rirv938-gy-grpo-cp624-9_14536

developer_uid: rirv938

submission_id: rirv938-gy-grpo-cp624-9_14536_v2

model_name: rirv938-gy-grpo-cp624-9_14536_v2

model_group: rirv938/gy_grpo_cp624_98

status: torndown

timestamp: 2025-07-09T16:43:17+00:00

num_battles: 7349

num_wins: 3842

celo_rating: 1308.39

family_friendly_score: 0.4968

family_friendly_standard_error: 0.007070922994913747

submission_type: basic

model_repo: rirv938/gy_grpo_cp624_98ff_b35_r1_merged

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5213074092484, 'latency_mean': 1.9181557929515838, 'latency_p50': 1.9114446640014648, 'latency_p90': 2.116592621803284}, {'batch_size': 3, 'throughput': 1.054366883418295, 'latency_mean': 2.8365796387195585, 'latency_p50': 2.8654617071151733, 'latency_p90': 3.1285487174987794}, {'batch_size': 5, 'throughput': 1.3256799292973906, 'latency_mean': 3.7568923377990724, 'latency_p50': 3.763554811477661, 'latency_p90': 4.104910850524902}, {'batch_size': 6, 'throughput': 1.4335758976552266, 'latency_mean': 4.160527300834656, 'latency_p50': 4.145205020904541, 'latency_p90': 4.704953837394714}, {'batch_size': 8, 'throughput': 1.5494940961830208, 'latency_mean': 5.113656642436982, 'latency_p50': 5.1225340366363525, 'latency_p90': 5.744130611419678}, {'batch_size': 10, 'throughput': 1.6188481964925907, 'latency_mean': 6.1223632645607, 'latency_p50': 6.067640542984009, 'latency_p90': 6.923806428909302}]

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

display_name: rirv938-gy-grpo-cp624-9_14536_v2

is_internal_developer: True

language_model: rirv938/gy_grpo_cp624_98ff_b35_r1_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.32

us_pacific_date: 2025-07-09

win_ratio: 0.5227922166281127

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': ['</s>', '\n', '###', 'You:'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', '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-gy-grpo-cp624-9-14536-v2-mkmlizer
Waiting for job on rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer to finish
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: ║                                                                     ║
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: ║                                                                     ║
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: ║  Version: 0.29.15                                                   ║
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: ║                                                                     ║
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: ║  belonging to:                                                      ║
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: ║                                                                     ║
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: ║                                                                     ║
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: Downloaded to shared memory in 140.393s
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: Checking if rirv938/gy_grpo_cp624_98ff_b35_r1_merged already exists in ChaiML
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvx62_61n, device:0
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: quantized model in 57.770s
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: Processed model rirv938/gy_grpo_cp624_98ff_b35_r1_merged in 198.249s
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: creating bucket guanaco-mkml-models
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-gy-grpo-cp624-9-14536-v2/nvidia
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-gy-grpo-cp624-9-14536-v2/nvidia/config.json
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-gy-grpo-cp624-9-14536-v2/nvidia/special_tokens_map.json
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-gy-grpo-cp624-9-14536-v2/nvidia/tokenizer_config.json
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-gy-grpo-cp624-9-14536-v2/nvidia/tokenizer.json
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-gy-grpo-cp624-9-14536-v2/nvidia/flywheel_model.1.safetensors
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-gy-grpo-cp624-9-14536-v2/nvidia/flywheel_model.0.safetensors
rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:13, 26.92it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:27, 12.92it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:18, 19.43it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:27, 12.50it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:33, 10.50it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:23, 14.87it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:23, 14.55it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:24, 13.61it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:19, 17.62it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:16, 20.64it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:23, 13.82it/s]
Loading 0:  10%|█         | 37/363 [00:02<00:25, 13.01it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:23, 13.91it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:28, 11.24it/s]
Loading 0:  13%|█▎        | 46/363 [00:03<00:18, 16.72it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:15, 19.66it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:23, 13.14it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:24, 12.48it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:22, 13.45it/s]
Loading 0:  16%|█▋        | 59/363 [00:04<00:27, 11.24it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:18, 16.54it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:15, 19.61it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:21, 13.58it/s]
Loading 0:  20%|██        | 73/363 [00:05<00:21, 13.36it/s]
Loading 0:  21%|██        | 75/363 [00:05<00:20, 14.33it/s]
Loading 0:  21%|██        | 77/363 [00:05<00:25, 11.43it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:16, 17.45it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 21.25it/s]
Loading 0:  25%|██▍       | 89/363 [00:06<00:18, 14.99it/s]
Loading 0:  25%|██▌       | 92/363 [00:06<00:17, 15.67it/s]
Loading 0:  26%|██▋       | 96/363 [00:06<00:13, 19.77it/s]
Loading 0:  28%|██▊       | 101/363 [00:06<00:12, 21.76it/s]
Loading 0:  29%|██▊       | 104/363 [00:06<00:14, 18.17it/s]
Loading 0:  29%|██▉       | 107/363 [00:07<00:18, 14.07it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:18, 13.63it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:17, 14.39it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:20, 12.03it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:13, 18.25it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:10, 22.10it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:15, 15.39it/s]
Loading 0:  35%|███▌      | 128/363 [00:08<00:14, 16.12it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:18, 12.73it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 17.82it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 21.33it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:14, 15.36it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:13, 16.18it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:16, 12.65it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 17.49it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:10, 20.39it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:13, 15.02it/s]
Loading 0:  45%|████▌     | 164/363 [00:10<00:12, 15.74it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:15, 12.64it/s]
Loading 0:  47%|████▋     | 172/363 [00:11<00:10, 17.61it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:09, 20.73it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:12, 15.08it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:11, 15.83it/s]
Loading 0:  51%|█████     | 185/363 [00:12<00:14, 12.52it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:09, 17.42it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:08, 20.80it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:11, 15.09it/s]
Loading 0:  55%|█████▌    | 200/363 [00:12<00:10, 15.84it/s]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:43,  1.40s/it]
Loading 0:  57%|█████▋    | 207/363 [00:27<02:24,  1.08it/s]
Loading 0:  58%|█████▊    | 210/363 [00:27<01:45,  1.44it/s]
Loading 0:  59%|█████▊    | 213/363 [00:28<01:19,  1.88it/s]
Loading 0:  59%|█████▉    | 215/363 [00:28<01:05,  2.26it/s]
Loading 0:  60%|█████▉    | 217/363 [00:28<00:52,  2.77it/s]
Loading 0:  60%|██████    | 219/363 [00:28<00:41,  3.51it/s]
Loading 0:  61%|██████    | 221/363 [00:29<00:35,  4.05it/s]
Loading 0:  62%|██████▏   | 226/363 [00:29<00:19,  7.08it/s]
Loading 0:  63%|██████▎   | 230/363 [00:29<00:13,  9.68it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:14,  8.98it/s]
Loading 0:  65%|██████▍   | 235/363 [00:29<00:13,  9.33it/s]
Loading 0:  65%|██████▌   | 237/363 [00:30<00:11, 10.55it/s]
Loading 0:  66%|██████▌   | 239/363 [00:30<00:12,  9.58it/s]
Loading 0:  67%|██████▋   | 244/363 [00:30<00:07, 15.00it/s]
Loading 0:  68%|██████▊   | 248/363 [00:30<00:06, 18.85it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:07, 14.22it/s]
Loading 0:  70%|██████▉   | 254/363 [00:31<00:07, 15.02it/s]
Loading 0:  71%|███████   | 257/363 [00:31<00:08, 12.32it/s]
Loading 0:  72%|███████▏  | 262/363 [00:31<00:05, 17.34it/s]
Loading 0:  73%|███████▎  | 266/363 [00:31<00:04, 20.69it/s]
Loading 0:  74%|███████▍  | 269/363 [00:31<00:06, 15.07it/s]
Loading 0:  75%|███████▍  | 272/363 [00:32<00:05, 15.82it/s]
Loading 0:  76%|███████▌  | 275/363 [00:32<00:06, 12.63it/s]
Loading 0:  77%|███████▋  | 280/363 [00:32<00:04, 17.61it/s]
Loading 0:  78%|███████▊  | 284/363 [00:32<00:03, 20.54it/s]
Loading 0:  79%|███████▉  | 287/363 [00:33<00:05, 15.11it/s]
Loading 0:  80%|███████▉  | 290/363 [00:33<00:04, 15.51it/s]
Loading 0:  81%|████████  | 293/363 [00:33<00:05, 12.46it/s]
Loading 0:  82%|████████▏ | 298/363 [00:33<00:03, 17.13it/s]
Loading 0:  83%|████████▎ | 302/363 [00:33<00:02, 20.58it/s]
Loading 0:  84%|████████▍ | 305/363 [00:34<00:03, 15.27it/s]
Loading 0:  85%|████████▍ | 308/363 [00:34<00:03, 15.91it/s]
Loading 0:  86%|████████▌ | 311/363 [00:34<00:04, 12.86it/s]
Loading 0:  87%|████████▋ | 316/363 [00:34<00:02, 17.75it/s]
Loading 0:  88%|████████▊ | 320/363 [00:34<00:02, 21.05it/s]
Loading 0:  89%|████████▉ | 323/363 [00:35<00:02, 15.56it/s]
Loading 0:  90%|████████▉ | 326/363 [00:35<00:02, 16.18it/s]
Loading 0:  91%|█████████ | 329/363 [00:35<00:02, 12.88it/s]
Loading 0:  92%|█████████▏| 334/363 [00:35<00:01, 18.00it/s]
Loading 0:  93%|█████████▎| 338/363 [00:36<00:01, 21.38it/s]
Loading 0:  94%|█████████▍| 341/363 [00:36<00:01, 15.62it/s]
Loading 0:  95%|█████████▍| 344/363 [00:36<00:01, 16.37it/s]
Loading 0:  96%|█████████▌| 347/363 [00:36<00:01, 12.93it/s]
Loading 0:  97%|█████████▋| 352/363 [00:37<00:00, 17.97it/s]
Loading 0:  98%|█████████▊| 356/363 [00:37<00:00, 21.20it/s]
Loading 0:  99%|█████████▉| 359/363 [00:37<00:00, 11.67it/s]
Loading 0: 100%|█████████▉| 362/363 [00:37<00:00, 11.76it/s]
                                                            
Job rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer completed after 228.76s with status: succeeded
Stopping job with name rirv938-gy-grpo-cp624-9-14536-v2-mkmlizer
Pipeline stage MKMLizer completed in 229.51s
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-gy-grpo-cp624-9-14536-v2
Waiting for inference service rirv938-gy-grpo-cp624-9-14536-v2 to be ready
Inference service rirv938-gy-grpo-cp624-9-14536-v2 ready after 191.10854649543762s
Pipeline stage MKMLDeployer completed in 191.75s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.483285903930664s
Received healthy response to inference request in 1.8561275005340576s
Received healthy response to inference request in 1.9464361667633057s
Received healthy response to inference request in 1.4791386127471924s
5 requests
1 failed requests
5th percentile: 1.5545363903045655
10th percentile: 1.6299341678619386
20th percentile: 1.7807297229766845
30th percentile: 1.8741892337799073
40th percentile: 1.9103127002716065
50th percentile: 1.9464361667633057
60th percentile: 2.161176061630249
70th percentile: 2.375915956497192
80th percentile: 6.017269229888919
90th percentile: 13.08523588180542
95th percentile: 16.61921920776367
99th percentile: 19.446405868530274
mean time: 5.583638143539429
%s, retrying in %s seconds...
Received healthy response to inference request in 1.6475589275360107s
Received healthy response to inference request in 1.8039097785949707s
Received healthy response to inference request in 2.364633321762085s
Received healthy response to inference request in 2.035223960876465s
Received healthy response to inference request in 1.7913391590118408s
5 requests
0 failed requests
5th percentile: 1.6763149738311767
10th percentile: 1.7050710201263428
20th percentile: 1.762583112716675
30th percentile: 1.7938532829284668
40th percentile: 1.7988815307617188
50th percentile: 1.8039097785949707
60th percentile: 1.8964354515075683
70th percentile: 1.988961124420166
80th percentile: 2.101105833053589
90th percentile: 2.232869577407837
95th percentile: 2.298751449584961
99th percentile: 2.35145694732666
mean time: 1.9285330295562744
Pipeline stage StressChecker completed in 41.79s
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 0.73s
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 0.98s
Shutdown handler de-registered
rirv938-gy-grpo-cp624-9_14536_v2 status is now deployed due to DeploymentManager action
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 3379.99s
Shutdown handler de-registered
rirv938-gy-grpo-cp624-9_14536_v2 status is now inactive due to auto deactivation removed underperforming models
rirv938-gy-grpo-cp624-9_14536_v2 status is now torndown due to DeploymentManager action