zonemercy-vingt-deux-v2-1e5

submission_id: zonemercy-vingt-deux-v2-1e5_v16

developer_uid: chai_backend_admin

best_of: 8

celo_rating: 1249.9

display_name: temp-6

family_friendly_score: 0.0

formatter: {'memory_template': 'Bot Name: {bot_name}\n####\n', 'prompt_template': '', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}

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}

gpu_counts: {'NVIDIA RTX A6000': 1}

ineligible_reason: num_battles<5000

is_internal_developer: True

language_model: zonemercy/Vingt-Deux-v2-1e5

latencies: [{'batch_size': 1, 'throughput': 0.38293710662908714, 'latency_mean': 2.6113041579723357, 'latency_p50': 2.614900827407837, 'latency_p90': 2.90797016620636}, {'batch_size': 2, 'throughput': 0.6107877069601669, 'latency_mean': 3.2682762789726256, 'latency_p50': 3.2468433380126953, 'latency_p90': 3.6191521883010864}, {'batch_size': 3, 'throughput': 0.7534242622244596, 'latency_mean': 3.970242017507553, 'latency_p50': 3.969525098800659, 'latency_p90': 4.366644191741943}, {'batch_size': 4, 'throughput': 0.8787060822991104, 'latency_mean': 4.530638256072998, 'latency_p50': 4.54577362537384, 'latency_p90': 4.987078285217285}, {'batch_size': 5, 'throughput': 0.9687160558226766, 'latency_mean': 5.13412019610405, 'latency_p50': 5.152184009552002, 'latency_p90': 5.691327333450317}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: zonemercy/Vingt-Deux-v2-

model_name: temp-6

model_num_parameters: 22247282688.0

model_repo: zonemercy/Vingt-Deux-v2-1e5

model_size: 22B

num_battles: 3567

num_wins: 1783

ranking_group: single

status: torndown

submission_type: basic

throughput_3p7s: 0.71

timestamp: 2024-09-24T22:33:07+00:00

us_pacific_date: 2024-09-24

win_ratio: 0.4998598261844687

Download Preference Data

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-v2-1e5-v16-mkmlizer
Waiting for job on zonemercy-vingt-deux-v2-1e5-v16-mkmlizer to finish
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: ║     _____            __           __                                ║
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: ║       /___/                                                         ║
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: ║  Version: 0.10.1                                                    ║
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: ║  https://mk1.ai                                                     ║
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: ║  The license key for the current software has been verified as      ║
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: ║  belonging to:                                                      ║
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: ║  Chai Research Corp.                                                ║
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: Downloaded to shared memory in 61.385s
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpqeaup5ad, device:0
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: quantized model in 45.068s
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: Processed model zonemercy/Vingt-Deux-v2-1e5 in 106.453s
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-vingt-deux-v2-1e5-v16
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v2-1e5-v16/special_tokens_map.json
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v2-1e5-v16/config.json
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v2-1e5-v16/tokenizer_config.json
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v2-1e5-v16/tokenizer.json
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/zonemercy-vingt-deux-v2-1e5-v16/flywheel_model.1.safetensors
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-vingt-deux-v2-1e5-v16/flywheel_model.0.safetensors
zonemercy-vingt-deux-v2-1e5-v16-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:19, 26.05it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:11, 42.55it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:12, 40.66it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:11, 41.28it/s]
Loading 0:   5%|▌         | 27/507 [00:00<00:11, 40.30it/s]
Loading 0:   6%|▋         | 32/507 [00:00<00:14, 33.38it/s]
Loading 0:   8%|▊         | 39/507 [00:00<00:11, 40.92it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:11, 40.65it/s]
Loading 0:  10%|▉         | 49/507 [00:01<00:12, 36.06it/s]
Loading 0:  10%|█         | 53/507 [00:01<00:16, 27.06it/s]
Loading 0:  11%|█         | 57/507 [00:01<00:16, 26.87it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:16, 27.72it/s]
Loading 0:  13%|█▎        | 66/507 [00:02<00:17, 25.40it/s]
Loading 0:  14%|█▍        | 72/507 [00:02<00:13, 32.11it/s]
Loading 0:  15%|█▌        | 78/507 [00:02<00:11, 37.72it/s]
Loading 0:  16%|█▋        | 83/507 [00:02<00:11, 37.58it/s]
Loading 0:  17%|█▋        | 88/507 [00:02<00:11, 37.76it/s]
Loading 0:  18%|█▊        | 92/507 [00:02<00:10, 38.15it/s]
Loading 0:  19%|█▉        | 97/507 [00:02<00:10, 38.46it/s]
Loading 0:  20%|█▉        | 101/507 [00:02<00:10, 38.29it/s]
Loading 0:  21%|██        | 106/507 [00:03<00:10, 38.74it/s]
Loading 0:  22%|██▏       | 110/507 [00:03<00:10, 38.26it/s]
Loading 0:  22%|██▏       | 114/507 [00:03<00:14, 26.25it/s]
Loading 0:  23%|██▎       | 118/507 [00:03<00:14, 26.53it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:14, 27.05it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:10, 35.26it/s]
Loading 0:  26%|██▌       | 133/507 [00:03<00:10, 34.70it/s]
Loading 0:  27%|██▋       | 138/507 [00:04<00:09, 37.88it/s]
Loading 0:  28%|██▊       | 143/507 [00:04<00:09, 38.29it/s]
Loading 0:  29%|██▉       | 148/507 [00:04<00:09, 39.31it/s]
Loading 0:  30%|███       | 153/507 [00:04<00:08, 40.90it/s]
Loading 0:  31%|███       | 158/507 [00:04<00:09, 35.34it/s]
Loading 0:  32%|███▏      | 164/507 [00:04<00:08, 40.73it/s]
Loading 0:  33%|███▎      | 169/507 [00:04<00:10, 31.77it/s]
Loading 0:  34%|███▍      | 173/507 [00:05<00:10, 32.00it/s]
Loading 0:  35%|███▍      | 177/507 [00:05<00:10, 30.99it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:08, 36.43it/s]
Loading 0:  37%|███▋      | 187/507 [00:05<00:08, 36.16it/s]
Loading 0:  38%|███▊      | 192/507 [00:05<00:08, 39.36it/s]
Loading 0:  39%|███▉      | 197/507 [00:05<00:07, 39.44it/s]
Loading 0:  40%|███▉      | 202/507 [00:05<00:07, 40.31it/s]
Loading 0:  41%|████      | 207/507 [00:05<00:07, 42.55it/s]
Loading 0:  42%|████▏     | 212/507 [00:06<00:08, 35.77it/s]
Loading 0:  43%|████▎     | 218/507 [00:06<00:07, 40.52it/s]
Loading 0:  44%|████▍     | 223/507 [00:06<00:07, 37.26it/s]
Loading 0:  45%|████▍     | 227/507 [00:06<00:09, 30.66it/s]
Loading 0:  46%|████▌     | 231/507 [00:06<00:09, 29.25it/s]
Loading 0:  47%|████▋     | 237/507 [00:06<00:07, 33.99it/s]
Loading 0:  48%|████▊     | 241/507 [00:06<00:07, 34.05it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:07, 36.85it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 35.71it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:06, 37.96it/s]
Loading 0:  51%|█████     | 259/507 [00:07<00:06, 37.04it/s]
Loading 0:  52%|█████▏    | 264/507 [00:07<00:06, 39.15it/s]
Loading 0:  53%|█████▎    | 268/507 [00:07<00:06, 36.74it/s]
Loading 0:  54%|█████▍    | 273/507 [00:07<00:06, 39.00it/s]
Loading 0:  55%|█████▍    | 277/507 [00:07<00:06, 37.01it/s]
Loading 0:  56%|█████▌    | 283/507 [00:07<00:05, 38.57it/s]
Loading 0:  57%|█████▋    | 287/507 [00:08<00:08, 24.92it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 28.26it/s]
Loading 0:  59%|█████▉    | 299/507 [00:23<00:07, 28.26it/s]
Loading 0:  59%|█████▉    | 300/507 [00:23<02:50,  1.22it/s]
Loading 0:  60%|█████▉    | 302/507 [00:23<02:28,  1.38it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:40,  1.99it/s]
Loading 0:  61%|██████    | 310/507 [00:23<01:19,  2.47it/s]
Loading 0:  62%|██████▏   | 313/507 [00:24<01:01,  3.13it/s]
Loading 0:  62%|██████▏   | 316/507 [00:24<00:47,  4.04it/s]
Loading 0:  63%|██████▎   | 320/507 [00:24<00:33,  5.52it/s]
Loading 0:  64%|██████▍   | 325/507 [00:24<00:22,  8.17it/s]
Loading 0:  65%|██████▍   | 329/507 [00:24<00:17, 10.11it/s]
Loading 0:  66%|██████▌   | 334/507 [00:24<00:12, 13.79it/s]
Loading 0:  67%|██████▋   | 339/507 [00:24<00:09, 17.36it/s]
Loading 0:  68%|██████▊   | 343/507 [00:25<00:10, 15.90it/s]
Loading 0:  68%|██████▊   | 347/507 [00:25<00:09, 17.69it/s]
Loading 0:  70%|██████▉   | 354/507 [00:25<00:06, 24.57it/s]
Loading 0:  71%|███████   | 358/507 [00:25<00:05, 25.72it/s]
Loading 0:  72%|███████▏  | 363/507 [00:25<00:04, 29.21it/s]
Loading 0:  72%|███████▏  | 367/507 [00:25<00:04, 29.04it/s]
Loading 0:  73%|███████▎  | 372/507 [00:25<00:04, 32.17it/s]
Loading 0:  74%|███████▍  | 376/507 [00:26<00:04, 31.95it/s]
Loading 0:  75%|███████▌  | 381/507 [00:26<00:03, 34.58it/s]
Loading 0:  76%|███████▌  | 385/507 [00:26<00:03, 33.15it/s]
Loading 0:  77%|███████▋  | 389/507 [00:26<00:03, 32.57it/s]
Loading 0:  78%|███████▊  | 393/507 [00:26<00:03, 31.94it/s]
Loading 0:  78%|███████▊  | 397/507 [00:26<00:04, 23.63it/s]
Loading 0:  79%|███████▉  | 401/507 [00:27<00:04, 23.53it/s]
Loading 0:  80%|████████  | 406/507 [00:27<00:03, 27.98it/s]
Loading 0:  81%|████████  | 410/507 [00:27<00:03, 26.60it/s]
Loading 0:  82%|████████▏ | 415/507 [00:27<00:02, 31.34it/s]
Loading 0:  83%|████████▎ | 419/507 [00:27<00:03, 26.89it/s]
Loading 0:  84%|████████▎ | 424/507 [00:27<00:02, 31.23it/s]
Loading 0:  84%|████████▍ | 428/507 [00:27<00:02, 29.23it/s]
Loading 0:  85%|████████▌ | 433/507 [00:28<00:02, 33.47it/s]
Loading 0:  86%|████████▌ | 437/507 [00:28<00:02, 30.57it/s]
Loading 0:  88%|████████▊ | 444/507 [00:28<00:01, 37.36it/s]
Loading 0:  88%|████████▊ | 448/507 [00:28<00:01, 35.67it/s]
Loading 0:  90%|████████▉ | 454/507 [00:28<00:01, 35.75it/s]
Loading 0:  90%|█████████ | 458/507 [00:30<00:08,  6.12it/s]
Loading 0:  91%|█████████ | 461/507 [00:31<00:06,  7.27it/s]
Loading 0:  92%|█████████▏| 465/507 [00:31<00:04,  9.06it/s]
Loading 0:  93%|█████████▎| 470/507 [00:31<00:02, 12.42it/s]
Loading 0:  93%|█████████▎| 474/507 [00:31<00:02, 13.92it/s]
Loading 0:  94%|█████████▍| 479/507 [00:31<00:01, 18.11it/s]
Loading 0:  95%|█████████▌| 483/507 [00:31<00:01, 19.50it/s]
Loading 0:  96%|█████████▋| 488/507 [00:31<00:00, 24.17it/s]
Loading 0:  97%|█████████▋| 492/507 [00:32<00:00, 24.01it/s]
Loading 0:  98%|█████████▊| 499/507 [00:32<00:00, 30.99it/s]
Loading 0:  99%|█████████▉| 503/507 [00:32<00:00, 30.51it/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
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Job zonemercy-vingt-deux-v2-1e5-v16-mkmlizer completed after 258.79s with status: succeeded
Stopping job with name zonemercy-vingt-deux-v2-1e5-v16-mkmlizer
Pipeline stage MKMLizer completed in 260.00s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 1.22s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service zonemercy-vingt-deux-v2-1e5-v16
Waiting for inference service zonemercy-vingt-deux-v2-1e5-v16 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
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-v2-1e5-v16 ready after 213.27093529701233s
Pipeline stage MKMLDeployer completed in 214.01s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.4841408729553223s
Received healthy response to inference request in 2.7455193996429443s
Received healthy response to inference request in 2.7749738693237305s
Received healthy response to inference request in 2.6746585369110107s
Received healthy response to inference request in 3.1697328090667725s
5 requests
0 failed requests
5th percentile: 2.6888307094573975
10th percentile: 2.7030028820037844
20th percentile: 2.7313472270965575
30th percentile: 2.7514102935791014
40th percentile: 2.763192081451416
50th percentile: 2.7749738693237305
60th percentile: 2.932877445220947
70th percentile: 3.090781021118164
80th percentile: 3.2326144218444823
90th percentile: 3.3583776473999025
95th percentile: 3.4212592601776124
99th percentile: 3.4715645503997803
mean time: 2.969805097579956
Pipeline stage StressChecker completed in 15.76s
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 5.70s
Shutdown handler de-registered
zonemercy-vingt-deux-v2-1e5_v16 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 0.16s
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-v2-1e5-v16-profiler
Waiting for inference service zonemercy-vingt-deux-v2-1e5-v16-profiler to be ready
Inference service zonemercy-vingt-deux-v2-1e5-v16-profiler ready after 220.49292993545532s
Pipeline stage MKMLProfilerDeployer completed in 220.89s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/zonemercy-vingt-deuxecc977c0e4b654121d7b178d5c594f4c-deplo7zjdl:/code/chaiverse_profiler_1727217952 --namespace tenant-chaiml-guanaco
kubectl exec -it zonemercy-vingt-deuxecc977c0e4b654121d7b178d5c594f4c-deplo7zjdl --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727217952 && 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_1727217952/summary.json'
kubectl exec -it zonemercy-vingt-deuxecc977c0e4b654121d7b178d5c594f4c-deplo7zjdl --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727217952/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1553.79s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service zonemercy-vingt-deux-v2-1e5-v16-profiler is running
Tearing down inference service zonemercy-vingt-deux-v2-1e5-v16-profiler
Service zonemercy-vingt-deux-v2-1e5-v16-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.03s
Shutdown handler de-registered
zonemercy-vingt-deux-v2-1e5_v16 status is now inactive due to auto deactivation removed underperforming models
Shutdown handler de-registered
Shutdown handler de-registered
zonemercy-vingt-deux-v1-1e5_v13 status is now torndown due to DeploymentManager action
zonemercy-vingt-deux-v2-_1790_v8 status is now torndown due to DeploymentManager action
zonemercy-vingt-deux-v2-1e5_v14 status is now torndown due to DeploymentManager action