chaiml-mistral32-deepse_25601

developer_uid: NischayDnk

submission_id: chaiml-mistral32-deepse_25601_v1

model_name: chaiml-mistral32-deepse_25601_v1

model_group: ChaiML/mistral32_deepsee

status: torndown

timestamp: 2025-07-07T17:55:09+00:00

num_battles: 7287

num_wins: 3924

celo_rating: 1314.11

family_friendly_score: 0.48860000000000003

family_friendly_standard_error: 0.007069229661002675

submission_type: basic

model_repo: ChaiML/mistral32_deepseek_cpo_mer_exp2

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': 0.5194529044448338, 'latency_mean': 1.924999760389328, 'latency_p50': 1.9217464923858643, 'latency_p90': 2.132977819442749}, {'batch_size': 3, 'throughput': 1.0467537365142723, 'latency_mean': 2.8637954986095426, 'latency_p50': 2.858826160430908, 'latency_p90': 3.1878544330596923}, {'batch_size': 5, 'throughput': 1.3324227706548917, 'latency_mean': 3.7389801931381226, 'latency_p50': 3.741175413131714, 'latency_p90': 4.177128314971924}, {'batch_size': 6, 'throughput': 1.4271767412503866, 'latency_mean': 4.1554566812515255, 'latency_p50': 4.115995526313782, 'latency_p90': 4.655203580856323}, {'batch_size': 8, 'throughput': 1.5549681965968332, 'latency_mean': 5.106391314268112, 'latency_p50': 5.040463209152222, 'latency_p90': 5.723244404792785}, {'batch_size': 10, 'throughput': 1.6422083485164114, 'latency_mean': 6.036243302822113, 'latency_p50': 6.0959566831588745, 'latency_p90': 6.761679911613464}]

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

display_name: chaiml-mistral32-deepse_25601_v1

is_internal_developer: False

language_model: ChaiML/mistral32_deepseek_cpo_mer_exp2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.33

us_pacific_date: 2025-07-07

win_ratio: 0.5384932070811034

generation_params: {'temperature': 0.55, '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': 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-deepse-25601-v1-mkmlizer
Waiting for job on chaiml-mistral32-deepse-25601-v1-mkmlizer to finish
chaiml-mistral32-deepse-25601-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral32-deepse-25601-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-25601-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mistral32-deepse-25601-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mistral32-deepse-25601-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mistral32-deepse-25601-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mistral32-deepse-25601-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mistral32-deepse-25601-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mistral32-deepse-25601-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mistral32-deepse-25601-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mistral32-deepse-25601-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-25601-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-mistral32-deepse-25601-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mistral32-deepse-25601-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mistral32-deepse-25601-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral32-deepse-25601-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-25601-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral32-deepse-25601-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral32-deepse-25601-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-25601-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral32-deepse-25601-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral32-deepse-25601-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral32-deepse-25601-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-25601-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral32-deepse-25601-v1-mkmlizer: Downloaded to shared memory in 78.350s
chaiml-mistral32-deepse-25601-v1-mkmlizer: Checking if ChaiML/mistral32_deepseek_cpo_mer_exp2 already exists in ChaiML
chaiml-mistral32-deepse-25601-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmprfgcyika, device:0
chaiml-mistral32-deepse-25601-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral32-deepse-25601-v1-mkmlizer: quantized model in 47.089s
chaiml-mistral32-deepse-25601-v1-mkmlizer: Processed model ChaiML/mistral32_deepseek_cpo_mer_exp2 in 125.439s
chaiml-mistral32-deepse-25601-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral32-deepse-25601-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-25601-v1/nvidia/config.json
chaiml-mistral32-deepse-25601-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-25601-v1/nvidia/special_tokens_map.json
chaiml-mistral32-deepse-25601-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-25601-v1/nvidia/tokenizer_config.json
chaiml-mistral32-deepse-25601-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-25601-v1/nvidia/tokenizer.json
chaiml-mistral32-deepse-25601-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral32-deepse-25601-v1/nvidia/flywheel_model.1.safetensors
chaiml-mistral32-deepse-25601-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral32-deepse-25601-v1/nvidia/flywheel_model.0.safetensors
chaiml-mistral32-deepse-25601-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:32,  3.08s/it]
Loading 0:   2%|▏         | 6/363 [00:06<05:00,  1.19it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:47,  3.26it/s]
Loading 0:   5%|▍         | 17/363 [00:06<01:14,  4.67it/s]
Loading 0:   6%|▌         | 22/363 [00:07<00:53,  6.34it/s]
Loading 0:   7%|▋         | 25/363 [00:07<00:44,  7.56it/s]
Loading 0:   9%|▊         | 31/363 [00:07<00:28, 11.51it/s]
Loading 0:   9%|▉         | 34/363 [00:07<00:26, 12.52it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:18, 17.38it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:17, 18.65it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:14, 22.09it/s]
Loading 0:  15%|█▍        | 53/363 [00:08<00:13, 22.74it/s]
Loading 0:  16%|█▌        | 58/363 [00:08<00:11, 26.13it/s]
Loading 0:  17%|█▋        | 62/363 [00:08<00:15, 18.98it/s]
Loading 0:  18%|█▊        | 67/363 [00:08<00:13, 22.16it/s]
Loading 0:  19%|█▉        | 70/363 [00:08<00:13, 21.49it/s]
Loading 0:  21%|██        | 76/363 [00:09<00:10, 26.91it/s]
Loading 0:  22%|██▏       | 80/363 [00:09<00:10, 26.82it/s]
Loading 0:  23%|██▎       | 85/363 [00:09<00:09, 29.71it/s]
Loading 0:  25%|██▍       | 89/363 [00:09<00:09, 28.49it/s]
Loading 0:  26%|██▌       | 94/363 [00:09<00:08, 31.10it/s]
Loading 0:  27%|██▋       | 98/363 [00:09<00:12, 21.83it/s]
Loading 0:  28%|██▊       | 103/363 [00:10<00:10, 25.16it/s]
Loading 0:  29%|██▉       | 106/363 [00:10<00:11, 23.01it/s]
Loading 0:  31%|███       | 112/363 [00:10<00:08, 27.95it/s]
Loading 0:  32%|███▏      | 116/363 [00:10<00:09, 26.74it/s]
Loading 0:  33%|███▎      | 121/363 [00:10<00:08, 28.97it/s]
Loading 0:  34%|███▍      | 125/363 [00:10<00:08, 27.53it/s]
Loading 0:  36%|███▌      | 130/363 [00:10<00:07, 29.96it/s]
Loading 0:  37%|███▋      | 134/363 [00:11<00:08, 28.09it/s]
Loading 0:  38%|███▊      | 139/363 [00:11<00:09, 23.01it/s]
Loading 0:  39%|███▉      | 142/363 [00:11<00:10, 21.49it/s]
Loading 0:  41%|████      | 148/363 [00:11<00:08, 26.36it/s]
Loading 0:  42%|████▏     | 151/363 [00:11<00:08, 24.11it/s]
Loading 0:  43%|████▎     | 157/363 [00:12<00:07, 28.50it/s]
Loading 0:  44%|████▍     | 160/363 [00:12<00:07, 25.70it/s]
Loading 0:  46%|████▌     | 166/363 [00:12<00:06, 30.25it/s]
Loading 0:  47%|████▋     | 170/363 [00:12<00:06, 28.20it/s]
Loading 0:  48%|████▊     | 175/363 [00:12<00:06, 30.39it/s]
Loading 0:  49%|████▉     | 179/363 [00:13<00:08, 21.08it/s]
Loading 0:  51%|█████     | 184/363 [00:13<00:07, 24.47it/s]
Loading 0:  51%|█████     | 185/363 [00:27<00:07, 24.47it/s]
Loading 0:  51%|█████     | 186/363 [00:27<03:24,  1.15s/it]
Loading 0:  53%|█████▎    | 191/363 [00:27<02:08,  1.34it/s]
Loading 0:  54%|█████▎    | 195/363 [00:27<01:32,  1.81it/s]
Loading 0:  56%|█████▌    | 202/363 [00:28<00:52,  3.05it/s]
Loading 0:  57%|█████▋    | 206/363 [00:28<00:39,  3.93it/s]
Loading 0:  58%|█████▊    | 211/363 [00:28<00:28,  5.42it/s]
Loading 0:  59%|█████▉    | 215/363 [00:28<00:23,  6.37it/s]
Loading 0:  61%|██████    | 220/363 [00:28<00:16,  8.64it/s]
Loading 0:  61%|██████▏   | 223/363 [00:28<00:14,  9.79it/s]
Loading 0:  63%|██████▎   | 229/363 [00:29<00:09, 13.88it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:08, 15.62it/s]
Loading 0:  66%|██████▌   | 238/363 [00:29<00:06, 18.90it/s]
Loading 0:  67%|██████▋   | 242/363 [00:29<00:06, 20.10it/s]
Loading 0:  68%|██████▊   | 247/363 [00:29<00:04, 23.63it/s]
Loading 0:  69%|██████▉   | 251/363 [00:29<00:04, 23.85it/s]
Loading 0:  71%|███████   | 256/363 [00:30<00:05, 21.10it/s]
Loading 0:  71%|███████▏  | 259/363 [00:30<00:05, 20.65it/s]
Loading 0:  73%|███████▎  | 265/363 [00:30<00:03, 25.78it/s]
Loading 0:  74%|███████▍  | 268/363 [00:30<00:03, 23.96it/s]
Loading 0:  75%|███████▌  | 274/363 [00:30<00:03, 28.91it/s]
Loading 0:  77%|███████▋  | 278/363 [00:30<00:03, 27.65it/s]
Loading 0:  78%|███████▊  | 283/363 [00:31<00:02, 29.78it/s]
Loading 0:  79%|███████▉  | 287/363 [00:31<00:02, 28.29it/s]
Loading 0:  80%|████████  | 292/363 [00:31<00:02, 30.85it/s]
Loading 0:  82%|████████▏ | 296/363 [00:31<00:03, 21.91it/s]
Loading 0:  83%|████████▎ | 301/363 [00:31<00:02, 25.34it/s]
Loading 0:  84%|████████▎ | 304/363 [00:31<00:02, 23.75it/s]
Loading 0:  85%|████████▌ | 310/363 [00:32<00:01, 28.56it/s]
Loading 0:  87%|████████▋ | 314/363 [00:32<00:01, 27.64it/s]
Loading 0:  88%|████████▊ | 319/363 [00:32<00:01, 30.27it/s]
Loading 0:  89%|████████▉ | 323/363 [00:32<00:01, 27.86it/s]
Loading 0:  90%|█████████ | 328/363 [00:32<00:01, 30.28it/s]
Loading 0:  91%|█████████▏| 332/363 [00:33<00:01, 21.36it/s]
Loading 0:  93%|█████████▎| 337/363 [00:33<00:01, 24.63it/s]
Loading 0:  94%|█████████▎| 340/363 [00:33<00:01, 23.00it/s]
Loading 0:  95%|█████████▌| 346/363 [00:33<00:00, 28.02it/s]
Loading 0:  96%|█████████▋| 350/363 [00:33<00:00, 26.96it/s]
Loading 0:  98%|█████████▊| 355/363 [00:33<00:00, 29.39it/s]
Loading 0:  99%|█████████▉| 359/363 [00:33<00:00, 27.77it/s]
                                                            
Job chaiml-mistral32-deepse-25601-v1-mkmlizer completed after 156.37s with status: succeeded
Stopping job with name chaiml-mistral32-deepse-25601-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.85s
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-deepse-25601-v1
Waiting for inference service chaiml-mistral32-deepse-25601-v1 to be ready
Unable to record family friendly update due to error: ('http://chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:54872->127.0.0.1:8080: read: connection reset by peer\n')
Inference service chaiml-mistral32-deepse-25601-v1 ready after 181.05730843544006s
Pipeline stage MKMLDeployer completed in 181.81s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8740487098693848s
Received healthy response to inference request in 1.8963277339935303s
Received healthy response to inference request in 1.938737154006958s
Received healthy response to inference request in 2.104417324066162s
Received healthy response to inference request in 2.021019220352173s
5 requests
0 failed requests
5th percentile: 1.9048096179962157
10th percentile: 1.9132915019989014
20th percentile: 1.9302552700042725
30th percentile: 1.955193567276001
40th percentile: 1.9881063938140868
50th percentile: 2.021019220352173
60th percentile: 2.0543784618377687
70th percentile: 2.087737703323364
80th percentile: 2.258343601226807
90th percentile: 2.566196155548096
95th percentile: 2.72012243270874
99th percentile: 2.8432634544372557
mean time: 2.1669100284576417
Pipeline stage StressChecker completed in 12.42s
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 0.63s
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-deepse_25601_v1 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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral32-deepse-25601-v1-profiler
Waiting for inference service chaiml-mistral32-deepse-25601-v1-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 5303.88s
Shutdown handler de-registered
chaiml-mistral32-deepse_25601_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral32-deepse_25601_v1 status is now torndown due to DeploymentManager action