zonemercy-vingt-deux-v0-1e5

developer_uid: zonemercy

submission_id: zonemercy-vingt-deux-v0-1e5_v18

model_name: zonemercy-vingt-deux-v0-1e5_v18

model_group: zonemercy/Vingt-Deux-v0-

status: torndown

timestamp: 2024-09-23T16:19:08+00:00

num_battles: 26048

num_wins: 13322

celo_rating: 1248.9

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': 0.3864170881199348, 'latency_mean': 2.587782361507416, 'latency_p50': 2.533265709877014, 'latency_p90': 2.897338557243347}, {'batch_size': 2, 'throughput': 0.5995432559100805, 'latency_mean': 3.3243013060092927, 'latency_p50': 3.339277505874634, 'latency_p90': 3.659127712249756}, {'batch_size': 3, 'throughput': 0.758018045109923, 'latency_mean': 3.946501100063324, 'latency_p50': 3.9209693670272827, 'latency_p90': 4.415676689147949}, {'batch_size': 4, 'throughput': 0.8749640295168604, 'latency_mean': 4.557655159235001, 'latency_p50': 4.583247423171997, 'latency_p90': 4.9951457500457765}, {'batch_size': 5, 'throughput': 0.9718445301959776, 'latency_mean': 5.105867754220963, 'latency_p50': 5.074813008308411, 'latency_p90': 5.702153992652893}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: zonemercy-vingt-deux-v0-1e5_v18

is_internal_developer: True

language_model: zonemercy/Vingt-Deux-v0-1e5

model_size: 22B

ranking_group: single

throughput_3p7s: 0.7

us_pacific_date: 2024-09-23

win_ratio: 0.5114404176904177

generation_params: {'temperature': 1.1235, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 100, '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-v18-mkmlizer
Waiting for job on zonemercy-vingt-deux-v0-1e5-v18-mkmlizer to finish
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: ║     _____            __           __                                ║
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: ║       /___/                                                         ║
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: ║  Version: 0.10.1                                                    ║
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: ║  https://mk1.ai                                                     ║
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: ║  The license key for the current software has been verified as      ║
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: ║  belonging to:                                                      ║
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: ║  Chai Research Corp.                                                ║
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: Downloaded to shared memory in 54.366s
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0zhn_9xt, device:0
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: quantized model in 44.953s
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: Processed model zonemercy/Vingt-Deux-v0-1e5 in 99.319s
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v18
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v18/config.json
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v18/special_tokens_map.json
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v18/tokenizer_config.json
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v18/flywheel_model.1.safetensors
zonemercy-vingt-deux-v0-1e5-v18-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:18, 27.10it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:12, 40.11it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:13, 36.36it/s]
Loading 0:   4%|▍         | 21/507 [00:00<00:13, 37.31it/s]
Loading 0:   5%|▍         | 25/507 [00:00<00:13, 35.53it/s]
Loading 0:   6%|▌         | 30/507 [00:00<00:12, 39.11it/s]
Loading 0:   7%|▋         | 35/507 [00:00<00:12, 37.68it/s]
Loading 0:   8%|▊         | 40/507 [00:01<00:11, 38.96it/s]
Loading 0:   9%|▉         | 45/507 [00:01<00:11, 41.23it/s]
Loading 0:  10%|▉         | 50/507 [00:01<00:12, 35.83it/s]
Loading 0:  11%|█         | 54/507 [00:01<00:16, 26.75it/s]
Loading 0:  11%|█▏        | 58/507 [00:01<00:16, 27.43it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:14, 30.59it/s]
Loading 0:  13%|█▎        | 67/507 [00:01<00:13, 31.49it/s]
Loading 0:  14%|█▍        | 73/507 [00:02<00:12, 34.82it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:11, 36.35it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:10, 40.80it/s]
Loading 0:  18%|█▊        | 92/507 [00:02<00:10, 38.43it/s]
Loading 0:  19%|█▉        | 96/507 [00:02<00:10, 38.69it/s]
Loading 0:  20%|█▉        | 100/507 [00:02<00:10, 37.17it/s]
Loading 0:  21%|██        | 105/507 [00:02<00:10, 38.91it/s]
Loading 0:  21%|██▏       | 109/507 [00:03<00:10, 37.59it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:14, 27.36it/s]
Loading 0:  23%|██▎       | 117/507 [00:03<00:14, 26.78it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:13, 28.23it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:10, 35.71it/s]
Loading 0:  26%|██▌       | 133/507 [00:03<00:10, 35.33it/s]
Loading 0:  27%|██▋       | 138/507 [00:03<00:09, 38.43it/s]
Loading 0:  28%|██▊       | 143/507 [00:04<00:09, 38.70it/s]
Loading 0:  29%|██▉       | 148/507 [00:04<00:09, 39.82it/s]
Loading 0:  30%|███       | 153/507 [00:04<00:08, 40.80it/s]
Loading 0:  31%|███       | 158/507 [00:04<00:09, 35.20it/s]
Loading 0:  33%|███▎      | 165/507 [00:04<00:07, 43.06it/s]
Loading 0:  34%|███▎      | 170/507 [00:04<00:10, 31.80it/s]
Loading 0:  34%|███▍      | 174/507 [00:04<00:10, 31.29it/s]
Loading 0:  35%|███▌      | 178/507 [00:05<00:10, 31.64it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:09, 35.62it/s]
Loading 0:  37%|███▋      | 187/507 [00:05<00:09, 35.23it/s]
Loading 0:  38%|███▊      | 192/507 [00:05<00:08, 37.68it/s]
Loading 0:  39%|███▊      | 196/507 [00:05<00:08, 36.72it/s]
Loading 0:  40%|███▉      | 201/507 [00:05<00:07, 39.09it/s]
Loading 0:  41%|████      | 206/507 [00:05<00:07, 40.12it/s]
Loading 0:  42%|████▏     | 211/507 [00:05<00:07, 40.81it/s]
Loading 0:  43%|████▎     | 216/507 [00:06<00:06, 42.93it/s]
Loading 0:  44%|████▎     | 221/507 [00:06<00:07, 37.20it/s]
Loading 0:  44%|████▍     | 225/507 [00:06<00:10, 27.71it/s]
Loading 0:  45%|████▌     | 230/507 [00:06<00:09, 29.12it/s]
Loading 0:  47%|████▋     | 237/507 [00:06<00:07, 36.14it/s]
Loading 0:  48%|████▊     | 242/507 [00:06<00:07, 36.44it/s]
Loading 0:  49%|████▊     | 246/507 [00:06<00:07, 37.12it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 35.25it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:06, 37.41it/s]
Loading 0:  51%|█████     | 259/507 [00:07<00:06, 35.50it/s]
Loading 0:  52%|█████▏    | 264/507 [00:07<00:06, 38.10it/s]
Loading 0:  53%|█████▎    | 268/507 [00:07<00:06, 37.00it/s]
Loading 0:  54%|█████▍    | 273/507 [00:07<00:05, 39.61it/s]
Loading 0:  55%|█████▍    | 278/507 [00:07<00:05, 39.30it/s]
Loading 0:  56%|█████▌    | 283/507 [00:07<00:05, 40.42it/s]
Loading 0:  57%|█████▋    | 288/507 [00:08<00:08, 27.32it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 28.11it/s]
Loading 0:  59%|█████▉    | 299/507 [00:24<00:07, 28.11it/s]
Loading 0:  59%|█████▉    | 300/507 [00:24<03:00,  1.15it/s]
Loading 0:  60%|█████▉    | 302/507 [00:24<02:36,  1.31it/s]
Loading 0:  61%|██████    | 307/507 [00:24<01:45,  1.90it/s]
Loading 0:  61%|██████    | 310/507 [00:24<01:23,  2.36it/s]
Loading 0:  62%|██████▏   | 314/507 [00:24<00:59,  3.24it/s]
Loading 0:  63%|██████▎   | 319/507 [00:24<00:39,  4.74it/s]
Loading 0:  64%|██████▍   | 324/507 [00:24<00:27,  6.74it/s]
Loading 0:  65%|██████▍   | 328/507 [00:24<00:20,  8.69it/s]
Loading 0:  65%|██████▌   | 332/507 [00:25<00:15, 11.14it/s]
Loading 0:  66%|██████▋   | 337/507 [00:25<00:11, 15.02it/s]
Loading 0:  67%|██████▋   | 342/507 [00:25<00:11, 14.70it/s]
Loading 0:  68%|██████▊   | 347/507 [00:25<00:08, 17.82it/s]
Loading 0:  70%|██████▉   | 354/507 [00:25<00:06, 24.71it/s]
Loading 0:  71%|███████   | 359/507 [00:25<00:05, 27.65it/s]
Loading 0:  72%|███████▏  | 364/507 [00:26<00:04, 30.67it/s]
Loading 0:  73%|███████▎  | 369/507 [00:26<00:04, 33.72it/s]
Loading 0:  74%|███████▍  | 374/507 [00:26<00:04, 31.55it/s]
Loading 0:  75%|███████▌  | 381/507 [00:26<00:03, 39.16it/s]
Loading 0:  76%|███████▌  | 386/507 [00:26<00:03, 38.56it/s]
Loading 0:  77%|███████▋  | 391/507 [00:26<00:03, 33.14it/s]
Loading 0:  78%|███████▊  | 395/507 [00:27<00:04, 27.13it/s]
Loading 0:  79%|███████▉  | 401/507 [00:27<00:03, 28.89it/s]
Loading 0:  80%|████████  | 408/507 [00:27<00:02, 35.61it/s]
Loading 0:  81%|████████▏ | 413/507 [00:27<00:02, 35.18it/s]
Loading 0:  82%|████████▏ | 417/507 [00:27<00:02, 36.15it/s]
Loading 0:  83%|████████▎ | 421/507 [00:27<00:02, 35.77it/s]
Loading 0:  84%|████████▍ | 426/507 [00:27<00:02, 38.97it/s]
Loading 0:  85%|████████▌ | 431/507 [00:27<00:01, 38.95it/s]
Loading 0:  86%|████████▌ | 436/507 [00:28<00:01, 39.97it/s]
Loading 0:  87%|████████▋ | 442/507 [00:28<00:01, 40.36it/s]
Loading 0:  88%|████████▊ | 447/507 [00:28<00:01, 39.10it/s]
Loading 0:  90%|████████▉ | 454/507 [00:28<00:01, 43.59it/s]
Loading 0:  91%|█████████ | 459/507 [00:30<00:07,  6.79it/s]
Loading 0:  92%|█████████▏| 465/507 [00:31<00:04,  9.13it/s]
Loading 0:  93%|█████████▎| 472/507 [00:31<00:02, 12.86it/s]
Loading 0:  94%|█████████▍| 476/507 [00:31<00:02, 14.77it/s]
Loading 0:  95%|█████████▍| 481/507 [00:31<00:01, 18.30it/s]
Loading 0:  96%|█████████▌| 485/507 [00:31<00:01, 20.70it/s]
Loading 0:  97%|█████████▋| 490/507 [00:31<00:00, 24.74it/s]
Loading 0:  98%|█████████▊| 495/507 [00:31<00:00, 27.76it/s]
Loading 0:  99%|█████████▊| 500/507 [00:31<00:00, 30.50it/s]
Loading 0:  99%|█████████▉| 504/507 [00:31<00:00, 32.28it/s]
                                                            
Job zonemercy-vingt-deux-v0-1e5-v18-mkmlizer completed after 167.75s with status: succeeded
Stopping job with name zonemercy-vingt-deux-v0-1e5-v18-mkmlizer
Pipeline stage MKMLizer completed in 168.49s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service zonemercy-vingt-deux-v0-1e5-v18
Waiting for inference service zonemercy-vingt-deux-v0-1e5-v18 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
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service zonemercy-vingt-deux-v0-1e5-v18 ready after 192.12996625900269s
Pipeline stage MKMLDeployer completed in 192.54s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.4246816635131836s
Received healthy response to inference request in 2.7955353260040283s
Received healthy response to inference request in 3.2274580001831055s
Received healthy response to inference request in 2.657478094100952s
Received healthy response to inference request in 2.503355026245117s
5 requests
0 failed requests
5th percentile: 2.5341796398162844
10th percentile: 2.565004253387451
20th percentile: 2.626653480529785
30th percentile: 2.6850895404815676
40th percentile: 2.740312433242798
50th percentile: 2.7955353260040283
60th percentile: 2.968304395675659
70th percentile: 3.14107346534729
80th percentile: 3.266902732849121
90th percentile: 3.3457921981811523
95th percentile: 3.385236930847168
99th percentile: 3.4167927169799803
mean time: 2.9217016220092775
Pipeline stage StressChecker completed in 17.33s
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 6.20s
Shutdown handler de-registered
zonemercy-vingt-deux-v0-1e5_v18 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 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service zonemercy-vingt-deux-v0-1e5-v18-profiler
Waiting for inference service zonemercy-vingt-deux-v0-1e5-v18-profiler to be ready
Inference service zonemercy-vingt-deux-v0-1e5-v18-profiler ready after 190.4659128189087s
Pipeline stage MKMLProfilerDeployer completed in 190.90s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/zonemercy-vingt-deuxfd94701dd32b71e71a8206dd262e851b-deplozq9vp:/code/chaiverse_profiler_1727108972 --namespace tenant-chaiml-guanaco
kubectl exec -it zonemercy-vingt-deuxfd94701dd32b71e71a8206dd262e851b-deplozq9vp --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727108972 && 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_1727108972/summary.json'
kubectl exec -it zonemercy-vingt-deuxfd94701dd32b71e71a8206dd262e851b-deplozq9vp --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727108972/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1554.37s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service zonemercy-vingt-deux-v0-1e5-v18-profiler is running
Tearing down inference service zonemercy-vingt-deux-v0-1e5-v18-profiler
Service zonemercy-vingt-deux-v0-1e5-v18-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.99s
Shutdown handler de-registered
zonemercy-vingt-deux-v0-1e5_v18 status is now inactive due to auto deactivation removed underperforming models
zonemercy-vingt-deux-v0-1e5_v18 status is now torndown due to DeploymentManager action