zonemercy-vingt-deux-v3-1e5v0

developer_uid: zonemercy

submission_id: zonemercy-vingt-deux-v3-1e5v0_v7

model_name: zonemercy-vingt-deux-v3-1e5v0_v7

model_group: zonemercy/Vingt-Deux-v3-

status: torndown

timestamp: 2024-09-26T12:57:50+00:00

num_battles: 3066

num_wins: 1482

celo_rating: 1242.1

family_friendly_score: 0.5836940836940836

family_friendly_standard_error: 0.008984748156347902

submission_type: basic

model_repo: zonemercy/Vingt-Deux-v3-1e5v0

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.3779594048773294, 'latency_mean': 2.6457273137569426, 'latency_p50': 2.658648371696472, 'latency_p90': 2.9142265558242797}, {'batch_size': 2, 'throughput': 0.5973753687391479, 'latency_mean': 3.34577645778656, 'latency_p50': 3.3563538789749146, 'latency_p90': 3.6555761098861694}, {'batch_size': 3, 'throughput': 0.7650158272974595, 'latency_mean': 3.904729028940201, 'latency_p50': 3.9117887020111084, 'latency_p90': 4.312515878677368}, {'batch_size': 4, 'throughput': 0.8786021341307809, 'latency_mean': 4.522594848871231, 'latency_p50': 4.537890553474426, 'latency_p90': 5.02103157043457}, {'batch_size': 5, 'throughput': 0.9748172791665503, 'latency_mean': 5.112056840658187, 'latency_p50': 5.122086405754089, 'latency_p90': 5.682306218147278}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: zonemercy-vingt-deux-v3-1e5v0_v7

ineligible_reason: num_battles<5000

is_internal_developer: True

language_model: zonemercy/Vingt-Deux-v3-1e5v0

model_size: 22B

ranking_group: single

throughput_3p7s: 0.71

us_pacific_date: 2024-09-26

win_ratio: 0.48336594911937375

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{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 zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer
Waiting for job on zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer to finish
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: ║     _____            __           __                                ║
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: ║       /___/                                                         ║
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: ║  Version: 0.11.12                                                   ║
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: ║  https://mk1.ai                                                     ║
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: ║  The license key for the current software has been verified as      ║
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: ║  belonging to:                                                      ║
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: ║  Chai Research Corp.                                                ║
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: Downloaded to shared memory in 51.235s
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpptirslyz, device:0
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: quantized model in 44.600s
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: Processed model zonemercy/Vingt-Deux-v3-1e5v0 in 95.835s
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-vingt-deux-v3-1e5v0-v7
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v3-1e5v0-v7/config.json
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v3-1e5v0-v7/special_tokens_map.json
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v3-1e5v0-v7/tokenizer_config.json
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v3-1e5v0-v7/tokenizer.json
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/zonemercy-vingt-deux-v3-1e5v0-v7/flywheel_model.1.safetensors
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-vingt-deux-v3-1e5v0-v7/flywheel_model.0.safetensors
zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:19, 25.20it/s]
Loading 0:   2%|▏         | 10/507 [00:00<00:14, 34.37it/s]
Loading 0:   3%|▎         | 14/507 [00:00<00:16, 30.30it/s]
Loading 0:   4%|▎         | 19/507 [00:00<00:13, 35.28it/s]
Loading 0:   5%|▍         | 23/507 [00:00<00:15, 31.79it/s]
Loading 0:   6%|▌         | 30/507 [00:00<00:11, 40.49it/s]
Loading 0:   7%|▋         | 35/507 [00:00<00:12, 37.63it/s]
Loading 0:   8%|▊         | 39/507 [00:01<00:12, 37.10it/s]
Loading 0:   8%|▊         | 43/507 [00:01<00:13, 35.69it/s]
Loading 0:   9%|▉         | 47/507 [00:01<00:12, 36.15it/s]
Loading 0:  10%|█         | 51/507 [00:01<00:12, 35.36it/s]
Loading 0:  11%|█         | 55/507 [00:01<00:19, 23.59it/s]
Loading 0:  11%|█▏        | 58/507 [00:01<00:18, 24.81it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:15, 29.17it/s]
Loading 0:  13%|█▎        | 67/507 [00:02<00:15, 28.92it/s]
Loading 0:  14%|█▍        | 73/507 [00:02<00:13, 32.34it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:12, 33.31it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:10, 38.53it/s]
Loading 0:  18%|█▊        | 92/507 [00:02<00:11, 37.38it/s]
Loading 0:  19%|█▉        | 96/507 [00:02<00:10, 37.44it/s]
Loading 0:  20%|█▉        | 100/507 [00:02<00:11, 35.05it/s]
Loading 0:  21%|██        | 105/507 [00:03<00:10, 37.18it/s]
Loading 0:  21%|██▏       | 109/507 [00:03<00:11, 35.50it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:15, 25.75it/s]
Loading 0:  23%|██▎       | 116/507 [00:03<00:16, 23.95it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:13, 27.70it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:10, 34.81it/s]
Loading 0:  26%|██▌       | 133/507 [00:04<00:11, 33.30it/s]
Loading 0:  27%|██▋       | 138/507 [00:04<00:10, 34.92it/s]
Loading 0:  28%|██▊       | 142/507 [00:04<00:10, 34.01it/s]
Loading 0:  29%|██▉       | 147/507 [00:04<00:09, 36.41it/s]
Loading 0:  30%|██▉       | 151/507 [00:04<00:10, 34.38it/s]
Loading 0:  31%|███       | 156/507 [00:04<00:09, 36.43it/s]
Loading 0:  32%|███▏      | 160/507 [00:04<00:09, 35.66it/s]
Loading 0:  32%|███▏      | 164/507 [00:04<00:09, 36.29it/s]
Loading 0:  33%|███▎      | 169/507 [00:05<00:11, 28.41it/s]
Loading 0:  34%|███▍      | 173/507 [00:05<00:11, 29.44it/s]
Loading 0:  35%|███▍      | 177/507 [00:05<00:11, 28.50it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:09, 34.27it/s]
Loading 0:  37%|███▋      | 187/507 [00:05<00:09, 33.33it/s]
Loading 0:  38%|███▊      | 192/507 [00:05<00:08, 36.44it/s]
Loading 0:  39%|███▊      | 196/507 [00:05<00:08, 35.02it/s]
Loading 0:  40%|███▉      | 201/507 [00:06<00:08, 37.44it/s]
Loading 0:  40%|████      | 205/507 [00:06<00:08, 35.43it/s]
Loading 0:  41%|████▏     | 210/507 [00:06<00:07, 38.34it/s]
Loading 0:  42%|████▏     | 214/507 [00:06<00:07, 36.92it/s]
Loading 0:  43%|████▎     | 218/507 [00:06<00:07, 37.13it/s]
Loading 0:  44%|████▍     | 222/507 [00:06<00:07, 35.88it/s]
Loading 0:  45%|████▍     | 226/507 [00:06<00:11, 25.39it/s]
Loading 0:  45%|████▌     | 230/507 [00:07<00:10, 25.21it/s]
Loading 0:  47%|████▋     | 237/507 [00:07<00:08, 32.91it/s]
Loading 0:  48%|████▊     | 241/507 [00:07<00:08, 32.55it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:07, 35.02it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 33.60it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:07, 35.53it/s]
Loading 0:  51%|█████     | 259/507 [00:07<00:07, 33.89it/s]
Loading 0:  52%|█████▏    | 264/507 [00:07<00:06, 36.55it/s]
Loading 0:  53%|█████▎    | 268/507 [00:08<00:06, 35.08it/s]
Loading 0:  54%|█████▍    | 273/507 [00:08<00:06, 37.40it/s]
Loading 0:  55%|█████▍    | 277/507 [00:08<00:06, 34.67it/s]
Loading 0:  56%|█████▌    | 283/507 [00:08<00:05, 37.47it/s]
Loading 0:  57%|█████▋    | 287/507 [00:08<00:09, 24.16it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 26.97it/s]
Loading 0:  59%|█████▉    | 298/507 [00:09<00:06, 30.90it/s]
Loading 0:  59%|█████▉    | 299/507 [00:23<00:06, 30.90it/s]
Loading 0:  59%|█████▉    | 300/507 [00:23<03:45,  1.09s/it]
Loading 0:  60%|█████▉    | 302/507 [00:23<03:07,  1.09it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:55,  1.73it/s]
Loading 0:  61%|██████    | 310/507 [00:24<01:28,  2.23it/s]
Loading 0:  62%|██████▏   | 313/507 [00:24<01:06,  2.93it/s]
Loading 0:  63%|██████▎   | 318/507 [00:24<00:41,  4.55it/s]
Loading 0:  64%|██████▎   | 322/507 [00:24<00:29,  6.17it/s]
Loading 0:  64%|██████▍   | 327/507 [00:24<00:20,  8.89it/s]
Loading 0:  65%|██████▌   | 331/507 [00:24<00:15, 11.26it/s]
Loading 0:  66%|██████▌   | 335/507 [00:24<00:12, 14.04it/s]
Loading 0:  67%|██████▋   | 340/507 [00:25<00:10, 15.31it/s]
Loading 0:  68%|██████▊   | 344/507 [00:25<00:09, 17.72it/s]
Loading 0:  69%|██████▊   | 348/507 [00:25<00:08, 19.35it/s]
Loading 0:  70%|██████▉   | 354/507 [00:25<00:05, 25.55it/s]
Loading 0:  71%|███████   | 358/507 [00:25<00:05, 26.96it/s]
Loading 0:  72%|███████▏  | 363/507 [00:25<00:04, 30.90it/s]
Loading 0:  72%|███████▏  | 367/507 [00:25<00:04, 31.23it/s]
Loading 0:  73%|███████▎  | 372/507 [00:25<00:03, 34.99it/s]
Loading 0:  74%|███████▍  | 376/507 [00:26<00:03, 33.77it/s]
Loading 0:  75%|███████▌  | 381/507 [00:26<00:03, 36.50it/s]
Loading 0:  76%|███████▌  | 385/507 [00:26<00:03, 35.94it/s]
Loading 0:  77%|███████▋  | 389/507 [00:26<00:03, 34.73it/s]
Loading 0:  78%|███████▊  | 393/507 [00:26<00:03, 34.65it/s]
Loading 0:  78%|███████▊  | 397/507 [00:26<00:04, 25.57it/s]
Loading 0:  79%|███████▉  | 401/507 [00:26<00:04, 25.64it/s]
Loading 0:  80%|████████  | 408/507 [00:27<00:02, 33.71it/s]
Loading 0:  81%|████████▏ | 412/507 [00:27<00:02, 33.42it/s]
Loading 0:  82%|████████▏ | 417/507 [00:27<00:02, 36.22it/s]
Loading 0:  83%|████████▎ | 421/507 [00:27<00:02, 33.72it/s]
Loading 0:  84%|████████▍ | 426/507 [00:27<00:02, 35.89it/s]
Loading 0:  85%|████████▍ | 430/507 [00:27<00:02, 34.55it/s]
Loading 0:  86%|████████▌ | 435/507 [00:27<00:01, 36.99it/s]
Loading 0:  87%|████████▋ | 439/507 [00:27<00:01, 35.59it/s]
Loading 0:  88%|████████▊ | 444/507 [00:28<00:01, 38.59it/s]
Loading 0:  88%|████████▊ | 448/507 [00:28<00:01, 36.81it/s]
Loading 0:  90%|████████▉ | 454/507 [00:28<00:01, 37.85it/s]
Loading 0:  90%|█████████ | 458/507 [00:30<00:08,  6.08it/s]
Loading 0:  91%|█████████ | 461/507 [00:30<00:06,  7.31it/s]
Loading 0:  92%|█████████▏| 465/507 [00:30<00:04,  9.34it/s]
Loading 0:  93%|█████████▎| 472/507 [00:30<00:02, 14.41it/s]
Loading 0:  94%|█████████▍| 476/507 [00:31<00:01, 16.80it/s]
Loading 0:  95%|█████████▍| 481/507 [00:31<00:01, 20.96it/s]
Loading 0:  96%|█████████▌| 485/507 [00:31<00:00, 23.20it/s]
Loading 0:  97%|█████████▋| 490/507 [00:31<00:00, 26.65it/s]
Loading 0:  97%|█████████▋| 494/507 [00:31<00:00, 27.89it/s]
Loading 0:  98%|█████████▊| 499/507 [00:31<00:00, 31.38it/s]
Loading 0:  99%|█████████▉| 503/507 [00:31<00:00, 30.54it/s]
                                                            
Job zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer completed after 122.65s with status: succeeded
Stopping job with name zonemercy-vingt-deux-v3-1e5v0-v7-mkmlizer
Pipeline stage MKMLizer completed in 123.45s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service zonemercy-vingt-deux-v3-1e5v0-v7
Waiting for inference service zonemercy-vingt-deux-v3-1e5v0-v7 to be ready
Inference service zonemercy-vingt-deux-v3-1e5v0-v7 ready after 220.4744508266449s
Pipeline stage MKMLDeployer completed in 220.81s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.061060667037964s
Received healthy response to inference request in 2.3932058811187744s
Received healthy response to inference request in 2.3690457344055176s
Received healthy response to inference request in 2.4685218334198s
Received healthy response to inference request in 2.525197982788086s
5 requests
0 failed requests
5th percentile: 2.373877763748169
10th percentile: 2.3787097930908203
20th percentile: 2.388373851776123
30th percentile: 2.4082690715789794
40th percentile: 2.43839545249939
50th percentile: 2.4685218334198
60th percentile: 2.4911922931671144
70th percentile: 2.5138627529144286
80th percentile: 2.632370519638062
90th percentile: 2.8467155933380126
95th percentile: 2.953888130187988
99th percentile: 3.039626159667969
mean time: 2.5634064197540285
Pipeline stage StressChecker completed in 13.45s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 4.53s
Shutdown handler de-registered
zonemercy-vingt-deux-v3-1e5v0_v7 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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service zonemercy-vingt-deux-v3-1e5v0-v7-profiler
Waiting for inference service zonemercy-vingt-deux-v3-1e5v0-v7-profiler to be ready
Inference service zonemercy-vingt-deux-v3-1e5v0-v7-profiler ready after 220.49527835845947s
Pipeline stage MKMLProfilerDeployer completed in 220.87s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/zonemercy-vingt-deux1d6c82c1d14dec05c1568c87d7d55263-deplo552ts:/code/chaiverse_profiler_1727356114 --namespace tenant-chaiml-guanaco
kubectl exec -it zonemercy-vingt-deux1d6c82c1d14dec05c1568c87d7d55263-deplo552ts --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727356114 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1727356114/summary.json'
kubectl exec -it zonemercy-vingt-deux1d6c82c1d14dec05c1568c87d7d55263-deplo552ts --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727356114/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1563.77s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service zonemercy-vingt-deux-v3-1e5v0-v7-profiler is running
Tearing down inference service zonemercy-vingt-deux-v3-1e5v0-v7-profiler
Service zonemercy-vingt-deux-v3-1e5v0-v7-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.12s
Shutdown handler de-registered
zonemercy-vingt-deux-v3-1e5v0_v7 status is now inactive due to auto deactivation removed underperforming models
zonemercy-vingt-deux-v3-1e5v0_v7 status is now torndown due to DeploymentManager action