submission_id: jic062-nemo-v1-1_v4
developer_uid: chace9580
best_of: 8
celo_rating: 1256.45
display_name: jic062-nemo-v1-1_v4
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': 0.75, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '\n\n', '\nYou:', '[/INST]', '<|im_end|>', '</s>'], 'max_input_tokens': 512, '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': 0.6836605771762447, 'latency_mean': 1.4626488256454468, 'latency_p50': 1.467058539390564, 'latency_p90': 1.6261132478713989}, {'batch_size': 3, 'throughput': 1.302767115652347, 'latency_mean': 2.296822350025177, 'latency_p50': 2.2899324893951416, 'latency_p90': 2.5320935964584352}, {'batch_size': 5, 'throughput': 1.5257869378317135, 'latency_mean': 3.2521691167354585, 'latency_p50': 3.2488224506378174, 'latency_p90': 3.6713428497314453}, {'batch_size': 6, 'throughput': 1.571248232412982, 'latency_mean': 3.790854618549347, 'latency_p50': 3.771217107772827, 'latency_p90': 4.312496280670166}, {'batch_size': 8, 'throughput': 1.5594906445095442, 'latency_mean': 5.091736034154892, 'latency_p50': 5.124643683433533, 'latency_p90': 5.791191959381104}, {'batch_size': 10, 'throughput': 1.5258208906653281, 'latency_mean': 6.506507868766785, 'latency_p50': 6.522159934043884, 'latency_p90': 7.426641416549683}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: jic062/Nemo-v1.1
model_name: jic062-nemo-v1-1_v4
model_num_parameters: 12772070400.0
model_repo: jic062/Nemo-v1.1
model_size: 13B
num_battles: 11258
num_wins: 5794
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 1.58
timestamp: 2024-09-13T17:44:06+00:00
us_pacific_date: 2024-09-13
win_ratio: 0.5146562444483923
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-v4-mkmlizer
Waiting for job on jic062-nemo-v1-1-v4-mkmlizer to finish
jic062-nemo-v1-1-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-nemo-v1-1-v4-mkmlizer: ║     _____            __           __                                ║
jic062-nemo-v1-1-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jic062-nemo-v1-1-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jic062-nemo-v1-1-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jic062-nemo-v1-1-v4-mkmlizer: ║       /___/                                                         ║
jic062-nemo-v1-1-v4-mkmlizer: ║                                                                     ║
jic062-nemo-v1-1-v4-mkmlizer: ║  Version: 0.10.1                                                    ║
jic062-nemo-v1-1-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jic062-nemo-v1-1-v4-mkmlizer: ║  https://mk1.ai                                                     ║
jic062-nemo-v1-1-v4-mkmlizer: ║                                                                     ║
jic062-nemo-v1-1-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
jic062-nemo-v1-1-v4-mkmlizer: ║  belonging to:                                                      ║
jic062-nemo-v1-1-v4-mkmlizer: ║                                                                     ║
jic062-nemo-v1-1-v4-mkmlizer: ║  Chai Research Corp.                                                ║
jic062-nemo-v1-1-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jic062-nemo-v1-1-v4-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jic062-nemo-v1-1-v4-mkmlizer: ║                                                                     ║
jic062-nemo-v1-1-v4-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
jic062-nemo-v1-1-v4-mkmlizer: Downloaded to shared memory in 49.100s
jic062-nemo-v1-1-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpi5x8p3l4, device:0
jic062-nemo-v1-1-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-nemo-v1-1-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-nemo-v1-1-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-nemo-v1-1-v4
jic062-nemo-v1-1-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-nemo-v1-1-v4/special_tokens_map.json
jic062-nemo-v1-1-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-nemo-v1-1-v4/config.json
jic062-nemo-v1-1-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-nemo-v1-1-v4/tokenizer_config.json
jic062-nemo-v1-1-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-nemo-v1-1-v4/tokenizer.json
jic062-nemo-v1-1-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-nemo-v1-1-v4/flywheel_model.0.safetensors
jic062-nemo-v1-1-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 33.55it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 53.04it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 46.26it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 44.47it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:06, 48.97it/s]
Loading 0:  10%|▉         | 36/363 [00:00<00:06, 49.74it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 45.68it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 51.89it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 50.19it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 37.06it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:07, 37.15it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 40.83it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 40.62it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 40.44it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 45.28it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:05, 45.49it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:07, 36.23it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:06, 39.59it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 42.66it/s]
Loading 0:  32%|███▏      | 117/363 [00:02<00:05, 41.00it/s]
Loading 0:  34%|███▎      | 122/363 [00:02<00:05, 41.72it/s]
Loading 0:  35%|███▍      | 127/363 [00:03<00:06, 33.96it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:05, 40.02it/s]
Loading 0:  38%|███▊      | 139/363 [00:03<00:05, 39.45it/s]
Loading 0:  40%|███▉      | 144/363 [00:03<00:08, 25.61it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 27.31it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:06, 33.64it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 34.32it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 34.94it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 33.90it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:05, 35.81it/s]
Loading 0:  49%|████▉     | 178/363 [00:04<00:05, 35.07it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 37.10it/s]
Loading 0:  52%|█████▏    | 187/363 [00:04<00:04, 35.55it/s]
Loading 0:  53%|█████▎    | 192/363 [00:04<00:04, 37.10it/s]
Loading 0:  54%|█████▍    | 196/363 [00:05<00:04, 35.85it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 38.37it/s]
Loading 0:  56%|█████▋    | 205/363 [00:05<00:04, 36.64it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 38.81it/s]
Loading 0:  59%|█████▉    | 214/363 [00:05<00:04, 36.96it/s]
Loading 0:  60%|██████    | 218/363 [00:05<00:03, 36.68it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:05, 27.85it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:04, 29.32it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 29.86it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 35.77it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 36.17it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 40.50it/s]
Loading 0:  70%|██████▉   | 253/363 [00:06<00:02, 42.07it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 40.13it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 43.14it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 42.76it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 43.85it/s]
Loading 0:  77%|███████▋  | 280/363 [00:07<00:01, 43.54it/s]
Loading 0:  79%|███████▊  | 285/363 [00:07<00:01, 42.61it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 45.14it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 45.41it/s]
Loading 0:  83%|████████▎ | 303/363 [00:07<00:01, 47.24it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:20,  2.63it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:15,  3.32it/s]
Loading 0:  88%|████████▊ | 319/363 [00:14<00:08,  5.12it/s]
Loading 0:  89%|████████▉ | 324/363 [00:14<00:05,  6.78it/s]
Loading 0:  91%|█████████ | 330/363 [00:15<00:03,  9.09it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 13.56it/s]
Loading 0:  94%|█████████▍| 343/363 [00:15<00:01, 16.58it/s]
Loading 0:  96%|█████████▌| 348/363 [00:15<00:00, 18.37it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 25.28it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 28.20it/s]
                                                            

Job jic062-nemo-v1-1-v4-mkmlizer completed after 127.84s with status: succeeded
Stopping job with name jic062-nemo-v1-1-v4-mkmlizer
Pipeline stage MKMLizer completed in 128.79s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.07s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service jic062-nemo-v1-1-v4
Waiting for inference service jic062-nemo-v1-1-v4 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 jic062-nemo-v1-1-v4 ready after 170.81986784934998s
Pipeline stage MKMLDeployer completed in 171.19s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3126299381256104s
Received healthy response to inference request in 2.381544589996338s
Received healthy response to inference request in 1.8771238327026367s
Received healthy response to inference request in 1.9627254009246826s
Received healthy response to inference request in 2.225510358810425s
5 requests
0 failed requests
5th percentile: 1.8942441463470459
10th percentile: 1.911364459991455
20th percentile: 1.9456050872802735
30th percentile: 2.015282392501831
40th percentile: 2.120396375656128
50th percentile: 2.225510358810425
60th percentile: 2.260358190536499
70th percentile: 2.2952060222625734
80th percentile: 2.326412868499756
90th percentile: 2.353978729248047
95th percentile: 2.367761659622192
99th percentile: 2.3787880039215086
mean time: 2.1519068241119386
Pipeline stage StressChecker completed in 11.47s
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 8.20s
Shutdown handler de-registered
jic062-nemo-v1-1_v4 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 0.13s
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 jic062-nemo-v1-1-v4-profiler
Waiting for inference service jic062-nemo-v1-1-v4-profiler to be ready
Inference service jic062-nemo-v1-1-v4-profiler ready after 170.3912868499756s
Pipeline stage MKMLProfilerDeployer completed in 170.76s
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-v4-profiler-predictor-00001-deployment-858dvkj:/code/chaiverse_profiler_1726249977 --namespace tenant-chaiml-guanaco
kubectl exec -it jic062-nemo-v1-1-v4-profiler-predictor-00001-deployment-858dvkj --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726249977 && 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 512 --output_tokens 64 --summary /code/chaiverse_profiler_1726249977/summary.json'
kubectl exec -it jic062-nemo-v1-1-v4-profiler-predictor-00001-deployment-858dvkj --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726249977/summary.json'
Pipeline stage MKMLProfilerRunner completed in 971.80s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service jic062-nemo-v1-1-v4-profiler is running
Tearing down inference service jic062-nemo-v1-1-v4-profiler
Service jic062-nemo-v1-1-v4-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.32s
Shutdown handler de-registered
jic062-nemo-v1-1_v4 status is now inactive due to auto deactivation removed underperforming models
jic062-nemo-v1-1_v4 status is now torndown due to DeploymentManager action