intervitens-mini-magnum-_5180

developer_uid: azuruce

submission_id: intervitens-mini-magnum-_5180_v3

model_name: intervitens-mini-magnum-_5180_v3

model_group: intervitens/mini-magnum-

status: torndown

timestamp: 2024-09-24T20:53:10+00:00

num_battles: 3216

num_wins: 1682

celo_rating: 1271.51

family_friendly_score: 0.0

submission_type: basic

model_repo: intervitens/mini-magnum-12b-v1.1

model_architecture: MistralForCausalLM

model_num_parameters: 12772080640.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6151577742044225, 'latency_mean': 1.6255394399166108, 'latency_p50': 1.6320379972457886, 'latency_p90': 1.7758327722549438}, {'batch_size': 3, 'throughput': 1.082814524894211, 'latency_mean': 2.766083000898361, 'latency_p50': 2.7879300117492676, 'latency_p90': 3.0337518215179444}, {'batch_size': 5, 'throughput': 1.2403574429174589, 'latency_mean': 4.003851753473282, 'latency_p50': 4.056594252586365, 'latency_p90': 4.553749513626099}, {'batch_size': 6, 'throughput': 1.2635021678599934, 'latency_mean': 4.728662643432617, 'latency_p50': 4.772611618041992, 'latency_p90': 5.271794986724854}, {'batch_size': 8, 'throughput': 1.2421610941321666, 'latency_mean': 6.420644464492798, 'latency_p50': 6.417357921600342, 'latency_p90': 7.326181077957153}, {'batch_size': 10, 'throughput': 1.2207082149230566, 'latency_mean': 8.143665438890457, 'latency_p50': 8.228175640106201, 'latency_p90': 9.326695418357849}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: intervitens-mini-magnum-_5180_v3

ineligible_reason: num_battles<5000

is_internal_developer: True

language_model: intervitens/mini-magnum-12b-v1.1

model_size: 13B

ranking_group: single

throughput_3p7s: 1.22

us_pacific_date: 2024-09-24

win_ratio: 0.5230099502487562

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>', '<|end_of_text|>'], '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': '### Response:\n{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 intervitens-mini-magnum-5180-v3-mkmlizer
Waiting for job on intervitens-mini-magnum-5180-v3-mkmlizer to finish
intervitens-mini-magnum-5180-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
intervitens-mini-magnum-5180-v3-mkmlizer: ║     _____            __           __                                ║
intervitens-mini-magnum-5180-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
intervitens-mini-magnum-5180-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
intervitens-mini-magnum-5180-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
intervitens-mini-magnum-5180-v3-mkmlizer: ║       /___/                                                         ║
intervitens-mini-magnum-5180-v3-mkmlizer: ║                                                                     ║
intervitens-mini-magnum-5180-v3-mkmlizer: ║  Version: 0.10.1                                                    ║
intervitens-mini-magnum-5180-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
intervitens-mini-magnum-5180-v3-mkmlizer: ║  https://mk1.ai                                                     ║
intervitens-mini-magnum-5180-v3-mkmlizer: ║                                                                     ║
intervitens-mini-magnum-5180-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
intervitens-mini-magnum-5180-v3-mkmlizer: ║  belonging to:                                                      ║
intervitens-mini-magnum-5180-v3-mkmlizer: ║                                                                     ║
intervitens-mini-magnum-5180-v3-mkmlizer: ║  Chai Research Corp.                                                ║
intervitens-mini-magnum-5180-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
intervitens-mini-magnum-5180-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
intervitens-mini-magnum-5180-v3-mkmlizer: ║                                                                     ║
intervitens-mini-magnum-5180-v3-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
intervitens-mini-magnum-5180-v3-mkmlizer: Downloaded to shared memory in 41.107s
intervitens-mini-magnum-5180-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkftm0w24, device:0
intervitens-mini-magnum-5180-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
intervitens-mini-magnum-5180-v3-mkmlizer: quantized model in 37.651s
intervitens-mini-magnum-5180-v3-mkmlizer: Processed model intervitens/mini-magnum-12b-v1.1 in 78.759s
intervitens-mini-magnum-5180-v3-mkmlizer: creating bucket guanaco-mkml-models
intervitens-mini-magnum-5180-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
intervitens-mini-magnum-5180-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/intervitens-mini-magnum-5180-v3
intervitens-mini-magnum-5180-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/intervitens-mini-magnum-5180-v3/config.json
intervitens-mini-magnum-5180-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/intervitens-mini-magnum-5180-v3/special_tokens_map.json
intervitens-mini-magnum-5180-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/intervitens-mini-magnum-5180-v3/tokenizer_config.json
intervitens-mini-magnum-5180-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/intervitens-mini-magnum-5180-v3/tokenizer.json
intervitens-mini-magnum-5180-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/intervitens-mini-magnum-5180-v3/flywheel_model.0.safetensors
intervitens-mini-magnum-5180-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 32.33it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 52.94it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:06, 49.30it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:06, 50.27it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 52.97it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 49.97it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:06, 50.86it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:05, 52.57it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 49.46it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 32.43it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 33.24it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 37.80it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 38.16it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:07, 38.12it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 43.69it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:05, 45.07it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:06, 37.72it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 46.83it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:05, 41.88it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:06, 40.65it/s]
Loading 0:  34%|███▍      | 125/363 [00:02<00:05, 44.44it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 43.56it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 44.09it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:05, 42.07it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:07, 30.26it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:07, 30.43it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 35.53it/s]
Loading 0:  44%|████▍     | 160/363 [00:03<00:05, 35.05it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 39.39it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:04, 40.10it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 38.63it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 43.38it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 42.92it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 44.39it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 43.03it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 40.82it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 45.95it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 43.91it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:04, 33.49it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:03, 34.49it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:03, 33.28it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 39.05it/s]
Loading 0:  67%|██████▋   | 242/363 [00:05<00:03, 39.69it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 41.30it/s]
Loading 0:  70%|██████▉   | 253/363 [00:06<00:02, 40.58it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 40.01it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 45.07it/s]
Loading 0:  74%|███████▍  | 270/363 [00:06<00:02, 46.24it/s]
Loading 0:  76%|███████▌  | 275/363 [00:06<00:02, 37.55it/s]
Loading 0:  78%|███████▊  | 282/363 [00:06<00:01, 44.49it/s]
Loading 0:  79%|███████▉  | 287/363 [00:06<00:01, 43.43it/s]
Loading 0:  80%|████████  | 292/363 [00:07<00:01, 44.04it/s]
Loading 0:  82%|████████▏ | 297/363 [00:07<00:01, 44.57it/s]
Loading 0:  83%|████████▎ | 303/363 [00:07<00:01, 43.33it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:22,  2.40it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:16,  3.06it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:08,  5.04it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:05,  6.93it/s]
Loading 0:  91%|█████████ | 331/363 [00:15<00:03,  8.88it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 12.60it/s]
Loading 0:  94%|█████████▍| 343/363 [00:15<00:01, 15.23it/s]
Loading 0:  96%|█████████▌| 348/363 [00:15<00:00, 17.25it/s]
Loading 0:  98%|█████████▊| 355/363 [00:15<00:00, 23.45it/s]
Loading 0:  99%|█████████▉| 360/363 [00:15<00:00, 26.67it/s]
                                                            
Job intervitens-mini-magnum-5180-v3-mkmlizer completed after 103.43s with status: succeeded
Stopping job with name intervitens-mini-magnum-5180-v3-mkmlizer
Pipeline stage MKMLizer completed in 104.24s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service intervitens-mini-magnum-5180-v3
Waiting for inference service intervitens-mini-magnum-5180-v3 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
Inference service intervitens-mini-magnum-5180-v3 ready after 210.9161241054535s
Pipeline stage MKMLDeployer completed in 211.37s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4095325469970703s
Received healthy response to inference request in 2.2189676761627197s
Received healthy response to inference request in 2.4201931953430176s
Received healthy response to inference request in 2.1435534954071045s
Received healthy response to inference request in 2.68312931060791s
5 requests
0 failed requests
5th percentile: 2.1586363315582275
10th percentile: 2.1737191677093506
20th percentile: 2.2038848400115967
30th percentile: 2.25708065032959
40th percentile: 2.33330659866333
50th percentile: 2.4095325469970703
60th percentile: 2.413796806335449
70th percentile: 2.418061065673828
80th percentile: 2.4727804183959963
90th percentile: 2.577954864501953
95th percentile: 2.6305420875549315
99th percentile: 2.6726118659973146
mean time: 2.3750752449035644
Pipeline stage StressChecker completed in 12.69s
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 4.96s
Shutdown handler de-registered
intervitens-mini-magnum-_5180_v3 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 0.12s
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 intervitens-mini-magnum-5180-v3-profiler
Waiting for inference service intervitens-mini-magnum-5180-v3-profiler to be ready
Tearing down inference service intervitens-mini-magnum-5180-v3-profiler
%s, retrying in %s seconds...
Creating inference service intervitens-mini-magnum-5180-v3-profiler
Waiting for inference service intervitens-mini-magnum-5180-v3-profiler to be ready
Inference service intervitens-mini-magnum-5180-v3-profiler ready after 270.65530228614807s
Pipeline stage MKMLProfilerDeployer completed in 873.68s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/intervitens-mini-mag32a0e642baa4b851aca609a296edc197-deplogw5jn:/code/chaiverse_profiler_1727212442 --namespace tenant-chaiml-guanaco
kubectl exec -it intervitens-mini-mag32a0e642baa4b851aca609a296edc197-deplogw5jn --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727212442 && 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_1727212442/summary.json'
kubectl exec -it intervitens-mini-mag32a0e642baa4b851aca609a296edc197-deplogw5jn --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727212442/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1159.95s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service intervitens-mini-magnum-5180-v3-profiler is running
Tearing down inference service intervitens-mini-magnum-5180-v3-profiler
Service intervitens-mini-magnum-5180-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.10s
Shutdown handler de-registered
intervitens-mini-magnum-_5180_v3 status is now inactive due to auto deactivation removed underperforming models
intervitens-mini-magnum-_5180_v3 status is now torndown due to DeploymentManager action