chaiml-lexical-viral-v5a_3842

developer_uid: zonemercy

submission_id: chaiml-lexical-viral-v5a_3842_v5

model_name: tempv1-0

model_group: ChaiML/Lexical-Viral-v5a

status: inactive

timestamp: 2024-12-10T13:07:35+00:00

num_battles: 16604

num_wins: 8113

celo_rating: 1255.3

family_friendly_score: 0.5851999999999999

family_friendly_standard_error: 0.006967653263474008

submission_type: basic

model_repo: ChaiML/Lexical-Viral-v5ava-22b11e5r128

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.3864745310348013, 'latency_mean': 2.5874087727069854, 'latency_p50': 2.6026506423950195, 'latency_p90': 2.854061222076416}, {'batch_size': 3, 'throughput': 0.814855727194699, 'latency_mean': 3.67111612200737, 'latency_p50': 3.675919532775879, 'latency_p90': 4.0241975545883175}, {'batch_size': 5, 'throughput': 1.0764172302639528, 'latency_mean': 4.610604853630066, 'latency_p50': 4.633986830711365, 'latency_p90': 5.147795820236206}, {'batch_size': 6, 'throughput': 1.163917164852227, 'latency_mean': 5.127887959480286, 'latency_p50': 5.109667420387268, 'latency_p90': 5.777391242980957}, {'batch_size': 10, 'throughput': 1.371587567259084, 'latency_mean': 7.213373078107834, 'latency_p50': 7.240866541862488, 'latency_p90': 8.084577202796936}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: tempv1-0

is_internal_developer: True

language_model: ChaiML/Lexical-Viral-v5ava-22b11e5r128

model_size: 22B

ranking_group: single

throughput_3p7s: 0.83

us_pacific_date: 2024-12-10

win_ratio: 0.48861720067453623

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 chaiml-lexical-viral-v5a-3842-v5-mkmlizer
Waiting for job on chaiml-lexical-viral-v5a-3842-v5-mkmlizer to finish
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: ║     _____            __           __                                ║
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: ║       /___/                                                         ║
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: ║                                                                     ║
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: ║                                                                     ║
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: ║  belonging to:                                                      ║
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: ║                                                                     ║
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: ║                                                                     ║
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: Downloaded to shared memory in 58.843s
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpos3mj3lq, device:0
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: quantized model in 47.339s
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: Processed model ChaiML/Lexical-Viral-v5ava-22b11e5r128 in 106.182s
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: creating bucket guanaco-mkml-models
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-lexical-viral-v5a-3842-v5
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-lexical-viral-v5a-3842-v5/config.json
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-lexical-viral-v5a-3842-v5/special_tokens_map.json
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-lexical-viral-v5a-3842-v5/tokenizer_config.json
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-lexical-viral-v5a-3842-v5/tokenizer.json
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-lexical-viral-v5a-3842-v5/flywheel_model.1.safetensors
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-lexical-viral-v5a-3842-v5/flywheel_model.0.safetensors
chaiml-lexical-viral-v5a-3842-v5-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:22, 22.78it/s]
Loading 0:   2%|▏         | 10/507 [00:00<00:15, 32.66it/s]
Loading 0:   3%|▎         | 14/507 [00:00<00:17, 28.30it/s]
Loading 0:   4%|▎         | 19/507 [00:00<00:14, 33.55it/s]
Loading 0:   5%|▍         | 23/507 [00:00<00:16, 29.28it/s]
Loading 0:   6%|▌         | 28/507 [00:00<00:14, 33.64it/s]
Loading 0:   6%|▋         | 32/507 [00:01<00:15, 29.70it/s]
Loading 0:   7%|▋         | 37/507 [00:01<00:13, 34.11it/s]
Loading 0:   8%|▊         | 41/507 [00:01<00:15, 30.03it/s]
Loading 0:   9%|▉         | 47/507 [00:01<00:13, 34.60it/s]
Loading 0:  10%|█         | 51/507 [00:01<00:13, 32.61it/s]
Loading 0:  11%|█         | 55/507 [00:01<00:20, 21.54it/s]
Loading 0:  11%|█▏        | 58/507 [00:02<00:19, 22.45it/s]
Loading 0:  12%|█▏        | 61/507 [00:02<00:18, 23.78it/s]
Loading 0:  13%|█▎        | 65/507 [00:02<00:19, 22.92it/s]
Loading 0:  14%|█▍        | 70/507 [00:02<00:15, 27.97it/s]
Loading 0:  15%|█▍        | 75/507 [00:02<00:13, 31.12it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:14, 30.18it/s]
Loading 0:  17%|█▋        | 85/507 [00:02<00:12, 34.15it/s]
Loading 0:  18%|█▊        | 89/507 [00:03<00:13, 30.21it/s]
Loading 0:  19%|█▊        | 94/507 [00:03<00:12, 33.87it/s]
Loading 0:  19%|█▉        | 98/507 [00:03<00:14, 28.73it/s]
Loading 0:  20%|██        | 103/507 [00:03<00:12, 32.79it/s]
Loading 0:  21%|██        | 107/507 [00:03<00:13, 29.32it/s]
Loading 0:  22%|██▏       | 112/507 [00:03<00:11, 33.16it/s]
Loading 0:  23%|██▎       | 116/507 [00:04<00:18, 20.82it/s]
Loading 0:  24%|██▍       | 122/507 [00:04<00:16, 23.86it/s]
Loading 0:  25%|██▌       | 127/507 [00:04<00:13, 28.16it/s]
Loading 0:  26%|██▌       | 131/507 [00:04<00:14, 26.71it/s]
Loading 0:  27%|██▋       | 136/507 [00:04<00:11, 31.07it/s]
Loading 0:  28%|██▊       | 140/507 [00:04<00:12, 28.51it/s]
Loading 0:  29%|██▊       | 145/507 [00:04<00:11, 32.48it/s]
Loading 0:  29%|██▉       | 149/507 [00:05<00:12, 29.49it/s]
Loading 0:  30%|███       | 154/507 [00:05<00:10, 33.49it/s]
Loading 0:  31%|███       | 158/507 [00:05<00:11, 30.37it/s]
Loading 0:  32%|███▏      | 164/507 [00:05<00:09, 34.73it/s]
Loading 0:  33%|███▎      | 168/507 [00:05<00:09, 35.70it/s]
Loading 0:  34%|███▍      | 172/507 [00:06<00:14, 23.23it/s]
Loading 0:  35%|███▍      | 176/507 [00:06<00:14, 23.49it/s]
Loading 0:  36%|███▌      | 183/507 [00:06<00:10, 30.67it/s]
Loading 0:  37%|███▋      | 187/507 [00:06<00:10, 30.63it/s]
Loading 0:  38%|███▊      | 192/507 [00:06<00:09, 33.53it/s]
Loading 0:  39%|███▊      | 196/507 [00:06<00:09, 32.51it/s]
Loading 0:  39%|███▉      | 200/507 [00:06<00:09, 33.92it/s]
Loading 0:  40%|████      | 204/507 [00:06<00:10, 29.38it/s]
Loading 0:  41%|████▏     | 210/507 [00:07<00:08, 34.23it/s]
Loading 0:  42%|████▏     | 214/507 [00:07<00:08, 32.97it/s]
Loading 0:  43%|████▎     | 218/507 [00:07<00:08, 32.98it/s]
Loading 0:  44%|████▍     | 222/507 [00:07<00:08, 32.41it/s]
Loading 0:  45%|████▍     | 226/507 [00:07<00:11, 24.85it/s]
Loading 0:  45%|████▌     | 230/507 [00:07<00:11, 24.97it/s]
Loading 0:  47%|████▋     | 237/507 [00:08<00:08, 32.47it/s]
Loading 0:  48%|████▊     | 241/507 [00:08<00:08, 32.23it/s]
Loading 0:  49%|████▊     | 246/507 [00:08<00:07, 34.59it/s]
Loading 0:  49%|████▉     | 250/507 [00:08<00:07, 34.17it/s]
Loading 0:  50%|█████     | 255/507 [00:08<00:06, 36.54it/s]
Loading 0:  51%|█████     | 259/507 [00:08<00:07, 35.16it/s]
Loading 0:  52%|█████▏    | 264/507 [00:08<00:06, 37.42it/s]
Loading 0:  53%|█████▎    | 268/507 [00:08<00:06, 34.78it/s]
Loading 0:  54%|█████▎    | 272/507 [00:08<00:06, 36.00it/s]
Loading 0:  54%|█████▍    | 276/507 [00:09<00:07, 31.07it/s]
Loading 0:  55%|█████▌    | 281/507 [00:09<00:06, 35.45it/s]
Loading 0:  56%|█████▌    | 285/507 [00:09<00:09, 24.26it/s]
Loading 0:  57%|█████▋    | 289/507 [00:09<00:08, 24.77it/s]
Loading 0:  58%|█████▊    | 293/507 [00:09<00:08, 25.08it/s]
Loading 0:  59%|█████▉    | 299/507 [00:19<00:08, 25.08it/s]
Loading 0:  59%|█████▉    | 300/507 [00:25<03:17,  1.05it/s]
Loading 0:  60%|█████▉    | 302/507 [00:25<02:50,  1.21it/s]
Loading 0:  61%|██████    | 307/507 [00:25<01:51,  1.80it/s]
Loading 0:  61%|██████    | 310/507 [00:25<01:26,  2.27it/s]
Loading 0:  62%|██████▏   | 313/507 [00:26<01:06,  2.93it/s]
Loading 0:  63%|██████▎   | 317/507 [00:26<00:45,  4.16it/s]
Loading 0:  63%|██████▎   | 320/507 [00:26<00:36,  5.17it/s]
Loading 0:  64%|██████▍   | 327/507 [00:26<00:20,  8.84it/s]
Loading 0:  65%|██████▌   | 331/507 [00:26<00:16, 10.85it/s]
Loading 0:  66%|██████▌   | 335/507 [00:26<00:12, 13.27it/s]
Loading 0:  67%|██████▋   | 339/507 [00:26<00:10, 16.38it/s]
Loading 0:  68%|██████▊   | 343/507 [00:27<00:11, 14.45it/s]
Loading 0:  68%|██████▊   | 347/507 [00:27<00:09, 16.13it/s]
Loading 0:  69%|██████▉   | 352/507 [00:27<00:07, 20.59it/s]
Loading 0:  70%|███████   | 356/507 [00:27<00:07, 21.48it/s]
Loading 0:  71%|███████▏  | 362/507 [00:27<00:05, 28.31it/s]
Loading 0:  72%|███████▏  | 366/507 [00:27<00:05, 27.37it/s]
Loading 0:  73%|███████▎  | 372/507 [00:27<00:04, 32.19it/s]
Loading 0:  74%|███████▍  | 376/507 [00:28<00:04, 31.60it/s]
Loading 0:  75%|███████▌  | 381/507 [00:28<00:03, 34.17it/s]
Loading 0:  76%|███████▌  | 385/507 [00:28<00:03, 31.59it/s]
Loading 0:  77%|███████▋  | 389/507 [00:28<00:03, 31.64it/s]
Loading 0:  78%|███████▊  | 393/507 [00:28<00:03, 30.97it/s]
Loading 0:  78%|███████▊  | 397/507 [00:28<00:04, 22.12it/s]
Loading 0:  79%|███████▉  | 401/507 [00:29<00:04, 22.52it/s]
Loading 0:  80%|████████  | 406/507 [00:29<00:03, 27.36it/s]
Loading 0:  81%|████████  | 410/507 [00:29<00:04, 23.78it/s]
Loading 0:  82%|████████▏ | 415/507 [00:29<00:03, 28.27it/s]
Loading 0:  83%|████████▎ | 419/507 [00:29<00:03, 27.37it/s]
Loading 0:  84%|████████▍ | 426/507 [00:29<00:02, 34.93it/s]
Loading 0:  85%|████████▍ | 430/507 [00:29<00:02, 33.84it/s]
Loading 0:  86%|████████▌ | 435/507 [00:30<00:01, 36.35it/s]
Loading 0:  87%|████████▋ | 439/507 [00:30<00:01, 35.03it/s]
Loading 0:  88%|████████▊ | 444/507 [00:30<00:01, 37.23it/s]
Loading 0:  88%|████████▊ | 448/507 [00:30<00:01, 35.70it/s]
Loading 0:  90%|████████▉ | 454/507 [00:30<00:01, 37.42it/s]
Loading 0:  90%|█████████ | 458/507 [00:32<00:08,  5.88it/s]
Loading 0:  91%|█████████ | 461/507 [00:33<00:06,  7.02it/s]
Loading 0:  92%|█████████▏| 465/507 [00:33<00:04,  8.85it/s]
Loading 0:  93%|█████████▎| 470/507 [00:33<00:03, 12.26it/s]
Loading 0:  93%|█████████▎| 474/507 [00:33<00:02, 14.06it/s]
Loading 0:  94%|█████████▍| 479/507 [00:33<00:01, 18.44it/s]
Loading 0:  95%|█████████▌| 483/507 [00:33<00:01, 19.32it/s]
Loading 0:  96%|█████████▋| 488/507 [00:33<00:00, 23.23it/s]
Loading 0:  97%|█████████▋| 492/507 [00:34<00:00, 22.49it/s]
Loading 0:  98%|█████████▊| 497/507 [00:34<00:00, 27.27it/s]
Loading 0:  99%|█████████▉| 501/507 [00:34<00:00, 25.50it/s]
Loading 0: 100%|█████████▉| 506/507 [00:34<00:00, 29.97it/s]
                                                            
Job chaiml-lexical-viral-v5a-3842-v5-mkmlizer completed after 135.26s with status: succeeded
Stopping job with name chaiml-lexical-viral-v5a-3842-v5-mkmlizer
Pipeline stage MKMLizer completed in 135.83s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-lexical-viral-v5a-3842-v5
Waiting for inference service chaiml-lexical-viral-v5a-3842-v5 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
Inference service chaiml-lexical-viral-v5a-3842-v5 ready after 170.97424364089966s
Pipeline stage MKMLDeployer completed in 171.60s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.761061668395996s
Received healthy response to inference request in 2.752063274383545s
Received healthy response to inference request in 2.323580265045166s
Received healthy response to inference request in 2.075434446334839s
Received healthy response to inference request in 2.6417977809906006s
5 requests
0 failed requests
5th percentile: 2.1250636100769045
10th percentile: 2.1746927738189696
20th percentile: 2.2739511013031004
30th percentile: 2.3872237682342528
40th percentile: 2.5145107746124267
50th percentile: 2.6417977809906006
60th percentile: 2.6859039783477785
70th percentile: 2.730010175704956
80th percentile: 2.7538629531860352
90th percentile: 2.7574623107910154
95th percentile: 2.7592619895935058
99th percentile: 2.760701732635498
mean time: 2.5107874870300293
Pipeline stage StressChecker completed in 14.40s
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 2.39s
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 2.26s
Shutdown handler de-registered
chaiml-lexical-viral-v5a_3842_v5 status is now deployed due to DeploymentManager action
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 3232.41s
Shutdown handler de-registered
chaiml-lexical-viral-v5a_3842_v5 status is now inactive due to auto deactivation removed underperforming models