developer_uid: NischayDnk
submission_id: chaiml-mistral32-deepse_89261_v5
model_name: chaiml-mistral32-deepse_89261_v5
model_group: ChaiML/mistral32_deepsee
status: torndown
timestamp: 2025-07-09T13:27:31+00:00
num_battles: 6826
num_wins: 3619
celo_rating: 1315.55
family_friendly_score: 0.5036
family_friendly_standard_error: 0.0070708845274123945
submission_type: basic
model_repo: ChaiML/mistral32_deepseek_cpos3_cpos21322_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': 0.5171804552670113, 'latency_mean': 1.9334622895717621, 'latency_p50': 1.9397432804107666, 'latency_p90': 2.1457966804504394}, {'batch_size': 3, 'throughput': 1.0466340124552498, 'latency_mean': 2.855715820789337, 'latency_p50': 2.854305386543274, 'latency_p90': 3.1442755699157714}, {'batch_size': 5, 'throughput': 1.3461970653615605, 'latency_mean': 3.699695395231247, 'latency_p50': 3.6838855743408203, 'latency_p90': 4.151194524765015}, {'batch_size': 6, 'throughput': 1.4349337116799779, 'latency_mean': 4.1448152482509615, 'latency_p50': 4.139586329460144, 'latency_p90': 4.674569392204285}, {'batch_size': 8, 'throughput': 1.5686509848330092, 'latency_mean': 5.055265045166015, 'latency_p50': 5.089349627494812, 'latency_p90': 5.664507126808166}, {'batch_size': 10, 'throughput': 1.6435673404072233, 'latency_mean': 6.0179923105239865, 'latency_p50': 6.060186982154846, 'latency_p90': 6.788075828552246}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-mistral32-deepse_89261_v5
is_internal_developer: False
language_model: ChaiML/mistral32_deepseek_cpos3_cpos21322_sfts11306_seq96_exp6
model_size: 24B
ranking_group: single
throughput_3p7s: 1.35
us_pacific_date: 2025-07-09
win_ratio: 0.5301787283914445
generation_params: {'temperature': 0.65, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 80, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['###', '</s>', '<|im_end|>', '<|im_start|>', '\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-deepse-89261-v5-mkmlizer
Waiting for job on chaiml-mistral32-deepse-89261-v5-mkmlizer to finish
chaiml-mistral32-deepse-89261-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral32-deepse-89261-v5-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-89261-v5-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mistral32-deepse-89261-v5-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mistral32-deepse-89261-v5-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mistral32-deepse-89261-v5-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mistral32-deepse-89261-v5-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mistral32-deepse-89261-v5-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mistral32-deepse-89261-v5-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mistral32-deepse-89261-v5-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mistral32-deepse-89261-v5-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-89261-v5-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-mistral32-deepse-89261-v5-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mistral32-deepse-89261-v5-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mistral32-deepse-89261-v5-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral32-deepse-89261-v5-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-89261-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral32-deepse-89261-v5-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral32-deepse-89261-v5-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-89261-v5-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral32-deepse-89261-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral32-deepse-89261-v5-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral32-deepse-89261-v5-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-89261-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral32-deepse-89261-v5-mkmlizer: Downloaded to shared memory in 50.659s
chaiml-mistral32-deepse-89261-v5-mkmlizer: Checking if ChaiML/mistral32_deepseek_cpos3_cpos21322_sfts11306_seq96_exp6 already exists in ChaiML
chaiml-mistral32-deepse-89261-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpchn374qf, device:0
chaiml-mistral32-deepse-89261-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral32-deepse-89261-v5-mkmlizer: quantized model in 49.321s
chaiml-mistral32-deepse-89261-v5-mkmlizer: Processed model ChaiML/mistral32_deepseek_cpos3_cpos21322_sfts11306_seq96_exp6 in 99.981s
chaiml-mistral32-deepse-89261-v5-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral32-deepse-89261-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral32-deepse-89261-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral32-deepse-89261-v5/nvidia
chaiml-mistral32-deepse-89261-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-89261-v5/nvidia/config.json
chaiml-mistral32-deepse-89261-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-89261-v5/nvidia/special_tokens_map.json
chaiml-mistral32-deepse-89261-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-89261-v5/nvidia/tokenizer_config.json
chaiml-mistral32-deepse-89261-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-89261-v5/nvidia/tokenizer.json
chaiml-mistral32-deepse-89261-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral32-deepse-89261-v5/nvidia/flywheel_model.1.safetensors
chaiml-mistral32-deepse-89261-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral32-deepse-89261-v5/nvidia/flywheel_model.0.safetensors
chaiml-mistral32-deepse-89261-v5-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:46,  3.12s/it]
Loading 0:   1%|▏         | 5/363 [00:06<06:03,  1.02s/it]
Loading 0:   2%|▏         | 7/363 [00:06<03:49,  1.55it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:28,  3.95it/s]
Loading 0:   4%|▍         | 16/363 [00:06<01:06,  5.20it/s]
Loading 0:   6%|▌         | 22/363 [00:07<00:44,  7.74it/s]
Loading 0:   7%|▋         | 25/363 [00:07<00:37,  8.94it/s]
Loading 0:   9%|▊         | 31/363 [00:07<00:24, 13.33it/s]
Loading 0:   9%|▉         | 34/363 [00:07<00:23, 13.91it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:17, 18.98it/s]
Loading 0:  12%|█▏        | 43/363 [00:07<00:17, 18.42it/s]
Loading 0:  13%|█▎        | 49/363 [00:08<00:13, 23.52it/s]
Loading 0:  15%|█▍        | 53/363 [00:08<00:13, 23.18it/s]
Loading 0:  16%|█▌        | 58/363 [00:08<00:11, 25.95it/s]
Loading 0:  17%|█▋        | 62/363 [00:08<00:15, 18.85it/s]
Loading 0:  18%|█▊        | 67/363 [00:08<00:13, 22.21it/s]
Loading 0:  19%|█▉        | 70/363 [00:09<00:13, 21.08it/s]
Loading 0:  20%|██        | 74/363 [00:09<00:11, 24.24it/s]
Loading 0:  21%|██        | 77/363 [00:09<00:11, 25.20it/s]
Loading 0:  22%|██▏       | 80/363 [00:09<00:11, 24.73it/s]
Loading 0:  23%|██▎       | 84/363 [00:09<00:09, 28.24it/s]
Loading 0:  24%|██▍       | 88/363 [00:09<00:11, 23.67it/s]
Loading 0:  26%|██▌       | 94/363 [00:09<00:09, 28.23it/s]
Loading 0:  27%|██▋       | 98/363 [00:10<00:13, 19.10it/s]
Loading 0:  28%|██▊       | 103/363 [00:10<00:11, 22.34it/s]
Loading 0:  29%|██▉       | 106/363 [00:10<00:12, 20.91it/s]
Loading 0:  31%|███       | 112/363 [00:10<00:09, 25.59it/s]
Loading 0:  32%|███▏      | 115/363 [00:10<00:10, 22.58it/s]
Loading 0:  33%|███▎      | 121/363 [00:11<00:08, 27.16it/s]
Loading 0:  34%|███▍      | 124/363 [00:11<00:09, 24.10it/s]
Loading 0:  36%|███▌      | 130/363 [00:11<00:08, 28.31it/s]
Loading 0:  37%|███▋      | 133/363 [00:11<00:09, 25.06it/s]
Loading 0:  38%|███▊      | 139/363 [00:11<00:10, 21.72it/s]
Loading 0:  39%|███▉      | 142/363 [00:12<00:10, 20.87it/s]
Loading 0:  41%|████      | 148/363 [00:12<00:08, 25.83it/s]
Loading 0:  42%|████▏     | 151/363 [00:12<00:08, 23.73it/s]
Loading 0:  43%|████▎     | 157/363 [00:12<00:07, 28.10it/s]
Loading 0:  44%|████▍     | 160/363 [00:12<00:08, 24.95it/s]
Loading 0:  46%|████▌     | 166/363 [00:12<00:06, 29.58it/s]
Loading 0:  47%|████▋     | 170/363 [00:13<00:06, 27.77it/s]
Loading 0:  48%|████▊     | 175/363 [00:13<00:06, 30.01it/s]
Loading 0:  49%|████▉     | 179/363 [00:13<00:09, 20.44it/s]
Loading 0:  51%|█████     | 184/363 [00:13<00:07, 23.65it/s]
Loading 0:  52%|█████▏    | 187/363 [00:28<03:14,  1.11s/it]
Loading 0:  53%|█████▎    | 191/363 [00:28<02:16,  1.26it/s]
Loading 0:  53%|█████▎    | 194/363 [00:28<01:44,  1.61it/s]
Loading 0:  54%|█████▍    | 197/363 [00:28<01:18,  2.12it/s]
Loading 0:  56%|█████▌    | 202/363 [00:29<00:49,  3.28it/s]
Loading 0:  56%|█████▋    | 205/363 [00:29<00:38,  4.06it/s]
Loading 0:  58%|█████▊    | 209/363 [00:29<00:27,  5.67it/s]
Loading 0:  58%|█████▊    | 212/363 [00:29<00:21,  7.12it/s]
Loading 0:  59%|█████▉    | 215/363 [00:29<00:19,  7.48it/s]
Loading 0:  60%|██████    | 218/363 [00:29<00:15,  9.40it/s]
Loading 0:  61%|██████    | 221/363 [00:30<00:12, 11.63it/s]
Loading 0:  62%|██████▏   | 224/363 [00:30<00:10, 13.44it/s]
Loading 0:  63%|██████▎   | 227/363 [00:30<00:08, 15.96it/s]
Loading 0:  63%|██████▎   | 230/363 [00:30<00:07, 18.39it/s]
Loading 0:  64%|██████▍   | 233/363 [00:30<00:06, 19.51it/s]
Loading 0:  65%|██████▌   | 236/363 [00:30<00:05, 21.74it/s]
Loading 0:  66%|██████▌   | 239/363 [00:30<00:05, 23.52it/s]
Loading 0:  67%|██████▋   | 242/363 [00:30<00:05, 23.46it/s]
Loading 0:  68%|██████▊   | 247/363 [00:31<00:04, 26.65it/s]
Loading 0:  69%|██████▉   | 250/363 [00:31<00:04, 23.02it/s]
Loading 0:  71%|███████   | 256/363 [00:31<00:05, 20.34it/s]
Loading 0:  71%|███████▏  | 259/363 [00:31<00:05, 19.41it/s]
Loading 0:  72%|███████▏  | 263/363 [00:31<00:04, 23.03it/s]
Loading 0:  73%|███████▎  | 266/363 [00:31<00:03, 24.27it/s]
Loading 0:  74%|███████▍  | 269/363 [00:32<00:03, 23.86it/s]
Loading 0:  75%|███████▌  | 274/363 [00:32<00:03, 26.44it/s]
Loading 0:  76%|███████▋  | 277/363 [00:32<00:03, 23.53it/s]
Loading 0:  77%|███████▋  | 281/363 [00:32<00:03, 26.86it/s]
Loading 0:  78%|███████▊  | 284/363 [00:32<00:02, 27.41it/s]
Loading 0:  79%|███████▉  | 287/363 [00:32<00:02, 26.49it/s]
Loading 0:  80%|████████  | 292/363 [00:32<00:02, 28.89it/s]
Loading 0:  81%|████████▏ | 295/363 [00:33<00:03, 17.90it/s]
Loading 0:  83%|████████▎ | 301/363 [00:33<00:02, 23.20it/s]
Loading 0:  84%|████████▎ | 304/363 [00:33<00:02, 21.72it/s]
Loading 0:  85%|████████▌ | 310/363 [00:33<00:01, 26.55it/s]
Loading 0:  86%|████████▌ | 313/363 [00:33<00:02, 24.02it/s]
Loading 0:  88%|████████▊ | 319/363 [00:34<00:01, 28.35it/s]
Loading 0:  89%|████████▉ | 323/363 [00:34<00:01, 26.61it/s]
Loading 0:  90%|█████████ | 328/363 [00:34<00:01, 28.91it/s]
Loading 0:  91%|█████████▏| 332/363 [00:34<00:01, 19.85it/s]
Loading 0:  93%|█████████▎| 337/363 [00:34<00:01, 22.78it/s]
Loading 0:  94%|█████████▎| 340/363 [00:35<00:01, 21.54it/s]
Loading 0:  95%|█████████▌| 346/363 [00:35<00:00, 26.35it/s]
Loading 0:  96%|█████████▌| 349/363 [00:35<00:00, 23.74it/s]
Loading 0:  98%|█████████▊| 355/363 [00:35<00:00, 27.86it/s]
Loading 0:  99%|█████████▊| 358/363 [00:35<00:00, 24.76it/s]
Loading 0: 100%|█████████▉| 362/363 [00:35<00:00, 27.79it/s]
                                                            

Job chaiml-mistral32-deepse-89261-v5-mkmlizer completed after 126.48s with status: succeeded
Stopping job with name chaiml-mistral32-deepse-89261-v5-mkmlizer
Pipeline stage MKMLizer completed in 127.18s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral32-deepse-89261-v5
Waiting for inference service chaiml-mistral32-deepse-89261-v5 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)
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-v5 ready after 201.0376455783844s
Pipeline stage MKMLDeployer completed in 201.93s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.791640281677246s
Received healthy response to inference request in 2.3059866428375244s
Received healthy response to inference request in 2.2055933475494385s
Received healthy response to inference request in 1.9081063270568848s
Received healthy response to inference request in 2.3128416538238525s
5 requests
0 failed requests
5th percentile: 1.9676037311553956
10th percentile: 2.0271011352539063
20th percentile: 2.146095943450928
30th percentile: 2.2256720066070557
40th percentile: 2.26582932472229
50th percentile: 2.3059866428375244
60th percentile: 2.308728647232056
70th percentile: 2.311470651626587
80th percentile: 2.4086013793945313
90th percentile: 2.6001208305358885
95th percentile: 2.6958805561065673
99th percentile: 2.7724883365631103
mean time: 2.3048336505889893
Pipeline stage StressChecker completed in 12.92s
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 0.70s
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 0.68s
Shutdown handler de-registered
chaiml-mistral32-deepse_89261_v5 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral32-deepse-89261-v5-profiler
Waiting for inference service chaiml-mistral32-deepse-89261-v5-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 3094.65s
Shutdown handler de-registered
chaiml-mistral32-deepse_89261_v5 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral32-deepse_89261_v5 status is now torndown due to DeploymentManager action