chaiml-gy-grpo-cp624-98f_2782

developer_uid: rirv938

submission_id: chaiml-gy-grpo-cp624-98f_2782_v1

model_name: chaiml-gy-grpo-cp624-98f_2782_v1

model_group: ChaiML/gy_grpo_cp624_98f

status: torndown

timestamp: 2025-07-09T15:11:20+00:00

num_battles: 7534

num_wins: 3883

celo_rating: 1305.6

family_friendly_score: 0.49960000000000004

family_friendly_standard_error: 0.007071065549123414

submission_type: basic

model_repo: ChaiML/gy_grpo_cp624_98ff_b35_r1_merged

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 768

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5386450308494832, 'latency_mean': 1.8563904237747193, 'latency_p50': 1.867211103439331, 'latency_p90': 2.0621612787246706}, {'batch_size': 3, 'throughput': 1.120058301405073, 'latency_mean': 2.6688899874687193, 'latency_p50': 2.685004711151123, 'latency_p90': 2.9072043895721436}, {'batch_size': 5, 'throughput': 1.4853350141545816, 'latency_mean': 3.3491535079479218, 'latency_p50': 3.354788661003113, 'latency_p90': 3.7246476650238036}, {'batch_size': 6, 'throughput': 1.6126235976401269, 'latency_mean': 3.6979092156887052, 'latency_p50': 3.6905736923217773, 'latency_p90': 4.118709897994995}, {'batch_size': 8, 'throughput': 1.7878935378808105, 'latency_mean': 4.455319482088089, 'latency_p50': 4.474014043807983, 'latency_p90': 4.961746335029602}, {'batch_size': 10, 'throughput': 1.8769565092635723, 'latency_mean': 5.273346173763275, 'latency_p50': 5.295455813407898, 'latency_p90': 5.936542320251465}]

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

display_name: chaiml-gy-grpo-cp624-98f_2782_v1

is_internal_developer: True

language_model: ChaiML/gy_grpo_cp624_98ff_b35_r1_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.62

us_pacific_date: 2025-07-09

win_ratio: 0.5153968675338466

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': ['You:', '\n', '###', '</s>'], 'max_input_tokens': 768, '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 chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer
Waiting for job on chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer to finish
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: ║                                                                     ║
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: ║                                                                     ║
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: ║                                                                     ║
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: ║                                                                     ║
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: ║                                                                     ║
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: Downloaded to shared memory in 174.932s
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: Checking if ChaiML/gy_grpo_cp624_98ff_b35_r1_merged already exists in ChaiML
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkh3z1j7n, device:0
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: quantized model in 58.806s
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: Processed model ChaiML/gy_grpo_cp624_98ff_b35_r1_merged in 233.739s
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-grpo-cp624-98f-2782-v1/nvidia
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-grpo-cp624-98f-2782-v1/nvidia/config.json
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-grpo-cp624-98f-2782-v1/nvidia/special_tokens_map.json
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-grpo-cp624-98f-2782-v1/nvidia/tokenizer_config.json
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-grpo-cp624-98f-2782-v1/nvidia/tokenizer.json
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-grpo-cp624-98f-2782-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-grpo-cp624-98f-2782-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:13, 26.97it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:26, 13.29it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:17, 20.64it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:27, 12.55it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:28, 12.35it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:21, 15.78it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:26, 12.75it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:18, 18.47it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.49it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:22, 14.62it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:21, 15.29it/s]
Loading 0:  11%|█         | 40/363 [00:02<00:23, 13.56it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:24, 13.08it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:18, 17.15it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:15, 20.71it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:21, 14.29it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:22, 13.61it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:21, 14.45it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:25, 11.80it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:16, 17.92it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:13, 21.69it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:19, 14.71it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:18, 15.29it/s]
Loading 0:  21%|██        | 76/363 [00:04<00:21, 13.52it/s]
Loading 0:  21%|██▏       | 78/363 [00:05<00:22, 12.95it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:16, 17.10it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 20.40it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:19, 14.07it/s]
Loading 0:  25%|██▌       | 91/363 [00:05<00:20, 13.48it/s]
Loading 0:  26%|██▌       | 95/363 [00:06<00:15, 17.48it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:12, 21.05it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:13, 18.93it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:18, 13.93it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:19, 12.82it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:20, 12.46it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:18, 13.39it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:23, 10.87it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:14, 16.91it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 20.48it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:16, 14.28it/s]
Loading 0:  35%|███▍      | 127/363 [00:08<00:17, 13.58it/s]
Loading 0:  36%|███▌      | 129/363 [00:08<00:16, 14.30it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:20, 11.60it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 17.71it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 21.27it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:15, 14.62it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:14, 15.16it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:16, 13.33it/s]
Loading 0:  41%|████▏     | 150/363 [00:09<00:16, 12.87it/s]
Loading 0:  42%|████▏     | 154/363 [00:10<00:12, 16.84it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:09, 20.57it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:14, 14.05it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:14, 13.41it/s]
Loading 0:  45%|████▌     | 165/363 [00:10<00:13, 14.27it/s]
Loading 0:  46%|████▌     | 167/363 [00:11<00:16, 11.64it/s]
Loading 0:  47%|████▋     | 172/363 [00:11<00:10, 17.76it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:08, 21.24it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:12, 14.50it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:11, 15.33it/s]
Loading 0:  51%|█████     | 184/363 [00:12<00:13, 13.72it/s]
Loading 0:  51%|█████     | 186/363 [00:12<00:13, 13.07it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:09, 17.50it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:07, 21.52it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:11, 14.85it/s]
Loading 0:  55%|█████▌    | 200/363 [00:13<00:10, 15.60it/s]
Loading 0:  56%|█████▌    | 202/363 [00:28<04:28,  1.67s/it]
Loading 0:  56%|█████▌    | 203/363 [00:28<03:55,  1.47s/it]
Loading 0:  57%|█████▋    | 207/363 [00:28<02:12,  1.18it/s]
Loading 0:  58%|█████▊    | 210/363 [00:28<01:31,  1.67it/s]
Loading 0:  59%|█████▊    | 213/363 [00:28<01:06,  2.26it/s]
Loading 0:  59%|█████▉    | 215/363 [00:29<00:53,  2.74it/s]
Loading 0:  60%|█████▉    | 217/363 [00:29<00:43,  3.38it/s]
Loading 0:  60%|██████    | 219/363 [00:29<00:33,  4.30it/s]
Loading 0:  61%|██████    | 221/363 [00:29<00:29,  4.85it/s]
Loading 0:  62%|██████▏   | 226/363 [00:29<00:15,  8.58it/s]
Loading 0:  63%|██████▎   | 230/363 [00:29<00:11, 11.65it/s]
Loading 0:  64%|██████▍   | 233/363 [00:30<00:12, 10.34it/s]
Loading 0:  65%|██████▍   | 235/363 [00:30<00:12, 10.55it/s]
Loading 0:  65%|██████▌   | 237/363 [00:30<00:10, 11.61it/s]
Loading 0:  66%|██████▌   | 239/363 [00:30<00:12, 10.14it/s]
Loading 0:  67%|██████▋   | 244/363 [00:30<00:07, 15.53it/s]
Loading 0:  68%|██████▊   | 248/363 [00:31<00:06, 18.93it/s]
Loading 0:  69%|██████▉   | 251/363 [00:31<00:08, 13.74it/s]
Loading 0:  70%|██████▉   | 253/363 [00:31<00:08, 13.23it/s]
Loading 0:  70%|███████   | 255/363 [00:31<00:07, 13.89it/s]
Loading 0:  71%|███████   | 257/363 [00:31<00:09, 11.59it/s]
Loading 0:  72%|███████▏  | 262/363 [00:32<00:05, 17.76it/s]
Loading 0:  73%|███████▎  | 266/363 [00:32<00:04, 21.32it/s]
Loading 0:  74%|███████▍  | 269/363 [00:32<00:06, 14.68it/s]
Loading 0:  75%|███████▍  | 272/363 [00:32<00:05, 15.44it/s]
Loading 0:  76%|███████▌  | 275/363 [00:33<00:07, 12.20it/s]
Loading 0:  77%|███████▋  | 280/363 [00:33<00:04, 16.88it/s]
Loading 0:  78%|███████▊  | 284/363 [00:33<00:04, 19.61it/s]
Loading 0:  79%|███████▉  | 287/363 [00:33<00:05, 14.20it/s]
Loading 0:  80%|███████▉  | 290/363 [00:33<00:04, 14.76it/s]
Loading 0:  80%|████████  | 292/363 [00:34<00:05, 13.14it/s]
Loading 0:  81%|████████  | 294/363 [00:34<00:05, 12.80it/s]
Loading 0:  82%|████████▏ | 298/363 [00:34<00:03, 17.30it/s]
Loading 0:  83%|████████▎ | 302/363 [00:34<00:02, 21.44it/s]
Loading 0:  84%|████████▍ | 305/363 [00:34<00:03, 15.05it/s]
Loading 0:  85%|████████▍ | 308/363 [00:35<00:03, 15.74it/s]
Loading 0:  86%|████████▌ | 311/363 [00:35<00:04, 12.31it/s]
Loading 0:  87%|████████▋ | 316/363 [00:35<00:02, 17.30it/s]
Loading 0:  88%|████████▊ | 320/363 [00:35<00:02, 20.61it/s]
Loading 0:  89%|████████▉ | 323/363 [00:36<00:02, 14.95it/s]
Loading 0:  90%|████████▉ | 326/363 [00:36<00:02, 15.74it/s]
Loading 0:  91%|█████████ | 329/363 [00:36<00:02, 12.37it/s]
Loading 0:  92%|█████████▏| 334/363 [00:36<00:01, 17.32it/s]
Loading 0:  93%|█████████▎| 338/363 [00:36<00:01, 20.32it/s]
Loading 0:  94%|█████████▍| 341/363 [00:37<00:01, 14.81it/s]
Loading 0:  95%|█████████▍| 344/363 [00:37<00:01, 15.01it/s]
Loading 0:  95%|█████████▌| 346/363 [00:37<00:01, 13.59it/s]
Loading 0:  96%|█████████▌| 348/363 [00:37<00:01, 13.21it/s]
Loading 0:  97%|█████████▋| 352/363 [00:37<00:00, 17.39it/s]
Loading 0:  98%|█████████▊| 356/363 [00:37<00:00, 21.16it/s]
Loading 0:  99%|█████████▉| 359/363 [00:38<00:00, 10.69it/s]
Loading 0:  99%|█████████▉| 361/363 [00:38<00:00,  9.80it/s]
                                                            
Job chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer completed after 269.23s with status: succeeded
Stopping job with name chaiml-gy-grpo-cp624-98f-2782-v1-mkmlizer
Pipeline stage MKMLizer completed in 269.87s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-grpo-cp624-98f-2782-v1
Waiting for inference service chaiml-gy-grpo-cp624-98f-2782-v1 to be ready
Inference service chaiml-gy-grpo-cp624-98f-2782-v1 ready after 191.02955746650696s
Pipeline stage MKMLDeployer completed in 191.78s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.496217966079712s
Received healthy response to inference request in 1.888756275177002s
Received healthy response to inference request in 1.796494722366333s
Received healthy response to inference request in 1.8850855827331543s
Received healthy response to inference request in 2.074707508087158s
5 requests
0 failed requests
5th percentile: 1.8142128944396974
10th percentile: 1.8319310665130615
20th percentile: 1.86736741065979
30th percentile: 1.8858197212219239
40th percentile: 1.8872879981994628
50th percentile: 1.888756275177002
60th percentile: 1.9631367683410645
70th percentile: 2.037517261505127
80th percentile: 2.159009599685669
90th percentile: 2.3276137828826906
95th percentile: 2.4119158744812013
99th percentile: 2.4793575477600096
mean time: 2.0282524108886717
Pipeline stage StressChecker completed in 11.36s
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 0.61s
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 0.96s
Shutdown handler de-registered
chaiml-gy-grpo-cp624-98f_2782_v1 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 3286.36s
Shutdown handler de-registered
chaiml-gy-grpo-cp624-98f_2782_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-grpo-cp624-98f_2782_v1 status is now torndown due to DeploymentManager action