zonemercy-virgo-edit-v3-1e6b1

developer_uid: chai_backend_admin

submission_id: zonemercy-virgo-edit-v3-1e6b1_v1

model_name: 0919v2-1

model_group: zonemercy/Virgo-Edit-v3-

status: torndown

timestamp: 2024-09-19T21:09:48+00:00

num_battles: 13948

num_wins: 7069

celo_rating: 1256.71

family_friendly_score: 0.0

submission_type: basic

model_repo: zonemercy/Virgo-Edit-v3-1e6b1

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6226465926317124, 'latency_mean': 1.6059867167472839, 'latency_p50': 1.6067906618118286, 'latency_p90': 1.7622466325759887}, {'batch_size': 3, 'throughput': 1.0875844090314586, 'latency_mean': 2.7513751471042633, 'latency_p50': 2.731279730796814, 'latency_p90': 3.046421432495117}, {'batch_size': 5, 'throughput': 1.227693931093015, 'latency_mean': 4.055345101356506, 'latency_p50': 4.091117739677429, 'latency_p90': 4.58586905002594}, {'batch_size': 6, 'throughput': 1.2586324687541592, 'latency_mean': 4.736925455331803, 'latency_p50': 4.774107933044434, 'latency_p90': 5.417175269126892}, {'batch_size': 8, 'throughput': 1.2376430289383211, 'latency_mean': 6.423228478431701, 'latency_p50': 6.449165225028992, 'latency_p90': 7.315393924713134}, {'batch_size': 10, 'throughput': 1.188603027137469, 'latency_mean': 8.35144413113594, 'latency_p50': 8.379242658615112, 'latency_p90': 9.556248307228088}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: 0919v2-1

is_internal_developer: True

language_model: zonemercy/Virgo-Edit-v3-1e6b1

model_size: 13B

ranking_group: single

throughput_3p7s: 1.2

us_pacific_date: 2024-09-19

win_ratio: 0.506811012331517

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|>'], '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-virgo-edit-v3-1e6b1-v1-mkmlizer
Waiting for job on zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer to finish
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: ║     _____            __           __                                ║
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: ║       /___/                                                         ║
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: ║                                                                     ║
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: ║  https://mk1.ai                                                     ║
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: ║                                                                     ║
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: ║  belonging to:                                                      ║
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: ║                                                                     ║
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: ║  Chai Research Corp.                                                ║
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: ║                                                                     ║
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: Downloaded to shared memory in 102.426s
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp1qs66ppq, device:0
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: quantized model in 40.638s
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: Processed model zonemercy/Virgo-Edit-v3-1e6b1 in 143.064s
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-virgo-edit-v3-1e6b1-v1
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-virgo-edit-v3-1e6b1-v1/config.json
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-virgo-edit-v3-1e6b1-v1/special_tokens_map.json
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-virgo-edit-v3-1e6b1-v1/tokenizer_config.json
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-virgo-edit-v3-1e6b1-v1/tokenizer.json
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-virgo-edit-v3-1e6b1-v1/flywheel_model.0.safetensors
zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:14, 25.11it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:11, 30.96it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:12, 27.85it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:08, 39.46it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:14, 23.60it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:12, 25.77it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:10, 31.60it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:10, 30.19it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.36it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 30.67it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:10, 30.43it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.41it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:12, 23.56it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:09, 30.39it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:09, 29.78it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 28.90it/s]
Loading 0:  23%|██▎       | 84/363 [00:02<00:09, 30.75it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 30.05it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 31.95it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 30.45it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 24.97it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:11, 22.45it/s]
Loading 0:  31%|███       | 111/363 [00:03<00:08, 29.67it/s]
Loading 0:  32%|███▏      | 115/363 [00:03<00:08, 29.07it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 31.46it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 29.86it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 31.97it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 29.89it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 29.98it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:08, 25.58it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 24.18it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 23.62it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:06, 30.59it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:06, 30.13it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.50it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.34it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 33.54it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:05, 32.37it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 25.63it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:07, 23.10it/s]
Loading 0:  53%|█████▎    | 192/363 [00:06<00:05, 30.63it/s]
Loading 0:  54%|█████▍    | 196/363 [00:06<00:05, 29.54it/s]
Loading 0:  55%|█████▌    | 201/363 [00:06<00:05, 32.12it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 31.09it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 32.88it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:04, 30.61it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 30.84it/s]
Loading 0:  61%|██████▏   | 223/363 [00:07<00:05, 26.56it/s]
Loading 0:  62%|██████▏   | 226/363 [00:07<00:05, 25.11it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 24.22it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 31.37it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 30.46it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 32.10it/s]
Loading 0:  69%|██████▉   | 250/363 [00:08<00:03, 30.88it/s]
Loading 0:  70%|███████   | 255/363 [00:08<00:03, 33.33it/s]
Loading 0:  71%|███████▏  | 259/363 [00:08<00:03, 31.68it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:03, 25.89it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 22.44it/s]
Loading 0:  75%|███████▌  | 273/363 [00:09<00:03, 29.11it/s]
Loading 0:  76%|███████▋  | 277/363 [00:09<00:03, 28.64it/s]
Loading 0:  78%|███████▊  | 282/363 [00:09<00:02, 30.86it/s]
Loading 0:  79%|███████▉  | 286/363 [00:09<00:02, 29.79it/s]
Loading 0:  80%|████████  | 291/363 [00:09<00:02, 32.31it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 30.94it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 30.87it/s]
Loading 0:  84%|████████▎ | 304/363 [00:10<00:02, 26.54it/s]
Loading 0:  85%|████████▍ | 307/363 [00:10<00:02, 24.82it/s]
Loading 0:  86%|████████▌ | 311/363 [00:10<00:02, 23.81it/s]
Loading 0:  87%|████████▋ | 317/363 [00:10<00:01, 31.09it/s]
Loading 0:  88%|████████▊ | 321/363 [00:11<00:01, 27.27it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 31.60it/s]
Loading 0:  91%|█████████ | 331/363 [00:11<00:01, 30.47it/s]
Loading 0:  93%|█████████▎| 336/363 [00:11<00:00, 32.15it/s]
Loading 0:  94%|█████████▎| 340/363 [00:11<00:00, 31.07it/s]
Loading 0:  95%|█████████▍| 344/363 [00:18<00:09,  1.97it/s]
Loading 0:  96%|█████████▌| 348/363 [00:18<00:05,  2.65it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.85it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  4.98it/s]
                                                            
Job zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer completed after 165.38s with status: succeeded
Stopping job with name zonemercy-virgo-edit-v3-1e6b1-v1-mkmlizer
Pipeline stage MKMLizer completed in 166.02s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service zonemercy-virgo-edit-v3-1e6b1-v1
Waiting for inference service zonemercy-virgo-edit-v3-1e6b1-v1 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
Inference service zonemercy-virgo-edit-v3-1e6b1-v1 ready after 200.94999051094055s
Pipeline stage MKMLDeployer completed in 201.35s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.057122230529785s
Received healthy response to inference request in 1.7891976833343506s
Received healthy response to inference request in 1.38444185256958s
Received healthy response to inference request in 1.2713806629180908s
Received healthy response to inference request in 1.4314062595367432s
5 requests
0 failed requests
5th percentile: 1.2939929008483886
10th percentile: 1.3166051387786866
20th percentile: 1.3618296146392823
30th percentile: 1.3938347339630126
40th percentile: 1.4126204967498779
50th percentile: 1.4314062595367432
60th percentile: 1.5745228290557862
70th percentile: 1.717639398574829
80th percentile: 1.8427825927734376
90th percentile: 1.9499524116516114
95th percentile: 2.003537321090698
99th percentile: 2.046405248641968
mean time: 1.58670973777771
Pipeline stage StressChecker completed in 8.52s
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 4.58s
Shutdown handler de-registered
zonemercy-virgo-edit-v3-1e6b1_v1 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service zonemercy-virgo-edit-v3-1e6b1-v1-profiler
Waiting for inference service zonemercy-virgo-edit-v3-1e6b1-v1-profiler to be ready
Inference service zonemercy-virgo-edit-v3-1e6b1-v1-profiler ready after 200.51316380500793s
Pipeline stage MKMLProfilerDeployer completed in 200.86s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/zonemercy-virgo-edit207cb6e93a380e4daa72e5800e7e297d-deplodt2wj:/code/chaiverse_profiler_1726780825 --namespace tenant-chaiml-guanaco
kubectl exec -it zonemercy-virgo-edit207cb6e93a380e4daa72e5800e7e297d-deplodt2wj --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726780825 && 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_1726780825/summary.json'
kubectl exec -it zonemercy-virgo-edit207cb6e93a380e4daa72e5800e7e297d-deplodt2wj --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726780825/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1162.75s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service zonemercy-virgo-edit-v3-1e6b1-v1-profiler is running
Tearing down inference service zonemercy-virgo-edit-v3-1e6b1-v1-profiler
Service zonemercy-virgo-edit-v3-1e6b1-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.04s
Shutdown handler de-registered
zonemercy-virgo-edit-v3-1e6b1_v1 status is now inactive due to auto deactivation removed underperforming models
zonemercy-virgo-edit-v3-1e6b1_v1 status is now torndown due to DeploymentManager action