jic062-nemo-v1-1

submission_id: jic062-nemo-v1-1_v6

developer_uid: chace9580

best_of: 8

celo_rating: 1270.71

display_name: jic062-nemo-v1-1_v6

family_friendly_score: 0.0

formatter: {'memory_template': '[INST]system\n{memory}[/INST]\n', 'prompt_template': '[INST]user\n{prompt}[/INST]\n', 'bot_template': '[INST]assistant\n{bot_name}: {message}[/INST]\n', 'user_template': '[INST]user\n{user_name}: {message}[/INST]\n', 'response_template': '[INST]assistant\n{bot_name}:', 'truncate_by_message': False}

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', '[/INST]'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

gpu_counts: {'NVIDIA RTX A5000': 1}

is_internal_developer: False

language_model: jic062/Nemo-v1.1

latencies: [{'batch_size': 1, 'throughput': 0.612254721488548, 'latency_mean': 1.6332461214065552, 'latency_p50': 1.6252261400222778, 'latency_p90': 1.8161974906921388}, {'batch_size': 3, 'throughput': 1.0747486884660262, 'latency_mean': 2.7828653144836424, 'latency_p50': 2.7909388542175293, 'latency_p90': 3.0667200088500977}, {'batch_size': 5, 'throughput': 1.2334054208118017, 'latency_mean': 4.034251993894577, 'latency_p50': 4.060039162635803, 'latency_p90': 4.549235105514526}, {'batch_size': 6, 'throughput': 1.2693656306595449, 'latency_mean': 4.712166337966919, 'latency_p50': 4.720810890197754, 'latency_p90': 5.273747539520263}, {'batch_size': 8, 'throughput': 1.2408924900446305, 'latency_mean': 6.411581802368164, 'latency_p50': 6.425309538841248, 'latency_p90': 7.177511119842529}, {'batch_size': 10, 'throughput': 1.2086774288439894, 'latency_mean': 8.22531257033348, 'latency_p50': 8.230416297912598, 'latency_p90': 9.302290344238282}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: jic062/Nemo-v1.1

model_name: jic062-nemo-v1-1_v6

model_num_parameters: 12772070400.0

model_repo: jic062/Nemo-v1.1

model_size: 13B

num_battles: 13460

num_wins: 7302

ranking_group: single

status: torndown

submission_type: basic

throughput_3p7s: 1.21

timestamp: 2024-09-24T04:53:08+00:00

us_pacific_date: 2024-09-23

win_ratio: 0.5424962852897474

Download Preference Data

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 jic062-nemo-v1-1-v6-mkmlizer
Waiting for job on jic062-nemo-v1-1-v6-mkmlizer to finish
jic062-nemo-v1-1-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-nemo-v1-1-v6-mkmlizer: ║     _____            __           __                                ║
jic062-nemo-v1-1-v6-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jic062-nemo-v1-1-v6-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jic062-nemo-v1-1-v6-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jic062-nemo-v1-1-v6-mkmlizer: ║       /___/                                                         ║
jic062-nemo-v1-1-v6-mkmlizer: ║                                                                     ║
jic062-nemo-v1-1-v6-mkmlizer: ║  Version: 0.10.1                                                    ║
jic062-nemo-v1-1-v6-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jic062-nemo-v1-1-v6-mkmlizer: ║  https://mk1.ai                                                     ║
jic062-nemo-v1-1-v6-mkmlizer: ║                                                                     ║
jic062-nemo-v1-1-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
jic062-nemo-v1-1-v6-mkmlizer: ║  belonging to:                                                      ║
jic062-nemo-v1-1-v6-mkmlizer: ║                                                                     ║
jic062-nemo-v1-1-v6-mkmlizer: ║  Chai Research Corp.                                                ║
jic062-nemo-v1-1-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jic062-nemo-v1-1-v6-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jic062-nemo-v1-1-v6-mkmlizer: ║                                                                     ║
jic062-nemo-v1-1-v6-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
jic062-nemo-v1-1-v6-mkmlizer: Downloaded to shared memory in 44.458s
jic062-nemo-v1-1-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpp9aqhwmn, device:0
jic062-nemo-v1-1-v6-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
jic062-nemo-v1-1-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-nemo-v1-1-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-nemo-v1-1-v6
jic062-nemo-v1-1-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-nemo-v1-1-v6/special_tokens_map.json
jic062-nemo-v1-1-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-nemo-v1-1-v6/config.json
jic062-nemo-v1-1-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-nemo-v1-1-v6/tokenizer_config.json
jic062-nemo-v1-1-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-nemo-v1-1-v6/tokenizer.json
jic062-nemo-v1-1-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-nemo-v1-1-v6/flywheel_model.0.safetensors
jic062-nemo-v1-1-v6-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 35.61it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 57.00it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:06, 55.06it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:06, 53.57it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 46.03it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:05, 53.97it/s]
Loading 0:  13%|█▎        | 46/363 [00:00<00:06, 49.41it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:06, 50.03it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:05, 51.39it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 36.16it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 40.14it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 40.67it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 41.54it/s]
Loading 0:  25%|██▍       | 90/363 [00:01<00:05, 46.73it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 44.43it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 43.45it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 49.86it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:05, 45.61it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:05, 44.82it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:04, 49.55it/s]
Loading 0:  36%|███▋      | 132/363 [00:02<00:04, 47.83it/s]
Loading 0:  38%|███▊      | 137/363 [00:02<00:04, 46.50it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 36.65it/s]
Loading 0:  40%|████      | 147/363 [00:03<00:05, 37.77it/s]
Loading 0:  42%|████▏     | 152/363 [00:03<00:05, 39.42it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 39.96it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 40.58it/s]
Loading 0:  46%|████▋     | 168/363 [00:03<00:04, 41.55it/s]
Loading 0:  48%|████▊     | 174/363 [00:03<00:04, 45.25it/s]
Loading 0:  49%|████▉     | 179/363 [00:04<00:04, 45.31it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:03, 46.47it/s]
Loading 0:  52%|█████▏    | 190/363 [00:04<00:03, 45.25it/s]
Loading 0:  54%|█████▎    | 195/363 [00:04<00:03, 44.07it/s]
Loading 0:  56%|█████▌    | 202/363 [00:04<00:03, 48.71it/s]
Loading 0:  57%|█████▋    | 208/363 [00:04<00:03, 45.60it/s]
Loading 0:  59%|█████▊    | 213/363 [00:04<00:03, 44.19it/s]
Loading 0:  60%|██████    | 219/363 [00:04<00:03, 47.95it/s]
Loading 0:  62%|██████▏   | 224/363 [00:05<00:03, 35.93it/s]
Loading 0:  63%|██████▎   | 229/363 [00:05<00:03, 36.90it/s]
Loading 0:  65%|██████▍   | 235/363 [00:05<00:03, 38.27it/s]
Loading 0:  66%|██████▌   | 240/363 [00:05<00:03, 39.43it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:02, 45.17it/s]
Loading 0:  70%|██████▉   | 253/363 [00:05<00:02, 43.93it/s]
Loading 0:  71%|███████   | 258/363 [00:05<00:02, 43.24it/s]
Loading 0:  73%|███████▎  | 265/363 [00:05<00:02, 47.72it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 44.61it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:02, 43.40it/s]
Loading 0:  78%|███████▊  | 282/363 [00:06<00:01, 46.89it/s]
Loading 0:  79%|███████▉  | 287/363 [00:06<00:01, 46.85it/s]
Loading 0:  80%|████████  | 292/363 [00:06<00:01, 47.27it/s]
Loading 0:  82%|████████▏ | 298/363 [00:06<00:01, 45.67it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:21,  2.72it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:15,  3.47it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:11,  4.48it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:05,  7.35it/s]
Loading 0:  90%|████████▉ | 326/363 [00:13<00:03,  9.91it/s]
Loading 0:  91%|█████████ | 331/363 [00:13<00:02, 12.57it/s]
Loading 0:  93%|█████████▎| 339/363 [00:14<00:01, 17.48it/s]
Loading 0:  96%|█████████▌| 348/363 [00:14<00:00, 23.54it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 30.48it/s]
Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 32.07it/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
Job jic062-nemo-v1-1-v6-mkmlizer completed after 106.84s with status: succeeded
Stopping job with name jic062-nemo-v1-1-v6-mkmlizer
Pipeline stage MKMLizer completed in 110.41s
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 jic062-nemo-v1-1-v6
Waiting for inference service jic062-nemo-v1-1-v6 to be ready
Failed to get response for submission cycy233-nemo-p-e-v3-c2_v1: ('http://cycy233-nemo-p-e-v3-c2-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission cycy233-nemo-p-e-v3-c2_v1: ('http://cycy233-nemo-p-e-v3-c2-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
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 cycy233-nemo-p-e-v3-c1_v1: ('http://cycy233-nemo-p-e-v3-c1-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:50580->127.0.0.1:8080: read: connection reset by peer\n')
Inference service jic062-nemo-v1-1-v6 ready after 202.7175178527832s
Pipeline stage MKMLDeployer completed in 203.09s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.397521495819092s
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
Received healthy response to inference request in 1.9997966289520264s
Received healthy response to inference request in 3.488157272338867s
Received healthy response to inference request in 2.0151078701019287s
Received healthy response to inference request in 2.047388792037964s
5 requests
0 failed requests
5th percentile: 2.002858877182007
10th percentile: 2.0059211254119873
20th percentile: 2.0120456218719482
30th percentile: 2.0215640544891356
40th percentile: 2.0344764232635497
50th percentile: 2.047388792037964
60th percentile: 2.187441873550415
70th percentile: 2.3274949550628663
80th percentile: 2.6156486511230472
90th percentile: 3.051902961730957
95th percentile: 3.2700301170349118
99th percentile: 3.444531841278076
mean time: 2.3895944118499757
Pipeline stage StressChecker completed in 12.85s
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 5.68s
Shutdown handler de-registered
jic062-nemo-v1-1_v6 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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service jic062-nemo-v1-1-v6-profiler
Waiting for inference service jic062-nemo-v1-1-v6-profiler to be ready
Inference service jic062-nemo-v1-1-v6-profiler ready after 190.45153141021729s
Pipeline stage MKMLProfilerDeployer completed in 190.84s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/jic062-nemo-v1-1-v6-profiler-predictor-00001-deployment-65pwlff:/code/chaiverse_profiler_1727154155 --namespace tenant-chaiml-guanaco
kubectl exec -it jic062-nemo-v1-1-v6-profiler-predictor-00001-deployment-65pwlff --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727154155 && 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_1727154155/summary.json'
kubectl exec -it jic062-nemo-v1-1-v6-profiler-predictor-00001-deployment-65pwlff --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727154155/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1165.41s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service jic062-nemo-v1-1-v6-profiler is running
Tearing down inference service jic062-nemo-v1-1-v6-profiler
Service jic062-nemo-v1-1-v6-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.25s
Shutdown handler de-registered
jic062-nemo-v1-1_v6 status is now inactive due to auto deactivation removed underperforming models
jic062-nemo-v1-1_v6 status is now torndown due to DeploymentManager action