developer_uid: rirv938
submission_id: chaiml-mistral32-sftexp1_2523_v4
model_name: chaiml-mistral32-sftexp1_2523_v4
model_group: ChaiML/mistral32-sftexp1
status: torndown
timestamp: 2025-07-07T15:53:12+00:00
num_battles: 9163
num_wins: 4568
celo_rating: 1289.4
family_friendly_score: 0.5409999999999999
family_friendly_standard_error: 0.007047254784666153
submission_type: basic
model_repo: ChaiML/mistral32-sftexp1-s1-groksyn30jun-full-4e-top750
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': 0.4855455244858205, 'latency_mean': 2.0593853414058687, 'latency_p50': 2.0534321069717407, 'latency_p90': 2.278879165649414}, {'batch_size': 3, 'throughput': 0.9424077327807231, 'latency_mean': 3.176190108060837, 'latency_p50': 3.172636866569519, 'latency_p90': 3.592897391319275}, {'batch_size': 5, 'throughput': 1.1867091027303096, 'latency_mean': 4.190413179397583, 'latency_p50': 4.1801087856292725, 'latency_p90': 4.67766420841217}, {'batch_size': 6, 'throughput': 1.265955118853689, 'latency_mean': 4.725724673271179, 'latency_p50': 4.6892372369766235, 'latency_p90': 5.336690545082092}, {'batch_size': 8, 'throughput': 1.3751157712988171, 'latency_mean': 5.779098551273346, 'latency_p50': 5.76723575592041, 'latency_p90': 6.570519280433655}, {'batch_size': 10, 'throughput': 1.4511814838677908, 'latency_mean': 6.83569746017456, 'latency_p50': 6.783677339553833, 'latency_p90': 7.783966660499573}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-mistral32-sftexp1_2523_v4
is_internal_developer: True
language_model: ChaiML/mistral32-sftexp1-s1-groksyn30jun-full-4e-top750
model_size: 24B
ranking_group: single
throughput_3p7s: 1.09
us_pacific_date: 2025-07-07
win_ratio: 0.498526683400633
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': ['<|im_end|>', '\n', '<|im_start|>'], 'max_input_tokens': 1536, 'best_of': 6, '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-mistral32-sftexp1-2523-v4-mkmlizer
Waiting for job on chaiml-mistral32-sftexp1-2523-v4-mkmlizer to finish
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: ║                                                                     ║
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: ║                                                                     ║
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: ║                                                                     ║
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: ║                                                                     ║
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: ║                                                                     ║
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: Downloaded to shared memory in 76.698s
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: Checking if ChaiML/mistral32-sftexp1-s1-groksyn30jun-full-4e-top750 already exists in ChaiML
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5ip_0mvd, device:0
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: quantized model in 49.789s
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: Processed model ChaiML/mistral32-sftexp1-s1-groksyn30jun-full-4e-top750 in 126.488s
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral32-sftexp1-2523-v4/nvidia
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral32-sftexp1-2523-v4/nvidia/config.json
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral32-sftexp1-2523-v4/nvidia/special_tokens_map.json
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral32-sftexp1-2523-v4/nvidia/tokenizer_config.json
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral32-sftexp1-2523-v4/nvidia/tokenizer.json
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral32-sftexp1-2523-v4/nvidia/flywheel_model.1.safetensors
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral32-sftexp1-2523-v4/nvidia/flywheel_model.0.safetensors
chaiml-mistral32-sftexp1-2523-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 38.55it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 28.08it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:12, 28.81it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:15, 23.16it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:12, 27.58it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:14, 23.12it/s]
Loading 0:   8%|▊         | 30/363 [00:01<00:09, 33.32it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:14, 22.36it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:14, 22.24it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:17, 18.85it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:13, 23.82it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:12, 24.93it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:13, 23.78it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:12, 24.43it/s]
Loading 0:  16%|█▌        | 58/363 [00:02<00:12, 25.40it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 24.29it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:12, 24.90it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:10, 27.98it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:14, 19.77it/s]
Loading 0:  21%|██        | 75/363 [00:03<00:14, 20.43it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:12, 22.08it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:13, 21.60it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 23.30it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:11, 23.82it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:14, 18.95it/s]
Loading 0:  27%|██▋       | 99/363 [00:04<00:10, 26.34it/s]
Loading 0:  28%|██▊       | 102/363 [00:04<00:10, 23.80it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 21.70it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:10, 24.93it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 22.65it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:09, 25.76it/s]
Loading 0:  33%|███▎      | 121/363 [00:05<00:09, 26.14it/s]
Loading 0:  34%|███▍      | 124/363 [00:05<00:09, 25.33it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 27.48it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:09, 24.07it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:08, 27.42it/s]
Loading 0:  38%|███▊      | 139/363 [00:05<00:08, 27.15it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 26.03it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:08, 26.98it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:07, 30.09it/s]
Loading 0:  42%|████▏     | 153/363 [00:06<00:12, 17.49it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:09, 21.03it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:09, 21.28it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:08, 22.76it/s]
Loading 0:  46%|████▌     | 166/363 [00:06<00:08, 24.00it/s]
Loading 0:  47%|████▋     | 169/363 [00:07<00:08, 23.38it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:07, 24.69it/s]
Loading 0:  48%|████▊     | 175/363 [00:07<00:07, 25.56it/s]
Loading 0:  49%|████▉     | 178/363 [00:07<00:07, 24.72it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 26.02it/s]
Loading 0:  51%|█████     | 186/363 [00:07<00:06, 28.39it/s]
Loading 0:  52%|█████▏    | 189/363 [00:08<00:10, 17.04it/s]
Loading 0:  53%|█████▎    | 193/363 [00:08<00:08, 20.69it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:07, 21.05it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:07, 22.28it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:07, 22.28it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<04:08,  1.54s/it]
Loading 0:  56%|█████▌    | 203/363 [00:23<03:13,  1.21s/it]
Loading 0:  57%|█████▋    | 208/363 [00:23<01:45,  1.47it/s]
Loading 0:  58%|█████▊    | 211/363 [00:23<01:17,  1.95it/s]
Loading 0:  59%|█████▉    | 214/363 [00:23<00:56,  2.64it/s]
Loading 0:  60%|█████▉    | 217/363 [00:23<00:40,  3.58it/s]
Loading 0:  61%|██████    | 220/363 [00:23<00:30,  4.62it/s]
Loading 0:  61%|██████▏   | 223/363 [00:24<00:22,  6.14it/s]
Loading 0:  62%|██████▏   | 226/363 [00:24<00:19,  7.15it/s]
Loading 0:  63%|██████▎   | 230/363 [00:24<00:14,  9.08it/s]
Loading 0:  65%|██████▍   | 235/363 [00:24<00:09, 13.19it/s]
Loading 0:  66%|██████▌   | 238/363 [00:24<00:08, 15.28it/s]
Loading 0:  66%|██████▋   | 241/363 [00:24<00:07, 16.54it/s]
Loading 0:  67%|██████▋   | 244/363 [00:24<00:06, 18.51it/s]
Loading 0:  68%|██████▊   | 247/363 [00:25<00:05, 20.08it/s]
Loading 0:  69%|██████▉   | 250/363 [00:25<00:05, 20.72it/s]
Loading 0:  70%|███████   | 255/363 [00:25<00:04, 24.22it/s]
Loading 0:  71%|███████   | 258/363 [00:25<00:04, 22.20it/s]
Loading 0:  72%|███████▏  | 262/363 [00:25<00:03, 25.49it/s]
Loading 0:  74%|███████▎  | 267/363 [00:25<00:04, 22.83it/s]
Loading 0:  74%|███████▍  | 270/363 [00:26<00:04, 19.79it/s]
Loading 0:  75%|███████▌  | 274/363 [00:26<00:03, 23.32it/s]
Loading 0:  76%|███████▋  | 277/363 [00:26<00:03, 23.54it/s]
Loading 0:  78%|███████▊  | 282/363 [00:26<00:03, 26.43it/s]
Loading 0:  79%|███████▊  | 285/363 [00:26<00:03, 23.80it/s]
Loading 0:  80%|███████▉  | 289/363 [00:26<00:02, 26.90it/s]
Loading 0:  80%|████████  | 292/363 [00:26<00:02, 26.69it/s]
Loading 0:  81%|████████▏ | 295/363 [00:27<00:02, 25.90it/s]
Loading 0:  82%|████████▏ | 299/363 [00:27<00:02, 25.29it/s]
Loading 0:  83%|████████▎ | 303/363 [00:27<00:02, 28.48it/s]
Loading 0:  84%|████████▍ | 306/363 [00:27<00:03, 17.45it/s]
Loading 0:  85%|████████▌ | 310/363 [00:27<00:02, 20.89it/s]
Loading 0:  86%|████████▌ | 313/363 [00:27<00:02, 21.05it/s]
Loading 0:  87%|████████▋ | 316/363 [00:28<00:02, 22.72it/s]
Loading 0:  88%|████████▊ | 319/363 [00:28<00:01, 23.92it/s]
Loading 0:  89%|████████▊ | 322/363 [00:28<00:01, 23.34it/s]
Loading 0:  90%|████████▉ | 325/363 [00:28<00:01, 24.09it/s]
Loading 0:  90%|█████████ | 328/363 [00:28<00:01, 25.17it/s]
Loading 0:  91%|█████████ | 331/363 [00:28<00:01, 24.57it/s]
Loading 0:  92%|█████████▏| 334/363 [00:28<00:01, 25.69it/s]
Loading 0:  93%|█████████▎| 337/363 [00:28<00:01, 21.52it/s]
Loading 0:  94%|█████████▎| 340/363 [00:29<00:00, 23.24it/s]
Loading 0:  94%|█████████▍| 343/363 [00:29<00:01, 13.69it/s]
Loading 0:  96%|█████████▌| 348/363 [00:29<00:00, 16.27it/s]
Loading 0:  97%|█████████▋| 353/363 [00:29<00:00, 21.09it/s]
Loading 0:  98%|█████████▊| 357/363 [00:30<00:00, 20.08it/s]
Loading 0: 100%|█████████▉| 362/363 [00:30<00:00, 25.00it/s]
                                                            

Job chaiml-mistral32-sftexp1-2523-v4-mkmlizer completed after 167.19s with status: succeeded
Stopping job with name chaiml-mistral32-sftexp1-2523-v4-mkmlizer
Pipeline stage MKMLizer completed in 167.70s
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-mistral32-sftexp1-2523-v4
Waiting for inference service chaiml-mistral32-sftexp1-2523-v4 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-mistral32-sftexp1-2523-v4 ready after 191.15035104751587s
Pipeline stage MKMLDeployer completed in 191.77s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7900726795196533s
Received healthy response to inference request in 1.2723844051361084s
Received healthy response to inference request in 1.1649720668792725s
Received healthy response to inference request in 1.4736061096191406s
Received healthy response to inference request in 1.6137831211090088s
5 requests
Failed to get response for submission blend_hunen_2025-06-23: HTTPConnectionPool(host='guanaco-model-mesh.k2.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
0 failed requests
5th percentile: 1.1864545345306396
10th percentile: 1.2079370021820068
20th percentile: 1.2509019374847412
30th percentile: 1.3126287460327148
40th percentile: 1.3931174278259277
50th percentile: 1.4736061096191406
60th percentile: 1.529676914215088
70th percentile: 1.5857477188110352
80th percentile: 1.6490410327911378
90th percentile: 1.7195568561553956
95th percentile: 1.7548147678375243
99th percentile: 1.7830210971832274
mean time: 1.4629636764526368
Pipeline stage StressChecker completed in 8.66s
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 0.69s
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 0.71s
Shutdown handler de-registered
chaiml-mistral32-sftexp1_2523_v4 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 3721.88s
Shutdown handler de-registered
chaiml-mistral32-sftexp1_2523_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral32-sftexp1_2523_v4 status is now torndown due to DeploymentManager action