cycy233-nemo-p-e-v3-c2

developer_uid: shiroe40

submission_id: cycy233-nemo-p-e-v3-c2_v1

model_name: auto

model_group: cycy233/nemo-p-e-v3-c2

status: torndown

timestamp: 2024-09-24T03:41:30+00:00

num_battles: 20729

num_wins: 11626

celo_rating: 1281.99

family_friendly_score: 0.0

submission_type: basic

model_repo: cycy233/nemo-p-e-v3-c2

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6184114671473548, 'latency_mean': 1.6169384002685547, 'latency_p50': 1.6155866384506226, 'latency_p90': 1.7879999876022339}, {'batch_size': 3, 'throughput': 1.0840445655121256, 'latency_mean': 2.7585986137390135, 'latency_p50': 2.753437638282776, 'latency_p90': 3.0868427276611325}, {'batch_size': 5, 'throughput': 1.229509219700294, 'latency_mean': 4.050428907871247, 'latency_p50': 4.030285835266113, 'latency_p90': 4.538213920593262}, {'batch_size': 6, 'throughput': 1.2753239031679102, 'latency_mean': 4.688183344602585, 'latency_p50': 4.698653340339661, 'latency_p90': 5.203422236442566}, {'batch_size': 8, 'throughput': 1.2538695862646707, 'latency_mean': 6.349644858837127, 'latency_p50': 6.339525818824768, 'latency_p90': 7.275168228149414}, {'batch_size': 10, 'throughput': 1.2040656190075192, 'latency_mean': 8.260253882408142, 'latency_p50': 8.293887257575989, 'latency_p90': 9.356022214889526}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: auto

is_internal_developer: False

language_model: cycy233/nemo-p-e-v3-c2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.2

us_pacific_date: 2024-09-23

win_ratio: 0.5608567707077042

generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', '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 cycy233-nemo-p-e-v3-c2-v1-mkmlizer
Waiting for job on cycy233-nemo-p-e-v3-c2-v1-mkmlizer to finish
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
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: ║       /___/                                                         ║
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: ║                                                                     ║
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: ║                                                                     ║
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: ║                                                                     ║
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: ║                                                                     ║
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: Downloaded to shared memory in 47.526s
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4r3je69u, device:0
cycy233-nemo-p-e-v3-c2-v1-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
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: quantized model in 38.022s
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: Processed model cycy233/nemo-p-e-v3-c2 in 85.548s
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-nemo-p-e-v3-c2-v1
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-nemo-p-e-v3-c2-v1/special_tokens_map.json
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-nemo-p-e-v3-c2-v1/config.json
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-nemo-p-e-v3-c2-v1/tokenizer_config.json
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-nemo-p-e-v3-c2-v1/tokenizer.json
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
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-nemo-p-e-v3-c2-v1/flywheel_model.0.safetensors
cycy233-nemo-p-e-v3-c2-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 29.50it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 46.72it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 45.13it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 33.82it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 41.64it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:08, 39.93it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:08, 39.75it/s]
Loading 0:  12%|█▏        | 45/363 [00:01<00:07, 41.21it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:09, 33.58it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:08, 38.20it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:11, 25.96it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:11, 25.88it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:09, 31.07it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:09, 30.83it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:08, 33.58it/s]
Loading 0:  23%|██▎       | 84/363 [00:02<00:08, 31.10it/s]
Loading 0:  24%|██▍       | 88/363 [00:02<00:08, 32.17it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:09, 30.05it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:07, 35.16it/s]
Loading 0:  28%|██▊       | 102/363 [00:02<00:07, 34.10it/s]
Loading 0:  29%|██▉       | 106/363 [00:03<00:07, 33.64it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:06, 37.81it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:06, 35.72it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 34.05it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:06, 36.19it/s]
Loading 0:  36%|███▌      | 129/363 [00:03<00:06, 34.00it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:06, 35.42it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 33.74it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:09, 23.25it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:09, 23.12it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:08, 24.00it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 31.61it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:06, 31.38it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:05, 33.69it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:05, 32.85it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 34.58it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 33.59it/s]
Loading 0:  50%|█████     | 183/363 [00:05<00:04, 36.62it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:04, 36.48it/s]
Loading 0:  53%|█████▎    | 193/363 [00:05<00:04, 41.07it/s]
Loading 0:  55%|█████▍    | 199/363 [00:05<00:03, 41.01it/s]
Loading 0:  56%|█████▌    | 204/363 [00:06<00:03, 40.50it/s]
Loading 0:  58%|█████▊    | 211/363 [00:06<00:03, 46.41it/s]
Loading 0:  60%|█████▉    | 217/363 [00:06<00:03, 46.27it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:04, 34.61it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:03, 35.48it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:03, 35.02it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 40.38it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 38.82it/s]
Loading 0:  68%|██████▊   | 247/363 [00:07<00:02, 39.95it/s]
Loading 0:  69%|██████▉   | 252/363 [00:07<00:02, 42.22it/s]
Loading 0:  71%|███████   | 257/363 [00:07<00:03, 34.36it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 41.85it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 41.39it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 41.87it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:01, 43.50it/s]
Loading 0:  78%|███████▊  | 284/363 [00:08<00:02, 34.35it/s]
Loading 0:  80%|███████▉  | 289/363 [00:08<00:01, 37.24it/s]
Loading 0:  81%|████████  | 294/363 [00:08<00:01, 36.53it/s]
Loading 0:  82%|████████▏ | 299/363 [00:08<00:01, 38.46it/s]
Loading 0:  84%|████████▎ | 304/363 [00:15<00:25,  2.34it/s]
Loading 0:  85%|████████▍ | 307/363 [00:15<00:19,  2.87it/s]
Loading 0:  86%|████████▌ | 312/363 [00:15<00:12,  4.10it/s]
Loading 0:  88%|████████▊ | 319/363 [00:15<00:06,  6.52it/s]
Loading 0:  89%|████████▉ | 324/363 [00:15<00:04,  8.58it/s]
Loading 0:  91%|█████████ | 329/363 [00:15<00:03, 11.19it/s]
Loading 0:  92%|█████████▏| 334/363 [00:16<00:02, 14.45it/s]
Loading 0:  93%|█████████▎| 339/363 [00:16<00:01, 16.62it/s]
Loading 0:  96%|█████████▌| 347/363 [00:16<00:00, 23.88it/s]
Loading 0:  97%|█████████▋| 352/363 [00:16<00:00, 27.35it/s]
Loading 0:  98%|█████████▊| 357/363 [00:16<00:00, 26.33it/s]
                                                            
Job cycy233-nemo-p-e-v3-c2-v1-mkmlizer completed after 114.26s with status: succeeded
Stopping job with name cycy233-nemo-p-e-v3-c2-v1-mkmlizer
Pipeline stage MKMLizer completed in 116.63s
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 cycy233-nemo-p-e-v3-c2-v1
Waiting for inference service cycy233-nemo-p-e-v3-c2-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission blend_batat_2024-09-20: ('http://zonemercy-virgo-edit-v1-1e5-v13-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:51366->127.0.0.1:8080: read: connection reset by peer\n')
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 cycy233-nemo-p-e-v3-c2-v1 ready after 200.92999458312988s
Pipeline stage MKMLDeployer completed in 201.34s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3107850551605225s
Received healthy response to inference request in 3.1838877201080322s
Received healthy response to inference request in 1.745985507965088s
Received healthy response to inference request in 3.097898483276367s
Received healthy response to inference request in 2.08528208732605s
5 requests
0 failed requests
5th percentile: 1.8138448238372802
10th percentile: 1.8817041397094727
20th percentile: 2.0174227714538575
30th percentile: 2.1303826808929442
40th percentile: 2.2205838680267336
50th percentile: 2.3107850551605225
60th percentile: 2.62563042640686
70th percentile: 2.940475797653198
80th percentile: 3.1150963306427
90th percentile: 3.149492025375366
95th percentile: 3.166689872741699
99th percentile: 3.1804481506347657
mean time: 2.484767770767212
Pipeline stage StressChecker completed in 14.69s
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 4.78s
Shutdown handler de-registered
cycy233-nemo-p-e-v3-c2_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 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cycy233-nemo-p-e-v3-c2-v1-profiler
Waiting for inference service cycy233-nemo-p-e-v3-c2-v1-profiler to be ready
Inference service cycy233-nemo-p-e-v3-c2-v1-profiler ready after 200.45133066177368s
Pipeline stage MKMLProfilerDeployer completed in 200.85s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-nemo-p-e-v3-c2-v1-profiler-predictor-00001-deploym5wcsx:/code/chaiverse_profiler_1727149873 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-nemo-p-e-v3-c2-v1-profiler-predictor-00001-deploym5wcsx --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727149873 && 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_1727149873/summary.json'
kubectl exec -it cycy233-nemo-p-e-v3-c2-v1-profiler-predictor-00001-deploym5wcsx --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727149873/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1159.07s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-nemo-p-e-v3-c2-v1-profiler is running
Tearing down inference service cycy233-nemo-p-e-v3-c2-v1-profiler
Service cycy233-nemo-p-e-v3-c2-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.21s
Shutdown handler de-registered
cycy233-nemo-p-e-v3-c2_v1 status is now inactive due to auto deactivation removed underperforming models
Pipeline stage MKMLModelDeleter completed in 2.26s
cycy233-nemo-p-e-v3-c2_v1 status is now torndown due to DeploymentManager action