chaiml-mistral32-cpos1-_24046

developer_uid: NischayDnk

submission_id: chaiml-mistral32-cpos1-_24046_v2

model_name: chaiml-mistral32-cpos1-_24046_v2

model_group: ChaiML/mistral32-cpos1-g

status: torndown

timestamp: 2025-06-29T06:38:41+00:00

num_battles: 7176

num_wins: 3706

celo_rating: 1293.06

family_friendly_score: 0.526

family_friendly_standard_error: 0.007061501256815012

submission_type: basic

model_repo: ChaiML/mistral32-cpos1-go-s2-exp1-5ksamp-1-1-1

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 6

max_input_tokens: 1536

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.488034065510911, 'latency_mean': 2.048942769765854, 'latency_p50': 2.042533755302429, 'latency_p90': 2.2757126808166506}, {'batch_size': 3, 'throughput': 0.9403657230211869, 'latency_mean': 3.181388269662857, 'latency_p50': 3.1755964756011963, 'latency_p90': 3.471282696723938}, {'batch_size': 5, 'throughput': 1.186845540962199, 'latency_mean': 4.193976678848267, 'latency_p50': 4.1672362089157104, 'latency_p90': 4.73810122013092}, {'batch_size': 6, 'throughput': 1.2544438476896784, 'latency_mean': 4.751111742258072, 'latency_p50': 4.7945733070373535, 'latency_p90': 5.30805139541626}, {'batch_size': 8, 'throughput': 1.3753909625750698, 'latency_mean': 5.762405626773834, 'latency_p50': 5.76366114616394, 'latency_p90': 6.452794909477234}, {'batch_size': 10, 'throughput': 1.4410123143941072, 'latency_mean': 6.8934737646579745, 'latency_p50': 6.917060375213623, 'latency_p90': 7.833848023414612}]

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

display_name: chaiml-mistral32-cpos1-_24046_v2

is_internal_developer: False

language_model: ChaiML/mistral32-cpos1-go-s2-exp1-5ksamp-1-1-1

model_size: 24B

ranking_group: single

throughput_3p7s: 1.09

us_pacific_date: 2025-06-28

win_ratio: 0.5164437012263099

generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n', '<|im_end|>', '<|im_start|>'], 'max_input_tokens': 1536, 'best_of': 6, 'max_output_tokens': 64}

formatter: {'memory_template': '<|system|>Family Friendly{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-mistral32-cpos1-24046-v2-mkmlizer
Waiting for job on chaiml-mistral32-cpos1-24046-v2-mkmlizer to finish
chaiml-mistral32-cpos1-24046-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral32-cpos1-24046-v2-mkmlizer: ║                                                                     ║
chaiml-mistral32-cpos1-24046-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mistral32-cpos1-24046-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mistral32-cpos1-24046-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mistral32-cpos1-24046-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mistral32-cpos1-24046-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mistral32-cpos1-24046-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mistral32-cpos1-24046-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mistral32-cpos1-24046-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mistral32-cpos1-24046-v2-mkmlizer: ║                                                                     ║
chaiml-mistral32-cpos1-24046-v2-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-mistral32-cpos1-24046-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mistral32-cpos1-24046-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mistral32-cpos1-24046-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral32-cpos1-24046-v2-mkmlizer: ║                                                                     ║
chaiml-mistral32-cpos1-24046-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral32-cpos1-24046-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral32-cpos1-24046-v2-mkmlizer: ║                                                                     ║
chaiml-mistral32-cpos1-24046-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral32-cpos1-24046-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral32-cpos1-24046-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral32-cpos1-24046-v2-mkmlizer: ║                                                                     ║
chaiml-mistral32-cpos1-24046-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral32-cpos1-24046-v2-mkmlizer: Downloaded to shared memory in 61.710s
chaiml-mistral32-cpos1-24046-v2-mkmlizer: Checking if ChaiML/mistral32-cpos1-go-s2-exp1-5ksamp-1-1-1 already exists in ChaiML
chaiml-mistral32-cpos1-24046-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpgfgo4jem, device:0
chaiml-mistral32-cpos1-24046-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral32-cpos1-24046-v2-mkmlizer: quantized model in 60.049s
chaiml-mistral32-cpos1-24046-v2-mkmlizer: Processed model ChaiML/mistral32-cpos1-go-s2-exp1-5ksamp-1-1-1 in 121.760s
chaiml-mistral32-cpos1-24046-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral32-cpos1-24046-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral32-cpos1-24046-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral32-cpos1-24046-v2
chaiml-mistral32-cpos1-24046-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral32-cpos1-24046-v2/config.json
chaiml-mistral32-cpos1-24046-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral32-cpos1-24046-v2/special_tokens_map.json
chaiml-mistral32-cpos1-24046-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral32-cpos1-24046-v2/tokenizer_config.json
chaiml-mistral32-cpos1-24046-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral32-cpos1-24046-v2/tokenizer.json
chaiml-mistral32-cpos1-24046-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral32-cpos1-24046-v2/flywheel_model.1.safetensors
chaiml-mistral32-cpos1-24046-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral32-cpos1-24046-v2/flywheel_model.0.safetensors
chaiml-mistral32-cpos1-24046-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:15, 23.61it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:31, 11.46it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:19, 17.94it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:23, 14.72it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:26, 13.34it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:18, 18.17it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:20, 16.56it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:22, 15.16it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:18, 18.56it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 22.20it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:20, 15.88it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:19, 16.33it/s]
Loading 0:  11%|█         | 40/363 [00:02<00:24, 12.97it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:26, 12.17it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:19, 16.41it/s]
Loading 0:  13%|█▎        | 49/363 [00:03<00:20, 15.21it/s]
Loading 0:  14%|█▍        | 51/363 [00:03<00:22, 13.97it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:16, 18.37it/s]
Loading 0:  16%|█▌        | 58/363 [00:03<00:20, 14.81it/s]
Loading 0:  17%|█▋        | 60/363 [00:03<00:19, 15.24it/s]
Loading 0:  18%|█▊        | 65/363 [00:03<00:14, 20.10it/s]
Loading 0:  19%|█▉        | 70/363 [00:04<00:13, 21.30it/s]
Loading 0:  20%|██        | 73/363 [00:04<00:15, 19.14it/s]
Loading 0:  22%|██▏       | 79/363 [00:04<00:11, 25.15it/s]
Loading 0:  23%|██▎       | 82/363 [00:04<00:11, 24.73it/s]
Loading 0:  24%|██▎       | 86/363 [00:04<00:10, 27.25it/s]
Loading 0:  25%|██▍       | 89/363 [00:04<00:10, 27.35it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:12, 21.78it/s]
Loading 0:  27%|██▋       | 99/363 [00:05<00:08, 29.79it/s]
Loading 0:  28%|██▊       | 103/363 [00:05<00:09, 28.29it/s]
Loading 0:  29%|██▉       | 107/363 [00:05<00:10, 23.38it/s]
Loading 0:  31%|███       | 112/363 [00:05<00:09, 26.41it/s]
Loading 0:  32%|███▏      | 115/363 [00:05<00:09, 25.95it/s]
Loading 0:  33%|███▎      | 120/363 [00:06<00:08, 29.49it/s]
Loading 0:  34%|███▍      | 124/363 [00:06<00:08, 28.18it/s]
Loading 0:  36%|███▌      | 129/363 [00:06<00:07, 31.81it/s]
Loading 0:  37%|███▋      | 133/363 [00:06<00:07, 29.51it/s]
Loading 0:  38%|███▊      | 138/363 [00:06<00:06, 32.23it/s]
Loading 0:  39%|███▉      | 142/363 [00:06<00:07, 29.70it/s]
Loading 0:  40%|████      | 147/363 [00:06<00:06, 33.97it/s]
Loading 0:  42%|████▏     | 151/363 [00:07<00:08, 24.62it/s]
Loading 0:  42%|████▏     | 154/363 [00:07<00:09, 22.99it/s]
Loading 0:  43%|████▎     | 157/363 [00:07<00:08, 24.07it/s]
Loading 0:  44%|████▍     | 160/363 [00:07<00:08, 24.55it/s]
Loading 0:  45%|████▍     | 163/363 [00:07<00:07, 25.22it/s]
Loading 0:  46%|████▌     | 166/363 [00:07<00:07, 26.37it/s]
Loading 0:  47%|████▋     | 169/363 [00:07<00:07, 25.94it/s]
Loading 0:  48%|████▊     | 174/363 [00:07<00:06, 28.90it/s]
Loading 0:  49%|████▉     | 177/363 [00:08<00:07, 25.64it/s]
Loading 0:  50%|█████     | 182/363 [00:08<00:06, 27.88it/s]
Loading 0:  52%|█████▏    | 187/363 [00:08<00:07, 24.05it/s]
Loading 0:  52%|█████▏    | 190/363 [00:08<00:07, 22.55it/s]
Loading 0:  53%|█████▎    | 193/363 [00:08<00:07, 23.59it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:06, 24.10it/s]
Loading 0:  55%|█████▌    | 200/363 [00:20<00:06, 24.10it/s]
Loading 0:  55%|█████▌    | 201/363 [00:28<04:13,  1.56s/it]
Loading 0:  56%|█████▌    | 203/363 [00:29<03:28,  1.30s/it]
Loading 0:  57%|█████▋    | 208/363 [00:29<02:04,  1.25it/s]
Loading 0:  58%|█████▊    | 211/363 [00:29<01:33,  1.62it/s]
Loading 0:  59%|█████▉    | 214/363 [00:29<01:09,  2.15it/s]
Loading 0:  60%|██████    | 218/363 [00:29<00:46,  3.12it/s]
Loading 0:  61%|██████    | 221/363 [00:29<00:35,  4.04it/s]
Loading 0:  62%|██████▏   | 224/363 [00:30<00:27,  4.97it/s]
Loading 0:  63%|██████▎   | 229/363 [00:30<00:17,  7.50it/s]
Loading 0:  64%|██████▍   | 232/363 [00:30<00:14,  9.12it/s]
Loading 0:  65%|██████▌   | 237/363 [00:30<00:09, 12.80it/s]
Loading 0:  66%|██████▌   | 240/363 [00:30<00:08, 13.94it/s]
Loading 0:  68%|██████▊   | 246/363 [00:30<00:05, 19.71it/s]
Loading 0:  69%|██████▉   | 250/363 [00:30<00:05, 20.87it/s]
Loading 0:  70%|███████   | 255/363 [00:31<00:04, 24.69it/s]
Loading 0:  71%|███████▏  | 259/363 [00:31<00:04, 24.56it/s]
Loading 0:  73%|███████▎  | 264/363 [00:31<00:03, 29.25it/s]
Loading 0:  74%|███████▍  | 268/363 [00:31<00:04, 22.16it/s]
Loading 0:  75%|███████▍  | 271/363 [00:31<00:04, 21.22it/s]
Loading 0:  75%|███████▌  | 274/363 [00:31<00:03, 22.57it/s]
Loading 0:  76%|███████▋  | 277/363 [00:32<00:03, 23.14it/s]
Loading 0:  78%|███████▊  | 282/363 [00:32<00:03, 26.85it/s]
Loading 0:  79%|███████▊  | 285/363 [00:32<00:03, 23.81it/s]
Loading 0:  80%|████████  | 291/363 [00:32<00:02, 28.80it/s]
Loading 0:  81%|████████▏ | 295/363 [00:32<00:02, 27.53it/s]
Loading 0:  82%|████████▏ | 299/363 [00:32<00:02, 27.87it/s]
Loading 0:  84%|████████▎ | 304/363 [00:33<00:02, 24.48it/s]
Loading 0:  85%|████████▍ | 307/363 [00:33<00:02, 22.71it/s]
Loading 0:  85%|████████▌ | 310/363 [00:33<00:02, 23.67it/s]
Loading 0:  86%|████████▌ | 313/363 [00:33<00:02, 24.17it/s]
Loading 0:  88%|████████▊ | 318/363 [00:33<00:01, 28.13it/s]
Loading 0:  88%|████████▊ | 321/363 [00:33<00:01, 25.19it/s]
Loading 0:  90%|█████████ | 327/363 [00:33<00:01, 30.56it/s]
Loading 0:  91%|█████████ | 331/363 [00:34<00:01, 28.82it/s]
Loading 0:  92%|█████████▏| 335/363 [00:34<00:00, 30.01it/s]
Loading 0:  93%|█████████▎| 339/363 [00:34<00:00, 29.38it/s]
Loading 0:  94%|█████████▍| 342/363 [00:34<00:01, 16.56it/s]
Loading 0:  96%|█████████▌| 347/363 [00:34<00:00, 20.54it/s]
Loading 0:  96%|█████████▋| 350/363 [00:34<00:00, 21.62it/s]
Loading 0:  98%|█████████▊| 355/363 [00:35<00:00, 26.21it/s]
Loading 0:  99%|█████████▉| 359/363 [00:35<00:00, 25.63it/s]
                                                            
Job chaiml-mistral32-cpos1-24046-v2-mkmlizer completed after 156.43s with status: succeeded
Stopping job with name chaiml-mistral32-cpos1-24046-v2-mkmlizer
Pipeline stage MKMLizer completed in 157.06s
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 chaiml-mistral32-cpos1-24046-v2
Waiting for inference service chaiml-mistral32-cpos1-24046-v2 to be ready
Failed to get response for submission junhua024-chai-1-full-002_v15: HTTPConnectionPool(host='junhua024-chai-1-full-002-v15-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-mistral32-cpos1-24046-v2 ready after 171.74946212768555s
Pipeline stage MKMLDeployer completed in 172.27s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5764734745025635s
Received healthy response to inference request in 2.3249807357788086s
Received healthy response to inference request in 2.166715383529663s
Received healthy response to inference request in 2.4308276176452637s
Received healthy response to inference request in 1.8156464099884033s
5 requests
0 failed requests
5th percentile: 1.8858602046966553
10th percentile: 1.9560739994049072
20th percentile: 2.096501588821411
30th percentile: 2.198368453979492
40th percentile: 2.2616745948791506
50th percentile: 2.3249807357788086
60th percentile: 2.3673194885253905
70th percentile: 2.4096582412719725
80th percentile: 2.4599567890167235
90th percentile: 2.5182151317596437
95th percentile: 2.5473443031311036
99th percentile: 2.5706476402282714
mean time: 2.2629287242889404
Pipeline stage StressChecker completed in 12.94s
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 0.74s
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 0.79s
Shutdown handler de-registered
chaiml-mistral32-cpos1-_24046_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 3213.63s
Shutdown handler de-registered
chaiml-mistral32-cpos1-_24046_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral32-cpos1-_24046_v2 status is now torndown due to DeploymentManager action