developer_uid: zonemercy
submission_id: zonemercy-vingt-deux-v0-1e5_v19
model_name: zonemercy-vingt-deux-v0-1e5_v19
model_group: zonemercy/Vingt-Deux-v0-
status: torndown
timestamp: 2024-09-23T16:35:19+00:00
num_battles: 25215
num_wins: 12913
celo_rating: 1248.93
family_friendly_score: 0.0
submission_type: basic
model_repo: zonemercy/Vingt-Deux-v0-1e5
model_architecture: MistralForCausalLM
model_num_parameters: 22247282688.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.3774999848074919, 'latency_mean': 2.6489131772518157, 'latency_p50': 2.6505556106567383, 'latency_p90': 2.9242725133895875}, {'batch_size': 2, 'throughput': 0.5938467277082651, 'latency_mean': 3.3633164513111113, 'latency_p50': 3.3708044290542603, 'latency_p90': 3.7004452466964723}, {'batch_size': 3, 'throughput': 0.747792399684774, 'latency_mean': 3.9892921900749205, 'latency_p50': 4.017625689506531, 'latency_p90': 4.393727874755859}, {'batch_size': 4, 'throughput': 0.868379284426235, 'latency_mean': 4.595271449089051, 'latency_p50': 4.629689693450928, 'latency_p90': 5.168057894706726}, {'batch_size': 5, 'throughput': 0.9525903526307019, 'latency_mean': 5.218423534631729, 'latency_p50': 5.161831617355347, 'latency_p90': 5.843510103225708}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: zonemercy-vingt-deux-v0-1e5_v19
is_internal_developer: True
language_model: zonemercy/Vingt-Deux-v0-1e5
model_size: 22B
ranking_group: single
throughput_3p7s: 0.69
us_pacific_date: 2024-09-23
win_ratio: 0.5121158040848701
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.01, 'top_k': 40, '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: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', '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-v0-1e5-v19-mkmlizer
Waiting for job on zonemercy-vingt-deux-v0-1e5-v19-mkmlizer to finish
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: ║     _____            __           __                                ║
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: ║       /___/                                                         ║
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: ║  Version: 0.10.1                                                    ║
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: ║  https://mk1.ai                                                     ║
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: ║  The license key for the current software has been verified as      ║
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: ║  belonging to:                                                      ║
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: ║  Chai Research Corp.                                                ║
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: Downloaded to shared memory in 51.979s
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpup109_lv, device:0
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: quantized model in 43.500s
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: Processed model zonemercy/Vingt-Deux-v0-1e5 in 95.480s
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v19
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v19/config.json
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v19/special_tokens_map.json
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v19/tokenizer_config.json
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v19/tokenizer.json
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v19/flywheel_model.1.safetensors
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v19/flywheel_model.0.safetensors
zonemercy-vingt-deux-v0-1e5-v19-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:19, 26.37it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:11, 43.32it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:12, 38.97it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:12, 40.04it/s]
Loading 0:   5%|▌         | 27/507 [00:00<00:11, 41.85it/s]
Loading 0:   6%|▋         | 32/507 [00:00<00:13, 35.37it/s]
Loading 0:   8%|▊         | 39/507 [00:00<00:10, 42.93it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:10, 42.30it/s]
Loading 0:  10%|▉         | 49/507 [00:01<00:12, 36.88it/s]
Loading 0:  10%|█         | 53/507 [00:01<00:16, 27.16it/s]
Loading 0:  11%|█         | 57/507 [00:01<00:16, 26.79it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:13, 32.09it/s]
Loading 0:  13%|█▎        | 67/507 [00:01<00:13, 31.63it/s]
Loading 0:  14%|█▍        | 72/507 [00:02<00:12, 35.47it/s]
Loading 0:  15%|█▌        | 78/507 [00:02<00:10, 40.32it/s]
Loading 0:  16%|█▋        | 83/507 [00:02<00:11, 38.34it/s]
Loading 0:  17%|█▋        | 88/507 [00:02<00:10, 38.25it/s]
Loading 0:  18%|█▊        | 92/507 [00:02<00:11, 37.01it/s]
Loading 0:  19%|█▉        | 97/507 [00:02<00:10, 37.34it/s]
Loading 0:  20%|█▉        | 101/507 [00:02<00:10, 37.48it/s]
Loading 0:  21%|██        | 106/507 [00:02<00:10, 37.95it/s]
Loading 0:  22%|██▏       | 110/507 [00:03<00:10, 38.20it/s]
Loading 0:  22%|██▏       | 114/507 [00:03<00:15, 25.95it/s]
Loading 0:  23%|██▎       | 118/507 [00:03<00:15, 25.86it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:14, 26.45it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:10, 34.58it/s]
Loading 0:  26%|██▌       | 133/507 [00:03<00:10, 34.35it/s]
Loading 0:  27%|██▋       | 138/507 [00:03<00:09, 37.85it/s]
Loading 0:  28%|██▊       | 143/507 [00:04<00:09, 38.08it/s]
Loading 0:  29%|██▉       | 148/507 [00:04<00:09, 39.40it/s]
Loading 0:  30%|███       | 153/507 [00:04<00:08, 40.86it/s]
Loading 0:  31%|███       | 158/507 [00:04<00:09, 35.99it/s]
Loading 0:  33%|███▎      | 165/507 [00:04<00:07, 43.80it/s]
Loading 0:  34%|███▎      | 170/507 [00:04<00:11, 30.50it/s]
Loading 0:  34%|███▍      | 174/507 [00:04<00:10, 30.87it/s]
Loading 0:  35%|███▌      | 178/507 [00:05<00:10, 31.39it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:09, 34.94it/s]
Loading 0:  37%|███▋      | 187/507 [00:05<00:09, 34.00it/s]
Loading 0:  38%|███▊      | 192/507 [00:05<00:08, 37.13it/s]
Loading 0:  39%|███▊      | 196/507 [00:05<00:08, 35.63it/s]
Loading 0:  40%|███▉      | 201/507 [00:05<00:07, 38.61it/s]
Loading 0:  41%|████      | 206/507 [00:05<00:07, 38.88it/s]
Loading 0:  42%|████▏     | 211/507 [00:05<00:07, 39.24it/s]
Loading 0:  43%|████▎     | 216/507 [00:06<00:07, 41.18it/s]
Loading 0:  44%|████▎     | 221/507 [00:06<00:08, 35.45it/s]
Loading 0:  44%|████▍     | 225/507 [00:06<00:12, 23.32it/s]
Loading 0:  45%|████▌     | 230/507 [00:06<00:10, 25.42it/s]
Loading 0:  47%|████▋     | 237/507 [00:06<00:08, 32.48it/s]
Loading 0:  48%|████▊     | 241/507 [00:06<00:08, 32.18it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:07, 34.10it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 32.54it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:07, 34.27it/s]
Loading 0:  51%|█████     | 259/507 [00:07<00:07, 33.34it/s]
Loading 0:  52%|█████▏    | 264/507 [00:07<00:06, 36.47it/s]
Loading 0:  53%|█████▎    | 268/507 [00:07<00:06, 35.72it/s]
Loading 0:  54%|█████▍    | 273/507 [00:07<00:06, 38.64it/s]
Loading 0:  55%|█████▍    | 277/507 [00:07<00:06, 37.89it/s]
Loading 0:  56%|█████▌    | 283/507 [00:08<00:05, 40.89it/s]
Loading 0:  57%|█████▋    | 288/507 [00:08<00:08, 26.51it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 27.98it/s]
Loading 0:  59%|█████▉    | 299/507 [00:23<00:07, 27.98it/s]
Loading 0:  59%|█████▉    | 300/507 [00:23<02:48,  1.23it/s]
Loading 0:  60%|█████▉    | 302/507 [00:23<02:26,  1.40it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:39,  2.02it/s]
Loading 0:  61%|██████    | 310/507 [00:23<01:18,  2.50it/s]
Loading 0:  62%|██████▏   | 314/507 [00:23<00:56,  3.44it/s]
Loading 0:  63%|██████▎   | 319/507 [00:24<00:37,  5.01it/s]
Loading 0:  64%|██████▎   | 323/507 [00:24<00:27,  6.61it/s]
Loading 0:  65%|██████▍   | 328/507 [00:24<00:19,  9.13it/s]
Loading 0:  65%|██████▌   | 332/507 [00:24<00:15, 11.36it/s]
Loading 0:  66%|██████▋   | 337/507 [00:24<00:11, 15.12it/s]
Loading 0:  67%|██████▋   | 341/507 [00:24<00:11, 15.04it/s]
Loading 0:  68%|██████▊   | 345/507 [00:24<00:09, 17.36it/s]
Loading 0:  69%|██████▉   | 349/507 [00:25<00:08, 19.70it/s]
Loading 0:  70%|██████▉   | 354/507 [00:25<00:06, 23.78it/s]
Loading 0:  71%|███████   | 358/507 [00:25<00:05, 25.15it/s]
Loading 0:  72%|███████▏  | 363/507 [00:25<00:04, 29.91it/s]
Loading 0:  72%|███████▏  | 367/507 [00:25<00:04, 31.01it/s]
Loading 0:  73%|███████▎  | 372/507 [00:25<00:03, 35.41it/s]
Loading 0:  74%|███████▍  | 377/507 [00:25<00:03, 37.39it/s]
Loading 0:  75%|███████▌  | 382/507 [00:25<00:03, 39.02it/s]
Loading 0:  77%|███████▋  | 388/507 [00:25<00:02, 40.24it/s]
Loading 0:  78%|███████▊  | 393/507 [00:26<00:02, 39.18it/s]
Loading 0:  79%|███████▊  | 398/507 [00:26<00:03, 29.93it/s]
Loading 0:  79%|███████▉  | 402/507 [00:26<00:03, 29.17it/s]
Loading 0:  80%|████████  | 408/507 [00:26<00:02, 33.18it/s]
Loading 0:  81%|████████▏ | 412/507 [00:26<00:02, 33.32it/s]
Loading 0:  82%|████████▏ | 417/507 [00:26<00:02, 36.34it/s]
Loading 0:  83%|████████▎ | 421/507 [00:27<00:02, 35.96it/s]
Loading 0:  84%|████████▍ | 426/507 [00:27<00:02, 39.26it/s]
Loading 0:  85%|████████▌ | 431/507 [00:27<00:01, 39.51it/s]
Loading 0:  86%|████████▌ | 436/507 [00:27<00:01, 40.38it/s]
Loading 0:  87%|████████▋ | 441/507 [00:27<00:01, 42.52it/s]
Loading 0:  88%|████████▊ | 446/507 [00:27<00:01, 34.31it/s]
Loading 0:  90%|████████▉ | 454/507 [00:27<00:01, 41.18it/s]
Loading 0:  91%|█████████ | 459/507 [00:30<00:06,  7.00it/s]
Loading 0:  92%|█████████▏| 465/507 [00:30<00:04,  9.38it/s]
Loading 0:  93%|█████████▎| 472/507 [00:30<00:02, 13.14it/s]
Loading 0:  94%|█████████▍| 476/507 [00:30<00:02, 15.01it/s]
Loading 0:  95%|█████████▍| 481/507 [00:30<00:01, 18.63it/s]
Loading 0:  96%|█████████▌| 486/507 [00:30<00:00, 22.04it/s]
Loading 0:  97%|█████████▋| 491/507 [00:30<00:00, 25.32it/s]
Loading 0:  98%|█████████▊| 496/507 [00:31<00:00, 29.17it/s]
Loading 0:  99%|█████████▉| 501/507 [00:31<00:00, 27.88it/s]
                                                            

Job zonemercy-vingt-deux-v0-1e5-v19-mkmlizer completed after 136.02s with status: succeeded
Stopping job with name zonemercy-vingt-deux-v0-1e5-v19-mkmlizer
Pipeline stage MKMLizer completed in 137.37s
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-v0-1e5-v19
Waiting for inference service zonemercy-vingt-deux-v0-1e5-v19 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service zonemercy-vingt-deux-v0-1e5-v19 ready after 191.0501983165741s
Pipeline stage MKMLDeployer completed in 191.38s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.836742639541626s
Received healthy response to inference request in 2.9270153045654297s
Received healthy response to inference request in 2.797149181365967s
Received healthy response to inference request in 3.1552886962890625s
Received healthy response to inference request in 2.92911434173584s
5 requests
0 failed requests
5th percentile: 2.8231224060058593
10th percentile: 2.8490956306457518
20th percentile: 2.901042079925537
30th percentile: 2.927435111999512
40th percentile: 2.928274726867676
50th percentile: 2.92911434173584
60th percentile: 3.019584083557129
70th percentile: 3.110053825378418
80th percentile: 3.291579484939575
90th percentile: 3.5641610622406006
95th percentile: 3.7004518508911133
99th percentile: 3.8094844818115234
mean time: 3.129062032699585
Pipeline stage StressChecker completed in 16.90s
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 5.25s
Shutdown handler de-registered
zonemercy-vingt-deux-v0-1e5_v19 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 0.14s
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-v0-1e5-v19-profiler
Waiting for inference service zonemercy-vingt-deux-v0-1e5-v19-profiler to be ready
Inference service zonemercy-vingt-deux-v0-1e5-v19-profiler ready after 200.44659519195557s
Pipeline stage MKMLProfilerDeployer completed in 200.83s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/zonemercy-vingt-deux88e64f597a5f31024bae248963048dbd-deplorpdcc:/code/chaiverse_profiler_1727109918 --namespace tenant-chaiml-guanaco
kubectl exec -it zonemercy-vingt-deux88e64f597a5f31024bae248963048dbd-deplorpdcc --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727109918 && 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_1727109918/summary.json'
kubectl exec -it zonemercy-vingt-deux88e64f597a5f31024bae248963048dbd-deplorpdcc --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727109918/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1579.76s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service zonemercy-vingt-deux-v0-1e5-v19-profiler is running
Tearing down inference service zonemercy-vingt-deux-v0-1e5-v19-profiler
Service zonemercy-vingt-deux-v0-1e5-v19-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.98s
Shutdown handler de-registered
zonemercy-vingt-deux-v0-1e5_v19 status is now inactive due to auto deactivation removed underperforming models
zonemercy-vingt-deux-v0-1e5_v19 status is now torndown due to DeploymentManager action