zonemercy-lexical-viral-_2744

developer_uid: chai_backend_admin

submission_id: zonemercy-lexical-viral-_2744_v7

model_name: tempv1-3

model_group: zonemercy/Lexical-Viral-

status: inactive

timestamp: 2024-11-21T10:27:31+00:00

num_battles: 10009

num_wins: 5197

celo_rating: 1267.46

family_friendly_score: 0.5928

family_friendly_standard_error: 0.006948210704922527

submission_type: basic

model_repo: zonemercy/Lexical-Viral-v6ava-22b11e5r256b005

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.3858030879602616, 'latency_mean': 2.591935329437256, 'latency_p50': 2.6030672788619995, 'latency_p90': 2.8599082946777346}, {'batch_size': 3, 'throughput': 0.8263011741917021, 'latency_mean': 3.6270980858802795, 'latency_p50': 3.5949437618255615, 'latency_p90': 4.004859828948975}, {'batch_size': 5, 'throughput': 1.0830399112130702, 'latency_mean': 4.602041758298874, 'latency_p50': 4.629769682884216, 'latency_p90': 5.103961181640625}, {'batch_size': 6, 'throughput': 1.1591975290231529, 'latency_mean': 5.1305084848403935, 'latency_p50': 5.125546455383301, 'latency_p90': 5.8594338417053216}, {'batch_size': 10, 'throughput': 1.3723132145154255, 'latency_mean': 7.198134945631027, 'latency_p50': 7.202673673629761, 'latency_p90': 8.209156322479249}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: tempv1-3

is_internal_developer: True

language_model: zonemercy/Lexical-Viral-v6ava-22b11e5r256b005

model_size: 22B

ranking_group: single

throughput_3p7s: 0.85

us_pacific_date: 2024-11-21

win_ratio: 0.5192326905784793

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': 4, '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-lexical-viral-2744-v7-mkmlizer
Waiting for job on zonemercy-lexical-viral-2744-v7-mkmlizer to finish
zonemercy-lexical-viral-2744-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-lexical-viral-2744-v7-mkmlizer: ║     _____            __           __                                ║
zonemercy-lexical-viral-2744-v7-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
zonemercy-lexical-viral-2744-v7-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
zonemercy-lexical-viral-2744-v7-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
zonemercy-lexical-viral-2744-v7-mkmlizer: ║       /___/                                                         ║
zonemercy-lexical-viral-2744-v7-mkmlizer: ║                                                                     ║
zonemercy-lexical-viral-2744-v7-mkmlizer: ║  Version: 0.11.12                                                   ║
zonemercy-lexical-viral-2744-v7-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
zonemercy-lexical-viral-2744-v7-mkmlizer: ║  https://mk1.ai                                                     ║
zonemercy-lexical-viral-2744-v7-mkmlizer: ║                                                                     ║
zonemercy-lexical-viral-2744-v7-mkmlizer: ║  The license key for the current software has been verified as      ║
zonemercy-lexical-viral-2744-v7-mkmlizer: ║  belonging to:                                                      ║
zonemercy-lexical-viral-2744-v7-mkmlizer: ║                                                                     ║
zonemercy-lexical-viral-2744-v7-mkmlizer: ║  Chai Research Corp.                                                ║
zonemercy-lexical-viral-2744-v7-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
zonemercy-lexical-viral-2744-v7-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
zonemercy-lexical-viral-2744-v7-mkmlizer: ║                                                                     ║
zonemercy-lexical-viral-2744-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
zonemercy-lexical-viral-2744-v7-mkmlizer: Downloaded to shared memory in 82.518s
zonemercy-lexical-viral-2744-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxvvifgq4, device:0
zonemercy-lexical-viral-2744-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zonemercy-lexical-viral-2744-v7-mkmlizer: quantized model in 47.871s
zonemercy-lexical-viral-2744-v7-mkmlizer: Processed model zonemercy/Lexical-Viral-v6ava-22b11e5r256b005 in 130.390s
zonemercy-lexical-viral-2744-v7-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-lexical-viral-2744-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-lexical-viral-2744-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-lexical-viral-2744-v7
zonemercy-lexical-viral-2744-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-lexical-viral-2744-v7/config.json
zonemercy-lexical-viral-2744-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-lexical-viral-2744-v7/special_tokens_map.json
zonemercy-lexical-viral-2744-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-lexical-viral-2744-v7/tokenizer_config.json
zonemercy-lexical-viral-2744-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-lexical-viral-2744-v7/tokenizer.json
zonemercy-lexical-viral-2744-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/zonemercy-lexical-viral-2744-v7/flywheel_model.1.safetensors
zonemercy-lexical-viral-2744-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-lexical-viral-2744-v7/flywheel_model.0.safetensors
zonemercy-lexical-viral-2744-v7-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:22, 22.80it/s]
Loading 0:   2%|▏         | 10/507 [00:00<00:15, 32.08it/s]
Loading 0:   3%|▎         | 14/507 [00:00<00:17, 28.03it/s]
Loading 0:   4%|▎         | 19/507 [00:00<00:14, 33.14it/s]
Loading 0:   5%|▍         | 23/507 [00:00<00:16, 29.03it/s]
Loading 0:   6%|▌         | 28/507 [00:00<00:14, 33.13it/s]
Loading 0:   6%|▋         | 32/507 [00:01<00:16, 28.80it/s]
Loading 0:   7%|▋         | 37/507 [00:01<00:14, 33.06it/s]
Loading 0:   8%|▊         | 41/507 [00:01<00:15, 29.91it/s]
Loading 0:   9%|▉         | 46/507 [00:01<00:13, 34.35it/s]
Loading 0:  10%|▉         | 50/507 [00:01<00:14, 31.05it/s]
Loading 0:  11%|█         | 54/507 [00:01<00:21, 21.51it/s]
Loading 0:  11%|█         | 57/507 [00:02<00:20, 21.51it/s]
Loading 0:  12%|█▏        | 61/507 [00:02<00:18, 23.87it/s]
Loading 0:  13%|█▎        | 65/507 [00:02<00:18, 23.53it/s]
Loading 0:  14%|█▍        | 70/507 [00:02<00:15, 28.28it/s]
Loading 0:  15%|█▍        | 75/507 [00:02<00:13, 31.32it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:13, 30.96it/s]
Loading 0:  17%|█▋        | 85/507 [00:02<00:12, 34.44it/s]
Loading 0:  18%|█▊        | 89/507 [00:03<00:13, 30.72it/s]
Loading 0:  19%|█▊        | 94/507 [00:03<00:12, 34.07it/s]
Loading 0:  19%|█▉        | 98/507 [00:03<00:13, 29.80it/s]
Loading 0:  20%|██        | 103/507 [00:03<00:12, 33.24it/s]
Loading 0:  21%|██        | 107/507 [00:03<00:13, 28.79it/s]
Loading 0:  22%|██▏       | 112/507 [00:03<00:12, 32.19it/s]
Loading 0:  23%|██▎       | 116/507 [00:04<00:18, 20.88it/s]
Loading 0:  24%|██▍       | 122/507 [00:04<00:16, 23.94it/s]
Loading 0:  25%|██▌       | 127/507 [00:04<00:13, 27.62it/s]
Loading 0:  26%|██▌       | 131/507 [00:04<00:14, 25.79it/s]
Loading 0:  27%|██▋       | 136/507 [00:04<00:12, 29.46it/s]
Loading 0:  28%|██▊       | 140/507 [00:04<00:13, 27.52it/s]
Loading 0:  29%|██▊       | 145/507 [00:05<00:11, 31.20it/s]
Loading 0:  29%|██▉       | 149/507 [00:05<00:12, 29.47it/s]
Loading 0:  30%|███       | 154/507 [00:05<00:10, 32.33it/s]
Loading 0:  31%|███       | 158/507 [00:05<00:11, 29.81it/s]
Loading 0:  32%|███▏      | 163/507 [00:05<00:10, 34.16it/s]
Loading 0:  33%|███▎      | 168/507 [00:05<00:09, 35.25it/s]
Loading 0:  34%|███▍      | 172/507 [00:06<00:14, 23.47it/s]
Loading 0:  35%|███▍      | 176/507 [00:06<00:13, 23.90it/s]
Loading 0:  36%|███▌      | 181/507 [00:06<00:11, 28.53it/s]
Loading 0:  36%|███▋      | 185/507 [00:06<00:11, 26.86it/s]
Loading 0:  37%|███▋      | 190/507 [00:06<00:10, 31.38it/s]
Loading 0:  38%|███▊      | 194/507 [00:06<00:10, 28.68it/s]
Loading 0:  39%|███▉      | 199/507 [00:06<00:09, 32.87it/s]
Loading 0:  40%|████      | 203/507 [00:07<00:10, 30.01it/s]
Loading 0:  41%|████      | 208/507 [00:07<00:08, 34.27it/s]
Loading 0:  42%|████▏     | 212/507 [00:07<00:09, 30.77it/s]
Loading 0:  43%|████▎     | 217/507 [00:07<00:08, 34.93it/s]
Loading 0:  44%|████▎     | 221/507 [00:07<00:09, 31.73it/s]
Loading 0:  44%|████▍     | 225/507 [00:07<00:12, 22.34it/s]
Loading 0:  45%|████▌     | 230/507 [00:08<00:11, 24.36it/s]
Loading 0:  46%|████▋     | 235/507 [00:08<00:09, 28.57it/s]
Loading 0:  47%|████▋     | 239/507 [00:08<00:10, 26.29it/s]
Loading 0:  48%|████▊     | 244/507 [00:08<00:08, 30.42it/s]
Loading 0:  49%|████▉     | 248/507 [00:08<00:09, 28.13it/s]
Loading 0:  50%|████▉     | 253/507 [00:08<00:07, 32.52it/s]
Loading 0:  51%|█████     | 257/507 [00:08<00:08, 29.94it/s]
Loading 0:  52%|█████▏    | 262/507 [00:09<00:07, 34.00it/s]
Loading 0:  52%|█████▏    | 266/507 [00:09<00:07, 30.88it/s]
Loading 0:  53%|█████▎    | 271/507 [00:09<00:06, 34.53it/s]
Loading 0:  54%|█████▍    | 275/507 [00:09<00:07, 31.33it/s]
Loading 0:  55%|█████▌    | 280/507 [00:09<00:06, 35.49it/s]
Loading 0:  56%|█████▌    | 284/507 [00:09<00:08, 25.64it/s]
Loading 0:  57%|█████▋    | 288/507 [00:09<00:08, 25.40it/s]
Loading 0:  58%|█████▊    | 293/507 [00:10<00:08, 26.34it/s]
Loading 0:  59%|█████▉    | 298/507 [00:10<00:06, 30.74it/s]
Loading 0:  59%|█████▉    | 299/507 [00:20<00:06, 30.74it/s]
Loading 0:  59%|█████▉    | 300/507 [00:25<04:07,  1.20s/it]
Loading 0:  60%|█████▉    | 302/507 [00:25<03:23,  1.01it/s]
Loading 0:  61%|██████    | 307/507 [00:25<02:03,  1.62it/s]
Loading 0:  61%|██████    | 310/507 [00:25<01:33,  2.11it/s]
Loading 0:  62%|██████▏   | 313/507 [00:25<01:09,  2.79it/s]
Loading 0:  62%|██████▏   | 316/507 [00:26<00:51,  3.70it/s]
Loading 0:  63%|██████▎   | 320/507 [00:26<00:35,  5.22it/s]
Loading 0:  64%|██████▍   | 325/507 [00:26<00:23,  7.87it/s]
Loading 0:  65%|██████▍   | 329/507 [00:26<00:18,  9.83it/s]
Loading 0:  66%|██████▌   | 334/507 [00:26<00:12, 13.40it/s]
Loading 0:  67%|██████▋   | 339/507 [00:26<00:10, 16.43it/s]
Loading 0:  68%|██████▊   | 343/507 [00:27<00:11, 14.12it/s]
Loading 0:  68%|██████▊   | 347/507 [00:27<00:10, 15.82it/s]
Loading 0:  69%|██████▉   | 352/507 [00:27<00:07, 20.43it/s]
Loading 0:  70%|███████   | 356/507 [00:27<00:06, 21.64it/s]
Loading 0:  71%|███████   | 361/507 [00:27<00:05, 26.51it/s]
Loading 0:  72%|███████▏  | 365/507 [00:27<00:05, 25.77it/s]
Loading 0:  73%|███████▎  | 370/507 [00:27<00:04, 30.50it/s]
Loading 0:  74%|███████▍  | 374/507 [00:28<00:04, 28.76it/s]
Loading 0:  75%|███████▌  | 381/507 [00:28<00:03, 35.73it/s]
Loading 0:  76%|███████▌  | 386/507 [00:28<00:03, 35.25it/s]
Loading 0:  77%|███████▋  | 390/507 [00:28<00:04, 27.53it/s]
Loading 0:  78%|███████▊  | 394/507 [00:28<00:03, 29.22it/s]
Loading 0:  79%|███████▊  | 398/507 [00:28<00:04, 23.87it/s]
Loading 0:  79%|███████▉  | 401/507 [00:29<00:04, 21.82it/s]
Loading 0:  80%|████████  | 406/507 [00:29<00:03, 26.29it/s]
Loading 0:  81%|████████  | 410/507 [00:29<00:03, 24.40it/s]
Loading 0:  82%|████████▏ | 415/507 [00:29<00:03, 28.67it/s]
Loading 0:  83%|████████▎ | 419/507 [00:29<00:03, 26.89it/s]
Loading 0:  84%|████████▎ | 424/507 [00:29<00:02, 30.92it/s]
Loading 0:  84%|████████▍ | 428/507 [00:30<00:02, 28.00it/s]
Loading 0:  85%|████████▌ | 433/507 [00:30<00:02, 32.32it/s]
Loading 0:  86%|████████▌ | 437/507 [00:30<00:02, 30.15it/s]
Loading 0:  88%|████████▊ | 444/507 [00:30<00:01, 36.92it/s]
Loading 0:  88%|████████▊ | 448/507 [00:30<00:01, 35.04it/s]
Loading 0:  89%|████████▉ | 453/507 [00:30<00:01, 37.93it/s]
Loading 0:  90%|█████████ | 457/507 [00:32<00:08,  6.06it/s]
Loading 0:  91%|█████████ | 460/507 [00:33<00:06,  7.20it/s]
Loading 0:  92%|█████████▏| 465/507 [00:33<00:04,  9.65it/s]
Loading 0:  93%|█████████▎| 470/507 [00:33<00:02, 13.05it/s]
Loading 0:  93%|█████████▎| 474/507 [00:33<00:02, 14.81it/s]
Loading 0:  94%|█████████▍| 479/507 [00:33<00:01, 18.91it/s]
Loading 0:  95%|█████████▌| 483/507 [00:33<00:01, 20.14it/s]
Loading 0:  96%|█████████▋| 488/507 [00:33<00:00, 24.77it/s]
Loading 0:  97%|█████████▋| 492/507 [00:34<00:00, 24.54it/s]
Loading 0:  98%|█████████▊| 497/507 [00:34<00:00, 28.95it/s]
Loading 0:  99%|█████████▉| 501/507 [00:34<00:00, 27.21it/s]
Loading 0: 100%|█████████▉| 506/507 [00:34<00:00, 31.72it/s]
                                                            
Job zonemercy-lexical-viral-2744-v7-mkmlizer completed after 167.51s with status: succeeded
Stopping job with name zonemercy-lexical-viral-2744-v7-mkmlizer
Pipeline stage MKMLizer completed in 168.15s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service zonemercy-lexical-viral-2744-v7
Waiting for inference service zonemercy-lexical-viral-2744-v7 to be ready
Failed to get response for submission bbchicago-nana-nemo-12b-v1-0_v8: ('http://bbchicago-nana-nemo-12b-v1-0-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
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
Failed to get response for submission chaiml-nemo-20241010-tie_5991_v2: ('http://chaiml-nemo-20241010-tie-5991-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:59112->127.0.0.1:8080: read: connection reset by peer\n')
Inference service zonemercy-lexical-viral-2744-v7 ready after 231.0451157093048s
Pipeline stage MKMLDeployer completed in 231.64s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.697233200073242s
Received healthy response to inference request in 2.3008573055267334s
Received healthy response to inference request in 2.3349480628967285s
Received healthy response to inference request in 2.216862201690674s
Received healthy response to inference request in 2.2348556518554688s
5 requests
0 failed requests
5th percentile: 2.220460891723633
10th percentile: 2.224059581756592
20th percentile: 2.2312569618225098
30th percentile: 2.2480559825897215
40th percentile: 2.2744566440582275
50th percentile: 2.3008573055267334
60th percentile: 2.3144936084747316
70th percentile: 2.3281299114227294
80th percentile: 2.4074050903320314
90th percentile: 2.552319145202637
95th percentile: 2.6247761726379393
99th percentile: 2.682741794586182
mean time: 2.356951284408569
Pipeline stage StressChecker completed in 13.18s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 2.97s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 3.11s
Shutdown handler de-registered
zonemercy-lexical-viral-_2744_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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service zonemercy-lexical-viral-2744-v7-profiler
Waiting for inference service zonemercy-lexical-viral-2744-v7-profiler to be ready
Inference service zonemercy-lexical-viral-2744-v7-profiler ready after 230.51942920684814s
Pipeline stage MKMLProfilerDeployer completed in 230.90s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/zonemercy-lexical-vi5700ec53bf57c3d0ec2e1eb5b25fb404-deplohxjk6:/code/chaiverse_profiler_1732185531 --namespace tenant-chaiml-guanaco
kubectl exec -it zonemercy-lexical-vi5700ec53bf57c3d0ec2e1eb5b25fb404-deplohxjk6 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1732185531 && python profiles.py profile --best_of_n 4 --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_1732185531/summary.json'
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 3189.60s
Shutdown handler de-registered
zonemercy-lexical-viral-_2744_v7 status is now inactive due to auto deactivation removed underperforming models