jic062-nemo-v1-2

submission_id: jic062-nemo-v1-2_v1

developer_uid: chace9580

best_of: 8

celo_rating: 1257.53

display_name: jic062-nemo-v1-2_v1

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': 80, '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-v1.2

latencies: [{'batch_size': 1, 'throughput': 0.6844549025765424, 'latency_mean': 1.460957601070404, 'latency_p50': 1.461259365081787, 'latency_p90': 1.618291449546814}, {'batch_size': 3, 'throughput': 1.3196511287231076, 'latency_mean': 2.261894677877426, 'latency_p50': 2.2573232650756836, 'latency_p90': 2.5306148529052734}, {'batch_size': 5, 'throughput': 1.5616921695772603, 'latency_mean': 3.1873308861255647, 'latency_p50': 3.189086675643921, 'latency_p90': 3.582643675804138}, {'batch_size': 6, 'throughput': 1.6054549973322825, 'latency_mean': 3.720084156990051, 'latency_p50': 3.7634326219558716, 'latency_p90': 4.202585077285766}, {'batch_size': 8, 'throughput': 1.5920524640664568, 'latency_mean': 4.998916575908661, 'latency_p50': 5.011911630630493, 'latency_p90': 5.686991882324219}, {'batch_size': 10, 'throughput': 1.5395330771273237, 'latency_mean': 6.468786809444428, 'latency_p50': 6.48987078666687, 'latency_p90': 7.36030490398407}]

max_input_tokens: 512

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: jic062/Nemo-v1.2

model_name: jic062-nemo-v1-2_v1

model_num_parameters: 12772070400.0

model_repo: jic062/Nemo-v1.2

model_size: 13B

num_battles: 14718

num_wins: 7681

ranking_group: single

status: torndown

submission_type: basic

throughput_3p7s: 1.61

timestamp: 2024-09-03T19:48:29+00:00

us_pacific_date: 2024-09-03

win_ratio: 0.5218779725506183

Resubmit model

run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name jic062-nemo-v1-2-v1-mkmlizer
Waiting for job on jic062-nemo-v1-2-v1-mkmlizer to finish
Stopping job with name jic062-nemo-v1-2-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name jic062-nemo-v1-2-v1-mkmlizer
Waiting for job on jic062-nemo-v1-2-v1-mkmlizer to finish
jic062-nemo-v1-2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-nemo-v1-2-v1-mkmlizer: ║     _____            __           __                                ║
jic062-nemo-v1-2-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jic062-nemo-v1-2-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jic062-nemo-v1-2-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jic062-nemo-v1-2-v1-mkmlizer: ║       /___/                                                         ║
jic062-nemo-v1-2-v1-mkmlizer: ║                                                                     ║
jic062-nemo-v1-2-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
jic062-nemo-v1-2-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jic062-nemo-v1-2-v1-mkmlizer: ║  https://mk1.ai                                                     ║
jic062-nemo-v1-2-v1-mkmlizer: ║                                                                     ║
jic062-nemo-v1-2-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
jic062-nemo-v1-2-v1-mkmlizer: ║  belonging to:                                                      ║
jic062-nemo-v1-2-v1-mkmlizer: ║                                                                     ║
jic062-nemo-v1-2-v1-mkmlizer: ║  Chai Research Corp.                                                ║
jic062-nemo-v1-2-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jic062-nemo-v1-2-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jic062-nemo-v1-2-v1-mkmlizer: ║                                                                     ║
jic062-nemo-v1-2-v1-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
jic062-nemo-v1-2-v1-mkmlizer: Downloaded to shared memory in 54.098s
jic062-nemo-v1-2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplqzp_vvw, device:0
jic062-nemo-v1-2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-nemo-v1-2-v1-mkmlizer: quantized model in 36.150s
jic062-nemo-v1-2-v1-mkmlizer: Processed model jic062/Nemo-v1.2 in 90.249s
jic062-nemo-v1-2-v1-mkmlizer: creating bucket guanaco-mkml-models
jic062-nemo-v1-2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-nemo-v1-2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-nemo-v1-2-v1
jic062-nemo-v1-2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-nemo-v1-2-v1/special_tokens_map.json
jic062-nemo-v1-2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-nemo-v1-2-v1/config.json
jic062-nemo-v1-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-nemo-v1-2-v1/tokenizer_config.json
jic062-nemo-v1-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-nemo-v1-2-v1/tokenizer.json
jic062-nemo-v1-2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-nemo-v1-2-v1/flywheel_model.0.safetensors
jic062-nemo-v1-2-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 33.15it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 49.09it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:06, 50.20it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 41.40it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 46.07it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 44.54it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 44.61it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:07, 43.42it/s]
Loading 0:  14%|█▍        | 51/363 [00:01<00:07, 42.97it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:06, 44.73it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 33.75it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 33.31it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 41.07it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 41.52it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:06, 40.14it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:05, 45.88it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:05, 46.33it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:07, 36.97it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:06, 40.96it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 43.70it/s]
Loading 0:  32%|███▏      | 117/363 [00:02<00:05, 41.76it/s]
Loading 0:  34%|███▎      | 122/363 [00:02<00:05, 42.14it/s]
Loading 0:  35%|███▍      | 127/363 [00:03<00:06, 34.52it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:05, 41.08it/s]
Loading 0:  38%|███▊      | 139/363 [00:03<00:05, 39.89it/s]
Loading 0:  40%|███▉      | 144/363 [00:03<00:08, 27.11it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 29.48it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 37.74it/s]
Loading 0:  45%|████▍     | 163/363 [00:04<00:05, 38.66it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:05, 37.63it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:04, 41.26it/s]
Loading 0:  49%|████▉     | 179/363 [00:04<00:04, 41.69it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:04, 40.92it/s]
Loading 0:  52%|█████▏    | 189/363 [00:04<00:04, 42.13it/s]
Loading 0:  53%|█████▎    | 194/363 [00:04<00:04, 35.55it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:03, 41.68it/s]
Loading 0:  57%|█████▋    | 206/363 [00:05<00:03, 40.96it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 42.14it/s]
Loading 0:  60%|█████▉    | 216/363 [00:05<00:03, 42.63it/s]
Loading 0:  61%|██████    | 221/363 [00:05<00:03, 43.73it/s]
Loading 0:  62%|██████▏   | 226/363 [00:05<00:04, 27.62it/s]
Loading 0:  63%|██████▎   | 230/363 [00:05<00:04, 27.94it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 34.88it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 36.96it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 39.72it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 41.53it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:03, 34.28it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 41.11it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 41.46it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:02, 40.55it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:01, 42.15it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 34.62it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 40.39it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 41.12it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 42.16it/s]
Loading 0:  84%|████████▍ | 306/363 [00:14<00:22,  2.48it/s]
Loading 0:  85%|████████▌ | 310/363 [00:14<00:16,  3.21it/s]
Loading 0:  87%|████████▋ | 314/363 [00:14<00:11,  4.18it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  6.26it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  8.84it/s]
Loading 0:  91%|█████████ | 331/363 [00:15<00:02, 11.34it/s]
Loading 0:  93%|█████████▎| 337/363 [00:15<00:01, 15.42it/s]
Loading 0:  94%|█████████▍| 342/363 [00:15<00:01, 19.02it/s]
Loading 0:  96%|█████████▌| 348/363 [00:15<00:00, 22.03it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 29.69it/s]
Loading 0:  99%|█████████▉| 361/363 [00:15<00:00, 33.02it/s]
                                                            
Job jic062-nemo-v1-2-v1-mkmlizer completed after 115.62s with status: succeeded
Stopping job with name jic062-nemo-v1-2-v1-mkmlizer
Pipeline stage MKMLizer completed in 117.05s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.21s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service jic062-nemo-v1-2-v1
Waiting for inference service jic062-nemo-v1-2-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
Inference service jic062-nemo-v1-2-v1 ready after 141.51919770240784s
Pipeline stage MKMLDeployer completed in 142.48s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.266494035720825s
Received healthy response to inference request in 2.2948901653289795s
Received healthy response to inference request in 1.7018852233886719s
Received healthy response to inference request in 1.8444621562957764s
Received healthy response to inference request in 2.1009535789489746s
5 requests
0 failed requests
5th percentile: 1.7304006099700928
10th percentile: 1.7589159965515138
20th percentile: 1.8159467697143554
30th percentile: 1.895760440826416
40th percentile: 1.9983570098876953
50th percentile: 2.1009535789489746
60th percentile: 2.167169761657715
70th percentile: 2.233385944366455
80th percentile: 2.272173261642456
90th percentile: 2.2835317134857176
95th percentile: 2.2892109394073485
99th percentile: 2.2937543201446533
mean time: 2.0417370319366457
Pipeline stage StressChecker completed in 10.89s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 4.96s
jic062-nemo-v1-2_v1 status is now deployed due to DeploymentManager action
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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service jic062-nemo-v1-2-v1-profiler
Waiting for inference service jic062-nemo-v1-2-v1-profiler to be ready
Inference service jic062-nemo-v1-2-v1-profiler ready after 150.35003471374512s
Pipeline stage MKMLProfilerDeployer completed in 150.78s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/jic062-nemo-v1-2-v1-profiler-predictor-00001-deployment-672mkpf:/code/chaiverse_profiler_1725393396 --namespace tenant-chaiml-guanaco
kubectl exec -it jic062-nemo-v1-2-v1-profiler-predictor-00001-deployment-672mkpf --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725393396 && 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_1725393396/summary.json'
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service jic062-nemo-v1-2-v1-profiler is running
Tearing down inference service jic062-nemo-v1-2-v1-profiler
Service jic062-nemo-v1-2-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.59s
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 jic062-nemo-v1-2-v1-profiler
Waiting for inference service jic062-nemo-v1-2-v1-profiler to be ready
Inference service jic062-nemo-v1-2-v1-profiler ready after 60.21142053604126s
Pipeline stage MKMLProfilerDeployer completed in 60.60s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/jic062-nemo-v1-2-v1-profiler-predictor-00001-deployment-5b8zntj:/code/chaiverse_profiler_1725395555 --namespace tenant-chaiml-guanaco
kubectl exec -it jic062-nemo-v1-2-v1-profiler-predictor-00001-deployment-5b8zntj --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725395555 && chmod +x profiles.py && 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_1725395555/summary.json'
kubectl exec -it jic062-nemo-v1-2-v1-profiler-predictor-00001-deployment-5b8zntj --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725395555/summary.json'
Pipeline stage MKMLProfilerRunner completed in 958.28s
cleanup pipeline after completion
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service jic062-nemo-v1-2-v1-profiler is running
Tearing down inference service jic062-nemo-v1-2-v1-profiler
Service jic062-nemo-v1-2-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.75s
jic062-nemo-v1-2_v1 status is now inactive due to auto deactivation removed underperforming models
jic062-nemo-v1-2_v1 status is now torndown due to DeploymentManager action