developer_uid: NischayDnk
submission_id: chaiml-mistral32-deepse_89261_v3
model_name: chaiml-mistral32-deepse_89261_v3
model_group: ChaiML/mistral32_deepsee
status: torndown
timestamp: 2025-07-09T13:26:19+00:00
num_battles: 7576
num_wins: 4255
celo_rating: 1338.53
family_friendly_score: 0.4858
family_friendly_standard_error: 0.0070682156164056
submission_type: basic
model_repo: ChaiML/mistral32_deepseek_cpos3_cpos21322_sfts11306_seq96_exp6
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 5
max_input_tokens: 1280
max_output_tokens: 88
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.3913046820022358, 'latency_mean': 2.5554321610927584, 'latency_p50': 2.5423972606658936, 'latency_p90': 2.7519466638565064}, {'batch_size': 3, 'throughput': 0.8434698541405561, 'latency_mean': 3.5433257961273195, 'latency_p50': 3.5410077571868896, 'latency_p90': 3.7795177936553954}, {'batch_size': 5, 'throughput': 1.1275193429007517, 'latency_mean': 4.409664194583893, 'latency_p50': 4.426709055900574, 'latency_p90': 4.90852689743042}, {'batch_size': 6, 'throughput': 1.2284903550470083, 'latency_mean': 4.857547016143799, 'latency_p50': 4.841674208641052, 'latency_p90': 5.317359185218811}, {'batch_size': 8, 'throughput': 1.3693215089727773, 'latency_mean': 5.803623285293579, 'latency_p50': 5.795018315315247, 'latency_p90': 6.398184299468994}, {'batch_size': 10, 'throughput': 1.451127091738347, 'latency_mean': 6.831424943208694, 'latency_p50': 6.792433142662048, 'latency_p90': 7.502026510238648}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-mistral32-deepse_89261_v3
ineligible_reason: max_output_tokens!=64
is_internal_developer: False
language_model: ChaiML/mistral32_deepseek_cpos3_cpos21322_sfts11306_seq96_exp6
model_size: 24B
ranking_group: single
throughput_3p7s: 0.91
us_pacific_date: 2025-07-09
win_ratio: 0.5616420274551215
generation_params: {'temperature': 0.725, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 80, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n', '<|im_end|>', '###', '<|im_start|>', '</s>'], 'max_input_tokens': 1280, 'best_of': 5, 'max_output_tokens': 88}
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-deepse-89261-v3-mkmlizer
Waiting for job on chaiml-mistral32-deepse-89261-v3-mkmlizer to finish
chaiml-mistral32-deepse-89261-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral32-deepse-89261-v3-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-89261-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mistral32-deepse-89261-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mistral32-deepse-89261-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mistral32-deepse-89261-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mistral32-deepse-89261-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mistral32-deepse-89261-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mistral32-deepse-89261-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mistral32-deepse-89261-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mistral32-deepse-89261-v3-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-89261-v3-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-mistral32-deepse-89261-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mistral32-deepse-89261-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mistral32-deepse-89261-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral32-deepse-89261-v3-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-89261-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral32-deepse-89261-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral32-deepse-89261-v3-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-89261-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral32-deepse-89261-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral32-deepse-89261-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral32-deepse-89261-v3-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-89261-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral32-deepse-89261-v3-mkmlizer: Downloaded to shared memory in 58.033s
chaiml-mistral32-deepse-89261-v3-mkmlizer: Checking if ChaiML/mistral32_deepseek_cpos3_cpos21322_sfts11306_seq96_exp6 already exists in ChaiML
chaiml-mistral32-deepse-89261-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpehdhap36, device:0
chaiml-mistral32-deepse-89261-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission chaiml-gy-exp134-dpo-ex_41829_v1: HTTPConnectionPool(host='chaiml-gy-exp134-dpo-ex-41829-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-mistral32-deepse-89261-v3-mkmlizer: quantized model in 48.683s
chaiml-mistral32-deepse-89261-v3-mkmlizer: Processed model ChaiML/mistral32_deepseek_cpos3_cpos21322_sfts11306_seq96_exp6 in 106.716s
chaiml-mistral32-deepse-89261-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral32-deepse-89261-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral32-deepse-89261-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral32-deepse-89261-v3/nvidia
chaiml-mistral32-deepse-89261-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-89261-v3/nvidia/config.json
chaiml-mistral32-deepse-89261-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-89261-v3/nvidia/special_tokens_map.json
chaiml-mistral32-deepse-89261-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-89261-v3/nvidia/tokenizer_config.json
chaiml-mistral32-deepse-89261-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-89261-v3/nvidia/tokenizer.json
chaiml-mistral32-deepse-89261-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral32-deepse-89261-v3/nvidia/flywheel_model.1.safetensors
chaiml-mistral32-deepse-89261-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral32-deepse-89261-v3/nvidia/flywheel_model.0.safetensors
chaiml-mistral32-deepse-89261-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:38,  3.10s/it]
Loading 0:   1%|▏         | 5/363 [00:06<06:01,  1.01s/it]
Loading 0:   2%|▏         | 7/363 [00:06<03:47,  1.56it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:27,  3.98it/s]
Loading 0:   4%|▍         | 16/363 [00:06<01:06,  5.24it/s]
Loading 0:   6%|▌         | 22/363 [00:07<00:42,  7.96it/s]
Loading 0:   7%|▋         | 25/363 [00:07<00:36,  9.17it/s]
Loading 0:   9%|▊         | 31/363 [00:07<00:24, 13.77it/s]
Loading 0:   9%|▉         | 34/363 [00:07<00:22, 14.55it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:16, 19.58it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:15, 20.36it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:13, 23.40it/s]
Loading 0:  14%|█▍        | 52/363 [00:08<00:14, 21.33it/s]
Loading 0:  16%|█▌        | 58/363 [00:08<00:11, 26.19it/s]
Loading 0:  17%|█▋        | 62/363 [00:08<00:15, 19.07it/s]
Loading 0:  18%|█▊        | 67/363 [00:08<00:13, 22.45it/s]
Loading 0:  19%|█▉        | 70/363 [00:08<00:13, 21.29it/s]
Loading 0:  21%|██        | 76/363 [00:09<00:11, 26.06it/s]
Loading 0:  22%|██▏       | 79/363 [00:09<00:12, 23.20it/s]
Loading 0:  23%|██▎       | 85/363 [00:09<00:09, 27.86it/s]
Loading 0:  25%|██▍       | 89/363 [00:09<00:10, 26.62it/s]
Loading 0:  26%|██▌       | 94/363 [00:09<00:09, 29.07it/s]
Loading 0:  27%|██▋       | 98/363 [00:10<00:13, 20.06it/s]
Loading 0:  28%|██▊       | 103/363 [00:10<00:11, 23.01it/s]
Loading 0:  29%|██▉       | 106/363 [00:10<00:11, 21.79it/s]
Loading 0:  31%|███       | 112/363 [00:10<00:09, 26.73it/s]
Loading 0:  32%|███▏      | 115/363 [00:10<00:10, 23.86it/s]
Loading 0:  33%|███▎      | 121/363 [00:10<00:08, 28.51it/s]
Loading 0:  34%|███▍      | 125/363 [00:11<00:08, 27.05it/s]
Loading 0:  36%|███▌      | 130/363 [00:11<00:07, 29.31it/s]
Loading 0:  37%|███▋      | 134/363 [00:11<00:08, 27.47it/s]
Loading 0:  38%|███▊      | 139/363 [00:11<00:10, 22.32it/s]
Loading 0:  39%|███▉      | 142/363 [00:11<00:10, 21.12it/s]
Loading 0:  41%|████      | 148/363 [00:12<00:08, 25.92it/s]
Loading 0:  42%|████▏     | 151/363 [00:12<00:08, 23.58it/s]
Loading 0:  43%|████▎     | 157/363 [00:12<00:07, 28.30it/s]
Loading 0:  44%|████▍     | 161/363 [00:12<00:07, 26.69it/s]
Loading 0:  46%|████▌     | 166/363 [00:12<00:06, 28.98it/s]
Loading 0:  47%|████▋     | 170/363 [00:12<00:07, 27.27it/s]
Loading 0:  48%|████▊     | 175/363 [00:12<00:06, 29.30it/s]
Loading 0:  49%|████▉     | 179/363 [00:13<00:09, 20.29it/s]
Loading 0:  51%|█████     | 184/363 [00:13<00:07, 23.51it/s]
Loading 0:  51%|█████     | 185/363 [00:28<00:07, 23.51it/s]
Loading 0:  51%|█████     | 186/363 [00:28<03:30,  1.19s/it]
Loading 0:  53%|█████▎    | 191/363 [00:28<02:12,  1.30it/s]
Loading 0:  54%|█████▎    | 195/363 [00:28<01:36,  1.75it/s]
Loading 0:  56%|█████▌    | 202/363 [00:28<00:54,  2.94it/s]
Loading 0:  57%|█████▋    | 206/363 [00:28<00:41,  3.78it/s]
Loading 0:  58%|█████▊    | 211/363 [00:29<00:28,  5.26it/s]
Loading 0:  59%|█████▉    | 215/363 [00:29<00:24,  6.09it/s]
Loading 0:  61%|██████    | 220/363 [00:29<00:17,  8.29it/s]
Loading 0:  61%|██████▏   | 223/363 [00:29<00:14,  9.36it/s]
Loading 0:  63%|██████▎   | 229/363 [00:29<00:10, 13.26it/s]
Loading 0:  64%|██████▍   | 233/363 [00:30<00:08, 14.92it/s]
Loading 0:  66%|██████▌   | 238/363 [00:30<00:06, 18.28it/s]
Loading 0:  66%|██████▋   | 241/363 [00:30<00:06, 18.13it/s]
Loading 0:  68%|██████▊   | 247/363 [00:30<00:05, 22.91it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:04, 22.88it/s]
Loading 0:  71%|███████   | 256/363 [00:31<00:05, 19.59it/s]
Loading 0:  71%|███████▏  | 259/363 [00:31<00:05, 19.06it/s]
Loading 0:  73%|███████▎  | 265/363 [00:31<00:04, 23.90it/s]
Loading 0:  74%|███████▍  | 268/363 [00:31<00:04, 22.27it/s]
Loading 0:  75%|███████▌  | 274/363 [00:31<00:03, 26.83it/s]
Loading 0:  76%|███████▋  | 277/363 [00:31<00:03, 24.15it/s]
Loading 0:  78%|███████▊  | 283/363 [00:32<00:02, 28.35it/s]
Loading 0:  79%|███████▉  | 287/363 [00:32<00:02, 26.90it/s]
Loading 0:  80%|████████  | 292/363 [00:32<00:02, 29.28it/s]
Loading 0:  82%|████████▏ | 296/363 [00:32<00:03, 20.45it/s]
Loading 0:  83%|████████▎ | 301/363 [00:32<00:02, 23.66it/s]
Loading 0:  84%|████████▎ | 304/363 [00:33<00:02, 22.26it/s]
Loading 0:  85%|████████▌ | 310/363 [00:33<00:01, 27.14it/s]
Loading 0:  87%|████████▋ | 314/363 [00:33<00:01, 25.95it/s]
Loading 0:  88%|████████▊ | 319/363 [00:33<00:01, 27.93it/s]
Loading 0:  89%|████████▊ | 322/363 [00:33<00:01, 25.19it/s]
Loading 0:  90%|█████████ | 328/363 [00:33<00:01, 29.50it/s]
Loading 0:  91%|█████████▏| 332/363 [00:34<00:01, 20.73it/s]
Loading 0:  93%|█████████▎| 337/363 [00:34<00:01, 24.02it/s]
Loading 0:  94%|█████████▎| 340/363 [00:34<00:01, 22.11it/s]
Loading 0:  95%|█████████▌| 345/363 [00:34<00:00, 27.27it/s]
Loading 0:  96%|█████████▌| 349/363 [00:34<00:00, 23.89it/s]
Loading 0:  98%|█████████▊| 355/363 [00:34<00:00, 28.48it/s]
Loading 0:  99%|█████████▉| 359/363 [00:35<00:00, 26.87it/s]
                                                            

Job chaiml-mistral32-deepse-89261-v3-mkmlizer completed after 137.07s with status: succeeded
Stopping job with name chaiml-mistral32-deepse-89261-v3-mkmlizer
Pipeline stage MKMLizer completed in 137.94s
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-mistral32-deepse-89261-v3
Waiting for inference service chaiml-mistral32-deepse-89261-v3 to be ready
Inference service chaiml-mistral32-deepse-89261-v3 ready after 191.00284624099731s
Pipeline stage MKMLDeployer completed in 191.67s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.95729923248291s
Received healthy response to inference request in 2.488046407699585s
Received healthy response to inference request in 2.6548526287078857s
Received healthy response to inference request in 2.536498785018921s
Received healthy response to inference request in 2.4589242935180664s
5 requests
0 failed requests
5th percentile: 2.46474871635437
10th percentile: 2.470573139190674
20th percentile: 2.482221984863281
30th percentile: 2.4977368831634523
40th percentile: 2.5171178340911866
50th percentile: 2.536498785018921
60th percentile: 2.583840322494507
70th percentile: 2.6311818599700927
80th percentile: 2.7153419494628905
90th percentile: 2.8363205909729006
95th percentile: 2.8968099117279054
99th percentile: 2.9452013683319094
mean time: 2.6191242694854737
Pipeline stage StressChecker completed in 14.75s
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 0.72s
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 0.67s
Shutdown handler de-registered
chaiml-mistral32-deepse_89261_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral32-deepse-89261-v3-profiler
Waiting for inference service chaiml-mistral32-deepse-89261-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3264.79s
Shutdown handler de-registered
chaiml-mistral32-deepse_89261_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral32-deepse_89261_v3 status is now torndown due to DeploymentManager action