chaiml-mistral32-sftexp1_2523

developer_uid: NischayDnk

submission_id: chaiml-mistral32-sftexp1_2523_v2

model_name: chaiml-mistral32-sftexp1_2523_v2

model_group: ChaiML/mistral32-sftexp1

status: torndown

timestamp: 2025-06-30T22:41:31+00:00

num_battles: 6669

num_wins: 3407

celo_rating: 1290.54

family_friendly_score: 0.548

family_friendly_standard_error: 0.0070384089111105224

submission_type: basic

model_repo: ChaiML/mistral32-sftexp1-s1-groksyn30jun-full-4e-top750

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': 0.48229261972396636, 'latency_mean': 2.0732923436164854, 'latency_p50': 2.069647789001465, 'latency_p90': 2.2807638883590697}, {'batch_size': 3, 'throughput': 0.9376828316857927, 'latency_mean': 3.1957751011848448, 'latency_p50': 3.2062662839889526, 'latency_p90': 3.475938582420349}, {'batch_size': 5, 'throughput': 1.1844415807265007, 'latency_mean': 4.1997923600673674, 'latency_p50': 4.185238599777222, 'latency_p90': 4.688229107856751}, {'batch_size': 6, 'throughput': 1.2583661898163496, 'latency_mean': 4.745227901935578, 'latency_p50': 4.747109889984131, 'latency_p90': 5.247408938407898}, {'batch_size': 8, 'throughput': 1.364203848483917, 'latency_mean': 5.823924816846848, 'latency_p50': 5.812820672988892, 'latency_p90': 6.521362066268921}, {'batch_size': 10, 'throughput': 1.4434883033257657, 'latency_mean': 6.874915189743042, 'latency_p50': 6.8740164041519165, 'latency_p90': 7.66588327884674}]

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

display_name: chaiml-mistral32-sftexp1_2523_v2

is_internal_developer: False

language_model: ChaiML/mistral32-sftexp1-s1-groksyn30jun-full-4e-top750

model_size: 24B

ranking_group: single

throughput_3p7s: 1.08

us_pacific_date: 2025-06-30

win_ratio: 0.5108711950817214

generation_params: {'temperature': 0.5, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|im_start|>', '<|im_end|>', '\n'], 'max_input_tokens': 1536, 'best_of': 6, 'max_output_tokens': 64}

formatter: {'memory_template': '<|system|>{bot_name}memory:{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': False}

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-sftexp1-2523-v2-mkmlizer
Waiting for job on chaiml-mistral32-sftexp1-2523-v2-mkmlizer to finish
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: ║                                                                     ║
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: ║                                                                     ║
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: ║                                                                     ║
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: ║                                                                     ║
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: ║                                                                     ║
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: Downloaded to shared memory in 80.480s
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: Checking if ChaiML/mistral32-sftexp1-s1-groksyn30jun-full-4e-top750 already exists in ChaiML
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmprerpz7dz, device:0
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: quantized model in 60.490s
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: Processed model ChaiML/mistral32-sftexp1-s1-groksyn30jun-full-4e-top750 in 140.971s
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral32-sftexp1-2523-v2
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral32-sftexp1-2523-v2/config.json
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral32-sftexp1-2523-v2/special_tokens_map.json
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral32-sftexp1-2523-v2/tokenizer_config.json
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral32-sftexp1-2523-v2/tokenizer.json
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral32-sftexp1-2523-v2/flywheel_model.1.safetensors
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral32-sftexp1-2523-v2/flywheel_model.0.safetensors
chaiml-mistral32-sftexp1-2523-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:12, 28.82it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:16, 21.31it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:13, 26.78it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:16, 21.41it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:13, 25.55it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:14, 24.33it/s]
Loading 0:   7%|▋         | 25/363 [00:01<00:15, 22.45it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:14, 23.76it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:12, 26.21it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:20, 15.89it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:19, 16.29it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:22, 14.01it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:16, 19.45it/s]
Loading 0:  13%|█▎        | 49/363 [00:02<00:15, 20.31it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:15, 19.82it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:14, 21.67it/s]
Loading 0:  16%|█▌        | 58/363 [00:02<00:13, 22.20it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:14, 21.44it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:13, 22.93it/s]
Loading 0:  19%|█▉        | 69/363 [00:03<00:11, 24.82it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:18, 16.12it/s]
Loading 0:  21%|██        | 75/363 [00:03<00:16, 17.21it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:14, 19.27it/s]
Loading 0:  23%|██▎       | 82/363 [00:04<00:14, 19.25it/s]
Loading 0:  24%|██▎       | 86/363 [00:04<00:13, 20.75it/s]
Loading 0:  25%|██▍       | 89/363 [00:04<00:13, 20.97it/s]
Loading 0:  25%|██▌       | 92/363 [00:04<00:16, 16.54it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:12, 21.91it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:11, 22.07it/s]
Loading 0:  28%|██▊       | 103/363 [00:05<00:11, 22.09it/s]
Loading 0:  29%|██▉       | 107/363 [00:05<00:14, 17.74it/s]
Loading 0:  31%|███       | 111/363 [00:05<00:12, 20.94it/s]
Loading 0:  31%|███▏      | 114/363 [00:05<00:12, 19.21it/s]
Loading 0:  33%|███▎      | 118/363 [00:05<00:10, 23.05it/s]
Loading 0:  33%|███▎      | 121/363 [00:05<00:10, 22.95it/s]
Loading 0:  34%|███▍      | 124/363 [00:06<00:11, 21.40it/s]
Loading 0:  35%|███▍      | 127/363 [00:06<00:10, 22.33it/s]
Loading 0:  36%|███▌      | 130/363 [00:06<00:10, 22.70it/s]
Loading 0:  37%|███▋      | 133/363 [00:06<00:10, 22.45it/s]
Loading 0:  38%|███▊      | 138/363 [00:06<00:09, 24.80it/s]
Loading 0:  39%|███▉      | 141/363 [00:06<00:10, 21.11it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:08, 24.86it/s]
Loading 0:  41%|████▏     | 150/363 [00:07<00:10, 21.08it/s]
Loading 0:  42%|████▏     | 153/363 [00:07<00:11, 17.57it/s]
Loading 0:  43%|████▎     | 157/363 [00:07<00:10, 20.23it/s]
Loading 0:  44%|████▍     | 160/363 [00:07<00:10, 19.73it/s]
Loading 0:  45%|████▍     | 163/363 [00:07<00:09, 21.49it/s]
Loading 0:  46%|████▌     | 166/363 [00:07<00:09, 21.52it/s]
Loading 0:  47%|████▋     | 169/363 [00:08<00:08, 21.76it/s]
Loading 0:  47%|████▋     | 172/363 [00:08<00:08, 23.09it/s]
Loading 0:  48%|████▊     | 175/363 [00:08<00:08, 22.55it/s]
Loading 0:  49%|████▉     | 178/363 [00:08<00:08, 22.27it/s]
Loading 0:  50%|█████     | 182/363 [00:08<00:07, 23.02it/s]
Loading 0:  52%|█████▏    | 187/363 [00:08<00:08, 19.77it/s]
Loading 0:  52%|█████▏    | 190/363 [00:09<00:09, 17.88it/s]
Loading 0:  53%|█████▎    | 193/363 [00:09<00:09, 18.59it/s]
Loading 0:  54%|█████▎    | 195/363 [00:09<00:09, 17.56it/s]
Loading 0:  55%|█████▍    | 199/363 [00:09<00:07, 21.76it/s]
Loading 0:  55%|█████▌    | 200/363 [00:19<00:07, 21.76it/s]
Loading 0:  55%|█████▌    | 201/363 [00:26<04:56,  1.83s/it]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:51,  1.45s/it]
Loading 0:  57%|█████▋    | 208/363 [00:27<02:05,  1.23it/s]
Loading 0:  58%|█████▊    | 211/363 [00:27<01:31,  1.66it/s]
Loading 0:  59%|█████▉    | 214/363 [00:27<01:06,  2.24it/s]
Loading 0:  60%|██████    | 218/363 [00:27<00:44,  3.29it/s]
Loading 0:  61%|██████    | 221/363 [00:28<00:33,  4.26it/s]
Loading 0:  62%|██████▏   | 224/363 [00:28<00:27,  5.06it/s]
Loading 0:  63%|██████▎   | 228/363 [00:28<00:18,  7.20it/s]
Loading 0:  64%|██████▎   | 231/363 [00:28<00:15,  8.26it/s]
Loading 0:  65%|██████▍   | 235/363 [00:28<00:11, 11.28it/s]
Loading 0:  66%|██████▌   | 238/363 [00:28<00:09, 13.06it/s]
Loading 0:  66%|██████▋   | 241/363 [00:29<00:08, 14.59it/s]
Loading 0:  67%|██████▋   | 244/363 [00:29<00:06, 17.03it/s]
Loading 0:  68%|██████▊   | 247/363 [00:29<00:06, 18.43it/s]
Loading 0:  69%|██████▉   | 250/363 [00:29<00:05, 19.19it/s]
Loading 0:  70%|██████▉   | 253/363 [00:29<00:05, 21.18it/s]
Loading 0:  71%|███████   | 256/363 [00:29<00:04, 21.63it/s]
Loading 0:  71%|███████▏  | 259/363 [00:29<00:04, 21.11it/s]
Loading 0:  73%|███████▎  | 264/363 [00:29<00:03, 26.98it/s]
Loading 0:  74%|███████▎  | 267/363 [00:30<00:05, 18.90it/s]
Loading 0:  74%|███████▍  | 270/363 [00:30<00:05, 16.06it/s]
Loading 0:  75%|███████▌  | 274/363 [00:30<00:04, 18.86it/s]
Loading 0:  76%|███████▋  | 277/363 [00:30<00:04, 19.11it/s]
Loading 0:  77%|███████▋  | 280/363 [00:30<00:03, 21.16it/s]
Loading 0:  78%|███████▊  | 283/363 [00:31<00:03, 21.65it/s]
Loading 0:  79%|███████▉  | 286/363 [00:31<00:03, 21.58it/s]
Loading 0:  80%|███████▉  | 289/363 [00:31<00:03, 23.25it/s]
Loading 0:  80%|████████  | 292/363 [00:31<00:03, 23.43it/s]
Loading 0:  81%|████████▏ | 295/363 [00:31<00:02, 23.26it/s]
Loading 0:  82%|████████▏ | 298/363 [00:31<00:02, 24.16it/s]
Loading 0:  83%|████████▎ | 303/363 [00:31<00:02, 26.03it/s]
Loading 0:  84%|████████▍ | 306/363 [00:32<00:03, 15.83it/s]
Loading 0:  85%|████████▌ | 310/363 [00:32<00:02, 18.49it/s]
Loading 0:  86%|████████▌ | 313/363 [00:32<00:02, 18.62it/s]
Loading 0:  87%|████████▋ | 316/363 [00:32<00:02, 20.71it/s]
Loading 0:  88%|████████▊ | 319/363 [00:32<00:02, 21.49it/s]
Loading 0:  89%|████████▊ | 322/363 [00:32<00:01, 21.13it/s]
Loading 0:  90%|████████▉ | 325/363 [00:33<00:01, 22.28it/s]
Loading 0:  90%|█████████ | 328/363 [00:33<00:01, 22.20it/s]
Loading 0:  91%|█████████ | 331/363 [00:33<00:01, 22.35it/s]
Loading 0:  92%|█████████▏| 334/363 [00:33<00:01, 23.88it/s]
Loading 0:  93%|█████████▎| 337/363 [00:33<00:01, 19.64it/s]
Loading 0:  94%|█████████▍| 341/363 [00:34<00:01, 12.48it/s]
Loading 0:  95%|█████████▌| 346/363 [00:34<00:00, 17.06it/s]
Loading 0:  96%|█████████▌| 349/363 [00:34<00:00, 16.61it/s]
Loading 0:  97%|█████████▋| 353/363 [00:34<00:00, 19.71it/s]
Loading 0:  98%|█████████▊| 356/363 [00:34<00:00, 20.95it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00, 21.45it/s]
                                                            
Job chaiml-mistral32-sftexp1-2523-v2-mkmlizer completed after 187.34s with status: succeeded
Stopping job with name chaiml-mistral32-sftexp1-2523-v2-mkmlizer
Pipeline stage MKMLizer completed in 187.85s
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-sftexp1-2523-v2
Waiting for inference service chaiml-mistral32-sftexp1-2523-v2 to be ready
Inference service chaiml-mistral32-sftexp1-2523-v2 ready after 210.90180110931396s
Pipeline stage MKMLDeployer completed in 211.67s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5296428203582764s
Received healthy response to inference request in 0.9985353946685791s
Received healthy response to inference request in 1.1929829120635986s
Received healthy response to inference request in 1.104156732559204s
Received healthy response to inference request in 1.230583906173706s
5 requests
0 failed requests
5th percentile: 1.019659662246704
10th percentile: 1.0407839298248291
20th percentile: 1.0830324649810792
30th percentile: 1.121921968460083
40th percentile: 1.157452440261841
50th percentile: 1.1929829120635986
60th percentile: 1.2080233097076416
70th percentile: 1.2230637073516846
80th percentile: 1.4903956890106205
90th percentile: 2.0100192546844484
95th percentile: 2.269831037521362
99th percentile: 2.4776804637908936
mean time: 1.411180353164673
Pipeline stage StressChecker completed in 8.31s
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 1.03s
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 0.65s
Shutdown handler de-registered
chaiml-mistral32-sftexp1_2523_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 3029.68s
Shutdown handler de-registered
chaiml-mistral32-sftexp1_2523_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral32-sftexp1_2523_v2 status is now torndown due to DeploymentManager action