cognitivecomputations-d_59118

developer_uid: azuruce

submission_id: cognitivecomputations-d_59118_v2

model_name: cognitivecomputations-d_59118_v2

model_group: cognitivecomputations/Do

status: torndown

timestamp: 2025-02-25T00:24:13+00:00

num_battles: 5857

num_wins: 1415

celo_rating: 1009.34

family_friendly_score: 0.8012

family_friendly_standard_error: 0.0056440864628387825

submission_type: basic

model_repo: cognitivecomputations/Dolphin3.0-Mistral-24B

model_architecture: MistralForCausalLM

model_num_parameters: 24096711680.0

best_of: 2

max_input_tokens: 64

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.47403711332850845, 'latency_mean': 2.109433068037033, 'latency_p50': 2.113213062286377, 'latency_p90': 2.373010754585266}, {'batch_size': 5, 'throughput': 1.9384760600156479, 'latency_mean': 2.5405935394763945, 'latency_p50': 2.546480894088745, 'latency_p90': 2.830623245239258}, {'batch_size': 10, 'throughput': 3.505212928507965, 'latency_mean': 2.812644259929657, 'latency_p50': 2.796856164932251, 'latency_p90': 3.1676597356796266}, {'batch_size': 15, 'throughput': 4.5917613776987585, 'latency_mean': 3.1630239522457124, 'latency_p50': 3.1340014934539795, 'latency_p90': 3.581355023384094}, {'batch_size': 20, 'throughput': 5.407618187425949, 'latency_mean': 3.555372952222824, 'latency_p50': 3.5724507570266724, 'latency_p90': 4.023379588127137}, {'batch_size': 25, 'throughput': 6.12230275931118, 'latency_mean': 3.9187259066104887, 'latency_p50': 3.9009422063827515, 'latency_p90': 4.428543496131897}, {'batch_size': 30, 'throughput': 6.852427063537098, 'latency_mean': 4.208385899066925, 'latency_p50': 4.2039501667022705, 'latency_p90': 4.84196527004242}, {'batch_size': 35, 'throughput': 7.1147951415747555, 'latency_mean': 4.657488875389099, 'latency_p50': 4.653241157531738, 'latency_p90': 5.342325019836426}, {'batch_size': 40, 'throughput': 7.424557102349103, 'latency_mean': 5.144542053937912, 'latency_p50': 5.095559597015381, 'latency_p90': 6.033616280555725}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: cognitivecomputations-d_59118_v2

is_internal_developer: False

language_model: cognitivecomputations/Dolphin3.0-Mistral-24B

model_size: 24B

ranking_group: single

throughput_3p7s: 5.94

us_pacific_date: 2025-02-24

win_ratio: 0.24159125832337375

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': 64, '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-v2-mkmlizer
Waiting for job on cognitivecomputations-d-59118-v2-mkmlizer to finish
cognitivecomputations-d-59118-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cognitivecomputations-d-59118-v2-mkmlizer: ║     _____            __           __                                ║
cognitivecomputations-d-59118-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cognitivecomputations-d-59118-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cognitivecomputations-d-59118-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cognitivecomputations-d-59118-v2-mkmlizer: ║       /___/                                                         ║
cognitivecomputations-d-59118-v2-mkmlizer: ║                                                                     ║
cognitivecomputations-d-59118-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
cognitivecomputations-d-59118-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cognitivecomputations-d-59118-v2-mkmlizer: ║  https://mk1.ai                                                     ║
cognitivecomputations-d-59118-v2-mkmlizer: ║                                                                     ║
cognitivecomputations-d-59118-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
cognitivecomputations-d-59118-v2-mkmlizer: ║  belonging to:                                                      ║
cognitivecomputations-d-59118-v2-mkmlizer: ║                                                                     ║
cognitivecomputations-d-59118-v2-mkmlizer: ║  Chai Research Corp.                                                ║
cognitivecomputations-d-59118-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cognitivecomputations-d-59118-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
cognitivecomputations-d-59118-v2-mkmlizer: ║                                                                     ║
cognitivecomputations-d-59118-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cognitivecomputations-d-59118-v2-mkmlizer: Downloaded to shared memory in 58.693s
cognitivecomputations-d-59118-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpl2j94bqo, device:0
cognitivecomputations-d-59118-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cognitivecomputations-d-59118-v2-mkmlizer: quantized model in 53.434s
cognitivecomputations-d-59118-v2-mkmlizer: Processed model cognitivecomputations/Dolphin3.0-Mistral-24B in 112.128s
cognitivecomputations-d-59118-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cognitivecomputations-d-59118-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cognitivecomputations-d-59118-v2
cognitivecomputations-d-59118-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cognitivecomputations-d-59118-v2/config.json
cognitivecomputations-d-59118-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cognitivecomputations-d-59118-v2/special_tokens_map.json
cognitivecomputations-d-59118-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cognitivecomputations-d-59118-v2/tokenizer_config.json
cognitivecomputations-d-59118-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cognitivecomputations-d-59118-v2/tokenizer.json
cognitivecomputations-d-59118-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/cognitivecomputations-d-59118-v2/flywheel_model.1.safetensors
cognitivecomputations-d-59118-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cognitivecomputations-d-59118-v2/flywheel_model.0.safetensors
cognitivecomputations-d-59118-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 39.15it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 30.50it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:10, 33.35it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:11, 29.90it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 33.91it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 30.44it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 36.61it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:15, 21.78it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 24.27it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 25.42it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.79it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:12, 25.89it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 28.45it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.87it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.46it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 24.80it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 20.37it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:11, 25.68it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 25.30it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 27.44it/s]
Loading 0:  25%|██▍       | 90/363 [00:03<00:10, 26.68it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:11, 24.18it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 29.13it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 27.31it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.63it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 25.78it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 23.30it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 28.06it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 25.59it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.05it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 28.35it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 30.47it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.92it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:06, 34.34it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:09, 22.49it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:08, 24.65it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:08, 25.11it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 27.87it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:07, 27.39it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 30.07it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 28.90it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 29.27it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 27.08it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 24.53it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:06, 25.01it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 25.46it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 25.46it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<03:02,  1.12s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:31,  1.06it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:31,  1.70it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:09,  2.18it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:52,  2.86it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:35,  4.10it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:27,  5.22it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:22,  6.26it/s]
Loading 0:  63%|██████▎   | 228/363 [00:23<00:15,  8.76it/s]
Loading 0:  64%|██████▎   | 231/363 [00:23<00:12, 10.15it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 15.12it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.59it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 21.06it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:05, 21.88it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 25.19it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 25.33it/s]
Loading 0:  73%|███████▎  | 266/363 [00:24<00:03, 31.34it/s]
Loading 0:  74%|███████▍  | 270/363 [00:24<00:04, 21.44it/s]
Loading 0:  75%|███████▌  | 274/363 [00:24<00:03, 24.14it/s]
Loading 0:  77%|███████▋  | 278/363 [00:24<00:03, 25.80it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:02, 27.77it/s]
Loading 0:  79%|███████▉  | 286/363 [00:25<00:02, 27.52it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 30.14it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 29.01it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 29.60it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 28.05it/s]
Loading 0:  85%|████████▍ | 307/363 [00:25<00:02, 24.58it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 25.19it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:01, 26.07it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 29.11it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 26.51it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 31.86it/s]
Loading 0:  91%|█████████ | 331/363 [00:26<00:01, 29.88it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:00, 29.57it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 28.26it/s]
Loading 0:  94%|█████████▍| 341/363 [00:33<00:13,  1.67it/s]
Loading 0:  96%|█████████▌| 347/363 [00:33<00:05,  2.79it/s]
Loading 0:  96%|█████████▋| 350/363 [00:34<00:03,  3.50it/s]
Loading 0:  98%|█████████▊| 355/363 [00:34<00:01,  5.15it/s]
Loading 0:  99%|█████████▊| 358/363 [00:34<00:00,  6.22it/s]
                                                            
Job cognitivecomputations-d-59118-v2-mkmlizer completed after 154.85s with status: succeeded
Stopping job with name cognitivecomputations-d-59118-v2-mkmlizer
Pipeline stage MKMLizer completed in 155.32s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cognitivecomputations-d-59118-v2
Waiting for inference service cognitivecomputations-d-59118-v2 to be ready
Inference service cognitivecomputations-d-59118-v2 ready after 240.99775409698486s
Pipeline stage MKMLDeployer completed in 241.51s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6258368492126465s
Received healthy response to inference request in 1.266084909439087s
Received healthy response to inference request in 2.152698516845703s
Received healthy response to inference request in 0.865511417388916s
Received healthy response to inference request in 1.7019762992858887s
5 requests
0 failed requests
5th percentile: 0.9456261157989502
10th percentile: 1.0257408142089843
20th percentile: 1.1859702110290526
30th percentile: 1.3380352973937988
40th percentile: 1.4819360733032227
50th percentile: 1.6258368492126465
60th percentile: 1.6562926292419433
70th percentile: 1.6867484092712401
80th percentile: 1.7921207427978516
90th percentile: 1.9724096298217775
95th percentile: 2.06255407333374
99th percentile: 2.1346696281433104
mean time: 1.5224215984344482
Pipeline stage StressChecker completed in 8.91s
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 0.59s
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 0.61s
Shutdown handler de-registered
cognitivecomputations-d_59118_v2 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 0.10s
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-v2-profiler
Waiting for inference service cognitivecomputations-d-59118-v2-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 1767.49s
Shutdown handler de-registered
cognitivecomputations-d_59118_v2 status is now inactive due to auto deactivation removed underperforming models
cognitivecomputations-d_59118_v2 status is now torndown due to DeploymentManager action