developer_uid: NischayDnk
submission_id: chaiml-mistral32-nis-de_96912_v1
model_name: chaiml-mistral32-nis-de_96912_v1
model_group: ChaiML/mistral32-nis-dee
status: torndown
timestamp: 2025-07-08T06:25:28+00:00
num_battles: 6324
num_wins: 3320
celo_rating: 1302.71
family_friendly_score: 0.5146
family_friendly_standard_error: 0.007068052631382989
submission_type: basic
model_repo: ChaiML/mistral32-nis-deepseek-dedup-cpos3-cpos2ft-sftexp1-1306-v1-pubpref-1-2
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': 0.5225066002864789, 'latency_mean': 1.9136433720588684, 'latency_p50': 1.9021354913711548, 'latency_p90': 2.1152214288711546}, {'batch_size': 3, 'throughput': 1.0466282575198886, 'latency_mean': 2.85555646777153, 'latency_p50': 2.8581314086914062, 'latency_p90': 3.1868157386779785}, {'batch_size': 5, 'throughput': 1.3375534710750279, 'latency_mean': 3.719125030040741, 'latency_p50': 3.6836671829223633, 'latency_p90': 4.176877737045288}, {'batch_size': 6, 'throughput': 1.423050170657542, 'latency_mean': 4.191472896337509, 'latency_p50': 4.163999319076538, 'latency_p90': 4.68986394405365}, {'batch_size': 8, 'throughput': 1.5697813555985303, 'latency_mean': 5.0643626773357395, 'latency_p50': 5.076908469200134, 'latency_p90': 5.721196293830872}, {'batch_size': 10, 'throughput': 1.6316538189336076, 'latency_mean': 6.050159033536911, 'latency_p50': 6.0797165632247925, 'latency_p90': 6.760193276405334}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-mistral32-nis-de_96912_v1
is_internal_developer: False
language_model: ChaiML/mistral32-nis-deepseek-dedup-cpos3-cpos2ft-sftexp1-1306-v1-pubpref-1-2
model_size: 24B
ranking_group: single
throughput_3p7s: 1.34
us_pacific_date: 2025-07-07
win_ratio: 0.5249841872232764
generation_params: {'temperature': 0.65, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.42, 'frequency_penalty': 0.42, 'stopping_words': ['<|im_start|>', '\n', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, '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': True}
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-nis-de-96912-v1-mkmlizer
Waiting for job on chaiml-mistral32-nis-de-96912-v1-mkmlizer to finish
chaiml-mistral32-nis-de-96912-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral32-nis-de-96912-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-nis-de-96912-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mistral32-nis-de-96912-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mistral32-nis-de-96912-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mistral32-nis-de-96912-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mistral32-nis-de-96912-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mistral32-nis-de-96912-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mistral32-nis-de-96912-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mistral32-nis-de-96912-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mistral32-nis-de-96912-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-nis-de-96912-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-mistral32-nis-de-96912-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mistral32-nis-de-96912-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mistral32-nis-de-96912-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral32-nis-de-96912-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-nis-de-96912-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral32-nis-de-96912-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral32-nis-de-96912-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-nis-de-96912-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral32-nis-de-96912-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral32-nis-de-96912-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral32-nis-de-96912-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-nis-de-96912-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral32-nis-de-96912-v1-mkmlizer: Downloaded to shared memory in 76.858s
chaiml-mistral32-nis-de-96912-v1-mkmlizer: Checking if ChaiML/mistral32-nis-deepseek-dedup-cpos3-cpos2ft-sftexp1-1306-v1-pubpref-1-2 already exists in ChaiML
chaiml-mistral32-nis-de-96912-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpf2rfv79x, device:0
chaiml-mistral32-nis-de-96912-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral32-nis-de-96912-v1-mkmlizer: quantized model in 48.631s
chaiml-mistral32-nis-de-96912-v1-mkmlizer: Processed model ChaiML/mistral32-nis-deepseek-dedup-cpos3-cpos2ft-sftexp1-1306-v1-pubpref-1-2 in 125.489s
chaiml-mistral32-nis-de-96912-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral32-nis-de-96912-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral32-nis-de-96912-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral32-nis-de-96912-v1/nvidia
chaiml-mistral32-nis-de-96912-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral32-nis-de-96912-v1/nvidia/config.json
chaiml-mistral32-nis-de-96912-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral32-nis-de-96912-v1/nvidia/special_tokens_map.json
chaiml-mistral32-nis-de-96912-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral32-nis-de-96912-v1/nvidia/tokenizer_config.json
chaiml-mistral32-nis-de-96912-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral32-nis-de-96912-v1/nvidia/flywheel_model.1.safetensors
chaiml-mistral32-nis-de-96912-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral32-nis-de-96912-v1/nvidia/flywheel_model.0.safetensors
chaiml-mistral32-nis-de-96912-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.29it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 36.43it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 33.72it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 34.01it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 30.23it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 35.11it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:15, 21.14it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 23.68it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:13, 23.75it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 26.79it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:12, 25.67it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 28.26it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.59it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:11, 26.51it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:13, 22.51it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:15, 19.29it/s]
Loading 0:  21%|██▏       | 78/363 [00:03<00:11, 24.14it/s]
Loading 0:  22%|██▏       | 81/363 [00:03<00:12, 21.88it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 24.97it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 24.91it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:13, 20.32it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 26.93it/s]
Loading 0:  28%|██▊       | 102/363 [00:04<00:10, 23.93it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 21.54it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:10, 24.71it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 22.89it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:09, 26.72it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:10, 23.97it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 28.33it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:09, 25.30it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 29.07it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:08, 25.93it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 32.38it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:09, 23.46it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:09, 22.10it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:08, 23.15it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 23.46it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.27it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 23.84it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.35it/s]
Loading 0:  49%|████▉     | 177/363 [00:06<00:07, 25.52it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 27.52it/s]
Loading 0:  51%|█████     | 186/363 [00:07<00:05, 29.79it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:08, 20.27it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 21.58it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 22.18it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:07, 22.18it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:00,  1.11s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:30,  1.07it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:30,  1.71it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:09,  2.18it/s]
Loading 0:  59%|█████▉    | 214/363 [00:23<00:52,  2.86it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:35,  4.06it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:27,  5.17it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:22,  6.10it/s]
Loading 0:  63%|██████▎   | 228/363 [00:23<00:15,  8.59it/s]
Loading 0:  64%|██████▎   | 231/363 [00:23<00:13,  9.91it/s]
Loading 0:  65%|██████▍   | 235/363 [00:23<00:09, 13.27it/s]
Loading 0:  66%|██████▌   | 238/363 [00:24<00:08, 15.33it/s]
Loading 0:  66%|██████▋   | 241/363 [00:24<00:07, 16.98it/s]
Loading 0:  67%|██████▋   | 244/363 [00:24<00:06, 19.27it/s]
Loading 0:  68%|██████▊   | 247/363 [00:24<00:05, 20.90it/s]
Loading 0:  69%|██████▉   | 250/363 [00:24<00:05, 21.83it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 25.65it/s]
Loading 0:  71%|███████   | 258/363 [00:24<00:04, 23.24it/s]
Loading 0:  73%|███████▎  | 264/363 [00:24<00:03, 30.73it/s]
Loading 0:  74%|███████▍  | 268/363 [00:25<00:04, 22.47it/s]
Loading 0:  75%|███████▍  | 271/363 [00:25<00:04, 21.35it/s]
Loading 0:  75%|███████▌  | 274/363 [00:25<00:03, 22.70it/s]
Loading 0:  76%|███████▋  | 277/363 [00:25<00:03, 23.31it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 26.54it/s]
Loading 0:  79%|███████▊  | 285/363 [00:25<00:03, 23.76it/s]
Loading 0:  80%|███████▉  | 289/363 [00:26<00:02, 26.95it/s]
Loading 0:  80%|████████  | 292/363 [00:26<00:02, 27.06it/s]
Loading 0:  81%|████████▏ | 295/363 [00:26<00:02, 26.28it/s]
Loading 0:  82%|████████▏ | 299/363 [00:26<00:02, 25.70it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 22.82it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 21.48it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 22.85it/s]
Loading 0:  86%|████████▌ | 313/363 [00:27<00:02, 23.34it/s]
Loading 0:  88%|████████▊ | 318/363 [00:27<00:01, 26.28it/s]
Loading 0:  88%|████████▊ | 321/363 [00:27<00:01, 23.64it/s]
Loading 0:  90%|█████████ | 327/363 [00:27<00:01, 28.44it/s]
Loading 0:  91%|█████████ | 330/363 [00:27<00:01, 25.29it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:01, 27.72it/s]
Loading 0:  93%|█████████▎| 338/363 [00:28<00:00, 26.12it/s]
Loading 0:  94%|█████████▍| 341/363 [00:28<00:01, 15.39it/s]
Loading 0:  96%|█████████▌| 347/363 [00:28<00:00, 20.94it/s]
Loading 0:  96%|█████████▋| 350/363 [00:28<00:00, 21.50it/s]
Loading 0:  97%|█████████▋| 353/363 [00:28<00:00, 23.11it/s]
Loading 0:  98%|█████████▊| 357/363 [00:29<00:00, 21.75it/s]
                                                            

Job chaiml-mistral32-nis-de-96912-v1-mkmlizer completed after 156.2s with status: succeeded
Stopping job with name chaiml-mistral32-nis-de-96912-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.69s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral32-nis-de-96912-v1
Waiting for inference service chaiml-mistral32-nis-de-96912-v1 to be ready
Inference service chaiml-mistral32-nis-de-96912-v1 ready after 190.7244689464569s
Pipeline stage MKMLDeployer completed in 191.14s
run pipeline stage %s
Running pipeline stage StressChecker
{"detail":"HTTPConnectionPool(host='chaiml-mistral32-nis-de-96912-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by ConnectTimeoutError(<urllib3.connection.HTTPConnection object at 0x757350513e50>, 'Connection to chaiml-mistral32-nis-de-96912-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com timed out. (connect timeout=12.0)'))"}
Received unhealthy response to inference request!
Received healthy response to inference request in 2.3137855529785156s
Received healthy response to inference request in 2.182722806930542s
Received healthy response to inference request in 2.0332682132720947s
Received healthy response to inference request in 2.245856761932373s
5 requests
1 failed requests
5th percentile: 2.063159132003784
10th percentile: 2.0930500507354735
20th percentile: 2.1528318881988526
30th percentile: 2.195349597930908
40th percentile: 2.220603179931641
50th percentile: 2.245856761932373
60th percentile: 2.27302827835083
70th percentile: 2.300199794769287
80th percentile: 4.344350862503053
90th percentile: 8.405481481552126
95th percentile: 10.43604679107666
99th percentile: 12.060499038696289
mean time: 4.248449087142944
%s, retrying in %s seconds...
Received healthy response to inference request in 2.141772508621216s
Received healthy response to inference request in 1.9834389686584473s
Received healthy response to inference request in 1.9077517986297607s
Received healthy response to inference request in 2.018519163131714s
Received healthy response to inference request in 2.0816309452056885s
5 requests
0 failed requests
5th percentile: 1.922889232635498
10th percentile: 1.9380266666412354
20th percentile: 1.96830153465271
30th percentile: 1.9904550075531007
40th percentile: 2.004487085342407
50th percentile: 2.018519163131714
60th percentile: 2.0437638759613037
70th percentile: 2.0690085887908936
80th percentile: 2.093659257888794
90th percentile: 2.1177158832550047
95th percentile: 2.1297441959381103
99th percentile: 2.1393668460845947
mean time: 2.026622676849365
Pipeline stage StressChecker completed in 33.88s
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 0.73s
Shutdown handler de-registered
chaiml-mistral32-nis-de_96912_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 3191.87s
Shutdown handler de-registered
chaiml-mistral32-nis-de_96912_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral32-nis-de_96912_v1 status is now torndown due to DeploymentManager action