chaiml-mistral32-deepse_89261

developer_uid: NischayDnk

submission_id: chaiml-mistral32-deepse_89261_v2

model_name: chaiml-mistral32-deepse_89261_v2

model_group: ChaiML/mistral32_deepsee

status: torndown

timestamp: 2025-07-09T06:31:43+00:00

num_battles: 5434

num_wins: 2868

celo_rating: 1317.68

family_friendly_score: 0.5074000000000001

family_friendly_standard_error: 0.007070293346106653

submission_type: basic

model_repo: ChaiML/mistral32_deepseek_cpos3_cpos21322_sfts11306_seq96_exp6

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': 0.47687615457181726, 'latency_mean': 2.096883237361908, 'latency_p50': 2.110402822494507, 'latency_p90': 2.303372025489807}, {'batch_size': 3, 'throughput': 0.9529567194396591, 'latency_mean': 3.1387472558021545, 'latency_p50': 3.1229934692382812, 'latency_p90': 3.4713784217834474}, {'batch_size': 5, 'throughput': 1.1881466767274114, 'latency_mean': 4.186957650184631, 'latency_p50': 4.197170853614807, 'latency_p90': 4.637877202033996}, {'batch_size': 6, 'throughput': 1.2665955800905515, 'latency_mean': 4.7078387999534606, 'latency_p50': 4.735343098640442, 'latency_p90': 5.259240436553955}, {'batch_size': 8, 'throughput': 1.3850310675384165, 'latency_mean': 5.733862525224685, 'latency_p50': 5.751191735267639, 'latency_p90': 6.385191631317139}, {'batch_size': 10, 'throughput': 1.4565130132097561, 'latency_mean': 6.805016241073608, 'latency_p50': 6.913261771202087, 'latency_p90': 7.6702872037887575}]

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

display_name: chaiml-mistral32-deepse_89261_v2

is_internal_developer: False

language_model: ChaiML/mistral32_deepseek_cpos3_cpos21322_sfts11306_seq96_exp6

model_size: 24B

ranking_group: single

throughput_3p7s: 1.1

us_pacific_date: 2025-07-08

win_ratio: 0.527788001472212

generation_params: {'temperature': 0.72, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 80, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|im_start|>', '<|im_end|>', '###', '\n', '</s>'], 'max_input_tokens': 1536, 'best_of': 6, '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-89261-v2-mkmlizer
Waiting for job on chaiml-mistral32-deepse-89261-v2-mkmlizer to finish
chaiml-mistral32-deepse-89261-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral32-deepse-89261-v2-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-89261-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mistral32-deepse-89261-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mistral32-deepse-89261-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mistral32-deepse-89261-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mistral32-deepse-89261-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mistral32-deepse-89261-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mistral32-deepse-89261-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mistral32-deepse-89261-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mistral32-deepse-89261-v2-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-89261-v2-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-mistral32-deepse-89261-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mistral32-deepse-89261-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mistral32-deepse-89261-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral32-deepse-89261-v2-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-89261-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral32-deepse-89261-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral32-deepse-89261-v2-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-89261-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral32-deepse-89261-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral32-deepse-89261-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral32-deepse-89261-v2-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-89261-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral32-deepse-89261-v2-mkmlizer: Downloaded to shared memory in 54.577s
chaiml-mistral32-deepse-89261-v2-mkmlizer: Checking if ChaiML/mistral32_deepseek_cpos3_cpos21322_sfts11306_seq96_exp6 already exists in ChaiML
chaiml-mistral32-deepse-89261-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7z67ne44, device:0
chaiml-mistral32-deepse-89261-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral32-deepse-89261-v2-mkmlizer: quantized model in 49.610s
chaiml-mistral32-deepse-89261-v2-mkmlizer: Processed model ChaiML/mistral32_deepseek_cpos3_cpos21322_sfts11306_seq96_exp6 in 104.187s
chaiml-mistral32-deepse-89261-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral32-deepse-89261-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral32-deepse-89261-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral32-deepse-89261-v2/nvidia
chaiml-mistral32-deepse-89261-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-89261-v2/nvidia/config.json
chaiml-mistral32-deepse-89261-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-89261-v2/nvidia/special_tokens_map.json
chaiml-mistral32-deepse-89261-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-89261-v2/nvidia/tokenizer_config.json
chaiml-mistral32-deepse-89261-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-89261-v2/nvidia/tokenizer.json
chaiml-mistral32-deepse-89261-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral32-deepse-89261-v2/nvidia/flywheel_model.1.safetensors
chaiml-mistral32-deepse-89261-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral32-deepse-89261-v2/nvidia/flywheel_model.0.safetensors
chaiml-mistral32-deepse-89261-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:39,  3.10s/it]
Loading 0:   1%|▏         | 5/363 [00:06<06:01,  1.01s/it]
Loading 0:   2%|▏         | 7/363 [00:06<03:48,  1.56it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:28,  3.94it/s]
Loading 0:   4%|▍         | 16/363 [00:06<01:06,  5.19it/s]
Loading 0:   6%|▌         | 22/363 [00:07<00:43,  7.75it/s]
Loading 0:   7%|▋         | 25/363 [00:07<00:37,  8.99it/s]
Loading 0:   9%|▊         | 31/363 [00:07<00:24, 13.47it/s]
Loading 0:   9%|▉         | 34/363 [00:07<00:23, 14.13it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:17, 18.97it/s]
Loading 0:  12%|█▏        | 43/363 [00:07<00:17, 18.50it/s]
Loading 0:  13%|█▎        | 47/363 [00:08<00:14, 21.88it/s]
Loading 0:  14%|█▍        | 50/363 [00:08<00:13, 23.09it/s]
Loading 0:  15%|█▍        | 53/363 [00:08<00:13, 22.83it/s]
Loading 0:  16%|█▌        | 58/363 [00:08<00:11, 26.23it/s]
Loading 0:  17%|█▋        | 61/363 [00:08<00:17, 16.93it/s]
Loading 0:  18%|█▊        | 67/363 [00:08<00:13, 22.27it/s]
Loading 0:  19%|█▉        | 70/363 [00:09<00:14, 20.93it/s]
Loading 0:  21%|██        | 76/363 [00:09<00:11, 25.84it/s]
Loading 0:  22%|██▏       | 79/363 [00:09<00:12, 23.45it/s]
Loading 0:  23%|██▎       | 83/363 [00:09<00:10, 26.12it/s]
Loading 0:  24%|██▎       | 86/363 [00:09<00:10, 26.59it/s]
Loading 0:  25%|██▍       | 89/363 [00:09<00:10, 25.73it/s]
Loading 0:  26%|██▌       | 94/363 [00:09<00:09, 28.54it/s]
Loading 0:  27%|██▋       | 97/363 [00:10<00:14, 17.76it/s]
Loading 0:  28%|██▊       | 103/363 [00:10<00:11, 23.12it/s]
Loading 0:  29%|██▉       | 106/363 [00:10<00:11, 21.49it/s]
Loading 0:  31%|███       | 112/363 [00:10<00:09, 26.34it/s]
Loading 0:  32%|███▏      | 115/363 [00:10<00:10, 23.90it/s]
Loading 0:  33%|███▎      | 121/363 [00:11<00:08, 28.38it/s]
Loading 0:  34%|███▍      | 125/363 [00:11<00:08, 26.51it/s]
Loading 0:  36%|███▌      | 130/363 [00:11<00:08, 29.03it/s]
Loading 0:  37%|███▋      | 134/363 [00:11<00:08, 26.84it/s]
Loading 0:  38%|███▊      | 139/363 [00:11<00:10, 21.77it/s]
Loading 0:  39%|███▉      | 142/363 [00:12<00:10, 20.57it/s]
Loading 0:  41%|████      | 148/363 [00:12<00:08, 25.29it/s]
Loading 0:  42%|████▏     | 151/363 [00:12<00:09, 23.25it/s]
Loading 0:  43%|████▎     | 157/363 [00:12<00:07, 27.76it/s]
Loading 0:  44%|████▍     | 160/363 [00:12<00:08, 24.78it/s]
Loading 0:  45%|████▌     | 164/363 [00:12<00:07, 27.77it/s]
Loading 0:  46%|████▌     | 167/363 [00:12<00:07, 27.80it/s]
Loading 0:  47%|████▋     | 170/363 [00:13<00:07, 26.80it/s]
Loading 0:  48%|████▊     | 175/363 [00:13<00:06, 29.08it/s]
Loading 0:  49%|████▉     | 178/363 [00:13<00:10, 17.94it/s]
Loading 0:  51%|█████     | 184/363 [00:13<00:07, 23.23it/s]
Loading 0:  51%|█████     | 185/363 [00:28<00:07, 23.23it/s]
Loading 0:  51%|█████     | 186/363 [00:28<03:42,  1.26s/it]
Loading 0:  53%|█████▎    | 191/363 [00:28<02:18,  1.24it/s]
Loading 0:  54%|█████▎    | 195/363 [00:29<01:39,  1.69it/s]
Loading 0:  56%|█████▌    | 202/363 [00:29<00:56,  2.87it/s]
Loading 0:  57%|█████▋    | 206/363 [00:29<00:42,  3.70it/s]
Loading 0:  58%|█████▊    | 211/363 [00:29<00:29,  5.15it/s]
Loading 0:  59%|█████▉    | 215/363 [00:29<00:24,  5.97it/s]
Loading 0:  61%|██████    | 220/363 [00:30<00:17,  8.14it/s]
Loading 0:  61%|██████▏   | 223/363 [00:30<00:15,  9.21it/s]
Loading 0:  63%|██████▎   | 229/363 [00:30<00:10, 13.09it/s]
Loading 0:  64%|██████▍   | 232/363 [00:30<00:09, 13.92it/s]
Loading 0:  66%|██████▌   | 238/363 [00:30<00:06, 18.57it/s]
Loading 0:  67%|██████▋   | 242/363 [00:30<00:06, 19.72it/s]
Loading 0:  68%|██████▊   | 247/363 [00:31<00:05, 22.98it/s]
Loading 0:  69%|██████▉   | 251/363 [00:31<00:04, 22.85it/s]
Loading 0:  71%|███████   | 256/363 [00:31<00:05, 20.33it/s]
Loading 0:  71%|███████▏  | 259/363 [00:31<00:05, 19.58it/s]
Loading 0:  73%|███████▎  | 265/363 [00:31<00:04, 24.49it/s]
Loading 0:  74%|███████▍  | 268/363 [00:31<00:04, 22.92it/s]
Loading 0:  75%|███████▌  | 274/363 [00:32<00:03, 27.39it/s]
Loading 0:  76%|███████▋  | 277/363 [00:32<00:03, 24.67it/s]
Loading 0:  78%|███████▊  | 283/363 [00:32<00:02, 29.23it/s]
Loading 0:  79%|███████▉  | 287/363 [00:32<00:02, 27.30it/s]
Loading 0:  80%|████████  | 292/363 [00:32<00:02, 29.08it/s]
Loading 0:  82%|████████▏ | 296/363 [00:33<00:03, 19.69it/s]
Loading 0:  83%|████████▎ | 301/363 [00:33<00:02, 22.70it/s]
Loading 0:  84%|████████▎ | 304/363 [00:33<00:02, 21.49it/s]
Loading 0:  85%|████████▌ | 310/363 [00:33<00:02, 25.95it/s]
Loading 0:  86%|████████▌ | 313/363 [00:33<00:02, 23.35it/s]
Loading 0:  87%|████████▋ | 317/363 [00:33<00:01, 26.19it/s]
Loading 0:  88%|████████▊ | 320/363 [00:34<00:01, 26.75it/s]
Loading 0:  89%|████████▉ | 323/363 [00:34<00:01, 25.87it/s]
Loading 0:  90%|█████████ | 328/363 [00:34<00:01, 27.97it/s]
Loading 0:  91%|█████████ | 331/363 [00:34<00:01, 17.66it/s]
Loading 0:  92%|█████████▏| 335/363 [00:34<00:01, 21.28it/s]
Loading 0:  93%|█████████▎| 338/363 [00:34<00:01, 22.51it/s]
Loading 0:  94%|█████████▍| 341/363 [00:35<00:00, 22.71it/s]
Loading 0:  95%|█████████▌| 346/363 [00:35<00:00, 25.82it/s]
Loading 0:  96%|█████████▌| 349/363 [00:35<00:00, 22.81it/s]
Loading 0:  98%|█████████▊| 355/363 [00:35<00:00, 27.86it/s]
Loading 0:  99%|█████████▊| 358/363 [00:35<00:00, 24.52it/s]
                                                            
Job chaiml-mistral32-deepse-89261-v2-mkmlizer completed after 136.09s with status: succeeded
Stopping job with name chaiml-mistral32-deepse-89261-v2-mkmlizer
Pipeline stage MKMLizer completed in 136.60s
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-mistral32-deepse-89261-v2
Waiting for inference service chaiml-mistral32-deepse-89261-v2 to be ready
Inference service chaiml-mistral32-deepse-89261-v2 ready after 200.7518274784088s
Pipeline stage MKMLDeployer completed in 202.01s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6803719997406006s
Received healthy response to inference request in 2.129721164703369s
Received healthy response to inference request in 2.0211973190307617s
Received healthy response to inference request in 2.049163818359375s
Received healthy response to inference request in 1.8440799713134766s
5 requests
0 failed requests
5th percentile: 1.8795034408569335
10th percentile: 1.9149269104003905
20th percentile: 1.9857738494873047
30th percentile: 2.0267906188964844
40th percentile: 2.0379772186279297
50th percentile: 2.049163818359375
60th percentile: 2.081386756896973
70th percentile: 2.1136096954345702
80th percentile: 2.2398513317108155
90th percentile: 2.460111665725708
95th percentile: 2.570241832733154
99th percentile: 2.658345966339111
mean time: 2.1449068546295167
Pipeline stage StressChecker completed in 12.30s
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 0.89s
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_v2 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 3213.85s
Shutdown handler de-registered
chaiml-mistral32-deepse_89261_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral32-deepse_89261_v2 status is now torndown due to DeploymentManager action