chaiml-mistral32-deepse_16364

developer_uid: NischayDnk

submission_id: chaiml-mistral32-deepse_16364_v1

model_name: chaiml-mistral32-deepse_16364_v1

model_group: ChaiML/mistral32_deepsee

status: torndown

timestamp: 2025-07-08T13:41:55+00:00

num_battles: 10989

num_wins: 5816

celo_rating: 1316.34

family_friendly_score: 0.521

family_friendly_standard_error: 0.007064828377250222

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': 0.4972013516514261, 'latency_mean': 2.0110147368907927, 'latency_p50': 1.9980548620224, 'latency_p90': 2.270876717567444}, {'batch_size': 3, 'throughput': 0.9482717935998778, 'latency_mean': 3.151100730895996, 'latency_p50': 3.169947862625122, 'latency_p90': 3.5061676263809205}, {'batch_size': 5, 'throughput': 1.211418183282365, 'latency_mean': 4.100194723606109, 'latency_p50': 4.097895264625549, 'latency_p90': 4.620445823669433}, {'batch_size': 6, 'throughput': 1.2760895787134818, 'latency_mean': 4.670135605335235, 'latency_p50': 4.653240919113159, 'latency_p90': 5.194941782951355}, {'batch_size': 8, 'throughput': 1.3688770985859202, 'latency_mean': 5.785575050115585, 'latency_p50': 5.745553374290466, 'latency_p90': 6.567448210716248}, {'batch_size': 10, 'throughput': 1.4706627809714727, 'latency_mean': 6.725784633159638, 'latency_p50': 6.71221661567688, 'latency_p90': 7.511281824111938}]

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

display_name: chaiml-mistral32-deepse_16364_v1

is_internal_developer: False

language_model: ChaiML/mistral32_deepseek_cpos2_sfts11306_seq96_exp6

model_size: 24B

ranking_group: single

throughput_3p7s: 1.12

us_pacific_date: 2025-07-08

win_ratio: 0.5292565292565292

generation_params: {'temperature': 0.525, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|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-16364-v1-mkmlizer
Waiting for job on chaiml-mistral32-deepse-16364-v1-mkmlizer to finish
chaiml-mistral32-deepse-16364-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral32-deepse-16364-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-16364-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mistral32-deepse-16364-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mistral32-deepse-16364-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mistral32-deepse-16364-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mistral32-deepse-16364-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mistral32-deepse-16364-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mistral32-deepse-16364-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mistral32-deepse-16364-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mistral32-deepse-16364-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-16364-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-mistral32-deepse-16364-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mistral32-deepse-16364-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mistral32-deepse-16364-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral32-deepse-16364-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-16364-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral32-deepse-16364-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral32-deepse-16364-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-16364-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral32-deepse-16364-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral32-deepse-16364-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral32-deepse-16364-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-deepse-16364-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral32-deepse-16364-v1-mkmlizer: Downloaded to shared memory in 78.291s
chaiml-mistral32-deepse-16364-v1-mkmlizer: Checking if ChaiML/mistral32_deepseek_cpos2_sfts11306_seq96_exp6 already exists in ChaiML
chaiml-mistral32-deepse-16364-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmprxy0r5gz, device:0
chaiml-mistral32-deepse-16364-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral32-deepse-16364-v1-mkmlizer: quantized model in 47.732s
chaiml-mistral32-deepse-16364-v1-mkmlizer: Processed model ChaiML/mistral32_deepseek_cpos2_sfts11306_seq96_exp6 in 126.024s
chaiml-mistral32-deepse-16364-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral32-deepse-16364-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral32-deepse-16364-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral32-deepse-16364-v1/nvidia
chaiml-mistral32-deepse-16364-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-16364-v1/nvidia/config.json
chaiml-mistral32-deepse-16364-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-16364-v1/nvidia/special_tokens_map.json
chaiml-mistral32-deepse-16364-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-16364-v1/nvidia/tokenizer_config.json
chaiml-mistral32-deepse-16364-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-16364-v1/nvidia/tokenizer.json
chaiml-mistral32-deepse-16364-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral32-deepse-16364-v1/nvidia/flywheel_model.1.safetensors
chaiml-mistral32-deepse-16364-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral32-deepse-16364-v1/nvidia/flywheel_model.0.safetensors
chaiml-mistral32-deepse-16364-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:31,  3.08s/it]
Loading 0:   2%|▏         | 6/363 [00:06<05:00,  1.19it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:47,  3.25it/s]
Loading 0:   5%|▍         | 17/363 [00:06<01:14,  4.65it/s]
Loading 0:   6%|▌         | 22/363 [00:07<00:53,  6.37it/s]
Loading 0:   7%|▋         | 25/363 [00:07<00:44,  7.60it/s]
Loading 0:   9%|▊         | 31/363 [00:07<00:28, 11.62it/s]
Loading 0:  10%|▉         | 35/363 [00:07<00:24, 13.66it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:18, 17.40it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:17, 18.59it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:14, 21.76it/s]
Loading 0:  15%|█▍        | 53/363 [00:08<00:13, 22.33it/s]
Loading 0:  16%|█▌        | 58/363 [00:08<00:12, 25.17it/s]
Loading 0:  17%|█▋        | 61/363 [00:08<00:17, 17.55it/s]
Loading 0:  18%|█▊        | 67/363 [00:08<00:13, 22.68it/s]
Loading 0:  19%|█▉        | 70/363 [00:08<00:13, 21.63it/s]
Loading 0:  21%|██        | 76/363 [00:09<00:10, 26.47it/s]
Loading 0:  22%|██▏       | 80/363 [00:09<00:10, 25.87it/s]
Loading 0:  23%|██▎       | 85/363 [00:09<00:09, 28.65it/s]
Loading 0:  25%|██▍       | 89/363 [00:09<00:10, 27.19it/s]
Loading 0:  26%|██▌       | 94/363 [00:09<00:09, 29.36it/s]
Loading 0:  27%|██▋       | 98/363 [00:10<00:13, 20.12it/s]
Loading 0:  28%|██▊       | 103/363 [00:10<00:10, 23.70it/s]
Loading 0:  29%|██▉       | 106/363 [00:10<00:11, 22.44it/s]
Loading 0:  31%|███       | 112/363 [00:10<00:09, 26.93it/s]
Loading 0:  32%|███▏      | 115/363 [00:10<00:10, 24.24it/s]
Loading 0:  33%|███▎      | 119/363 [00:10<00:08, 27.38it/s]
Loading 0:  34%|███▍      | 123/363 [00:10<00:10, 23.98it/s]
Loading 0:  36%|███▌      | 130/363 [00:11<00:07, 30.46it/s]
Loading 0:  37%|███▋      | 134/363 [00:11<00:08, 28.54it/s]
Loading 0:  38%|███▊      | 139/363 [00:11<00:09, 23.00it/s]
Loading 0:  39%|███▉      | 142/363 [00:11<00:10, 21.40it/s]
Loading 0:  41%|████      | 148/363 [00:11<00:08, 26.07it/s]
Loading 0:  42%|████▏     | 151/363 [00:12<00:08, 23.94it/s]
Loading 0:  43%|████▎     | 155/363 [00:12<00:07, 26.95it/s]
Loading 0:  44%|████▍     | 159/363 [00:12<00:08, 23.58it/s]
Loading 0:  46%|████▌     | 166/363 [00:12<00:06, 29.92it/s]
Loading 0:  47%|████▋     | 170/363 [00:12<00:06, 27.90it/s]
Loading 0:  48%|████▊     | 175/363 [00:12<00:06, 30.13it/s]
Loading 0:  49%|████▉     | 179/363 [00:13<00:08, 21.31it/s]
Loading 0:  51%|█████     | 184/363 [00:13<00:07, 24.30it/s]
Loading 0:  51%|█████     | 185/363 [00:27<00:07, 24.30it/s]
Loading 0:  51%|█████     | 186/363 [00:27<03:24,  1.15s/it]
Loading 0:  53%|█████▎    | 191/363 [00:27<02:09,  1.33it/s]
Loading 0:  54%|█████▎    | 195/363 [00:28<01:33,  1.79it/s]
Loading 0:  56%|█████▌    | 202/363 [00:28<00:53,  3.01it/s]
Loading 0:  57%|█████▋    | 206/363 [00:28<00:40,  3.86it/s]
Loading 0:  58%|█████▊    | 211/363 [00:28<00:28,  5.34it/s]
Loading 0:  59%|█████▉    | 215/363 [00:29<00:23,  6.21it/s]
Loading 0:  61%|██████    | 220/363 [00:29<00:16,  8.44it/s]
Loading 0:  61%|██████▏   | 223/363 [00:29<00:14,  9.57it/s]
Loading 0:  63%|██████▎   | 229/363 [00:29<00:09, 13.57it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:08, 15.28it/s]
Loading 0:  66%|██████▌   | 238/363 [00:29<00:06, 18.76it/s]
Loading 0:  67%|██████▋   | 242/363 [00:29<00:06, 19.94it/s]
Loading 0:  68%|██████▊   | 247/363 [00:30<00:04, 23.20it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:04, 23.30it/s]
Loading 0:  71%|███████   | 256/363 [00:30<00:05, 20.85it/s]
Loading 0:  71%|███████▏  | 259/363 [00:30<00:05, 20.36it/s]
Loading 0:  73%|███████▎  | 265/363 [00:30<00:03, 25.36it/s]
Loading 0:  74%|███████▍  | 268/363 [00:31<00:03, 23.78it/s]
Loading 0:  75%|███████▌  | 274/363 [00:31<00:03, 28.08it/s]
Loading 0:  77%|███████▋  | 278/363 [00:31<00:03, 26.17it/s]
Loading 0:  78%|███████▊  | 283/363 [00:31<00:02, 28.79it/s]
Loading 0:  79%|███████▉  | 287/363 [00:31<00:02, 27.64it/s]
Loading 0:  80%|████████  | 292/363 [00:31<00:02, 30.06it/s]
Loading 0:  82%|████████▏ | 296/363 [00:32<00:03, 21.43it/s]
Loading 0:  83%|████████▎ | 301/363 [00:32<00:02, 24.90it/s]
Loading 0:  84%|████████▎ | 304/363 [00:32<00:02, 23.29it/s]
Loading 0:  85%|████████▌ | 310/363 [00:32<00:01, 28.36it/s]
Loading 0:  87%|████████▋ | 314/363 [00:32<00:01, 27.19it/s]
Loading 0:  88%|████████▊ | 319/363 [00:32<00:01, 29.93it/s]
Loading 0:  89%|████████▉ | 323/363 [00:33<00:01, 28.24it/s]
Loading 0:  90%|█████████ | 328/363 [00:33<00:01, 30.70it/s]
Loading 0:  91%|█████████▏| 332/363 [00:33<00:01, 21.67it/s]
Loading 0:  93%|█████████▎| 337/363 [00:33<00:01, 24.82it/s]
Loading 0:  94%|█████████▎| 340/363 [00:33<00:00, 23.03it/s]
Loading 0:  95%|█████████▌| 346/363 [00:33<00:00, 27.76it/s]
Loading 0:  96%|█████████▋| 350/363 [00:34<00:00, 26.30it/s]
Loading 0:  98%|█████████▊| 355/363 [00:34<00:00, 28.47it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00, 26.68it/s]
                                                            
Job chaiml-mistral32-deepse-16364-v1-mkmlizer completed after 158.91s with status: succeeded
Stopping job with name chaiml-mistral32-deepse-16364-v1-mkmlizer
Pipeline stage MKMLizer completed in 159.50s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral32-deepse-16364-v1
Waiting for inference service chaiml-mistral32-deepse-16364-v1 to be ready
Failed to get response for submission chaiml-gy-exp120-dpo-ex_31713_v2: ('http://chaiml-gy-exp120-dpo-ex-31713-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:46562->127.0.0.1:8080: read: connection reset by peer\n')
Failed to get response for submission chaiml-gy-exp122-dpo-ex_18452_v2: HTTPConnectionPool(host='chaiml-gy-exp122-dpo-ex-18452-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-mistral32-deepse-16364-v1 ready after 190.71364068984985s
Pipeline stage MKMLDeployer completed in 191.37s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9154245853424072s
Received healthy response to inference request in 2.490347146987915s
Received healthy response to inference request in 2.318446636199951s
Received healthy response to inference request in 2.3753044605255127s
Received healthy response to inference request in 2.2408249378204346s
5 requests
0 failed requests
5th percentile: 2.256349277496338
10th percentile: 2.271873617172241
20th percentile: 2.3029222965240477
30th percentile: 2.3298182010650637
40th percentile: 2.352561330795288
50th percentile: 2.3753044605255127
60th percentile: 2.4213215351104735
70th percentile: 2.4673386096954344
80th percentile: 2.5753626346588137
90th percentile: 2.7453936100006104
95th percentile: 2.8304090976715086
99th percentile: 2.8984214878082275
mean time: 2.468069553375244
Pipeline stage StressChecker completed in 13.98s
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 0.80s
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 0.73s
Shutdown handler de-registered
chaiml-mistral32-deepse_16364_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-deepse-16364-v1-profiler
Waiting for inference service chaiml-mistral32-deepse-16364-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 3272.01s
Shutdown handler de-registered
chaiml-mistral32-deepse_16364_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral32-deepse_16364_v1 status is now torndown due to DeploymentManager action