developer_uid: NischayDnk
submission_id: chaiml-exp-grpo-cp312-_36146_v12
model_name: chaiml-exp-grpo-cp312-_36146_v12
model_group: ChaiML/exp_grpo_cp312_96
status: torndown
timestamp: 2025-07-18T21:43:29+00:00
num_battles: 6881
num_wins: 3677
celo_rating: 1309.44
family_friendly_score: 0.5304
family_friendly_standard_error: 0.007057986115033097
submission_type: basic
model_repo: ChaiML/exp_grpo_cp312_96ff_b6_r2_less_ff_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': 0.5189780761383518, 'latency_mean': 1.9267445600032806, 'latency_p50': 1.9217897653579712, 'latency_p90': 2.151102828979492}, {'batch_size': 3, 'throughput': 1.0446485874854867, 'latency_mean': 2.8669476187229157, 'latency_p50': 2.8566383123397827, 'latency_p90': 3.142846202850342}, {'batch_size': 5, 'throughput': 1.3320920748417924, 'latency_mean': 3.732246378660202, 'latency_p50': 3.7347347736358643, 'latency_p90': 4.18391604423523}, {'batch_size': 6, 'throughput': 1.4443272881701301, 'latency_mean': 4.130850392580032, 'latency_p50': 4.126672029495239, 'latency_p90': 4.69594898223877}, {'batch_size': 8, 'throughput': 1.5664060300304246, 'latency_mean': 5.068198227882386, 'latency_p50': 5.067690372467041, 'latency_p90': 5.739629054069519}, {'batch_size': 10, 'throughput': 1.6471111009287875, 'latency_mean': 5.99036161184311, 'latency_p50': 6.013569235801697, 'latency_p90': 6.794708466529846}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-exp-grpo-cp312-_36146_v12
is_internal_developer: False
language_model: ChaiML/exp_grpo_cp312_96ff_b6_r2_less_ff_merged
model_size: 24B
ranking_group: single
throughput_3p7s: 1.33
us_pacific_date: 2025-07-18
win_ratio: 0.5343700043598314
generation_params: {'temperature': 0.9, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['###', '</s>', 'You:', '\n'], '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 chaiml-exp-grpo-cp312-36146-v12-mkmlizer
Waiting for job on chaiml-exp-grpo-cp312-36146-v12-mkmlizer to finish
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: ║                                                                     ║
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: ║                                                                     ║
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: ║                                                                     ║
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: ║                                                                     ║
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: ║                                                                     ║
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: Downloaded to shared memory in 160.564s
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: Checking if ChaiML/exp_grpo_cp312_96ff_b6_r2_less_ff_merged already exists in ChaiML
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpe_5chzl9, device:0
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: quantized model in 55.877s
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: Processed model ChaiML/exp_grpo_cp312_96ff_b6_r2_less_ff_merged in 216.441s
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v12/nvidia
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v12/nvidia/config.json
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v12/nvidia/special_tokens_map.json
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v12/nvidia/tokenizer_config.json
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v12/nvidia/tokenizer.json
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v12/nvidia/flywheel_model.1.safetensors
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v12/nvidia/flywheel_model.0.safetensors
chaiml-exp-grpo-cp312-36146-v12-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:16, 21.19it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:19, 18.62it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:15, 22.99it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:25, 13.87it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:25, 13.62it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:19, 17.21it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:24, 14.14it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:16, 20.28it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 23.27it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:20, 16.19it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:19, 16.86it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:24, 13.37it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:16, 18.73it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 22.25it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:18, 16.36it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:18, 17.05it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:22, 13.40it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:16, 18.43it/s]
Loading 0:  19%|█▊        | 68/363 [00:03<00:13, 21.65it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:18, 15.90it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:17, 16.70it/s]
Loading 0:  21%|██        | 77/363 [00:04<00:21, 13.19it/s]
Loading 0:  23%|██▎       | 82/363 [00:04<00:15, 18.31it/s]
Loading 0:  24%|██▎       | 86/363 [00:04<00:13, 21.24it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:17, 15.76it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:16, 16.45it/s]
Loading 0:  26%|██▋       | 96/363 [00:05<00:13, 20.35it/s]
Loading 0:  28%|██▊       | 101/363 [00:05<00:11, 22.36it/s]
Loading 0:  29%|██▊       | 104/363 [00:05<00:13, 18.50it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:17, 14.50it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:18, 13.96it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:17, 14.78it/s]
Loading 0:  31%|███       | 113/363 [00:06<00:20, 12.19it/s]
Loading 0:  33%|███▎      | 118/363 [00:06<00:13, 18.12it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 21.86it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:15, 15.67it/s]
Loading 0:  35%|███▌      | 128/363 [00:07<00:14, 16.37it/s]
Loading 0:  36%|███▌      | 131/363 [00:07<00:17, 12.97it/s]
Loading 0:  37%|███▋      | 136/363 [00:07<00:12, 18.33it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 21.88it/s]
Loading 0:  39%|███▉      | 143/363 [00:08<00:13, 16.12it/s]
Loading 0:  40%|████      | 146/363 [00:08<00:12, 16.94it/s]
Loading 0:  41%|████      | 149/363 [00:08<00:15, 13.45it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 18.62it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 22.05it/s]
Loading 0:  44%|████▍     | 161/363 [00:09<00:12, 16.19it/s]
Loading 0:  45%|████▌     | 164/363 [00:09<00:11, 17.06it/s]
Loading 0:  46%|████▌     | 167/363 [00:09<00:14, 13.51it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 18.68it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:08, 21.83it/s]
Loading 0:  49%|████▉     | 179/363 [00:10<00:11, 16.07it/s]
Loading 0:  50%|█████     | 182/363 [00:10<00:10, 16.81it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:13, 13.46it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:09, 18.61it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:07, 21.95it/s]
Loading 0:  54%|█████▍    | 197/363 [00:11<00:10, 16.26it/s]
Loading 0:  55%|█████▌    | 200/363 [00:11<00:09, 17.10it/s]
Loading 0:  56%|█████▌    | 203/363 [00:26<03:38,  1.37s/it]
Loading 0:  57%|█████▋    | 207/363 [00:26<02:21,  1.10it/s]
Loading 0:  58%|█████▊    | 210/363 [00:26<01:43,  1.48it/s]
Loading 0:  59%|█████▊    | 213/363 [00:26<01:17,  1.94it/s]
Loading 0:  60%|█████▉    | 216/363 [00:27<00:58,  2.50it/s]
Loading 0:  60%|██████    | 219/363 [00:27<00:42,  3.39it/s]
Loading 0:  61%|██████    | 222/363 [00:27<00:32,  4.29it/s]
Loading 0:  62%|██████▏   | 226/363 [00:27<00:21,  6.26it/s]
Loading 0:  63%|██████▎   | 230/363 [00:27<00:15,  8.69it/s]
Loading 0:  64%|██████▍   | 233/363 [00:28<00:14,  8.73it/s]
Loading 0:  65%|██████▌   | 236/363 [00:28<00:12, 10.27it/s]
Loading 0:  66%|██████▌   | 239/363 [00:28<00:12,  9.66it/s]
Loading 0:  67%|██████▋   | 244/363 [00:28<00:08, 14.08it/s]
Loading 0:  68%|██████▊   | 248/363 [00:28<00:06, 17.48it/s]
Loading 0:  69%|██████▉   | 251/363 [00:29<00:07, 14.24it/s]
Loading 0:  70%|██████▉   | 254/363 [00:29<00:07, 15.32it/s]
Loading 0:  71%|███████   | 257/363 [00:29<00:08, 12.67it/s]
Loading 0:  72%|███████▏  | 262/363 [00:29<00:05, 17.32it/s]
Loading 0:  73%|███████▎  | 266/363 [00:29<00:04, 20.38it/s]
Loading 0:  74%|███████▍  | 269/363 [00:30<00:06, 15.57it/s]
Loading 0:  75%|███████▍  | 272/363 [00:30<00:05, 16.33it/s]
Loading 0:  76%|███████▌  | 275/363 [00:30<00:06, 13.07it/s]
Loading 0:  77%|███████▋  | 280/363 [00:30<00:04, 18.23it/s]
Loading 0:  78%|███████▊  | 284/363 [00:30<00:03, 21.28it/s]
Loading 0:  79%|███████▉  | 287/363 [00:31<00:04, 15.70it/s]
Loading 0:  80%|███████▉  | 290/363 [00:31<00:04, 16.53it/s]
Loading 0:  81%|████████  | 293/363 [00:31<00:05, 13.26it/s]
Loading 0:  82%|████████▏ | 298/363 [00:31<00:03, 18.37it/s]
Loading 0:  83%|████████▎ | 302/363 [00:31<00:02, 21.68it/s]
Loading 0:  84%|████████▍ | 305/363 [00:32<00:03, 15.89it/s]
Loading 0:  85%|████████▍ | 308/363 [00:32<00:03, 16.58it/s]
Loading 0:  86%|████████▌ | 311/363 [00:32<00:03, 13.25it/s]
Loading 0:  87%|████████▋ | 316/363 [00:32<00:02, 17.96it/s]
Loading 0:  88%|████████▊ | 320/363 [00:33<00:02, 21.02it/s]
Loading 0:  89%|████████▉ | 323/363 [00:33<00:02, 15.75it/s]
Loading 0:  90%|████████▉ | 326/363 [00:33<00:02, 16.54it/s]
Loading 0:  91%|█████████ | 329/363 [00:33<00:02, 13.36it/s]
Loading 0:  92%|█████████▏| 334/363 [00:34<00:01, 18.52it/s]
Loading 0:  93%|█████████▎| 338/363 [00:34<00:01, 21.96it/s]
Loading 0:  94%|█████████▍| 341/363 [00:34<00:01, 16.35it/s]
Loading 0:  95%|█████████▍| 344/363 [00:34<00:01, 16.97it/s]
Loading 0:  96%|█████████▌| 347/363 [00:34<00:01, 13.20it/s]
Loading 0:  97%|█████████▋| 352/363 [00:35<00:00, 18.25it/s]
Loading 0:  98%|█████████▊| 356/363 [00:35<00:00, 21.47it/s]
Loading 0:  99%|█████████▉| 359/363 [00:35<00:00, 11.87it/s]
Loading 0: 100%|█████████▉| 362/363 [00:36<00:00, 11.85it/s]
                                                            

Job chaiml-exp-grpo-cp312-36146-v12-mkmlizer completed after 252.86s with status: succeeded
Stopping job with name chaiml-exp-grpo-cp312-36146-v12-mkmlizer
Pipeline stage MKMLizer completed in 253.43s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-exp-grpo-cp312-36146-v12
Waiting for inference service chaiml-exp-grpo-cp312-36146-v12 to be ready
Inference service chaiml-exp-grpo-cp312-36146-v12 ready after 321.079149723053s
Pipeline stage MKMLDeployer completed in 321.61s
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 3.0243451595306396s
Received healthy response to inference request in 2.505662441253662s
Received healthy response to inference request in 2.2799723148345947s
Received healthy response to inference request in 1.8839824199676514s
5 requests
1 failed requests
5th percentile: 1.9631803989410401
10th percentile: 2.042378377914429
20th percentile: 2.200774335861206
30th percentile: 2.325110340118408
40th percentile: 2.4153863906860353
50th percentile: 2.505662441253662
60th percentile: 2.713135528564453
70th percentile: 2.9206086158752442
80th percentile: 6.445457029342654
90th percentile: 13.287680768966677
95th percentile: 16.708792638778682
99th percentile: 19.445682134628296
mean time: 5.964773368835449
%s, retrying in %s seconds...
Received healthy response to inference request in 2.0459256172180176s
Received healthy response to inference request in 2.2170426845550537s
Received healthy response to inference request in 1.8777310848236084s
Received healthy response to inference request in 1.782996416091919s
Received healthy response to inference request in 1.8842175006866455s
5 requests
0 failed requests
5th percentile: 1.8019433498382569
10th percentile: 1.8208902835845948
20th percentile: 1.8587841510772705
30th percentile: 1.8790283679962159
40th percentile: 1.8816229343414306
50th percentile: 1.8842175006866455
60th percentile: 1.9489007472991944
70th percentile: 2.0135839939117433
80th percentile: 2.080149030685425
90th percentile: 2.148595857620239
95th percentile: 2.1828192710876464
99th percentile: 2.2101980018615723
mean time: 1.9615826606750488
Pipeline stage StressChecker completed in 42.20s
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 0.74s
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 0.75s
Shutdown handler de-registered
chaiml-exp-grpo-cp312-_36146_v12 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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-exp-grpo-cp312-36146-v12-profiler
Waiting for inference service chaiml-exp-grpo-cp312-36146-v12-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 6364.51s
Shutdown handler de-registered
chaiml-exp-grpo-cp312-_36146_v12 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp-grpo-cp312-_36146_v12 status is now torndown due to DeploymentManager action
chaiml-exp-grpo-cp312-_36146_v12 status is now torndown due to DeploymentManager action