developer_uid: NischayDnk
submission_id: chaiml-mistral32-deepse_16364_v2
model_name: chaiml-mistral32-deepse_16364_v2
model_group: ChaiML/mistral32_deepsee
status: torndown
timestamp: 2025-07-08T15:08:42+00:00
num_battles: 12334
num_wins: 6609
celo_rating: 1321.43
family_friendly_score: 0.507
family_friendly_standard_error: 0.007070374813261317
submission_type: basic
model_repo: ChaiML/mistral32_deepseek_cpos2_sfts11306_seq96_exp6
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': 0.5273470529120874, 'latency_mean': 1.8961807143688203, 'latency_p50': 1.901291847229004, 'latency_p90': 2.103759694099426}, {'batch_size': 3, 'throughput': 1.0613283483160576, 'latency_mean': 2.8105668091773985, 'latency_p50': 2.80672550201416, 'latency_p90': 3.111886405944824}, {'batch_size': 5, 'throughput': 1.3613792312865558, 'latency_mean': 3.6510988271236418, 'latency_p50': 3.613126039505005, 'latency_p90': 4.058766293525696}, {'batch_size': 6, 'throughput': 1.465528729865987, 'latency_mean': 4.06519601225853, 'latency_p50': 4.081364035606384, 'latency_p90': 4.537576293945312}, {'batch_size': 8, 'throughput': 1.604419712874136, 'latency_mean': 4.947591465711594, 'latency_p50': 4.960890531539917, 'latency_p90': 5.524894618988037}, {'batch_size': 10, 'throughput': 1.6778326825905836, 'latency_mean': 5.897106581926346, 'latency_p50': 5.9394848346710205, 'latency_p90': 6.523821520805359}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-mistral32-deepse_16364_v2
is_internal_developer: False
language_model: ChaiML/mistral32_deepseek_cpos2_sfts11306_seq96_exp6
model_size: 24B
ranking_group: single
throughput_3p7s: 1.38
us_pacific_date: 2025-07-08
win_ratio: 0.535835900762121
generation_params: {'temperature': 0.7, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 80, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|im_end|>', '###', '\n', '<|im_start|>', '</s>'], '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-16364-v2-mkmlizer
Waiting for job on chaiml-mistral32-deepse-16364-v2-mkmlizer to finish
chaiml-mistral32-deepse-16364-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral32-deepse-16364-v2-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-16364-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mistral32-deepse-16364-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mistral32-deepse-16364-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mistral32-deepse-16364-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mistral32-deepse-16364-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mistral32-deepse-16364-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mistral32-deepse-16364-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mistral32-deepse-16364-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mistral32-deepse-16364-v2-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-16364-v2-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-mistral32-deepse-16364-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mistral32-deepse-16364-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mistral32-deepse-16364-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral32-deepse-16364-v2-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-16364-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral32-deepse-16364-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral32-deepse-16364-v2-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-16364-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral32-deepse-16364-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral32-deepse-16364-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral32-deepse-16364-v2-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-16364-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral32-deepse-16364-v2-mkmlizer: Downloaded to shared memory in 69.012s
chaiml-mistral32-deepse-16364-v2-mkmlizer: Checking if ChaiML/mistral32_deepseek_cpos2_sfts11306_seq96_exp6 already exists in ChaiML
chaiml-mistral32-deepse-16364-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7xpcr_zq, device:0
chaiml-mistral32-deepse-16364-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral32-deepse-16364-v2-mkmlizer: quantized model in 48.546s
chaiml-mistral32-deepse-16364-v2-mkmlizer: Processed model ChaiML/mistral32_deepseek_cpos2_sfts11306_seq96_exp6 in 117.558s
chaiml-mistral32-deepse-16364-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral32-deepse-16364-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral32-deepse-16364-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral32-deepse-16364-v2/nvidia
chaiml-mistral32-deepse-16364-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-16364-v2/nvidia/config.json
chaiml-mistral32-deepse-16364-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-16364-v2/nvidia/special_tokens_map.json
chaiml-mistral32-deepse-16364-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-16364-v2/nvidia/tokenizer.json
chaiml-mistral32-deepse-16364-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral32-deepse-16364-v2/nvidia/flywheel_model.1.safetensors
chaiml-mistral32-deepse-16364-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral32-deepse-16364-v2/nvidia/flywheel_model.0.safetensors
chaiml-mistral32-deepse-16364-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<19:25,  3.23s/it]
Loading 0:   2%|▏         | 6/363 [00:06<05:14,  1.14it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:51,  3.13it/s]
Loading 0:   5%|▍         | 17/363 [00:06<01:16,  4.50it/s]
Loading 0:   6%|▌         | 22/363 [00:07<00:54,  6.27it/s]
Loading 0:   7%|▋         | 25/363 [00:07<00:45,  7.49it/s]
Loading 0:   9%|▊         | 31/363 [00:07<00:28, 11.52it/s]
Loading 0:  10%|▉         | 35/363 [00:07<00:24, 13.60it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:18, 17.44it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:16, 18.97it/s]
Loading 0:  13%|█▎        | 49/363 [00:08<00:13, 23.03it/s]
Loading 0:  15%|█▍        | 53/363 [00:08<00:13, 23.35it/s]
Loading 0:  16%|█▌        | 58/363 [00:08<00:11, 26.84it/s]
Loading 0:  17%|█▋        | 62/363 [00:08<00:15, 19.76it/s]
Loading 0:  18%|█▊        | 67/363 [00:08<00:12, 23.55it/s]
Loading 0:  20%|█▉        | 71/363 [00:09<00:12, 23.97it/s]
Loading 0:  21%|██        | 76/363 [00:09<00:10, 27.55it/s]
Loading 0:  22%|██▏       | 80/363 [00:09<00:11, 25.64it/s]
Loading 0:  23%|██▎       | 85/363 [00:09<00:10, 27.76it/s]
Loading 0:  25%|██▍       | 89/363 [00:09<00:10, 26.03it/s]
Loading 0:  26%|██▌       | 94/363 [00:09<00:09, 28.52it/s]
Loading 0:  27%|██▋       | 98/363 [00:10<00:13, 20.19it/s]
Loading 0:  28%|██▊       | 103/363 [00:10<00:10, 23.76it/s]
Loading 0:  29%|██▉       | 106/363 [00:10<00:11, 21.92it/s]
Loading 0:  31%|███       | 112/363 [00:10<00:09, 26.87it/s]
Loading 0:  32%|███▏      | 116/363 [00:10<00:09, 25.47it/s]
Loading 0:  33%|███▎      | 121/363 [00:10<00:08, 27.63it/s]
Loading 0:  34%|███▍      | 124/363 [00:11<00:09, 24.57it/s]
Loading 0:  36%|███▌      | 130/363 [00:11<00:08, 28.90it/s]
Loading 0:  37%|███▋      | 134/363 [00:11<00:08, 26.15it/s]
Loading 0:  38%|███▊      | 139/363 [00:11<00:10, 20.86it/s]
Loading 0:  39%|███▉      | 142/363 [00:11<00:11, 19.96it/s]
Loading 0:  41%|████      | 148/363 [00:12<00:08, 25.37it/s]
Loading 0:  42%|████▏     | 151/363 [00:12<00:09, 23.22it/s]
Loading 0:  43%|████▎     | 157/363 [00:12<00:07, 27.66it/s]
Loading 0:  44%|████▍     | 160/363 [00:12<00:08, 24.65it/s]
Loading 0:  46%|████▌     | 166/363 [00:12<00:06, 29.20it/s]
Loading 0:  47%|████▋     | 170/363 [00:12<00:07, 26.86it/s]
Loading 0:  48%|████▊     | 175/363 [00:13<00:06, 29.42it/s]
Loading 0:  49%|████▉     | 179/363 [00:13<00:09, 20.41it/s]
Loading 0:  51%|█████     | 184/363 [00:13<00:07, 23.69it/s]
Loading 0:  51%|█████     | 185/363 [00:28<00:07, 23.69it/s]
Loading 0:  51%|█████     | 186/363 [00:28<03:31,  1.19s/it]
Loading 0:  53%|█████▎    | 191/363 [00:28<02:13,  1.29it/s]
Loading 0:  54%|█████▎    | 195/363 [00:28<01:36,  1.74it/s]
Loading 0:  56%|█████▌    | 202/363 [00:28<00:54,  2.94it/s]
Loading 0:  57%|█████▋    | 206/363 [00:29<00:41,  3.80it/s]
Loading 0:  58%|█████▊    | 211/363 [00:29<00:28,  5.28it/s]
Loading 0:  59%|█████▉    | 215/363 [00:29<00:24,  6.14it/s]
Loading 0:  61%|██████    | 220/363 [00:29<00:16,  8.41it/s]
Loading 0:  62%|██████▏   | 224/363 [00:29<00:13, 10.16it/s]
Loading 0:  63%|██████▎   | 229/363 [00:30<00:10, 13.29it/s]
Loading 0:  64%|██████▍   | 233/363 [00:30<00:08, 14.92it/s]
Loading 0:  66%|██████▌   | 238/363 [00:30<00:06, 18.37it/s]
Loading 0:  67%|██████▋   | 242/363 [00:30<00:06, 19.41it/s]
Loading 0:  68%|██████▊   | 247/363 [00:30<00:05, 23.02it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:04, 22.84it/s]
Loading 0:  71%|███████   | 256/363 [00:31<00:05, 20.29it/s]
Loading 0:  71%|███████▏  | 259/363 [00:31<00:05, 19.44it/s]
Loading 0:  73%|███████▎  | 265/363 [00:31<00:03, 24.54it/s]
Loading 0:  74%|███████▍  | 268/363 [00:31<00:04, 22.50it/s]
Loading 0:  75%|███████▌  | 274/363 [00:31<00:03, 27.05it/s]
Loading 0:  76%|███████▋  | 277/363 [00:31<00:03, 24.04it/s]
Loading 0:  77%|███████▋  | 281/363 [00:32<00:03, 26.48it/s]
Loading 0:  78%|███████▊  | 284/363 [00:32<00:02, 26.54it/s]
Loading 0:  79%|███████▉  | 287/363 [00:32<00:02, 25.41it/s]
Loading 0:  80%|████████  | 292/363 [00:32<00:02, 28.51it/s]
Loading 0:  81%|████████▏ | 295/363 [00:32<00:03, 17.70it/s]
Loading 0:  83%|████████▎ | 301/363 [00:32<00:02, 23.24it/s]
Loading 0:  84%|████████▎ | 304/363 [00:33<00:02, 21.49it/s]
Loading 0:  85%|████████▌ | 310/363 [00:33<00:02, 26.29it/s]
Loading 0:  86%|████████▌ | 313/363 [00:33<00:02, 23.74it/s]
Loading 0:  88%|████████▊ | 319/363 [00:33<00:01, 28.69it/s]
Loading 0:  89%|████████▉ | 323/363 [00:33<00:01, 26.93it/s]
Loading 0:  90%|█████████ | 328/363 [00:33<00:01, 29.33it/s]
Loading 0:  91%|█████████▏| 332/363 [00:34<00:01, 20.09it/s]
Loading 0:  93%|█████████▎| 337/363 [00:34<00:01, 23.34it/s]
Loading 0:  94%|█████████▎| 340/363 [00:34<00:01, 21.63it/s]
Loading 0:  95%|█████████▌| 346/363 [00:34<00:00, 26.89it/s]
Loading 0:  96%|█████████▋| 350/363 [00:34<00:00, 26.04it/s]
Loading 0:  98%|█████████▊| 355/363 [00:35<00:00, 28.31it/s]
Loading 0:  99%|█████████▉| 359/363 [00:35<00:00, 26.34it/s]
                                                            

Job chaiml-mistral32-deepse-16364-v2-mkmlizer completed after 148.38s with status: succeeded
Stopping job with name chaiml-mistral32-deepse-16364-v2-mkmlizer
Pipeline stage MKMLizer completed in 148.99s
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-16364-v2
Waiting for inference service chaiml-mistral32-deepse-16364-v2 to be ready
Inference service chaiml-mistral32-deepse-16364-v2 ready after 192.10147261619568s
Pipeline stage MKMLDeployer completed in 192.62s
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 3.157834529876709s
Received healthy response to inference request in 2.153872489929199s
Received healthy response to inference request in 2.82899808883667s
Received healthy response to inference request in 1.9649059772491455s
5 requests
1 failed requests
5th percentile: 2.002699279785156
10th percentile: 2.040492582321167
20th percentile: 2.1160791873931886
30th percentile: 2.2888976097106934
40th percentile: 2.5589478492736815
50th percentile: 2.82899808883667
60th percentile: 2.9605326652526855
70th percentile: 3.092067241668701
80th percentile: 6.556726646423343
90th percentile: 13.354510879516603
95th percentile: 16.75340299606323
99th percentile: 19.472516689300537
mean time: 6.051581239700317
%s, retrying in %s seconds...
Received healthy response to inference request in 1.8680269718170166s
Received healthy response to inference request in 1.9449756145477295s
Received healthy response to inference request in 1.9747951030731201s
Received healthy response to inference request in 2.0996031761169434s
Received healthy response to inference request in 2.3893814086914062s
5 requests
0 failed requests
5th percentile: 1.8834167003631592
10th percentile: 1.8988064289093018
20th percentile: 1.9295858860015869
30th percentile: 1.9509395122528077
40th percentile: 1.962867307662964
50th percentile: 1.9747951030731201
60th percentile: 2.0247183322906492
70th percentile: 2.074641561508179
80th percentile: 2.157558822631836
90th percentile: 2.2734701156616213
95th percentile: 2.3314257621765138
99th percentile: 2.3777902793884276
mean time: 2.0553564548492433
Pipeline stage StressChecker completed in 43.39s
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 0.77s
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_16364_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 6579.58s
Shutdown handler de-registered
chaiml-mistral32-deepse_16364_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral32-deepse_16364_v2 status is now torndown due to DeploymentManager action