jic062-nemo-v1-6

developer_uid: chace9580

submission_id: jic062-nemo-v1-6_v2

model_name: jic062-nemo-v1-6_v2

model_group: jic062/Nemo-v1.6

status: torndown

timestamp: 2024-09-20T05:00:41+00:00

num_battles: 11383

num_wins: 5871

celo_rating: 1263.8

family_friendly_score: 0.0

submission_type: basic

model_repo: jic062/Nemo-v1.6

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.620299837582474, 'latency_mean': 1.6120467615127563, 'latency_p50': 1.6220176219940186, 'latency_p90': 1.7690399885177612}, {'batch_size': 3, 'throughput': 1.0930733904106058, 'latency_mean': 2.740342477560043, 'latency_p50': 2.7319525480270386, 'latency_p90': 3.067507219314575}, {'batch_size': 5, 'throughput': 1.2549362127434247, 'latency_mean': 3.971250091791153, 'latency_p50': 4.005425214767456, 'latency_p90': 4.455667281150817}, {'batch_size': 6, 'throughput': 1.2726655675130636, 'latency_mean': 4.682068082094193, 'latency_p50': 4.689743280410767, 'latency_p90': 5.234178900718689}, {'batch_size': 8, 'throughput': 1.274544302378372, 'latency_mean': 6.251473860740662, 'latency_p50': 6.248603105545044, 'latency_p90': 7.180715560913086}, {'batch_size': 10, 'throughput': 1.2209886493998596, 'latency_mean': 8.13714196562767, 'latency_p50': 8.229353785514832, 'latency_p90': 9.291650366783141}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: jic062-nemo-v1-6_v2

is_internal_developer: False

language_model: jic062/Nemo-v1.6

model_size: 13B

ranking_group: single

throughput_3p7s: 1.23

us_pacific_date: 2024-09-19

win_ratio: 0.5157691294034964

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}

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}

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-v1-6-v2-mkmlizer
Waiting for job on jic062-nemo-v1-6-v2-mkmlizer to finish
jic062-nemo-v1-6-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-nemo-v1-6-v2-mkmlizer: ║     _____            __           __                                ║
jic062-nemo-v1-6-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jic062-nemo-v1-6-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jic062-nemo-v1-6-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jic062-nemo-v1-6-v2-mkmlizer: ║       /___/                                                         ║
jic062-nemo-v1-6-v2-mkmlizer: ║                                                                     ║
jic062-nemo-v1-6-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
jic062-nemo-v1-6-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jic062-nemo-v1-6-v2-mkmlizer: ║  https://mk1.ai                                                     ║
jic062-nemo-v1-6-v2-mkmlizer: ║                                                                     ║
jic062-nemo-v1-6-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
jic062-nemo-v1-6-v2-mkmlizer: ║  belonging to:                                                      ║
jic062-nemo-v1-6-v2-mkmlizer: ║                                                                     ║
jic062-nemo-v1-6-v2-mkmlizer: ║  Chai Research Corp.                                                ║
jic062-nemo-v1-6-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jic062-nemo-v1-6-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jic062-nemo-v1-6-v2-mkmlizer: ║                                                                     ║
jic062-nemo-v1-6-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
jic062-nemo-v1-6-v2-mkmlizer: Downloaded to shared memory in 44.294s
jic062-nemo-v1-6-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpuf_1kjbu, device:0
jic062-nemo-v1-6-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
jic062-nemo-v1-6-v2-mkmlizer: quantized model in 35.321s
jic062-nemo-v1-6-v2-mkmlizer: Processed model jic062/Nemo-v1.6 in 79.615s
jic062-nemo-v1-6-v2-mkmlizer: creating bucket guanaco-mkml-models
jic062-nemo-v1-6-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-nemo-v1-6-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-nemo-v1-6-v2
jic062-nemo-v1-6-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-nemo-v1-6-v2/config.json
jic062-nemo-v1-6-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-nemo-v1-6-v2/special_tokens_map.json
jic062-nemo-v1-6-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-nemo-v1-6-v2/tokenizer_config.json
jic062-nemo-v1-6-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-nemo-v1-6-v2/flywheel_model.0.safetensors
jic062-nemo-v1-6-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 34.57it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:07, 45.05it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:06, 52.88it/s]
Loading 0:   7%|▋         | 27/363 [00:00<00:06, 53.43it/s]
Loading 0:   9%|▉         | 33/363 [00:00<00:07, 46.91it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:06, 52.91it/s]
Loading 0:  13%|█▎        | 46/363 [00:00<00:06, 50.61it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:06, 50.51it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:05, 51.29it/s]
Loading 0:  18%|█▊        | 64/363 [00:01<00:09, 32.70it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 41.45it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 42.24it/s]
Loading 0:  23%|██▎       | 84/363 [00:01<00:06, 42.66it/s]
Loading 0:  25%|██▍       | 90/363 [00:01<00:06, 44.79it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:05, 45.86it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:06, 39.70it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:04, 51.24it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 43.77it/s]
Loading 0:  33%|███▎      | 120/363 [00:02<00:05, 43.05it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:05, 46.39it/s]
Loading 0:  36%|███▋      | 132/363 [00:02<00:05, 43.29it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:05, 41.31it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 31.65it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 32.36it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 31.18it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 36.43it/s]
Loading 0:  44%|████▍     | 160/363 [00:03<00:05, 35.67it/s]
Loading 0:  45%|████▌     | 165/363 [00:03<00:05, 39.10it/s]
Loading 0:  47%|████▋     | 170/363 [00:04<00:04, 41.52it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 43.46it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 44.34it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:03, 44.43it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 50.15it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 48.67it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 47.07it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:02, 51.86it/s]
Loading 0:  60%|█████▉    | 217/363 [00:04<00:02, 50.87it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:03, 37.22it/s]
Loading 0:  63%|██████▎   | 228/363 [00:05<00:03, 36.92it/s]
Loading 0:  64%|██████▍   | 233/363 [00:05<00:03, 37.58it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 37.89it/s]
Loading 0:  67%|██████▋   | 244/363 [00:05<00:03, 38.29it/s]
Loading 0:  68%|██████▊   | 248/363 [00:05<00:03, 36.64it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 44.31it/s]
Loading 0:  72%|███████▏  | 261/363 [00:06<00:02, 45.69it/s]
Loading 0:  73%|███████▎  | 266/363 [00:06<00:02, 38.22it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:01, 46.52it/s]
Loading 0:  77%|███████▋  | 280/363 [00:06<00:01, 45.06it/s]
Loading 0:  79%|███████▊  | 285/363 [00:06<00:01, 42.27it/s]
Loading 0:  80%|████████  | 291/363 [00:06<00:01, 44.60it/s]
Loading 0:  82%|████████▏ | 296/363 [00:06<00:01, 44.59it/s]
Loading 0:  83%|████████▎ | 303/363 [00:07<00:01, 46.22it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:20,  2.69it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:14,  3.40it/s]
Loading 0:  88%|████████▊ | 319/363 [00:14<00:08,  5.22it/s]
Loading 0:  89%|████████▉ | 324/363 [00:14<00:05,  6.85it/s]
Loading 0:  91%|█████████ | 329/363 [00:14<00:03,  8.94it/s]
Loading 0:  92%|█████████▏| 334/363 [00:14<00:02, 11.59it/s]
Loading 0:  93%|█████████▎| 339/363 [00:14<00:01, 13.99it/s]
Loading 0:  96%|█████████▌| 348/363 [00:14<00:00, 20.62it/s]
Loading 0:  98%|█████████▊| 357/363 [00:14<00:00, 27.05it/s]
                                                            
Job jic062-nemo-v1-6-v2-mkmlizer completed after 114.11s with status: succeeded
Stopping job with name jic062-nemo-v1-6-v2-mkmlizer
Pipeline stage MKMLizer completed in 115.01s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.66s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service jic062-nemo-v1-6-v2
Waiting for inference service jic062-nemo-v1-6-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
Inference service jic062-nemo-v1-6-v2 ready after 202.67128491401672s
Pipeline stage MKMLDeployer completed in 203.92s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.4332082271575928s
Received healthy response to inference request in 2.715449810028076s
Received healthy response to inference request in 2.844045400619507s
Received healthy response to inference request in 2.459981918334961s
Received healthy response to inference request in 2.290226459503174s
5 requests
0 failed requests
5th percentile: 2.324177551269531
10th percentile: 2.3581286430358888
20th percentile: 2.4260308265686037
30th percentile: 2.511075496673584
40th percentile: 2.61326265335083
50th percentile: 2.715449810028076
60th percentile: 2.7668880462646483
70th percentile: 2.8183262825012205
80th percentile: 2.961877965927124
90th percentile: 3.1975430965423586
95th percentile: 3.3153756618499757
99th percentile: 3.4096417140960695
mean time: 2.748582363128662
Pipeline stage StressChecker completed in 14.57s
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 3.31s
Shutdown handler de-registered
jic062-nemo-v1-6_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 0.12s
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 jic062-nemo-v1-6-v2-profiler
Waiting for inference service jic062-nemo-v1-6-v2-profiler to be ready
Inference service jic062-nemo-v1-6-v2-profiler ready after 210.50428891181946s
Pipeline stage MKMLProfilerDeployer completed in 210.91s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/jic062-nemo-v1-6-v2-profiler-predictor-00001-deployment-5dskrwq:/code/chaiverse_profiler_1726809040 --namespace tenant-chaiml-guanaco
kubectl exec -it jic062-nemo-v1-6-v2-profiler-predictor-00001-deployment-5dskrwq --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726809040 && 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_1726809040/summary.json'
kubectl exec -it jic062-nemo-v1-6-v2-profiler-predictor-00001-deployment-5dskrwq --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726809040/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1149.26s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service jic062-nemo-v1-6-v2-profiler is running
Tearing down inference service jic062-nemo-v1-6-v2-profiler
Service jic062-nemo-v1-6-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.45s
Shutdown handler de-registered
jic062-nemo-v1-6_v2 status is now inactive due to auto deactivation removed underperforming models
jic062-nemo-v1-6_v2 status is now torndown due to DeploymentManager action