chaiml-mistral32-nis-de_15507

developer_uid: NischayDnk

submission_id: chaiml-mistral32-nis-de_15507_v1

model_name: chaiml-mistral32-nis-de_15507_v1

model_group: ChaiML/mistral32-nis-dee

status: torndown

timestamp: 2025-07-08T07:49:10+00:00

num_battles: 6801

num_wins: 3532

celo_rating: 1305.58

family_friendly_score: 0.49639999999999995

family_friendly_standard_error: 0.0070708845274123945

submission_type: basic

model_repo: ChaiML/mistral32-nis-deepseek-dedup-cpos3-cpos2ft-sftexp2-1306-v4-pubpref

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': 0.5234873911439896, 'latency_mean': 1.9101575934886932, 'latency_p50': 1.8985040187835693, 'latency_p90': 2.112855052947998}, {'batch_size': 3, 'throughput': 1.050859117535941, 'latency_mean': 2.843638345003128, 'latency_p50': 2.842684507369995, 'latency_p90': 3.1096455097198485}, {'batch_size': 5, 'throughput': 1.3464536642327722, 'latency_mean': 3.701903661489487, 'latency_p50': 3.6931231021881104, 'latency_p90': 4.103615474700928}, {'batch_size': 6, 'throughput': 1.4407173515938156, 'latency_mean': 4.135387395620346, 'latency_p50': 4.128103733062744, 'latency_p90': 4.664160370826721}, {'batch_size': 8, 'throughput': 1.5765638820891918, 'latency_mean': 5.045081067085266, 'latency_p50': 5.04955530166626, 'latency_p90': 5.682892799377441}, {'batch_size': 10, 'throughput': 1.661489686476902, 'latency_mean': 5.966552075147629, 'latency_p50': 5.97150444984436, 'latency_p90': 6.734245800971984}]

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

display_name: chaiml-mistral32-nis-de_15507_v1

is_internal_developer: False

language_model: ChaiML/mistral32-nis-deepseek-dedup-cpos3-cpos2ft-sftexp2-1306-v4-pubpref

model_size: 24B

ranking_group: single

throughput_3p7s: 1.35

us_pacific_date: 2025-07-08

win_ratio: 0.5193353918541391

generation_params: {'temperature': 0.6, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.42, 'frequency_penalty': 0.42, 'stopping_words': ['<|im_start|>', '<|im_end|>', '\n'], '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-nis-de-15507-v1-mkmlizer
Waiting for job on chaiml-mistral32-nis-de-15507-v1-mkmlizer to finish
chaiml-mistral32-nis-de-15507-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral32-nis-de-15507-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-nis-de-15507-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mistral32-nis-de-15507-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mistral32-nis-de-15507-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mistral32-nis-de-15507-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mistral32-nis-de-15507-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mistral32-nis-de-15507-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mistral32-nis-de-15507-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mistral32-nis-de-15507-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mistral32-nis-de-15507-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-nis-de-15507-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-mistral32-nis-de-15507-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mistral32-nis-de-15507-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mistral32-nis-de-15507-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral32-nis-de-15507-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-nis-de-15507-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral32-nis-de-15507-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral32-nis-de-15507-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-nis-de-15507-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral32-nis-de-15507-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral32-nis-de-15507-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral32-nis-de-15507-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-nis-de-15507-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral32-nis-de-15507-v1-mkmlizer: Downloaded to shared memory in 75.972s
chaiml-mistral32-nis-de-15507-v1-mkmlizer: Checking if ChaiML/mistral32-nis-deepseek-dedup-cpos3-cpos2ft-sftexp2-1306-v4-pubpref already exists in ChaiML
chaiml-mistral32-nis-de-15507-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp31cf0reg, device:0
chaiml-mistral32-nis-de-15507-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral32-nis-de-15507-v1-mkmlizer: quantized model in 48.425s
chaiml-mistral32-nis-de-15507-v1-mkmlizer: Processed model ChaiML/mistral32-nis-deepseek-dedup-cpos3-cpos2ft-sftexp2-1306-v4-pubpref in 124.397s
chaiml-mistral32-nis-de-15507-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral32-nis-de-15507-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral32-nis-de-15507-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral32-nis-de-15507-v1/nvidia
chaiml-mistral32-nis-de-15507-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral32-nis-de-15507-v1/nvidia/tokenizer_config.json
chaiml-mistral32-nis-de-15507-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral32-nis-de-15507-v1/nvidia/tokenizer.json
chaiml-mistral32-nis-de-15507-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral32-nis-de-15507-v1/nvidia/flywheel_model.1.safetensors
chaiml-mistral32-nis-de-15507-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral32-nis-de-15507-v1/nvidia/flywheel_model.0.safetensors
chaiml-mistral32-nis-de-15507-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.53it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 36.45it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 33.62it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 34.35it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:10, 30.78it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 36.20it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:14, 22.64it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:12, 25.27it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 26.28it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.75it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 26.23it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:10, 28.84it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 27.20it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.91it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 24.30it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 20.91it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 25.97it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 25.39it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 27.11it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 27.30it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 21.73it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 28.37it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 26.90it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.96it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 25.66it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 24.84it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 27.67it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 24.87it/s]
Loading 0:  35%|███▍      | 127/363 [00:04<00:08, 27.79it/s]
Loading 0:  36%|███▌      | 130/363 [00:04<00:08, 27.96it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 27.56it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 30.09it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 27.32it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 31.91it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:08, 23.97it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:09, 22.15it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:08, 23.05it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 23.63it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.54it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 23.90it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.92it/s]
Loading 0:  49%|████▉     | 177/363 [00:06<00:07, 25.84it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 28.00it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 24.97it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 23.18it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.98it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 24.26it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:06, 24.26it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:05,  1.15s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:33,  1.04it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:32,  1.68it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:10,  2.14it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:52,  2.82it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:35,  4.03it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:27,  5.14it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:22,  6.07it/s]
Loading 0:  63%|██████▎   | 228/363 [00:23<00:15,  8.54it/s]
Loading 0:  64%|██████▎   | 231/363 [00:23<00:13,  9.98it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 14.75it/s]
Loading 0:  66%|██████▌   | 240/363 [00:24<00:07, 15.57it/s]
Loading 0:  68%|██████▊   | 246/363 [00:24<00:05, 20.76it/s]
Loading 0:  69%|██████▉   | 250/363 [00:24<00:05, 21.54it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 24.60it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 24.55it/s]
Loading 0:  73%|███████▎  | 264/363 [00:24<00:03, 29.27it/s]
Loading 0:  74%|███████▍  | 268/363 [00:25<00:04, 22.67it/s]
Loading 0:  75%|███████▍  | 271/363 [00:25<00:04, 21.11it/s]
Loading 0:  75%|███████▌  | 274/363 [00:25<00:04, 22.07it/s]
Loading 0:  76%|███████▋  | 277/363 [00:25<00:03, 22.55it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 25.53it/s]
Loading 0:  79%|███████▊  | 285/363 [00:25<00:03, 22.58it/s]
Loading 0:  80%|███████▉  | 289/363 [00:25<00:02, 26.22it/s]
Loading 0:  80%|████████  | 292/363 [00:25<00:02, 26.37it/s]
Loading 0:  81%|████████▏ | 295/363 [00:26<00:02, 25.72it/s]
Loading 0:  82%|████████▏ | 299/363 [00:26<00:02, 25.33it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 22.69it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 21.16it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 22.21it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 23.03it/s]
Loading 0:  88%|████████▊ | 318/363 [00:27<00:01, 26.07it/s]
Loading 0:  88%|████████▊ | 321/363 [00:27<00:01, 23.51it/s]
Loading 0:  90%|█████████ | 327/363 [00:27<00:01, 28.31it/s]
Loading 0:  91%|█████████ | 330/363 [00:27<00:01, 24.68it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:01, 26.27it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 25.27it/s]
Loading 0:  94%|█████████▍| 341/363 [00:28<00:01, 14.98it/s]
Loading 0:  96%|█████████▌| 347/363 [00:28<00:00, 20.44it/s]
Loading 0:  96%|█████████▋| 350/363 [00:28<00:00, 21.35it/s]
Loading 0:  98%|█████████▊| 355/363 [00:28<00:00, 24.83it/s]
Loading 0:  99%|█████████▊| 358/363 [00:28<00:00, 22.80it/s]
                                                            
Job chaiml-mistral32-nis-de-15507-v1-mkmlizer completed after 157.67s with status: succeeded
Stopping job with name chaiml-mistral32-nis-de-15507-v1-mkmlizer
Pipeline stage MKMLizer completed in 158.32s
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-nis-de-15507-v1
Waiting for inference service chaiml-mistral32-nis-de-15507-v1 to be ready
Inference service chaiml-mistral32-nis-de-15507-v1 ready after 181.51331520080566s
Pipeline stage MKMLDeployer completed in 181.96s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.671480894088745s
Received healthy response to inference request in 2.0400309562683105s
Received healthy response to inference request in 1.8381927013397217s
Received healthy response to inference request in 2.057551860809326s
5 requests
1 failed requests
5th percentile: 1.8785603523254395
10th percentile: 1.9189280033111573
20th percentile: 1.9996633052825927
30th percentile: 2.0435351371765136
40th percentile: 2.05054349899292
50th percentile: 2.057551860809326
60th percentile: 2.3031234741210938
70th percentile: 2.5486950874328613
80th percentile: 6.165224075317386
90th percentile: 13.15271043777466
95th percentile: 16.646453619003292
99th percentile: 19.441448163986205
mean time: 5.749490642547608
%s, retrying in %s seconds...
Received healthy response to inference request in 2.116844415664673s
Received healthy response to inference request in 2.0364818572998047s
Received healthy response to inference request in 1.9396297931671143s
Received healthy response to inference request in 1.9005696773529053s
Received healthy response to inference request in 2.011134624481201s
5 requests
0 failed requests
5th percentile: 1.908381700515747
10th percentile: 1.9161937236785889
20th percentile: 1.9318177700042725
30th percentile: 1.9539307594299316
40th percentile: 1.9825326919555664
50th percentile: 2.011134624481201
60th percentile: 2.0212735176086425
70th percentile: 2.031412410736084
80th percentile: 2.0525543689727783
90th percentile: 2.0846993923187256
95th percentile: 2.100771903991699
99th percentile: 2.113629913330078
mean time: 2.0009320735931397
Pipeline stage StressChecker completed in 41.34s
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 1.15s
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-nis-de_15507_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral32-nis-de-15507-v1-profiler
Waiting for inference service chaiml-mistral32-nis-de-15507-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3416.45s
Shutdown handler de-registered
chaiml-mistral32-nis-de_15507_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral32-nis-de_15507_v1 status is now torndown due to DeploymentManager action