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:24, 14.49it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:15, 22.15it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:26, 13.41it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:26, 13.19it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:20, 16.72it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:24, 13.63it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 19.57it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 23.11it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:20, 15.66it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:19, 16.40it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:24, 13.02it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:17, 18.15it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 21.56it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:19, 15.52it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:19, 16.11it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:23, 12.88it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:16, 17.88it/s]
Loading 0:  19%|█▊        | 68/363 [00:03<00:13, 21.26it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:18, 15.50it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:17, 16.27it/s]
Loading 0:  21%|██        | 77/363 [00:04<00:22, 12.80it/s]
Loading 0:  23%|██▎       | 82/363 [00:04<00:15, 17.81it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 20.73it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:18, 15.03it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:17, 15.70it/s]
Loading 0:  26%|██▋       | 96/363 [00:05<00:13, 19.56it/s]
Loading 0:  28%|██▊       | 101/363 [00:05<00:12, 21.52it/s]
Loading 0:  29%|██▊       | 104/363 [00:06<00:14, 17.93it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:18, 13.87it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:18, 13.68it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:17, 14.47it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:20, 12.29it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:13, 18.55it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:10, 22.39it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:14, 15.89it/s]
Loading 0:  35%|███▌      | 128/363 [00:07<00:14, 16.74it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:18, 12.85it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 17.80it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 20.88it/s]
Loading 0:  39%|███▉      | 143/363 [00:08<00:14, 15.17it/s]
Loading 0:  40%|████      | 146/363 [00:08<00:13, 15.96it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:16, 12.88it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 17.88it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 21.13it/s]
Loading 0:  44%|████▍     | 161/363 [00:09<00:13, 15.42it/s]
Loading 0:  45%|████▌     | 164/363 [00:09<00:12, 16.15it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:15, 12.94it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 17.98it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:08, 21.37it/s]
Loading 0:  49%|████▉     | 179/363 [00:10<00:11, 15.70it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:11, 16.23it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:13, 13.08it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:09, 18.07it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:07, 21.39it/s]
Loading 0:  54%|█████▍    | 197/363 [00:11<00:10, 15.89it/s]
Loading 0:  55%|█████▌    | 200/363 [00:12<00:09, 16.64it/s]
Loading 0:  55%|█████▌    | 200/363 [00:26<00:09, 16.64it/s]
Loading 0:  55%|█████▌    | 201/363 [00:26<04:24,  1.63s/it]
Loading 0:  56%|█████▌    | 203/363 [00:26<03:23,  1.27s/it]
Loading 0:  57%|█████▋    | 207/363 [00:26<01:59,  1.31it/s]
Loading 0:  58%|█████▊    | 210/363 [00:26<01:23,  1.83it/s]
Loading 0:  59%|█████▊    | 213/363 [00:27<01:01,  2.45it/s]
Loading 0:  59%|█████▉    | 215/363 [00:27<00:49,  2.96it/s]
Loading 0:  60%|█████▉    | 217/363 [00:27<00:40,  3.64it/s]
Loading 0:  60%|██████    | 219/363 [00:27<00:31,  4.61it/s]
Loading 0:  61%|██████    | 221/363 [00:27<00:27,  5.20it/s]
Loading 0:  62%|██████▏   | 226/363 [00:27<00:14,  9.14it/s]
Loading 0:  63%|██████▎   | 230/363 [00:28<00:10, 12.27it/s]
Loading 0:  64%|██████▍   | 233/363 [00:28<00:11, 11.00it/s]
Loading 0:  65%|██████▌   | 236/363 [00:28<00:10, 12.51it/s]
Loading 0:  66%|██████▌   | 239/363 [00:28<00:11, 10.89it/s]
Loading 0:  67%|██████▋   | 244/363 [00:29<00:07, 15.45it/s]
Loading 0:  68%|██████▊   | 248/363 [00:29<00:06, 18.78it/s]
Loading 0:  69%|██████▉   | 251/363 [00:29<00:07, 14.33it/s]
Loading 0:  70%|██████▉   | 254/363 [00:29<00:07, 15.25it/s]
Loading 0:  71%|███████   | 257/363 [00:29<00:08, 12.51it/s]
Loading 0:  72%|███████▏  | 262/363 [00:30<00:05, 17.45it/s]
Loading 0:  73%|███████▎  | 266/363 [00:30<00:04, 20.60it/s]
Loading 0:  74%|███████▍  | 269/363 [00:30<00:06, 15.19it/s]
Loading 0:  75%|███████▍  | 272/363 [00:30<00:05, 16.03it/s]
Loading 0:  76%|███████▌  | 275/363 [00:31<00:06, 12.95it/s]
Loading 0:  77%|███████▋  | 280/363 [00:31<00:04, 17.86it/s]
Loading 0:  78%|███████▊  | 284/363 [00:31<00:03, 21.14it/s]
Loading 0:  79%|███████▉  | 287/363 [00:31<00:04, 15.81it/s]
Loading 0:  80%|███████▉  | 290/363 [00:31<00:04, 16.22it/s]
Loading 0:  81%|████████  | 293/363 [00:32<00:05, 13.09it/s]
Loading 0:  82%|████████▏ | 298/363 [00:32<00:03, 18.26it/s]
Loading 0:  83%|████████▎ | 302/363 [00:32<00:02, 21.70it/s]
Loading 0:  84%|████████▍ | 305/363 [00:32<00:03, 16.04it/s]
Loading 0:  85%|████████▍ | 308/363 [00:32<00:03, 16.66it/s]
Loading 0:  86%|████████▌ | 311/363 [00:33<00:03, 13.18it/s]
Loading 0:  87%|████████▋ | 316/363 [00:33<00:02, 18.33it/s]
Loading 0:  88%|████████▊ | 320/363 [00:33<00:02, 21.25it/s]
Loading 0:  89%|████████▉ | 323/363 [00:33<00:02, 15.42it/s]
Loading 0:  90%|████████▉ | 326/363 [00:33<00:02, 16.36it/s]
Loading 0:  91%|█████████ | 329/363 [00:34<00:02, 12.99it/s]
Loading 0:  92%|█████████▏| 334/363 [00:34<00:01, 18.09it/s]
Loading 0:  93%|█████████▎| 338/363 [00:34<00:01, 21.47it/s]
Loading 0:  94%|█████████▍| 341/363 [00:34<00:01, 15.87it/s]
Loading 0:  95%|█████████▍| 344/363 [00:35<00:01, 16.67it/s]
Loading 0:  96%|█████████▌| 347/363 [00:35<00:01, 13.37it/s]
Loading 0:  97%|█████████▋| 352/363 [00:35<00:00, 18.52it/s]
Loading 0:  98%|█████████▊| 356/363 [00:35<00:00, 21.98it/s]
Loading 0:  99%|█████████▉| 359/363 [00:36<00:00, 11.85it/s]
Loading 0: 100%|█████████▉| 362/363 [00:36<00:00, 11.96it/s]
                                                            
Job rirv938-groksyn-grpo-cp-55837-v3-mkmlizer completed after 198.26s with status: succeeded
Stopping job with name rirv938-groksyn-grpo-cp-55837-v3-mkmlizer
Pipeline stage MKMLizer completed in 198.82s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-groksyn-grpo-cp-55837-v3
Waiting for inference service rirv938-groksyn-grpo-cp-55837-v3 to be ready
Inference service rirv938-groksyn-grpo-cp-55837-v3 ready after 200.86965608596802s
Pipeline stage MKMLDeployer completed in 201.37s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8958752155303955s
Received healthy response to inference request in 1.943803310394287s
Received healthy response to inference request in 2.0584893226623535s
Received healthy response to inference request in 1.9684147834777832s
Received healthy response to inference request in 1.8977231979370117s
5 requests
0 failed requests
5th percentile: 1.9069392204284668
10th percentile: 1.9161552429199218
20th percentile: 1.934587287902832
30th percentile: 1.9487256050109862
40th percentile: 1.9585701942443847
50th percentile: 1.9684147834777832
60th percentile: 2.0044445991516113
70th percentile: 2.0404744148254395
80th percentile: 2.225966501235962
90th percentile: 2.5609208583831786
95th percentile: 2.728398036956787
99th percentile: 2.8623797798156736
mean time: 2.152861166000366
Pipeline stage StressChecker completed in 12.45s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.92s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.68s
Shutdown handler de-registered
rirv938-groksyn-grpo-cp_55837_v3 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-groksyn-grpo-cp-55837-v3-profiler
Waiting for inference service rirv938-groksyn-grpo-cp-55837-v3-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 3207.74s
Shutdown handler de-registered
rirv938-groksyn-grpo-cp_55837_v3 status is now inactive due to auto deactivation removed underperforming models
rirv938-groksyn-grpo-cp_55837_v3 status is now torndown due to DeploymentManager action