chaiml-simp-grpo-cp312-_43926

developer_uid: rirv938

submission_id: chaiml-simp-grpo-cp312-_43926_v1

model_name: chaiml-simp-grpo-cp312-_43926_v1

model_group: ChaiML/simp_grpo_cp312_9

status: torndown

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

num_battles: 7665

num_wins: 3966

celo_rating: 1305.66

family_friendly_score: 0.49260000000000004

family_friendly_standard_error: 0.007070293346106652

submission_type: basic

model_repo: ChaiML/simp_grpo_cp312_96ff_b3_r1_12m_US_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': 0.5420097153032751, 'latency_mean': 1.8448609793186188, 'latency_p50': 1.8450320959091187, 'latency_p90': 2.0509856939315796}, {'batch_size': 3, 'throughput': 1.1381391996478896, 'latency_mean': 2.6309382450580596, 'latency_p50': 2.5936001539230347, 'latency_p90': 2.910175085067749}, {'batch_size': 5, 'throughput': 1.474145075092152, 'latency_mean': 3.388770200014114, 'latency_p50': 3.3964908123016357, 'latency_p90': 3.7942233800888063}, {'batch_size': 6, 'throughput': 1.589003886888164, 'latency_mean': 3.752223480939865, 'latency_p50': 3.778834104537964, 'latency_p90': 4.135681247711181}, {'batch_size': 8, 'throughput': 1.7741094264050365, 'latency_mean': 4.4690856111049655, 'latency_p50': 4.480126142501831, 'latency_p90': 4.9877839326858515}, {'batch_size': 10, 'throughput': 1.859635116466017, 'latency_mean': 5.319138122797012, 'latency_p50': 5.310011386871338, 'latency_p90': 5.986750292778015}]

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

display_name: chaiml-simp-grpo-cp312-_43926_v1

is_internal_developer: True

language_model: ChaiML/simp_grpo_cp312_96ff_b3_r1_12m_US_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.58

us_pacific_date: 2025-07-09

win_ratio: 0.5174168297455969

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:', '</s>', '\n'], '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-simp-grpo-cp312-43926-v1-mkmlizer
Waiting for job on chaiml-simp-grpo-cp312-43926-v1-mkmlizer to finish
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: ║                                                                     ║
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: ║                                                                     ║
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: ║                                                                     ║
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: ║                                                                     ║
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: ║                                                                     ║
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: Downloaded to shared memory in 224.652s
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: Checking if ChaiML/simp_grpo_cp312_96ff_b3_r1_12m_US_merged already exists in ChaiML
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpw_d9142_, device:0
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: quantized model in 57.563s
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: Processed model ChaiML/simp_grpo_cp312_96ff_b3_r1_12m_US_merged in 282.215s
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-simp-grpo-cp312-43926-v1/nvidia
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-simp-grpo-cp312-43926-v1/nvidia/config.json
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-simp-grpo-cp312-43926-v1/nvidia/special_tokens_map.json
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-simp-grpo-cp312-43926-v1/nvidia/tokenizer_config.json
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-simp-grpo-cp312-43926-v1/nvidia/tokenizer.json
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-simp-grpo-cp312-43926-v1/nvidia/flywheel_model.0.safetensors
chaiml-simp-grpo-cp312-43926-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:13, 27.68it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:26, 13.40it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:17, 20.32it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:27, 12.59it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:32, 10.60it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:21, 15.62it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:26, 12.82it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:18, 18.09it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.09it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:22, 14.67it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:21, 15.41it/s]
Loading 0:  11%|█         | 40/363 [00:02<00:23, 13.80it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:24, 13.17it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:18, 17.32it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:14, 20.89it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:21, 14.45it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:22, 13.78it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:20, 14.62it/s]
Loading 0:  16%|█▋        | 59/363 [00:04<00:25, 11.85it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:16, 17.68it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:13, 21.28it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:19, 14.81it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:18, 15.49it/s]
Loading 0:  21%|██        | 76/363 [00:04<00:20, 13.81it/s]
Loading 0:  21%|██▏       | 78/363 [00:05<00:21, 13.30it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:16, 17.47it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 21.17it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:18, 14.51it/s]
Loading 0:  25%|██▌       | 91/363 [00:05<00:19, 13.85it/s]
Loading 0:  26%|██▌       | 95/363 [00:06<00:14, 18.05it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:12, 21.63it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:13, 19.37it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:18, 13.81it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:19, 12.91it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:19, 12.74it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:18, 13.82it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:21, 11.39it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:13, 17.61it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 21.11it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:15, 14.98it/s]
Loading 0:  35%|███▌      | 128/363 [00:08<00:14, 15.78it/s]
Loading 0:  36%|███▌      | 130/363 [00:08<00:16, 14.06it/s]
Loading 0:  36%|███▋      | 132/363 [00:08<00:16, 13.65it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 17.98it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 21.75it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:14, 15.24it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:13, 16.03it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:15, 14.24it/s]
Loading 0:  41%|████▏     | 150/363 [00:09<00:15, 13.71it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 18.20it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 22.11it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:13, 15.49it/s]
Loading 0:  45%|████▌     | 164/363 [00:10<00:12, 16.13it/s]
Loading 0:  46%|████▌     | 166/363 [00:10<00:13, 14.39it/s]
Loading 0:  46%|████▋     | 168/363 [00:10<00:14, 13.87it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 18.04it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:08, 21.61it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:12, 15.30it/s]
Loading 0:  50%|████▉     | 181/363 [00:11<00:12, 14.26it/s]
Loading 0:  50%|█████     | 183/363 [00:11<00:11, 15.01it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:14, 11.88it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:09, 17.70it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:08, 19.54it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:11, 14.24it/s]
Loading 0:  55%|█████▍    | 199/363 [00:12<00:12, 13.46it/s]
Loading 0:  55%|█████▌    | 201/363 [00:27<04:38,  1.72s/it]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:32,  1.33s/it]
Loading 0:  57%|█████▋    | 207/363 [00:27<02:03,  1.26it/s]
Loading 0:  58%|█████▊    | 210/363 [00:27<01:26,  1.77it/s]
Loading 0:  59%|█████▊    | 213/363 [00:28<01:03,  2.37it/s]
Loading 0:  59%|█████▉    | 215/363 [00:28<00:51,  2.87it/s]
Loading 0:  60%|█████▉    | 217/363 [00:28<00:41,  3.52it/s]
Loading 0:  60%|██████    | 219/363 [00:28<00:32,  4.45it/s]
Loading 0:  61%|██████    | 221/363 [00:28<00:28,  5.02it/s]
Loading 0:  62%|██████▏   | 226/363 [00:29<00:15,  8.78it/s]
Loading 0:  63%|██████▎   | 230/363 [00:29<00:11, 11.99it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:11, 10.91it/s]
Loading 0:  65%|██████▌   | 236/363 [00:29<00:10, 12.32it/s]
Loading 0:  66%|██████▌   | 238/363 [00:29<00:10, 11.83it/s]
Loading 0:  66%|██████▌   | 240/363 [00:30<00:10, 11.92it/s]
Loading 0:  67%|██████▋   | 244/363 [00:30<00:07, 16.01it/s]
Loading 0:  68%|██████▊   | 248/363 [00:30<00:05, 19.96it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:07, 14.80it/s]
Loading 0:  70%|██████▉   | 254/363 [00:30<00:06, 15.84it/s]
Loading 0:  71%|███████   | 256/363 [00:30<00:07, 14.15it/s]
Loading 0:  71%|███████   | 258/363 [00:31<00:07, 13.60it/s]
Loading 0:  72%|███████▏  | 262/363 [00:31<00:05, 17.77it/s]
Loading 0:  73%|███████▎  | 266/363 [00:31<00:04, 21.43it/s]
Loading 0:  74%|███████▍  | 269/363 [00:31<00:06, 15.10it/s]
Loading 0:  75%|███████▍  | 271/363 [00:31<00:06, 14.31it/s]
Loading 0:  75%|███████▌  | 273/363 [00:31<00:05, 15.24it/s]
Loading 0:  76%|███████▌  | 275/363 [00:32<00:07, 12.37it/s]
Loading 0:  77%|███████▋  | 280/363 [00:32<00:04, 18.50it/s]
Loading 0:  78%|███████▊  | 284/363 [00:32<00:03, 21.87it/s]
Loading 0:  79%|███████▉  | 287/363 [00:32<00:04, 15.45it/s]
Loading 0:  80%|███████▉  | 290/363 [00:32<00:04, 16.11it/s]
Loading 0:  81%|████████  | 293/363 [00:33<00:05, 12.66it/s]
Loading 0:  82%|████████▏ | 298/363 [00:33<00:03, 17.70it/s]
Loading 0:  83%|████████▎ | 302/363 [00:33<00:02, 20.74it/s]
Loading 0:  84%|████████▍ | 305/363 [00:33<00:03, 15.40it/s]
Loading 0:  85%|████████▍ | 308/363 [00:34<00:03, 16.21it/s]
Loading 0:  86%|████████▌ | 311/363 [00:34<00:04, 12.92it/s]
Loading 0:  87%|████████▋ | 316/363 [00:34<00:02, 17.80it/s]
Loading 0:  88%|████████▊ | 320/363 [00:34<00:02, 21.12it/s]
Loading 0:  89%|████████▉ | 323/363 [00:34<00:02, 15.64it/s]
Loading 0:  90%|████████▉ | 326/363 [00:35<00:02, 16.34it/s]
Loading 0:  91%|█████████ | 329/363 [00:35<00:02, 13.06it/s]
Loading 0:  92%|█████████▏| 334/363 [00:35<00:01, 17.80it/s]
Loading 0:  93%|█████████▎| 338/363 [00:35<00:01, 20.79it/s]
Loading 0:  94%|█████████▍| 341/363 [00:36<00:01, 15.50it/s]
Loading 0:  95%|█████████▍| 344/363 [00:36<00:01, 16.10it/s]
Loading 0:  96%|█████████▌| 347/363 [00:36<00:01, 12.99it/s]
Loading 0:  97%|█████████▋| 352/363 [00:36<00:00, 17.93it/s]
Loading 0:  98%|█████████▊| 356/363 [00:36<00:00, 21.22it/s]
Loading 0:  99%|█████████▉| 359/363 [00:37<00:00, 11.80it/s]
Loading 0: 100%|█████████▉| 362/363 [00:37<00:00, 12.01it/s]
                                                            
Job chaiml-simp-grpo-cp312-43926-v1-mkmlizer completed after 310.9s with status: succeeded
Stopping job with name chaiml-simp-grpo-cp312-43926-v1-mkmlizer
Pipeline stage MKMLizer completed in 311.45s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-simp-grpo-cp312-43926-v1
Waiting for inference service chaiml-simp-grpo-cp312-43926-v1 to be ready
Inference service chaiml-simp-grpo-cp312-43926-v1 ready after 191.17898964881897s
Pipeline stage MKMLDeployer completed in 191.77s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.656944751739502s
Received healthy response to inference request in 1.9498538970947266s
Received healthy response to inference request in 1.8873238563537598s
Received healthy response to inference request in 2.0305116176605225s
Received healthy response to inference request in 2.1001131534576416s
5 requests
0 failed requests
5th percentile: 1.8998298645019531
10th percentile: 1.9123358726501465
20th percentile: 1.9373478889465332
30th percentile: 1.9659854412078857
40th percentile: 1.998248529434204
50th percentile: 2.0305116176605225
60th percentile: 2.05835223197937
70th percentile: 2.0861928462982178
80th percentile: 2.211479473114014
90th percentile: 2.4342121124267577
95th percentile: 2.5455784320831296
99th percentile: 2.6346714878082276
mean time: 2.1249494552612305
Pipeline stage StressChecker completed in 11.94s
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 0.94s
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 0.73s
Shutdown handler de-registered
chaiml-simp-grpo-cp312-_43926_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 3380.40s
Shutdown handler de-registered
chaiml-simp-grpo-cp312-_43926_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-simp-grpo-cp312-_43926_v1 status is now torndown due to DeploymentManager action