valentin87-0920-curated-_1744

developer_uid: valentin87

submission_id: valentin87-0920-curated-_1744_v2

model_name: valentin87-0920-curated-_1744_v2

model_group: valentin87/0920_curated_

status: torndown

timestamp: 2024-09-20T11:50:03+00:00

num_battles: 13923

num_wins: 6692

celo_rating: 1239.65

family_friendly_score: 0.0

submission_type: basic

model_repo: valentin87/0920_curated_convos_small

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.3795102151589912, 'latency_mean': 2.634916727542877, 'latency_p50': 2.615821361541748, 'latency_p90': 2.9300642013549805}, {'batch_size': 2, 'throughput': 0.5958100840384826, 'latency_mean': 3.3512751948833466, 'latency_p50': 3.3593467473983765, 'latency_p90': 3.6680795907974244}, {'batch_size': 3, 'throughput': 0.7496008575384169, 'latency_mean': 3.9881871700286866, 'latency_p50': 4.016576647758484, 'latency_p90': 4.393953108787537}, {'batch_size': 4, 'throughput': 0.873308689178202, 'latency_mean': 4.567617603540421, 'latency_p50': 4.561019659042358, 'latency_p90': 5.106625604629516}, {'batch_size': 5, 'throughput': 0.950770952711346, 'latency_mean': 5.236988426446914, 'latency_p50': 5.25752329826355, 'latency_p90': 5.846542096138}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: valentin87-0920-curated-_1744_v2

is_internal_developer: True

language_model: valentin87/0920_curated_convos_small

model_size: 22B

ranking_group: single

throughput_3p7s: 0.69

us_pacific_date: 2024-09-20

win_ratio: 0.4806435394670689

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], '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 valentin87-0920-curated-1744-v2-mkmlizer
Waiting for job on valentin87-0920-curated-1744-v2-mkmlizer to finish
valentin87-0920-curated-1744-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
valentin87-0920-curated-1744-v2-mkmlizer: ║     _____            __           __                                ║
valentin87-0920-curated-1744-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
valentin87-0920-curated-1744-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
valentin87-0920-curated-1744-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
valentin87-0920-curated-1744-v2-mkmlizer: ║       /___/                                                         ║
valentin87-0920-curated-1744-v2-mkmlizer: ║                                                                     ║
valentin87-0920-curated-1744-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
valentin87-0920-curated-1744-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
valentin87-0920-curated-1744-v2-mkmlizer: ║  https://mk1.ai                                                     ║
valentin87-0920-curated-1744-v2-mkmlizer: ║                                                                     ║
valentin87-0920-curated-1744-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
valentin87-0920-curated-1744-v2-mkmlizer: ║  belonging to:                                                      ║
valentin87-0920-curated-1744-v2-mkmlizer: ║                                                                     ║
valentin87-0920-curated-1744-v2-mkmlizer: ║  Chai Research Corp.                                                ║
valentin87-0920-curated-1744-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
valentin87-0920-curated-1744-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
valentin87-0920-curated-1744-v2-mkmlizer: ║                                                                     ║
valentin87-0920-curated-1744-v2-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
valentin87-0920-curated-1744-v2-mkmlizer: Downloaded to shared memory in 49.027s
valentin87-0920-curated-1744-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmh6phsb3, device:0
valentin87-0920-curated-1744-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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
valentin87-0920-curated-1744-v2-mkmlizer: quantized model in 43.623s
valentin87-0920-curated-1744-v2-mkmlizer: Processed model valentin87/0920_curated_convos_small in 92.650s
valentin87-0920-curated-1744-v2-mkmlizer: creating bucket guanaco-mkml-models
valentin87-0920-curated-1744-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/valentin87-0920-curated-1744-v2/config.json
valentin87-0920-curated-1744-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/valentin87-0920-curated-1744-v2/special_tokens_map.json
valentin87-0920-curated-1744-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/valentin87-0920-curated-1744-v2/tokenizer_config.json
valentin87-0920-curated-1744-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/valentin87-0920-curated-1744-v2/tokenizer.json
valentin87-0920-curated-1744-v2-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:19, 25.66it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:11, 41.29it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:12, 40.01it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:12, 39.64it/s]
Loading 0:   5%|▌         | 27/507 [00:00<00:11, 41.22it/s]
Loading 0:   6%|▋         | 32/507 [00:00<00:13, 34.59it/s]
Loading 0:   8%|▊         | 39/507 [00:00<00:11, 42.09it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:11, 41.60it/s]
Loading 0:  10%|▉         | 49/507 [00:01<00:12, 35.88it/s]
Loading 0:  10%|█         | 53/507 [00:01<00:17, 26.37it/s]
Loading 0:  11%|█         | 57/507 [00:01<00:16, 26.54it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:14, 31.47it/s]
Loading 0:  13%|█▎        | 67/507 [00:01<00:14, 31.29it/s]
Loading 0:  14%|█▍        | 71/507 [00:02<00:13, 33.15it/s]
Loading 0:  15%|█▍        | 75/507 [00:02<00:12, 34.63it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:12, 34.57it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:10, 41.52it/s]
Loading 0:  18%|█▊        | 92/507 [00:02<00:10, 40.82it/s]
Loading 0:  19%|█▉        | 97/507 [00:02<00:10, 40.36it/s]
Loading 0:  20%|██        | 102/507 [00:02<00:09, 40.72it/s]
Loading 0:  21%|██        | 107/507 [00:03<00:11, 33.90it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:13, 29.77it/s]
Loading 0:  23%|██▎       | 117/507 [00:03<00:13, 29.00it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:12, 30.07it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:10, 37.15it/s]
Loading 0:  26%|██▋       | 134/507 [00:03<00:10, 37.01it/s]
Loading 0:  27%|██▋       | 139/507 [00:03<00:09, 38.57it/s]
Loading 0:  28%|██▊       | 144/507 [00:04<00:08, 40.83it/s]
Loading 0:  29%|██▉       | 149/507 [00:04<00:10, 34.58it/s]
Loading 0:  31%|███       | 156/507 [00:04<00:08, 41.71it/s]
Loading 0:  32%|███▏      | 161/507 [00:04<00:08, 39.49it/s]
Loading 0:  33%|███▎      | 166/507 [00:04<00:08, 40.34it/s]
Loading 0:  34%|███▎      | 171/507 [00:04<00:12, 26.24it/s]
Loading 0:  35%|███▍      | 176/507 [00:05<00:11, 28.31it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:09, 35.49it/s]
Loading 0:  37%|███▋      | 188/507 [00:05<00:09, 34.55it/s]
Loading 0:  38%|███▊      | 192/507 [00:05<00:09, 34.48it/s]
Loading 0:  39%|███▊      | 196/507 [00:05<00:09, 33.75it/s]
Loading 0:  40%|███▉      | 201/507 [00:05<00:08, 37.25it/s]
Loading 0:  40%|████      | 205/507 [00:05<00:08, 36.63it/s]
Loading 0:  41%|████▏     | 210/507 [00:05<00:07, 40.00it/s]
Loading 0:  42%|████▏     | 215/507 [00:06<00:07, 40.23it/s]
Loading 0:  43%|████▎     | 220/507 [00:06<00:08, 34.01it/s]
Loading 0:  44%|████▍     | 224/507 [00:06<00:10, 26.90it/s]
Loading 0:  45%|████▌     | 230/507 [00:06<00:09, 28.42it/s]
Loading 0:  47%|████▋     | 237/507 [00:06<00:07, 35.09it/s]
Loading 0:  48%|████▊     | 241/507 [00:06<00:07, 33.71it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:07, 36.48it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 36.08it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:06, 38.44it/s]
Loading 0:  51%|█████     | 259/507 [00:07<00:06, 37.00it/s]
Loading 0:  52%|█████▏    | 264/507 [00:07<00:06, 39.46it/s]
Loading 0:  53%|█████▎    | 269/507 [00:07<00:06, 38.79it/s]
Loading 0:  54%|█████▍    | 274/507 [00:07<00:05, 39.81it/s]
Loading 0:  55%|█████▌    | 279/507 [00:07<00:05, 40.87it/s]
Loading 0:  56%|█████▌    | 284/507 [00:08<00:08, 27.81it/s]
Loading 0:  57%|█████▋    | 288/507 [00:08<00:08, 26.76it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 27.31it/s]
Loading 0:  59%|█████▉    | 299/507 [00:23<00:07, 27.31it/s]
Loading 0:  59%|█████▉    | 300/507 [00:23<02:52,  1.20it/s]
Loading 0:  60%|█████▉    | 302/507 [00:23<02:29,  1.37it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:40,  1.99it/s]
Loading 0:  61%|██████    | 310/507 [00:23<01:19,  2.48it/s]
Loading 0:  62%|██████▏   | 313/507 [00:23<01:01,  3.17it/s]
Loading 0:  63%|██████▎   | 318/507 [00:23<00:39,  4.76it/s]
Loading 0:  64%|██████▎   | 322/507 [00:24<00:29,  6.37it/s]
Loading 0:  65%|██████▍   | 328/507 [00:24<00:18,  9.57it/s]
Loading 0:  66%|██████▌   | 333/507 [00:24<00:13, 12.73it/s]
Loading 0:  67%|██████▋   | 339/507 [00:24<00:10, 16.71it/s]
Loading 0:  68%|██████▊   | 343/507 [00:24<00:10, 16.03it/s]
Loading 0:  68%|██████▊   | 347/507 [00:24<00:09, 17.66it/s]
Loading 0:  70%|██████▉   | 354/507 [00:24<00:06, 24.15it/s]
Loading 0:  71%|███████   | 358/507 [00:25<00:05, 25.72it/s]
Loading 0:  72%|███████▏  | 363/507 [00:25<00:04, 29.61it/s]
Loading 0:  72%|███████▏  | 367/507 [00:25<00:04, 29.84it/s]
Loading 0:  73%|███████▎  | 371/507 [00:25<00:04, 31.89it/s]
Loading 0:  74%|███████▍  | 375/507 [00:25<00:04, 30.39it/s]
Loading 0:  75%|███████▌  | 382/507 [00:25<00:03, 37.10it/s]
Loading 0:  76%|███████▋  | 387/507 [00:25<00:03, 39.37it/s]
Loading 0:  77%|███████▋  | 392/507 [00:26<00:03, 32.54it/s]
Loading 0:  78%|███████▊  | 396/507 [00:26<00:04, 25.23it/s]
Loading 0:  79%|███████▉  | 401/507 [00:26<00:03, 27.29it/s]
Loading 0:  80%|████████  | 408/507 [00:26<00:02, 33.94it/s]
Loading 0:  81%|████████▏ | 412/507 [00:26<00:02, 33.61it/s]
Loading 0:  82%|████████▏ | 417/507 [00:26<00:02, 36.08it/s]
Loading 0:  83%|████████▎ | 421/507 [00:26<00:02, 34.92it/s]
Loading 0:  84%|████████▍ | 426/507 [00:27<00:02, 37.96it/s]
Loading 0:  85%|████████▍ | 430/507 [00:27<00:02, 35.58it/s]
Loading 0:  86%|████████▌ | 435/507 [00:27<00:01, 37.68it/s]
Loading 0:  87%|████████▋ | 439/507 [00:27<00:01, 35.80it/s]
Loading 0:  88%|████████▊ | 444/507 [00:27<00:01, 39.03it/s]
Loading 0:  89%|████████▊ | 449/507 [00:27<00:01, 37.92it/s]
Loading 0:  90%|████████▉ | 454/507 [00:27<00:01, 37.69it/s]
Loading 0:  90%|█████████ | 458/507 [00:30<00:08,  6.08it/s]
Loading 0:  91%|█████████ | 461/507 [00:30<00:06,  7.30it/s]
Loading 0:  92%|█████████▏| 465/507 [00:30<00:04,  9.21it/s]
Loading 0:  93%|█████████▎| 470/507 [00:30<00:02, 12.81it/s]
Loading 0:  93%|█████████▎| 474/507 [00:30<00:02, 14.87it/s]
Loading 0:  95%|█████████▍| 481/507 [00:30<00:01, 21.72it/s]
Loading 0:  96%|█████████▌| 486/507 [00:30<00:00, 24.94it/s]
Loading 0:  97%|█████████▋| 491/507 [00:30<00:00, 28.11it/s]
Loading 0:  98%|█████████▊| 495/507 [00:31<00:00, 30.24it/s]
Loading 0:  98%|█████████▊| 499/507 [00:31<00:00, 31.89it/s]
Loading 0:  99%|█████████▉| 503/507 [00:31<00:00, 32.01it/s]
                                                            
Job valentin87-0920-curated-1744-v2-mkmlizer completed after 125.7s with status: succeeded
Stopping job with name valentin87-0920-curated-1744-v2-mkmlizer
Pipeline stage MKMLizer completed in 126.66s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service valentin87-0920-curated-1744-v2
Waiting for inference service valentin87-0920-curated-1744-v2 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
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 valentin87-0920-curated-1744-v2 ready after 200.91396737098694s
Pipeline stage MKMLDeployer completed in 201.34s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.1420938968658447s
Received healthy response to inference request in 2.218872547149658s
Received healthy response to inference request in 2.036839485168457s
Received healthy response to inference request in 2.9263579845428467s
Received healthy response to inference request in 3.4834158420562744s
5 requests
0 failed requests
5th percentile: 2.0732460975646974
10th percentile: 2.1096527099609377
20th percentile: 2.182465934753418
30th percentile: 2.360369634628296
40th percentile: 2.6433638095855714
50th percentile: 2.9263579845428467
60th percentile: 3.012652349472046
70th percentile: 3.098946714401245
80th percentile: 3.2103582859039306
90th percentile: 3.3468870639801027
95th percentile: 3.4151514530181886
99th percentile: 3.469762964248657
mean time: 2.7615159511566163
Pipeline stage StressChecker completed in 16.20s
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 4.75s
Shutdown handler de-registered
valentin87-0920-curated-_1744_v2 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 1.18s
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 valentin87-0920-curated-1744-v2-profiler
Waiting for inference service valentin87-0920-curated-1744-v2-profiler to be ready
Inference service valentin87-0920-curated-1744-v2-profiler ready after 210.4892976284027s
Pipeline stage MKMLProfilerDeployer completed in 210.87s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/valentin87-0920-cura2d32ea613e3c9b7924c1bf24f9b73743-deploqp7c9:/code/chaiverse_profiler_1726833616 --namespace tenant-chaiml-guanaco
kubectl exec -it valentin87-0920-cura2d32ea613e3c9b7924c1bf24f9b73743-deploqp7c9 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726833616 && 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_1726833616/summary.json'
kubectl exec -it valentin87-0920-cura2d32ea613e3c9b7924c1bf24f9b73743-deploqp7c9 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726833616/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1574.75s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service valentin87-0920-curated-1744-v2-profiler is running
Tearing down inference service valentin87-0920-curated-1744-v2-profiler
Service valentin87-0920-curated-1744-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.30s
Shutdown handler de-registered
valentin87-0920-curated-_1744_v2 status is now inactive due to auto deactivation removed underperforming models
valentin87-0920-curated-_1744_v2 status is now torndown due to DeploymentManager action