chaiml-wolverine2507082_32278

developer_uid: chai_backend_admin

submission_id: chaiml-wolverine2507082_32278_v1

model_name: chaiml-wolverine2507082_32278_v1

model_group: ChaiML/Wolverine25070821

status: torndown

timestamp: 2025-07-09T05:03:26+00:00

num_battles: 7618

num_wins: 3755

celo_rating: 1289.93

family_friendly_score: 0.5056

family_friendly_standard_error: 0.007070624300583366

submission_type: basic

model_repo: ChaiML/Wolverine250708211633_sft

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': 0.5252643146909396, 'latency_mean': 1.9037057733535767, 'latency_p50': 1.9115244150161743, 'latency_p90': 2.1126140356063843}, {'batch_size': 3, 'throughput': 1.0522101286032204, 'latency_mean': 2.842054079771042, 'latency_p50': 2.847574472427368, 'latency_p90': 3.118890142440796}, {'batch_size': 5, 'throughput': 1.3461461668974581, 'latency_mean': 3.691571813821793, 'latency_p50': 3.6684876680374146, 'latency_p90': 4.131164598464966}, {'batch_size': 6, 'throughput': 1.4472808208802808, 'latency_mean': 4.121517684459686, 'latency_p50': 4.119437217712402, 'latency_p90': 4.6098846912384035}, {'batch_size': 8, 'throughput': 1.5912545978124912, 'latency_mean': 4.993279849290848, 'latency_p50': 4.973293900489807, 'latency_p90': 5.59562566280365}, {'batch_size': 10, 'throughput': 1.6612035421849392, 'latency_mean': 5.963002965450287, 'latency_p50': 5.956492900848389, 'latency_p90': 6.7429849863052365}]

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

display_name: chaiml-wolverine2507082_32278_v1

is_internal_developer: True

language_model: ChaiML/Wolverine250708211633_sft

model_size: 24B

ranking_group: single

throughput_3p7s: 1.36

us_pacific_date: 2025-07-08

win_ratio: 0.49291152533473354

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>', '\n', 'You:', '####', '####\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}</s>\n', 'user_template': 'You: {message}\n', 'response_template': '{bot_name}:', '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-wolverine2507082-32278-v1-mkmlizer
Waiting for job on chaiml-wolverine2507082-32278-v1-mkmlizer to finish
chaiml-wolverine2507082-32278-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-wolverine2507082-32278-v1-mkmlizer: ║                                                                     ║
chaiml-wolverine2507082-32278-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-wolverine2507082-32278-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-wolverine2507082-32278-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-wolverine2507082-32278-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-wolverine2507082-32278-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-wolverine2507082-32278-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-wolverine2507082-32278-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-wolverine2507082-32278-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-wolverine2507082-32278-v1-mkmlizer: ║                                                                     ║
chaiml-wolverine2507082-32278-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-wolverine2507082-32278-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-wolverine2507082-32278-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-wolverine2507082-32278-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-wolverine2507082-32278-v1-mkmlizer: ║                                                                     ║
chaiml-wolverine2507082-32278-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-wolverine2507082-32278-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-wolverine2507082-32278-v1-mkmlizer: ║                                                                     ║
chaiml-wolverine2507082-32278-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-wolverine2507082-32278-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-wolverine2507082-32278-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-wolverine2507082-32278-v1-mkmlizer: ║                                                                     ║
chaiml-wolverine2507082-32278-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-wolverine2507082-32278-v1-mkmlizer: Downloaded to shared memory in 83.972s
chaiml-wolverine2507082-32278-v1-mkmlizer: Checking if ChaiML/Wolverine250708211633_sft already exists in ChaiML
chaiml-wolverine2507082-32278-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9ke5dyqc, device:0
chaiml-wolverine2507082-32278-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-wolverine2507082-32278-v1-mkmlizer: quantized model in 51.557s
chaiml-wolverine2507082-32278-v1-mkmlizer: Processed model ChaiML/Wolverine250708211633_sft in 135.530s
chaiml-wolverine2507082-32278-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-wolverine2507082-32278-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-wolverine2507082-32278-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-wolverine2507082-32278-v1/nvidia
chaiml-wolverine2507082-32278-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-wolverine2507082-32278-v1/nvidia/config.json
chaiml-wolverine2507082-32278-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-wolverine2507082-32278-v1/nvidia/special_tokens_map.json
chaiml-wolverine2507082-32278-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-wolverine2507082-32278-v1/nvidia/tokenizer_config.json
chaiml-wolverine2507082-32278-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-wolverine2507082-32278-v1/nvidia/tokenizer.json
chaiml-wolverine2507082-32278-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-wolverine2507082-32278-v1/nvidia/flywheel_model.1.safetensors
chaiml-wolverine2507082-32278-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-wolverine2507082-32278-v1/nvidia/flywheel_model.0.safetensors
chaiml-wolverine2507082-32278-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 37.17it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 27.42it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:12, 27.34it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:15, 21.83it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:13, 26.28it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:12, 26.62it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:13, 24.40it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:13, 25.76it/s]
Loading 0:   9%|▉         | 33/363 [00:01<00:15, 21.83it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:17, 18.96it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:14, 22.26it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:13, 23.31it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.67it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:12, 25.13it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 30.16it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 27.74it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 28.55it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 25.07it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:14, 20.46it/s]
Loading 0:  21%|██▏       | 78/363 [00:03<00:11, 25.23it/s]
Loading 0:  22%|██▏       | 81/363 [00:03<00:13, 21.62it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:12, 23.12it/s]
Loading 0:  24%|██▍       | 87/363 [00:03<00:13, 20.39it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:11, 23.28it/s]
Loading 0:  26%|██▌       | 94/363 [00:03<00:11, 22.54it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:11, 23.07it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:11, 23.72it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:11, 22.70it/s]
Loading 0:  29%|██▉       | 106/363 [00:04<00:10, 24.03it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:13, 18.29it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:12, 20.38it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:12, 20.27it/s]
Loading 0:  33%|███▎      | 118/363 [00:05<00:11, 22.24it/s]
Loading 0:  33%|███▎      | 121/363 [00:05<00:10, 23.24it/s]
Loading 0:  34%|███▍      | 124/363 [00:05<00:10, 22.78it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:09, 24.27it/s]
Loading 0:  36%|███▌      | 130/363 [00:05<00:09, 24.85it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:09, 23.67it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:09, 24.82it/s]
Loading 0:  38%|███▊      | 139/363 [00:05<00:09, 24.75it/s]
Loading 0:  39%|███▉      | 142/363 [00:06<00:09, 23.21it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:08, 24.31it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:07, 27.32it/s]
Loading 0:  42%|████▏     | 152/363 [00:06<00:11, 18.24it/s]
Loading 0:  43%|████▎     | 155/363 [00:06<00:10, 19.03it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:12, 16.00it/s]
Loading 0:  45%|████▍     | 163/363 [00:07<00:09, 21.42it/s]
Loading 0:  46%|████▌     | 166/363 [00:07<00:08, 22.27it/s]
Loading 0:  47%|████▋     | 169/363 [00:07<00:08, 22.03it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:08, 23.75it/s]
Loading 0:  48%|████▊     | 175/363 [00:07<00:07, 24.51it/s]
Loading 0:  49%|████▉     | 178/363 [00:07<00:07, 23.57it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:07, 25.05it/s]
Loading 0:  51%|█████     | 186/363 [00:07<00:06, 26.61it/s]
Loading 0:  52%|█████▏    | 189/363 [00:08<00:11, 15.81it/s]
Loading 0:  53%|█████▎    | 193/363 [00:08<00:08, 19.19it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:08, 19.47it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:07, 20.62it/s]
Loading 0:  55%|█████▌    | 200/363 [00:23<00:07, 20.62it/s]
Loading 0:  55%|█████▌    | 201/363 [00:23<04:17,  1.59s/it]
Loading 0:  56%|█████▌    | 203/363 [00:23<03:19,  1.25s/it]
Loading 0:  57%|█████▋    | 208/363 [00:24<01:48,  1.42it/s]
Loading 0:  58%|█████▊    | 211/363 [00:24<01:20,  1.89it/s]
Loading 0:  59%|█████▉    | 214/363 [00:24<00:58,  2.55it/s]
Loading 0:  60%|██████    | 218/363 [00:24<00:38,  3.72it/s]
Loading 0:  61%|██████    | 221/363 [00:24<00:29,  4.79it/s]
Loading 0:  62%|██████▏   | 224/363 [00:25<00:24,  5.72it/s]
Loading 0:  63%|██████▎   | 228/363 [00:25<00:16,  8.09it/s]
Loading 0:  64%|██████▎   | 231/363 [00:25<00:14,  9.32it/s]
Loading 0:  65%|██████▍   | 235/363 [00:25<00:10, 12.48it/s]
Loading 0:  66%|██████▌   | 238/363 [00:25<00:08, 14.45it/s]
Loading 0:  66%|██████▋   | 241/363 [00:25<00:07, 15.97it/s]
Loading 0:  68%|██████▊   | 246/363 [00:25<00:05, 19.70it/s]
Loading 0:  69%|██████▊   | 249/363 [00:26<00:06, 18.68it/s]
Loading 0:  70%|██████▉   | 253/363 [00:26<00:04, 22.59it/s]
Loading 0:  71%|███████   | 256/363 [00:26<00:04, 23.20it/s]
Loading 0:  71%|███████▏  | 259/363 [00:26<00:04, 22.35it/s]
Loading 0:  72%|███████▏  | 262/363 [00:26<00:04, 23.47it/s]
Loading 0:  73%|███████▎  | 266/363 [00:26<00:03, 27.08it/s]
Loading 0:  74%|███████▍  | 269/363 [00:26<00:05, 18.24it/s]
Loading 0:  75%|███████▍  | 272/363 [00:27<00:04, 19.30it/s]
Loading 0:  76%|███████▌  | 275/363 [00:27<00:05, 16.48it/s]
Loading 0:  77%|███████▋  | 280/363 [00:27<00:03, 21.22it/s]
Loading 0:  78%|███████▊  | 283/363 [00:27<00:03, 22.11it/s]
Loading 0:  79%|███████▉  | 286/363 [00:27<00:03, 21.38it/s]
Loading 0:  80%|███████▉  | 289/363 [00:27<00:03, 22.60it/s]
Loading 0:  80%|████████  | 292/363 [00:27<00:03, 23.51it/s]
Loading 0:  81%|████████▏ | 295/363 [00:28<00:03, 22.50it/s]
Loading 0:  82%|████████▏ | 298/363 [00:28<00:02, 23.75it/s]
Loading 0:  83%|████████▎ | 303/363 [00:28<00:02, 25.97it/s]
Loading 0:  84%|████████▍ | 306/363 [00:28<00:03, 15.22it/s]
Loading 0:  85%|████████▌ | 310/363 [00:28<00:02, 18.70it/s]
Loading 0:  86%|████████▌ | 313/363 [00:29<00:02, 19.36it/s]
Loading 0:  87%|████████▋ | 316/363 [00:29<00:02, 20.90it/s]
Loading 0:  88%|████████▊ | 319/363 [00:29<00:02, 21.93it/s]
Loading 0:  89%|████████▊ | 322/363 [00:29<00:01, 21.66it/s]
Loading 0:  90%|████████▉ | 325/363 [00:29<00:01, 23.02it/s]
Loading 0:  90%|█████████ | 328/363 [00:29<00:01, 23.76it/s]
Loading 0:  91%|█████████ | 331/363 [00:29<00:01, 23.00it/s]
Loading 0:  92%|█████████▏| 334/363 [00:29<00:01, 24.28it/s]
Loading 0:  93%|█████████▎| 337/363 [00:30<00:01, 20.37it/s]
Loading 0:  94%|█████████▎| 340/363 [00:30<00:01, 22.32it/s]
Loading 0:  94%|█████████▍| 343/363 [00:30<00:01, 13.12it/s]
Loading 0:  96%|█████████▌| 347/363 [00:30<00:00, 17.16it/s]
Loading 0:  96%|█████████▋| 350/363 [00:30<00:00, 17.95it/s]
Loading 0:  97%|█████████▋| 353/363 [00:31<00:00, 19.36it/s]
Loading 0:  98%|█████████▊| 356/363 [00:31<00:00, 21.48it/s]
Loading 0:  99%|█████████▉| 359/363 [00:31<00:00, 20.90it/s]
Loading 0: 100%|█████████▉| 362/363 [00:31<00:00, 22.47it/s]
                                                            
Job chaiml-wolverine2507082-32278-v1-mkmlizer completed after 189.21s with status: succeeded
Stopping job with name chaiml-wolverine2507082-32278-v1-mkmlizer
Pipeline stage MKMLizer completed in 189.75s
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-wolverine2507082-32278-v1
Waiting for inference service chaiml-wolverine2507082-32278-v1 to be ready
Inference service chaiml-wolverine2507082-32278-v1 ready after 190.70281982421875s
Pipeline stage MKMLDeployer completed in 191.27s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.523646593093872s
Received healthy response to inference request in 1.982208490371704s
Received healthy response to inference request in 2.180365562438965s
Received healthy response to inference request in 2.036477565765381s
Received healthy response to inference request in 2.0898735523223877s
5 requests
0 failed requests
5th percentile: 1.9930623054504395
10th percentile: 2.003916120529175
20th percentile: 2.0256237506866457
30th percentile: 2.0471567630767824
40th percentile: 2.068515157699585
50th percentile: 2.0898735523223877
60th percentile: 2.1260703563690186
70th percentile: 2.1622671604156496
80th percentile: 2.2490217685699463
90th percentile: 2.386334180831909
95th percentile: 2.4549903869628906
99th percentile: 2.509915351867676
mean time: 2.162514352798462
Pipeline stage StressChecker completed in 12.47s
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 0.67s
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 0.77s
Shutdown handler de-registered
chaiml-wolverine2507082_32278_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 0.13s
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-wolverine2507082-32278-v1-profiler
Waiting for inference service chaiml-wolverine2507082-32278-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
%s, retrying in %s seconds...
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 7028.18s
Shutdown handler de-registered
chaiml-wolverine2507082_32278_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-wolverine2507082_32278_v1 status is now protected
chaiml-wolverine2507082_32278_v1 status is now inactive
chaiml-wolverine2507082_32278_v1 status is now torndown due to DeploymentManager action
chaiml-wolverine2507082_32278_v1 status is now torndown due to DeploymentManager action
chaiml-wolverine2507082_32278_v1 status is now torndown due to DeploymentManager action
chaiml-wolverine2507082_32278_v1 status is now torndown due to DeploymentManager action