chaiml-groksyn-grpo-cp3_82161

developer_uid: rirv938

submission_id: chaiml-groksyn-grpo-cp3_82161_v1

model_name: chaiml-groksyn-grpo-cp3_82161_v1

model_group: ChaiML/groksyn_grpo_cp31

status: torndown

timestamp: 2025-07-09T15:13:10+00:00

num_battles: 9672

num_wins: 4941

celo_rating: 1301.0

family_friendly_score: 0.5378000000000001

family_friendly_standard_error: 0.007050832007642786

submission_type: basic

model_repo: ChaiML/groksyn_grpo_cp312_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': 0.5225172335096008, 'latency_mean': 1.913705656528473, 'latency_p50': 1.928760051727295, 'latency_p90': 2.1173604011535643}, {'batch_size': 3, 'throughput': 1.0545485265348404, 'latency_mean': 2.832076847553253, 'latency_p50': 2.8238365650177, 'latency_p90': 3.110871362686157}, {'batch_size': 5, 'throughput': 1.3503312541982109, 'latency_mean': 3.6816392910480498, 'latency_p50': 3.6307469606399536, 'latency_p90': 4.127448320388794}, {'batch_size': 6, 'throughput': 1.4405803231632832, 'latency_mean': 4.135918271541596, 'latency_p50': 4.130777359008789, 'latency_p90': 4.710872673988343}, {'batch_size': 8, 'throughput': 1.5798124724119018, 'latency_mean': 5.026998524665832, 'latency_p50': 5.012824892997742, 'latency_p90': 5.626122903823853}, {'batch_size': 10, 'throughput': 1.6569182850835862, 'latency_mean': 5.971323927640915, 'latency_p50': 6.025692462921143, 'latency_p90': 6.627571129798889}]

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

display_name: chaiml-groksyn-grpo-cp3_82161_v1

is_internal_developer: True

language_model: ChaiML/groksyn_grpo_cp312_98ff_b35_r1_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.36

us_pacific_date: 2025-07-09

win_ratio: 0.5108560794044665

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': '<|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 chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer
Waiting for job on chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer to finish
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: ║                                                                     ║
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: ║                                                                     ║
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: ║                                                                     ║
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: ║                                                                     ║
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: ║                                                                     ║
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: Downloaded to shared memory in 162.278s
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: Checking if ChaiML/groksyn_grpo_cp312_98ff_b35_r1_merged already exists in ChaiML
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpia42m23s, device:0
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: quantized model in 62.598s
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: Processed model ChaiML/groksyn_grpo_cp312_98ff_b35_r1_merged in 224.876s
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-groksyn-grpo-cp3-82161-v1/nvidia
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-groksyn-grpo-cp3-82161-v1/nvidia/config.json
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-groksyn-grpo-cp3-82161-v1/nvidia/special_tokens_map.json
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-groksyn-grpo-cp3-82161-v1/nvidia/tokenizer_config.json
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-groksyn-grpo-cp3-82161-v1/nvidia/tokenizer.json
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-groksyn-grpo-cp3-82161-v1/nvidia/flywheel_model.1.safetensors
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-groksyn-grpo-cp3-82161-v1/nvidia/flywheel_model.0.safetensors
chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 29.47it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:25, 14.22it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:16, 20.91it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:26, 13.44it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:30, 11.29it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:21, 16.15it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:22, 15.39it/s]
Loading 0:   7%|▋         | 25/363 [00:01<00:21, 15.64it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:18, 18.03it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.81it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:22, 14.37it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:21, 15.13it/s]
Loading 0:  11%|█         | 40/363 [00:02<00:23, 13.51it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:24, 12.92it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:18, 16.91it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:15, 20.66it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:21, 14.17it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:22, 13.45it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:21, 14.37it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:26, 11.62it/s]
Loading 0:  18%|█▊        | 64/363 [00:07<01:59,  2.50it/s]
Loading 0:  19%|█▊        | 68/363 [00:07<01:20,  3.69it/s]
Loading 0:  19%|█▉        | 70/363 [00:08<01:11,  4.10it/s]
Loading 0:  20%|█▉        | 72/363 [00:08<01:03,  4.58it/s]
Loading 0:  21%|██        | 75/363 [00:08<00:45,  6.29it/s]
Loading 0:  21%|██        | 77/363 [00:08<00:43,  6.59it/s]
Loading 0:  23%|██▎       | 82/363 [00:08<00:26, 10.72it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:19, 14.00it/s]
Loading 0:  25%|██▍       | 89/363 [00:09<00:22, 11.93it/s]
Loading 0:  25%|██▌       | 92/363 [00:09<00:20, 13.04it/s]
Loading 0:  26%|██▌       | 95/363 [00:09<00:17, 15.52it/s]
Loading 0:  27%|██▋       | 99/363 [00:09<00:13, 19.43it/s]
Loading 0:  28%|██▊       | 102/363 [00:09<00:14, 18.39it/s]
Loading 0:  29%|██▉       | 105/363 [00:10<00:18, 14.10it/s]
Loading 0:  29%|██▉       | 107/363 [00:10<00:19, 13.27it/s]
Loading 0:  30%|███       | 109/363 [00:10<00:19, 13.02it/s]
Loading 0:  31%|███       | 111/363 [00:10<00:17, 14.05it/s]
Loading 0:  31%|███       | 113/363 [00:10<00:21, 11.71it/s]
Loading 0:  33%|███▎      | 118/363 [00:11<00:13, 18.22it/s]
Loading 0:  34%|███▎      | 122/363 [00:11<00:14, 16.53it/s]
Loading 0:  34%|███▍      | 125/363 [00:11<00:18, 12.98it/s]
Loading 0:  35%|███▍      | 127/363 [00:11<00:18, 12.95it/s]
Loading 0:  36%|███▌      | 129/363 [00:11<00:16, 13.89it/s]
Loading 0:  36%|███▌      | 131/363 [00:12<00:19, 11.82it/s]
Loading 0:  37%|███▋      | 136/363 [00:12<00:12, 17.83it/s]
Loading 0:  39%|███▊      | 140/363 [00:12<00:10, 21.36it/s]
Loading 0:  39%|███▉      | 143/363 [00:12<00:14, 15.13it/s]
Loading 0:  40%|████      | 146/363 [00:12<00:13, 15.77it/s]
Loading 0:  41%|████      | 148/363 [00:13<00:15, 14.05it/s]
Loading 0:  41%|████▏     | 150/363 [00:13<00:15, 13.62it/s]
Loading 0:  42%|████▏     | 154/363 [00:13<00:11, 17.81it/s]
Loading 0:  44%|████▎     | 158/363 [00:13<00:09, 21.58it/s]
Loading 0:  44%|████▍     | 161/363 [00:13<00:13, 14.80it/s]
Loading 0:  45%|████▍     | 163/363 [00:14<00:14, 14.06it/s]
Loading 0:  45%|████▌     | 165/363 [00:14<00:13, 14.95it/s]
Loading 0:  46%|████▌     | 167/363 [00:14<00:16, 12.17it/s]
Loading 0:  47%|████▋     | 172/363 [00:14<00:10, 18.27it/s]
Loading 0:  48%|████▊     | 176/363 [00:14<00:08, 21.68it/s]
Loading 0:  49%|████▉     | 179/363 [00:15<00:12, 15.14it/s]
Loading 0:  50%|█████     | 182/363 [00:15<00:11, 15.87it/s]
Loading 0:  51%|█████     | 184/363 [00:15<00:12, 14.36it/s]
Loading 0:  51%|█████     | 186/363 [00:15<00:12, 13.87it/s]
Loading 0:  52%|█████▏    | 190/363 [00:15<00:09, 17.94it/s]
Loading 0:  53%|█████▎    | 194/363 [00:15<00:07, 21.48it/s]
Loading 0:  54%|█████▍    | 197/363 [00:16<00:11, 15.01it/s]
Loading 0:  55%|█████▍    | 199/363 [00:16<00:11, 14.44it/s]
Loading 0:  55%|█████▌    | 200/363 [00:32<00:11, 14.44it/s]
Loading 0:  55%|█████▌    | 201/363 [00:32<05:02,  1.87s/it]
Loading 0:  56%|█████▌    | 203/363 [00:32<03:50,  1.44s/it]
Loading 0:  57%|█████▋    | 207/363 [00:32<02:13,  1.17it/s]
Loading 0:  58%|█████▊    | 210/363 [00:32<01:32,  1.65it/s]
Loading 0:  59%|█████▊    | 213/363 [00:32<01:07,  2.23it/s]
Loading 0:  59%|█████▉    | 215/363 [00:33<00:54,  2.72it/s]
Loading 0:  60%|█████▉    | 217/363 [00:33<00:43,  3.36it/s]
Loading 0:  60%|██████    | 219/363 [00:33<00:33,  4.27it/s]
Loading 0:  61%|██████    | 221/363 [00:33<00:29,  4.88it/s]
Loading 0:  62%|██████▏   | 226/363 [00:33<00:15,  8.68it/s]
Loading 0:  63%|██████▎   | 230/363 [00:33<00:11, 11.95it/s]
Loading 0:  64%|██████▍   | 233/363 [00:34<00:12, 10.82it/s]
Loading 0:  65%|██████▌   | 236/363 [00:34<00:10, 12.13it/s]
Loading 0:  66%|██████▌   | 239/363 [00:34<00:11, 10.83it/s]
Loading 0:  67%|██████▋   | 244/363 [00:34<00:07, 15.48it/s]
Loading 0:  68%|██████▊   | 248/363 [00:34<00:06, 18.80it/s]
Loading 0:  69%|██████▉   | 251/363 [00:35<00:07, 14.60it/s]
Loading 0:  70%|██████▉   | 254/363 [00:35<00:07, 15.49it/s]
Loading 0:  71%|███████   | 257/363 [00:35<00:08, 12.64it/s]
Loading 0:  72%|███████▏  | 262/363 [00:35<00:05, 17.82it/s]
Loading 0:  73%|███████▎  | 266/363 [00:35<00:04, 21.01it/s]
Loading 0:  74%|███████▍  | 269/363 [00:36<00:06, 15.50it/s]
Loading 0:  75%|███████▍  | 272/363 [00:36<00:05, 16.42it/s]
Loading 0:  76%|███████▌  | 275/363 [00:36<00:06, 13.22it/s]
Loading 0:  77%|███████▋  | 280/363 [00:36<00:04, 18.40it/s]
Loading 0:  78%|███████▊  | 284/363 [00:37<00:03, 21.61it/s]
Loading 0:  79%|███████▉  | 287/363 [00:37<00:04, 16.06it/s]
Loading 0:  80%|███████▉  | 290/363 [00:37<00:04, 16.57it/s]
Loading 0:  81%|████████  | 293/363 [00:37<00:05, 13.27it/s]
Loading 0:  82%|████████▏ | 298/363 [00:37<00:03, 18.51it/s]
Loading 0:  83%|████████▎ | 302/363 [00:38<00:02, 21.75it/s]
Loading 0:  84%|████████▍ | 305/363 [00:38<00:03, 16.00it/s]
Loading 0:  85%|████████▍ | 308/363 [00:38<00:03, 16.77it/s]
Loading 0:  86%|████████▌ | 311/363 [00:38<00:03, 13.36it/s]
Loading 0:  87%|████████▋ | 316/363 [00:39<00:02, 18.51it/s]
Loading 0:  88%|████████▊ | 320/363 [00:39<00:01, 21.79it/s]
Loading 0:  89%|████████▉ | 323/363 [00:39<00:02, 16.03it/s]
Loading 0:  90%|████████▉ | 326/363 [00:39<00:02, 16.90it/s]
Loading 0:  91%|█████████ | 329/363 [00:39<00:02, 13.48it/s]
Loading 0:  92%|█████████▏| 334/363 [00:40<00:01, 18.65it/s]
Loading 0:  93%|█████████▎| 338/363 [00:40<00:01, 21.84it/s]
Loading 0:  94%|█████████▍| 341/363 [00:40<00:01, 15.99it/s]
Loading 0:  95%|█████████▍| 344/363 [00:40<00:01, 16.73it/s]
Loading 0:  96%|█████████▌| 347/363 [00:41<00:01, 13.36it/s]
Loading 0:  97%|█████████▋| 352/363 [00:41<00:00, 18.41it/s]
Loading 0:  98%|█████████▊| 356/363 [00:41<00:00, 21.61it/s]
Loading 0:  99%|█████████▉| 359/363 [00:41<00:00, 11.59it/s]
Loading 0: 100%|█████████▉| 362/363 [00:42<00:00, 11.77it/s]
                                                            
Job chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer completed after 248.57s with status: succeeded
Stopping job with name chaiml-groksyn-grpo-cp3-82161-v1-mkmlizer
Pipeline stage MKMLizer completed in 249.11s
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-groksyn-grpo-cp3-82161-v1
Waiting for inference service chaiml-groksyn-grpo-cp3-82161-v1 to be ready
Inference service chaiml-groksyn-grpo-cp3-82161-v1 ready after 200.69273686408997s
Pipeline stage MKMLDeployer completed in 201.23s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.370987892150879s
Received healthy response to inference request in 1.2190594673156738s
Received healthy response to inference request in 1.7986385822296143s
Received healthy response to inference request in 1.9971606731414795s
Received healthy response to inference request in 1.4374847412109375s
5 requests
0 failed requests
5th percentile: 1.2627445220947267
10th percentile: 1.3064295768737793
20th percentile: 1.3937996864318847
30th percentile: 1.5097155094146728
40th percentile: 1.6541770458221436
50th percentile: 1.7986385822296143
60th percentile: 1.8780474185943603
70th percentile: 1.9574562549591064
80th percentile: 2.0719261169433594
90th percentile: 2.221457004547119
95th percentile: 2.296222448348999
99th percentile: 2.3560348033905028
mean time: 1.7646662712097168
Pipeline stage StressChecker completed in 10.06s
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 0.80s
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 0.65s
Shutdown handler de-registered
chaiml-groksyn-grpo-cp3_82161_v1 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 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-groksyn-grpo-cp3-82161-v1-profiler
Waiting for inference service chaiml-groksyn-grpo-cp3-82161-v1-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5680.57s
Shutdown handler de-registered
chaiml-groksyn-grpo-cp3_82161_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-groksyn-grpo-cp3_82161_v1 status is now torndown due to DeploymentManager action