developer_uid: azuruce
submission_id: cognitivecomputations-d_59118_v3
model_name: cognitivecomputations-d_59118_v3
model_group: cognitivecomputations/Do
status: torndown
timestamp: 2025-02-25T09:03:28+00:00
num_battles: 5259
num_wins: 2182
celo_rating: 1206.55
family_friendly_score: 0.6636
family_friendly_standard_error: 0.006681841662296406
submission_type: basic
model_repo: cognitivecomputations/Dolphin3.0-Mistral-24B
model_architecture: MistralForCausalLM
model_num_parameters: 24096711680.0
best_of: 2
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.3872637111353438, 'latency_mean': 2.5821545243263246, 'latency_p50': 2.5976415872573853, 'latency_p90': 2.8334404945373537}, {'batch_size': 3, 'throughput': 0.836900409331365, 'latency_mean': 3.568520089387894, 'latency_p50': 3.5690019130706787, 'latency_p90': 3.8871978759765624}, {'batch_size': 5, 'throughput': 1.127212037800388, 'latency_mean': 4.4185729455947875, 'latency_p50': 4.394429326057434, 'latency_p90': 4.985197234153747}, {'batch_size': 6, 'throughput': 1.2281455962917307, 'latency_mean': 4.866185648441315, 'latency_p50': 4.854023098945618, 'latency_p90': 5.51389627456665}, {'batch_size': 8, 'throughput': 1.3881011932251168, 'latency_mean': 5.713755608797073, 'latency_p50': 5.696171998977661, 'latency_p90': 6.426460313796997}, {'batch_size': 10, 'throughput': 1.511954476396539, 'latency_mean': 6.535585682392121, 'latency_p50': 6.535155653953552, 'latency_p90': 7.273932385444641}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: cognitivecomputations-d_59118_v3
is_internal_developer: False
language_model: cognitivecomputations/Dolphin3.0-Mistral-24B
model_size: 24B
ranking_group: single
throughput_3p7s: 0.89
us_pacific_date: 2025-02-25
win_ratio: 0.4149077771439437
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 2, 'max_output_tokens': 64}
formatter: {'memory_template': '[INST]', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '[/INST]{bot_name}:', '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 cognitivecomputations-d-59118-v3-mkmlizer
Waiting for job on cognitivecomputations-d-59118-v3-mkmlizer to finish
cognitivecomputations-d-59118-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cognitivecomputations-d-59118-v3-mkmlizer: ║     _____            __           __                                ║
cognitivecomputations-d-59118-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cognitivecomputations-d-59118-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cognitivecomputations-d-59118-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cognitivecomputations-d-59118-v3-mkmlizer: ║       /___/                                                         ║
cognitivecomputations-d-59118-v3-mkmlizer: ║                                                                     ║
cognitivecomputations-d-59118-v3-mkmlizer: ║  Version: 0.12.8                                                    ║
cognitivecomputations-d-59118-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cognitivecomputations-d-59118-v3-mkmlizer: ║  https://mk1.ai                                                     ║
cognitivecomputations-d-59118-v3-mkmlizer: ║                                                                     ║
cognitivecomputations-d-59118-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
cognitivecomputations-d-59118-v3-mkmlizer: ║  belonging to:                                                      ║
cognitivecomputations-d-59118-v3-mkmlizer: ║                                                                     ║
cognitivecomputations-d-59118-v3-mkmlizer: ║  Chai Research Corp.                                                ║
cognitivecomputations-d-59118-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cognitivecomputations-d-59118-v3-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
cognitivecomputations-d-59118-v3-mkmlizer: ║                                                                     ║
cognitivecomputations-d-59118-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cognitivecomputations-d-59118-v3-mkmlizer: Downloaded to shared memory in 62.905s
cognitivecomputations-d-59118-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpa4aaa_y6, device:0
cognitivecomputations-d-59118-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cognitivecomputations-d-59118-v3-mkmlizer: quantized model in 55.477s
cognitivecomputations-d-59118-v3-mkmlizer: Processed model cognitivecomputations/Dolphin3.0-Mistral-24B in 118.383s
cognitivecomputations-d-59118-v3-mkmlizer: creating bucket guanaco-mkml-models
cognitivecomputations-d-59118-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cognitivecomputations-d-59118-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cognitivecomputations-d-59118-v3
cognitivecomputations-d-59118-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cognitivecomputations-d-59118-v3/config.json
cognitivecomputations-d-59118-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cognitivecomputations-d-59118-v3/special_tokens_map.json
cognitivecomputations-d-59118-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cognitivecomputations-d-59118-v3/tokenizer_config.json
cognitivecomputations-d-59118-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cognitivecomputations-d-59118-v3/tokenizer.json
cognitivecomputations-d-59118-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/cognitivecomputations-d-59118-v3/flywheel_model.1.safetensors
cognitivecomputations-d-59118-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cognitivecomputations-d-59118-v3/flywheel_model.0.safetensors
cognitivecomputations-d-59118-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 37.79it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 28.80it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 29.49it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:13, 25.82it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:11, 29.67it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:12, 27.72it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:09, 33.71it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:15, 21.04it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 23.92it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 25.12it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.34it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 26.48it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 29.81it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 27.15it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.87it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 25.97it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 21.66it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 27.04it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 26.14it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 27.44it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:09, 27.69it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 21.00it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 27.44it/s]
Loading 0:  28%|██▊       | 102/363 [00:03<00:10, 25.09it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:10, 23.90it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 26.02it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 23.83it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 29.17it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 27.52it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.06it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 28.33it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 30.77it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 29.05it/s]
Loading 0:  41%|████      | 148/363 [00:05<00:06, 35.63it/s]
Loading 0:  42%|████▏     | 152/363 [00:05<00:08, 23.85it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:09, 22.89it/s]
Loading 0:  44%|████▍     | 159/363 [00:06<00:09, 21.90it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.88it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:07, 24.96it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 29.33it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 27.61it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 27.69it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 23.31it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:08, 21.23it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 22.00it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 22.44it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:07, 22.44it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:05,  1.15s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:33,  1.04it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:32,  1.68it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:11,  2.13it/s]
Loading 0:  59%|█████▉    | 214/363 [00:23<00:52,  2.81it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:36,  4.03it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:27,  5.11it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:22,  6.15it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:14,  9.06it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:12, 10.81it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 14.80it/s]
Loading 0:  66%|██████▌   | 240/363 [00:24<00:08, 15.35it/s]
Loading 0:  68%|██████▊   | 246/363 [00:24<00:05, 20.87it/s]
Loading 0:  69%|██████▉   | 250/363 [00:24<00:05, 21.70it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 24.98it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 24.09it/s]
Loading 0:  73%|███████▎  | 264/363 [00:24<00:03, 29.03it/s]
Loading 0:  74%|███████▍  | 268/363 [00:25<00:04, 23.33it/s]
Loading 0:  75%|███████▍  | 271/363 [00:25<00:04, 21.80it/s]
Loading 0:  75%|███████▌  | 274/363 [00:25<00:03, 22.66it/s]
Loading 0:  76%|███████▋  | 277/363 [00:25<00:03, 22.90it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 26.54it/s]
Loading 0:  79%|███████▊  | 285/363 [00:25<00:03, 23.51it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 28.20it/s]
Loading 0:  81%|████████  | 294/363 [00:26<00:02, 25.39it/s]
Loading 0:  82%|████████▏ | 299/363 [00:26<00:02, 28.42it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 25.61it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 22.74it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 23.57it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 23.67it/s]
Loading 0:  88%|████████▊ | 318/363 [00:27<00:01, 26.59it/s]
Loading 0:  88%|████████▊ | 321/363 [00:27<00:01, 23.15it/s]
Loading 0:  90%|█████████ | 327/363 [00:27<00:01, 28.18it/s]
Loading 0:  91%|█████████ | 330/363 [00:27<00:01, 24.63it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:01, 26.97it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:01, 24.84it/s]
Loading 0:  94%|█████████▍| 341/363 [00:34<00:13,  1.63it/s]
Loading 0:  95%|█████████▌| 346/363 [00:35<00:06,  2.54it/s]
Loading 0:  96%|█████████▌| 349/363 [00:35<00:04,  3.21it/s]
Loading 0:  98%|█████████▊| 355/363 [00:35<00:01,  5.15it/s]
Loading 0:  99%|█████████▊| 358/363 [00:35<00:00,  6.14it/s]
                                                            

Job cognitivecomputations-d-59118-v3-mkmlizer completed after 144.69s with status: succeeded
Stopping job with name cognitivecomputations-d-59118-v3-mkmlizer
Pipeline stage MKMLizer completed in 145.16s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cognitivecomputations-d-59118-v3
Waiting for inference service cognitivecomputations-d-59118-v3 to be ready
Inference service cognitivecomputations-d-59118-v3 ready after 250.82462811470032s
Pipeline stage MKMLDeployer completed in 251.36s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8776772022247314s
Received healthy response to inference request in 0.9603617191314697s
Received healthy response to inference request in 2.2164952754974365s
Received healthy response to inference request in 2.344174861907959s
Received healthy response to inference request in 1.6965103149414062s
5 requests
0 failed requests
5th percentile: 1.107591438293457
10th percentile: 1.2548211574554444
20th percentile: 1.549280595779419
30th percentile: 1.8005073070526123
40th percentile: 2.0085012912750244
50th percentile: 2.2164952754974365
60th percentile: 2.2675671100616457
70th percentile: 2.3186389446258544
80th percentile: 2.4508753299713137
90th percentile: 2.6642762660980224
95th percentile: 2.7709767341613767
99th percentile: 2.8563371086120606
mean time: 2.0190438747406008
Pipeline stage StressChecker completed in 11.28s
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 0.62s
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 0.62s
Shutdown handler de-registered
cognitivecomputations-d_59118_v3 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cognitivecomputations-d-59118-v3-profiler
Waiting for inference service cognitivecomputations-d-59118-v3-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 2527.20s
Shutdown handler de-registered
cognitivecomputations-d_59118_v3 status is now inactive due to auto deactivation removed underperforming models
cognitivecomputations-d_59118_v3 status is now torndown due to DeploymentManager action