developer_uid: azuruce
submission_id: cognitivecomputations-d_59118_v1
model_name: cognitivecomputations-d_59118_v1
model_group: cognitivecomputations/Do
status: torndown
timestamp: 2025-02-25T00:17:49+00:00
num_battles: 6003
num_wins: 1401
celo_rating: 1000.93
family_friendly_score: 0.7989999999999999
family_friendly_standard_error: 0.005667433281477604
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': 0.4724602120292353, 'latency_mean': 2.1165128564834594, 'latency_p50': 2.1350637674331665, 'latency_p90': 2.399560570716858}, {'batch_size': 5, 'throughput': 1.9504849750962536, 'latency_mean': 2.535778979063034, 'latency_p50': 2.5329959392547607, 'latency_p90': 2.8357958793640137}, {'batch_size': 10, 'throughput': 3.448968393059006, 'latency_mean': 2.8384301900863647, 'latency_p50': 2.830975651741028, 'latency_p90': 3.183262348175049}, {'batch_size': 15, 'throughput': 4.590084293622673, 'latency_mean': 3.156511433124542, 'latency_p50': 3.140609622001648, 'latency_p90': 3.574959707260132}, {'batch_size': 20, 'throughput': 5.3984391623045695, 'latency_mean': 3.550169882774353, 'latency_p50': 3.5159449577331543, 'latency_p90': 4.018167805671692}, {'batch_size': 25, 'throughput': 6.241287671519273, 'latency_mean': 3.8756568312644957, 'latency_p50': 3.8869014978408813, 'latency_p90': 4.415177178382874}, {'batch_size': 30, 'throughput': 6.801508061043408, 'latency_mean': 4.219099416732788, 'latency_p50': 4.234048366546631, 'latency_p90': 4.869915223121643}, {'batch_size': 35, 'throughput': 7.115923876194749, 'latency_mean': 4.676015247106552, 'latency_p50': 4.6803834438323975, 'latency_p90': 5.353240132331848}, {'batch_size': 40, 'throughput': 7.505413159779148, 'latency_mean': 5.107002953290939, 'latency_p50': 5.101729989051819, 'latency_p90': 5.960096216201782}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: cognitivecomputations-d_59118_v1
ineligible_reason: num_battles<10000
is_internal_developer: False
language_model: cognitivecomputations/Dolphin3.0-Mistral-24B
model_size: 24B
ranking_group: single
throughput_3p7s: 6.03
us_pacific_date: 2025-02-24
win_ratio: 0.23338330834582707
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-v1-mkmlizer
Waiting for job on cognitivecomputations-d-59118-v1-mkmlizer to finish
cognitivecomputations-d-59118-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cognitivecomputations-d-59118-v1-mkmlizer: ║     _____            __           __                                ║
cognitivecomputations-d-59118-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cognitivecomputations-d-59118-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cognitivecomputations-d-59118-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cognitivecomputations-d-59118-v1-mkmlizer: ║       /___/                                                         ║
cognitivecomputations-d-59118-v1-mkmlizer: ║                                                                     ║
cognitivecomputations-d-59118-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
cognitivecomputations-d-59118-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cognitivecomputations-d-59118-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cognitivecomputations-d-59118-v1-mkmlizer: ║                                                                     ║
cognitivecomputations-d-59118-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cognitivecomputations-d-59118-v1-mkmlizer: ║  belonging to:                                                      ║
cognitivecomputations-d-59118-v1-mkmlizer: ║                                                                     ║
cognitivecomputations-d-59118-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cognitivecomputations-d-59118-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cognitivecomputations-d-59118-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
cognitivecomputations-d-59118-v1-mkmlizer: ║                                                                     ║
cognitivecomputations-d-59118-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cognitivecomputations-d-59118-v1-mkmlizer: Downloaded to shared memory in 59.767s
cognitivecomputations-d-59118-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpsjer6oai, device:0
cognitivecomputations-d-59118-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cognitivecomputations-d-59118-v1-mkmlizer: quantized model in 52.943s
cognitivecomputations-d-59118-v1-mkmlizer: Processed model cognitivecomputations/Dolphin3.0-Mistral-24B in 112.710s
cognitivecomputations-d-59118-v1-mkmlizer: creating bucket guanaco-mkml-models
cognitivecomputations-d-59118-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cognitivecomputations-d-59118-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cognitivecomputations-d-59118-v1
cognitivecomputations-d-59118-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cognitivecomputations-d-59118-v1/tokenizer_config.json
cognitivecomputations-d-59118-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cognitivecomputations-d-59118-v1/tokenizer.json
cognitivecomputations-d-59118-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/cognitivecomputations-d-59118-v1/flywheel_model.1.safetensors
cognitivecomputations-d-59118-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 20.62it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 36.71it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 32.46it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 33.23it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 29.31it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 35.98it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:15, 21.71it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 24.52it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 26.22it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 28.70it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 27.39it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:10, 30.18it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 27.33it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 28.32it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 25.59it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 21.34it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 26.11it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 25.21it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 26.95it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 27.20it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 21.62it/s]
Loading 0:  27%|██▋       | 98/363 [00:03<00:08, 29.59it/s]
Loading 0:  28%|██▊       | 102/363 [00:03<00:10, 25.09it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:10, 23.29it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 26.28it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 25.40it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 28.41it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 27.29it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 29.26it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 28.53it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 31.05it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 29.62it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:06, 35.32it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:09, 22.93it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:08, 25.45it/s]
Loading 0:  44%|████▍     | 161/363 [00:05<00:07, 26.31it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 27.69it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:07, 27.04it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 30.28it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 29.43it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 29.63it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 26.34it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 23.71it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:06, 24.35it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 24.09it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 24.09it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<03:01,  1.12s/it]
Loading 0:  56%|█████▌    | 203/363 [00:21<02:29,  1.07it/s]
Loading 0:  57%|█████▋    | 208/363 [00:21<01:29,  1.72it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:09,  2.19it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:51,  2.89it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:35,  4.14it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.27it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21,  6.42it/s]
Loading 0:  63%|██████▎   | 229/363 [00:22<00:14,  9.44it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:11, 11.26it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 15.36it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 16.38it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 21.97it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:04, 23.13it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:04, 26.76it/s]
Loading 0:  71%|███████▏  | 259/363 [00:23<00:03, 26.09it/s]
Loading 0:  73%|███████▎  | 266/363 [00:24<00:03, 32.08it/s]
Loading 0:  74%|███████▍  | 270/363 [00:24<00:04, 21.13it/s]
Loading 0:  75%|███████▌  | 274/363 [00:24<00:03, 23.92it/s]
Loading 0:  77%|███████▋  | 278/363 [00:24<00:03, 25.76it/s]
Loading 0:  78%|███████▊  | 282/363 [00:24<00:02, 27.76it/s]
Loading 0:  79%|███████▉  | 286/363 [00:24<00:02, 27.02it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 30.13it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 28.73it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 29.04it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 26.26it/s]
Loading 0:  85%|████████▍ | 307/363 [00:25<00:02, 24.13it/s]
Loading 0:  85%|████████▌ | 310/363 [00:25<00:02, 24.64it/s]
Loading 0:  86%|████████▌ | 313/363 [00:25<00:01, 25.48it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 29.11it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 26.57it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 31.63it/s]
Loading 0:  91%|█████████ | 331/363 [00:26<00:01, 30.06it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:00, 30.39it/s]
Loading 0:  93%|█████████▎| 339/363 [00:26<00:00, 30.97it/s]
Loading 0:  94%|█████████▍| 343/363 [00:33<00:10,  1.90it/s]
Loading 0:  96%|█████████▌| 348/363 [00:33<00:05,  2.79it/s]
Loading 0:  98%|█████████▊| 355/363 [00:33<00:01,  4.54it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00,  5.73it/s]
                                                            

Job cognitivecomputations-d-59118-v1-mkmlizer completed after 144.92s with status: succeeded
Stopping job with name cognitivecomputations-d-59118-v1-mkmlizer
Pipeline stage MKMLizer completed in 145.40s
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 cognitivecomputations-d-59118-v1
Waiting for inference service cognitivecomputations-d-59118-v1 to be ready
Inference service cognitivecomputations-d-59118-v1 ready after 241.09047484397888s
Pipeline stage MKMLDeployer completed in 241.63s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.856518030166626s
Received healthy response to inference request in 2.409916877746582s
Received healthy response to inference request in 1.2341840267181396s
Received healthy response to inference request in 2.2488248348236084s
Received healthy response to inference request in 1.039456844329834s
5 requests
0 failed requests
5th percentile: 1.0784022808074951
10th percentile: 1.1173477172851562
20th percentile: 1.1952385902404785
30th percentile: 1.3586508274078368
40th percentile: 1.6075844287872316
50th percentile: 1.856518030166626
60th percentile: 2.013440752029419
70th percentile: 2.1703634738922117
80th percentile: 2.2810432434082033
90th percentile: 2.3454800605773927
95th percentile: 2.377698469161987
99th percentile: 2.403473196029663
mean time: 1.757780122756958
Pipeline stage StressChecker completed in 10.07s
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 0.63s
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 0.66s
Shutdown handler de-registered
cognitivecomputations-d_59118_v1 status is now deployed due to DeploymentManager action
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 1768.30s
Shutdown handler de-registered
cognitivecomputations-d_59118_v1 status is now inactive due to auto deactivation removed underperforming models
cognitivecomputations-d_59118_v1 status is now torndown due to DeploymentManager action