chaiml-mistral-small-3-_70846

developer_uid: bogoconic1

submission_id: chaiml-mistral-small-3-_70846_v3

model_name: chaiml-mistral-small-3-_70846_v3

model_group: ChaiML/Mistral-Small-3.2

status: torndown

timestamp: 2025-07-21T09:41:43+00:00

num_battles: 10726

num_wins: 5130

celo_rating: 1270.2

family_friendly_score: 0.6154

family_friendly_standard_error: 0.006880157556335465

submission_type: basic

model_repo: ChaiML/Mistral-Small-3.2-24B-Instruct-2506-ChatML

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': 0.5253119146733651, 'latency_mean': 1.9035080659389496, 'latency_p50': 1.9204949140548706, 'latency_p90': 2.1137781143188477}, {'batch_size': 3, 'throughput': 1.0528090900448661, 'latency_mean': 2.835387192964554, 'latency_p50': 2.836477041244507, 'latency_p90': 3.1327450990676877}, {'batch_size': 5, 'throughput': 1.3428532078478765, 'latency_mean': 3.6993217289447786, 'latency_p50': 3.6685010194778442, 'latency_p90': 4.108320021629334}, {'batch_size': 6, 'throughput': 1.4455434452122797, 'latency_mean': 4.127349691390991, 'latency_p50': 4.126153111457825, 'latency_p90': 4.561739230155945}, {'batch_size': 8, 'throughput': 1.5673399182946701, 'latency_mean': 5.052601171731949, 'latency_p50': 5.083445191383362, 'latency_p90': 5.680460476875305}, {'batch_size': 10, 'throughput': 1.6470203889094308, 'latency_mean': 6.02125584602356, 'latency_p50': 6.0436413288116455, 'latency_p90': 6.707468509674072}]

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

display_name: chaiml-mistral-small-3-_70846_v3

is_internal_developer: False

language_model: ChaiML/Mistral-Small-3.2-24B-Instruct-2506-ChatML

model_size: 24B

ranking_group: single

throughput_3p7s: 1.35

us_pacific_date: 2025-07-21

win_ratio: 0.4782770837217975

generation_params: {'temperature': 0.6, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|im_end|>', '<|im_start|>', '\n'], '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-mistral-small-3-70846-v3-mkmlizer
Waiting for job on chaiml-mistral-small-3-70846-v3-mkmlizer to finish
chaiml-mistral-small-3-70846-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-small-3-70846-v3-mkmlizer: ║                                                                     ║
chaiml-mistral-small-3-70846-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mistral-small-3-70846-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mistral-small-3-70846-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mistral-small-3-70846-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mistral-small-3-70846-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mistral-small-3-70846-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mistral-small-3-70846-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mistral-small-3-70846-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mistral-small-3-70846-v3-mkmlizer: ║                                                                     ║
chaiml-mistral-small-3-70846-v3-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-mistral-small-3-70846-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mistral-small-3-70846-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mistral-small-3-70846-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-small-3-70846-v3-mkmlizer: ║                                                                     ║
chaiml-mistral-small-3-70846-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-small-3-70846-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-small-3-70846-v3-mkmlizer: ║                                                                     ║
chaiml-mistral-small-3-70846-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-small-3-70846-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-small-3-70846-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral-small-3-70846-v3-mkmlizer: ║                                                                     ║
chaiml-mistral-small-3-70846-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-small-3-70846-v3-mkmlizer: Downloaded to shared memory in 75.040s
chaiml-mistral-small-3-70846-v3-mkmlizer: Checking if ChaiML/Mistral-Small-3.2-24B-Instruct-2506-ChatML already exists in ChaiML
chaiml-mistral-small-3-70846-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpbndh37l4, device:0
chaiml-mistral-small-3-70846-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-small-3-70846-v3-mkmlizer: quantized model in 47.526s
chaiml-mistral-small-3-70846-v3-mkmlizer: Processed model ChaiML/Mistral-Small-3.2-24B-Instruct-2506-ChatML in 122.566s
chaiml-mistral-small-3-70846-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-small-3-70846-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-small-3-70846-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-small-3-70846-v3/nvidia
chaiml-mistral-small-3-70846-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-small-3-70846-v3/nvidia/config.json
chaiml-mistral-small-3-70846-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-small-3-70846-v3/nvidia/special_tokens_map.json
chaiml-mistral-small-3-70846-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-small-3-70846-v3/nvidia/tokenizer_config.json
chaiml-mistral-small-3-70846-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-small-3-70846-v3/nvidia/tokenizer.json
chaiml-mistral-small-3-70846-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral-small-3-70846-v3/nvidia/flywheel_model.1.safetensors
chaiml-mistral-small-3-70846-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-small-3-70846-v3/nvidia/flywheel_model.0.safetensors
chaiml-mistral-small-3-70846-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 39.52it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 31.09it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:10, 32.26it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 28.81it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:11, 30.38it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:13, 25.26it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:14, 23.29it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.27it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 26.83it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 23.70it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 29.95it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 28.03it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 28.05it/s]
Loading 0:  16%|█▋        | 59/363 [00:02<00:11, 26.34it/s]
Loading 0:  17%|█▋        | 62/363 [00:02<00:15, 19.70it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:16, 17.81it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:11, 25.20it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:10, 28.32it/s]
Loading 0:  22%|██▏       | 81/363 [00:03<00:10, 26.36it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:08, 31.57it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:09, 29.52it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 30.62it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:09, 28.66it/s]
Loading 0:  29%|██▉       | 105/363 [00:04<00:11, 23.07it/s]
Loading 0:  30%|██▉       | 108/363 [00:04<00:12, 19.90it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:10, 23.12it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:10, 23.46it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:09, 26.21it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 24.18it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:08, 29.10it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 27.68it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:08, 27.79it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:09, 23.72it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 22.14it/s]
Loading 0:  41%|████      | 148/363 [00:05<00:09, 23.30it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:09, 23.42it/s]
Loading 0:  43%|████▎     | 156/363 [00:06<00:07, 26.26it/s]
Loading 0:  44%|████▍     | 159/363 [00:06<00:08, 23.59it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 27.70it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:07, 25.05it/s]
Loading 0:  48%|████▊     | 173/363 [00:06<00:06, 27.26it/s]
Loading 0:  48%|████▊     | 176/363 [00:06<00:07, 25.47it/s]
Loading 0:  49%|████▉     | 179/363 [00:07<00:09, 19.72it/s]
Loading 0:  51%|█████     | 184/363 [00:07<00:07, 23.51it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 23.78it/s]
Loading 0:  53%|█████▎    | 192/363 [00:07<00:06, 26.65it/s]
Loading 0:  54%|█████▎    | 195/363 [00:07<00:06, 24.24it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 24.24it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<02:40,  1.01it/s]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:15,  1.18it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:24,  1.84it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:05,  2.31it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:49,  3.00it/s]
Loading 0:  60%|██████    | 219/363 [00:22<00:30,  4.65it/s]
Loading 0:  61%|██████▏   | 223/363 [00:23<00:23,  5.84it/s]
Loading 0:  62%|██████▏   | 226/363 [00:23<00:19,  7.02it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:15,  8.70it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:12, 10.62it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 14.38it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:08, 15.26it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 20.56it/s]
Loading 0:  69%|██████▊   | 249/363 [00:24<00:05, 20.10it/s]
Loading 0:  70%|██████▉   | 254/363 [00:24<00:04, 23.14it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 21.78it/s]
Loading 0:  72%|███████▏  | 262/363 [00:24<00:04, 20.96it/s]
Loading 0:  73%|███████▎  | 265/363 [00:24<00:04, 22.28it/s]
Loading 0:  74%|███████▍  | 268/363 [00:24<00:04, 23.25it/s]
Loading 0:  75%|███████▌  | 273/363 [00:24<00:03, 26.24it/s]
Loading 0:  76%|███████▌  | 276/363 [00:25<00:03, 23.98it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:02, 29.08it/s]
Loading 0:  79%|███████▉  | 286/363 [00:25<00:02, 27.63it/s]
Loading 0:  80%|███████▉  | 290/363 [00:25<00:02, 27.98it/s]
Loading 0:  81%|████████  | 293/363 [00:25<00:02, 26.34it/s]
Loading 0:  82%|████████▏ | 296/363 [00:25<00:03, 21.24it/s]
Loading 0:  83%|████████▎ | 301/363 [00:26<00:02, 24.76it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 24.83it/s]
Loading 0:  85%|████████▌ | 309/363 [00:26<00:01, 27.90it/s]
Loading 0:  86%|████████▌ | 312/363 [00:26<00:02, 25.37it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 30.01it/s]
Loading 0:  89%|████████▊ | 322/363 [00:26<00:01, 27.51it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 29.81it/s]
Loading 0:  91%|█████████ | 331/363 [00:27<00:01, 28.10it/s]
Loading 0:  93%|█████████▎| 336/363 [00:27<00:00, 32.42it/s]
Loading 0:  94%|█████████▎| 340/363 [00:27<00:01, 19.16it/s]
Loading 0:  94%|█████████▍| 343/363 [00:27<00:01, 18.02it/s]
Loading 0:  96%|█████████▌| 348/363 [00:28<00:00, 19.96it/s]
Loading 0:  98%|█████████▊| 355/363 [00:28<00:00, 26.11it/s]
Loading 0:  99%|█████████▉| 359/363 [00:28<00:00, 25.58it/s]
                                                            
Job chaiml-mistral-small-3-70846-v3-mkmlizer completed after 151.5s with status: succeeded
Stopping job with name chaiml-mistral-small-3-70846-v3-mkmlizer
Pipeline stage MKMLizer completed in 152.02s
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-mistral-small-3-70846-v3
Waiting for inference service chaiml-mistral-small-3-70846-v3 to be ready
Inference service chaiml-mistral-small-3-70846-v3 ready after 321.6960837841034s
Pipeline stage MKMLDeployer completed in 322.29s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5903608798980713s
Received healthy response to inference request in 2.140077829360962s
Received healthy response to inference request in 2.104003429412842s
Received healthy response to inference request in 3.2079906463623047s
Received healthy response to inference request in 1.9604742527008057s
5 requests
0 failed requests
5th percentile: 1.989180088043213
10th percentile: 2.01788592338562
20th percentile: 2.0752975940704346
30th percentile: 2.111218309402466
40th percentile: 2.1256480693817137
50th percentile: 2.140077829360962
60th percentile: 2.3201910495758056
70th percentile: 2.5003042697906492
80th percentile: 2.713886833190918
90th percentile: 2.960938739776611
95th percentile: 3.084464693069458
99th percentile: 3.1832854557037353
mean time: 2.400581407546997
Pipeline stage StressChecker completed in 13.51s
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 0.75s
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-mistral-small-3-_70846_v3 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral-small-3-70846-v3-profiler
Waiting for inference service chaiml-mistral-small-3-70846-v3-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 5400.09s
Shutdown handler de-registered
chaiml-mistral-small-3-_70846_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral-small-3-_70846_v3 status is now torndown due to DeploymentManager action