chaiml-mistral32-deepse_89261

developer_uid: NischayDnk

submission_id: chaiml-mistral32-deepse_89261_v4

model_name: chaiml-mistral32-deepse_89261_v4

model_group: ChaiML/mistral32_deepsee

status: torndown

timestamp: 2025-07-09T13:27:14+00:00

num_battles: 7453

num_wins: 4071

celo_rating: 1326.5

family_friendly_score: 0.4972

family_friendly_standard_error: 0.0070709569366529165

submission_type: basic

model_repo: ChaiML/mistral32_deepseek_cpos3_cpos21322_sfts11306_seq96_exp6

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 7

max_input_tokens: 1024

max_output_tokens: 72

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.47573880985389644, 'latency_mean': 2.10187130689621, 'latency_p50': 2.1064902544021606, 'latency_p90': 2.297831654548645}, {'batch_size': 3, 'throughput': 0.9827288607489961, 'latency_mean': 3.038926067352295, 'latency_p50': 3.044596552848816, 'latency_p90': 3.2918867111206054}, {'batch_size': 5, 'throughput': 1.273222321453241, 'latency_mean': 3.9080158853530884, 'latency_p50': 3.914086699485779, 'latency_p90': 4.305746078491211}, {'batch_size': 6, 'throughput': 1.379704943193426, 'latency_mean': 4.31481271982193, 'latency_p50': 4.290195941925049, 'latency_p90': 4.771479320526123}, {'batch_size': 8, 'throughput': 1.5257945641826156, 'latency_mean': 5.190628962516785, 'latency_p50': 5.248389720916748, 'latency_p90': 5.773107981681823}, {'batch_size': 10, 'throughput': 1.5988595201788007, 'latency_mean': 6.198255571126938, 'latency_p50': 6.21036434173584, 'latency_p90': 6.86856427192688}]

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

display_name: chaiml-mistral32-deepse_89261_v4

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: 1.22

us_pacific_date: 2025-07-09

win_ratio: 0.546222997450691

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': ['###', '<|im_end|>', '<|im_start|>', '</s>', '\n'], 'max_input_tokens': 1024, 'best_of': 7, 'max_output_tokens': 72}

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-v4-mkmlizer
Waiting for job on chaiml-mistral32-deepse-89261-v4-mkmlizer to finish
chaiml-mistral32-deepse-89261-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral32-deepse-89261-v4-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-89261-v4-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mistral32-deepse-89261-v4-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mistral32-deepse-89261-v4-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mistral32-deepse-89261-v4-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mistral32-deepse-89261-v4-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mistral32-deepse-89261-v4-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mistral32-deepse-89261-v4-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mistral32-deepse-89261-v4-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mistral32-deepse-89261-v4-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-89261-v4-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-mistral32-deepse-89261-v4-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mistral32-deepse-89261-v4-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mistral32-deepse-89261-v4-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral32-deepse-89261-v4-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-89261-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral32-deepse-89261-v4-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral32-deepse-89261-v4-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-89261-v4-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral32-deepse-89261-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral32-deepse-89261-v4-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral32-deepse-89261-v4-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-89261-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral32-deepse-89261-v4-mkmlizer: Downloaded to shared memory in 54.862s
chaiml-mistral32-deepse-89261-v4-mkmlizer: Checking if ChaiML/mistral32_deepseek_cpos3_cpos21322_sfts11306_seq96_exp6 already exists in ChaiML
chaiml-mistral32-deepse-89261-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpj1m4dd_8, device:0
chaiml-mistral32-deepse-89261-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral32-deepse-89261-v4-mkmlizer: quantized model in 47.730s
chaiml-mistral32-deepse-89261-v4-mkmlizer: Processed model ChaiML/mistral32_deepseek_cpos3_cpos21322_sfts11306_seq96_exp6 in 102.592s
chaiml-mistral32-deepse-89261-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral32-deepse-89261-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral32-deepse-89261-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral32-deepse-89261-v4/nvidia
chaiml-mistral32-deepse-89261-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-89261-v4/nvidia/config.json
chaiml-mistral32-deepse-89261-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-89261-v4/nvidia/special_tokens_map.json
chaiml-mistral32-deepse-89261-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-89261-v4/nvidia/tokenizer_config.json
chaiml-mistral32-deepse-89261-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-89261-v4/nvidia/tokenizer.json
chaiml-mistral32-deepse-89261-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral32-deepse-89261-v4/nvidia/flywheel_model.1.safetensors
chaiml-mistral32-deepse-89261-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral32-deepse-89261-v4/nvidia/flywheel_model.0.safetensors
chaiml-mistral32-deepse-89261-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:35,  3.09s/it]
Loading 0:   2%|▏         | 6/363 [00:06<05:01,  1.18it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:47,  3.25it/s]
Loading 0:   5%|▍         | 17/363 [00:06<01:14,  4.62it/s]
Loading 0:   6%|▌         | 22/363 [00:07<00:54,  6.28it/s]
Loading 0:   7%|▋         | 25/363 [00:07<00:45,  7.45it/s]
Loading 0:   9%|▊         | 31/363 [00:07<00:29, 11.32it/s]
Loading 0:   9%|▉         | 34/363 [00:07<00:26, 12.27it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:18, 17.10it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:17, 17.79it/s]
Loading 0:  13%|█▎        | 49/363 [00:08<00:14, 21.05it/s]
Loading 0:  14%|█▍        | 52/363 [00:08<00:15, 20.12it/s]
Loading 0:  16%|█▌        | 58/363 [00:08<00:12, 25.34it/s]
Loading 0:  17%|█▋        | 62/363 [00:08<00:15, 18.84it/s]
Loading 0:  18%|█▊        | 67/363 [00:08<00:13, 22.36it/s]
Loading 0:  19%|█▉        | 70/363 [00:09<00:13, 21.18it/s]
Loading 0:  21%|██        | 76/363 [00:09<00:10, 26.22it/s]
Loading 0:  22%|██▏       | 80/363 [00:09<00:11, 25.55it/s]
Loading 0:  23%|██▎       | 85/363 [00:09<00:09, 28.21it/s]
Loading 0:  25%|██▍       | 89/363 [00:09<00:10, 26.81it/s]
Loading 0:  26%|██▌       | 94/363 [00:09<00:09, 29.79it/s]
Loading 0:  27%|██▋       | 98/363 [00:10<00:12, 20.72it/s]
Loading 0:  28%|██▊       | 103/363 [00:10<00:10, 24.43it/s]
Loading 0:  29%|██▉       | 106/363 [00:10<00:11, 23.02it/s]
Loading 0:  31%|███       | 112/363 [00:10<00:08, 28.38it/s]
Loading 0:  32%|███▏      | 116/363 [00:10<00:09, 27.18it/s]
Loading 0:  33%|███▎      | 121/363 [00:10<00:07, 30.40it/s]
Loading 0:  34%|███▍      | 125/363 [00:10<00:08, 28.89it/s]
Loading 0:  36%|███▌      | 130/363 [00:11<00:07, 31.19it/s]
Loading 0:  37%|███▋      | 134/363 [00:11<00:07, 28.85it/s]
Loading 0:  38%|███▊      | 139/363 [00:11<00:09, 23.53it/s]
Loading 0:  39%|███▉      | 142/363 [00:11<00:10, 22.02it/s]
Loading 0:  41%|████      | 148/363 [00:11<00:07, 27.31it/s]
Loading 0:  42%|████▏     | 151/363 [00:12<00:08, 25.00it/s]
Loading 0:  43%|████▎     | 157/363 [00:12<00:06, 29.88it/s]
Loading 0:  44%|████▍     | 161/363 [00:12<00:07, 28.03it/s]
Loading 0:  46%|████▌     | 166/363 [00:12<00:06, 30.60it/s]
Loading 0:  47%|████▋     | 170/363 [00:12<00:06, 28.53it/s]
Loading 0:  48%|████▊     | 175/363 [00:12<00:06, 31.05it/s]
Loading 0:  49%|████▉     | 179/363 [00:13<00:08, 20.92it/s]
Loading 0:  51%|█████     | 184/363 [00:13<00:07, 24.56it/s]
Loading 0:  51%|█████     | 185/363 [00:27<00:07, 24.56it/s]
Loading 0:  51%|█████     | 186/363 [00:27<03:27,  1.17s/it]
Loading 0:  53%|█████▎    | 191/363 [00:27<02:10,  1.32it/s]
Loading 0:  54%|█████▎    | 195/363 [00:28<01:34,  1.78it/s]
Loading 0:  55%|█████▌    | 200/363 [00:28<01:01,  2.65it/s]
Loading 0:  56%|█████▌    | 204/363 [00:28<00:45,  3.47it/s]
Loading 0:  58%|█████▊    | 209/363 [00:28<00:30,  5.03it/s]
Loading 0:  59%|█████▊    | 213/363 [00:29<00:26,  5.74it/s]
Loading 0:  61%|██████    | 220/363 [00:29<00:15,  8.95it/s]
Loading 0:  62%|██████▏   | 224/363 [00:29<00:13, 10.54it/s]
Loading 0:  63%|██████▎   | 229/363 [00:29<00:09, 13.55it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:08, 15.26it/s]
Loading 0:  66%|██████▌   | 238/363 [00:29<00:06, 18.92it/s]
Loading 0:  67%|██████▋   | 242/363 [00:29<00:06, 19.92it/s]
Loading 0:  68%|██████▊   | 247/363 [00:30<00:04, 23.38it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:04, 23.41it/s]
Loading 0:  71%|███████   | 256/363 [00:30<00:05, 20.90it/s]
Loading 0:  71%|███████▏  | 259/363 [00:30<00:05, 20.21it/s]
Loading 0:  73%|███████▎  | 265/363 [00:30<00:03, 25.59it/s]
Loading 0:  74%|███████▍  | 268/363 [00:31<00:03, 23.93it/s]
Loading 0:  75%|███████▌  | 274/363 [00:31<00:03, 28.88it/s]
Loading 0:  77%|███████▋  | 278/363 [00:31<00:03, 27.52it/s]
Loading 0:  78%|███████▊  | 283/363 [00:31<00:02, 30.51it/s]
Loading 0:  79%|███████▉  | 287/363 [00:31<00:02, 28.85it/s]
Loading 0:  80%|████████  | 292/363 [00:31<00:02, 31.69it/s]
Loading 0:  82%|████████▏ | 296/363 [00:32<00:03, 21.46it/s]
Loading 0:  83%|████████▎ | 301/363 [00:32<00:02, 24.37it/s]
Loading 0:  84%|████████▎ | 304/363 [00:32<00:02, 22.71it/s]
Loading 0:  85%|████████▌ | 310/363 [00:32<00:01, 27.94it/s]
Loading 0:  87%|████████▋ | 314/363 [00:32<00:01, 26.67it/s]
Loading 0:  88%|████████▊ | 319/363 [00:32<00:01, 29.69it/s]
Loading 0:  89%|████████▉ | 323/363 [00:33<00:01, 28.12it/s]
Loading 0:  90%|█████████ | 328/363 [00:33<00:01, 30.37it/s]
Loading 0:  91%|█████████▏| 332/363 [00:33<00:01, 20.92it/s]
Loading 0:  93%|█████████▎| 337/363 [00:33<00:01, 24.26it/s]
Loading 0:  94%|█████████▎| 340/363 [00:33<00:01, 22.72it/s]
Loading 0:  95%|█████████▌| 346/363 [00:33<00:00, 27.63it/s]
Loading 0:  96%|█████████▋| 350/363 [00:34<00:00, 26.38it/s]
Loading 0:  98%|█████████▊| 355/363 [00:34<00:00, 29.32it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00, 26.73it/s]
                                                            
Job chaiml-mistral32-deepse-89261-v4-mkmlizer completed after 126.9s with status: succeeded
Stopping job with name chaiml-mistral32-deepse-89261-v4-mkmlizer
Pipeline stage MKMLizer completed in 127.44s
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-deepse-89261-v4
Waiting for inference service chaiml-mistral32-deepse-89261-v4 to be ready
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)
Inference service chaiml-mistral32-deepse-89261-v4 ready after 191.0167670249939s
Pipeline stage MKMLDeployer completed in 191.66s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.643793821334839s
Received healthy response to inference request in 2.1717307567596436s
Received healthy response to inference request in 2.455549955368042s
Received healthy response to inference request in 2.3902382850646973s
Received healthy response to inference request in 2.402852773666382s
5 requests
0 failed requests
5th percentile: 2.2154322624206544
10th percentile: 2.259133768081665
20th percentile: 2.3465367794036864
30th percentile: 2.3927611827850344
40th percentile: 2.397806978225708
50th percentile: 2.402852773666382
60th percentile: 2.4239316463470457
70th percentile: 2.44501051902771
80th percentile: 2.4931987285614015
90th percentile: 2.56849627494812
95th percentile: 2.6061450481414794
99th percentile: 2.636264066696167
mean time: 2.4128331184387206
Pipeline stage StressChecker completed in 13.57s
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 0.70s
Shutdown handler de-registered
chaiml-mistral32-deepse_89261_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 3230.28s
Shutdown handler de-registered
chaiml-mistral32-deepse_89261_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral32-deepse_89261_v4 status is now torndown due to DeploymentManager action