cycy233-nemo-p-v3-c2

developer_uid: shiroe40

submission_id: cycy233-nemo-p-v3-c2_v1

model_name: auto

model_group: cycy233/nemo-p-v3-c2

status: torndown

timestamp: 2024-09-19T07:56:47+00:00

num_battles: 10978

num_wins: 5616

celo_rating: 1250.86

family_friendly_score: 0.0

submission_type: basic

model_repo: cycy233/nemo-p-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': 0.6158144489628068, 'latency_mean': 1.6238038372993469, 'latency_p50': 1.6191836595535278, 'latency_p90': 1.7898728847503662}, {'batch_size': 3, 'throughput': 1.0870860237502087, 'latency_mean': 2.74984423995018, 'latency_p50': 2.726187825202942, 'latency_p90': 3.03615939617157}, {'batch_size': 5, 'throughput': 1.2323097716667144, 'latency_mean': 4.0298246383667, 'latency_p50': 4.05130410194397, 'latency_p90': 4.525972628593445}, {'batch_size': 6, 'throughput': 1.2640152202439998, 'latency_mean': 4.718609297275544, 'latency_p50': 4.706885933876038, 'latency_p90': 5.384436082839966}, {'batch_size': 8, 'throughput': 1.2574249662278905, 'latency_mean': 6.330375262498856, 'latency_p50': 6.4085458517074585, 'latency_p90': 7.1511634349822994}, {'batch_size': 10, 'throughput': 1.2206201345614334, 'latency_mean': 8.152206118106841, 'latency_p50': 8.203119277954102, 'latency_p90': 9.091365504264832}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: auto

is_internal_developer: False

language_model: cycy233/nemo-p-v3-c2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.21

us_pacific_date: 2024-09-19

win_ratio: 0.5115685917289123

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-v3-c2-v1-mkmlizer
Waiting for job on cycy233-nemo-p-v3-c2-v1-mkmlizer to finish
cycy233-nemo-p-v3-c2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-nemo-p-v3-c2-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-nemo-p-v3-c2-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-nemo-p-v3-c2-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-nemo-p-v3-c2-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-nemo-p-v3-c2-v1-mkmlizer: ║       /___/                                                         ║
cycy233-nemo-p-v3-c2-v1-mkmlizer: ║                                                                     ║
cycy233-nemo-p-v3-c2-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
cycy233-nemo-p-v3-c2-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-nemo-p-v3-c2-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-nemo-p-v3-c2-v1-mkmlizer: ║                                                                     ║
cycy233-nemo-p-v3-c2-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-nemo-p-v3-c2-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-nemo-p-v3-c2-v1-mkmlizer: ║                                                                     ║
cycy233-nemo-p-v3-c2-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-nemo-p-v3-c2-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-nemo-p-v3-c2-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-nemo-p-v3-c2-v1-mkmlizer: ║                                                                     ║
cycy233-nemo-p-v3-c2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-nemo-p-v3-c2-v1-mkmlizer: Downloaded to shared memory in 47.199s
cycy233-nemo-p-v3-c2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpiu4oemwa, device:0
cycy233-nemo-p-v3-c2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-nemo-p-v3-c2-v1-mkmlizer: quantized model in 35.299s
cycy233-nemo-p-v3-c2-v1-mkmlizer: Processed model cycy233/nemo-p-v3-c2 in 82.498s
cycy233-nemo-p-v3-c2-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-nemo-p-v3-c2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-nemo-p-v3-c2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-nemo-p-v3-c2-v1
cycy233-nemo-p-v3-c2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-nemo-p-v3-c2-v1/config.json
cycy233-nemo-p-v3-c2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-nemo-p-v3-c2-v1/special_tokens_map.json
cycy233-nemo-p-v3-c2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-nemo-p-v3-c2-v1/tokenizer_config.json
cycy233-nemo-p-v3-c2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-nemo-p-v3-c2-v1/tokenizer.json
cycy233-nemo-p-v3-c2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-nemo-p-v3-c2-v1/flywheel_model.0.safetensors
cycy233-nemo-p-v3-c2-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 38.07it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:05, 64.86it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:04, 75.62it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:03, 89.72it/s]
Loading 0:  14%|█▍        | 52/363 [00:00<00:03, 88.93it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:12, 23.67it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:08, 34.52it/s]
Loading 0:  24%|██▍       | 88/363 [00:02<00:06, 41.54it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:05, 47.02it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:05, 49.56it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:04, 55.22it/s]
Loading 0:  34%|███▍      | 124/363 [00:02<00:03, 60.30it/s]
Loading 0:  37%|███▋      | 133/363 [00:02<00:03, 65.06it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:10, 21.75it/s]
Loading 0:  42%|████▏     | 151/363 [00:03<00:07, 27.78it/s]
Loading 0:  44%|████▍     | 160/363 [00:03<00:05, 34.71it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:04, 41.76it/s]
Loading 0:  49%|████▉     | 178/363 [00:04<00:03, 48.85it/s]
Loading 0:  53%|█████▎    | 192/363 [00:04<00:02, 65.94it/s]
Loading 0:  56%|█████▌    | 202/363 [00:04<00:02, 65.94it/s]
Loading 0:  59%|█████▉    | 214/363 [00:04<00:02, 70.32it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:05, 24.29it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 34.45it/s]
Loading 0:  69%|██████▉   | 250/363 [00:05<00:02, 42.17it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:01, 53.34it/s]
Loading 0:  76%|███████▋  | 277/363 [00:06<00:01, 59.33it/s]
Loading 0:  80%|████████  | 292/363 [00:06<00:01, 69.22it/s]
Loading 0:  84%|████████▎ | 304/363 [00:07<00:02, 27.96it/s]
Loading 0:  88%|████████▊ | 319/363 [00:07<00:01, 36.92it/s]
Loading 0:  91%|█████████ | 331/363 [00:07<00:00, 43.69it/s]
Loading 0:  95%|█████████▌| 346/363 [00:07<00:00, 54.28it/s]
Loading 0:  98%|█████████▊| 355/363 [00:07<00:00, 59.46it/s]
                                                            
Job cycy233-nemo-p-v3-c2-v1-mkmlizer completed after 106.87s with status: succeeded
Stopping job with name cycy233-nemo-p-v3-c2-v1-mkmlizer
Pipeline stage MKMLizer completed in 108.28s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-nemo-p-v3-c2-v1
Waiting for inference service cycy233-nemo-p-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
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-v3-c2-v1 ready after 192.60965061187744s
Pipeline stage MKMLDeployer completed in 194.15s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.733046293258667s
Received healthy response to inference request in 2.621690273284912s
Received healthy response to inference request in 2.449439764022827s
Received healthy response to inference request in 2.056661367416382s
Received healthy response to inference request in 1.9629499912261963s
5 requests
0 failed requests
5th percentile: 1.9816922664642334
10th percentile: 2.0004345417022704
20th percentile: 2.0379190921783445
30th percentile: 2.135217046737671
40th percentile: 2.292328405380249
50th percentile: 2.449439764022827
60th percentile: 2.518339967727661
70th percentile: 2.5872401714324953
80th percentile: 2.643961477279663
90th percentile: 2.688503885269165
95th percentile: 2.710775089263916
99th percentile: 2.728592052459717
mean time: 2.364757537841797
Pipeline stage StressChecker completed in 14.73s
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 6.69s
Shutdown handler de-registered
cycy233-nemo-p-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 0.11s
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 cycy233-nemo-p-v3-c2-v1-profiler
Waiting for inference service cycy233-nemo-p-v3-c2-v1-profiler to be ready
Inference service cycy233-nemo-p-v3-c2-v1-profiler ready after 190.4347951412201s
Pipeline stage MKMLProfilerDeployer completed in 190.81s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-nemo-p-v3-c2-v1-profiler-predictor-00001-deploymentq42w:/code/chaiverse_profiler_1726733165 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-nemo-p-v3-c2-v1-profiler-predictor-00001-deploymentq42w --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726733165 && 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_1726733165/summary.json'
kubectl exec -it cycy233-nemo-p-v3-c2-v1-profiler-predictor-00001-deploymentq42w --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726733165/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1156.45s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-nemo-p-v3-c2-v1-profiler is running
Tearing down inference service cycy233-nemo-p-v3-c2-v1-profiler
Service cycy233-nemo-p-v3-c2-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.78s
Shutdown handler de-registered
cycy233-nemo-p-v3-c2_v1 status is now inactive due to auto deactivation removed underperforming models
cycy233-nemo-p-v3-c2_v1 status is now torndown due to DeploymentManager action
Pipeline stage MKMLDeleter completed in 4.32s
Pipeline stage MKMLModelDeleter completed in 4.10s
cycy233-nemo-p-v0-c3_v1 status is now torndown due to DeploymentManager action
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLDeleter
Shutdown handler de-registered
run pipeline stage %s
run pipeline %s
admin requested tearing down of chaiml-0916-intent-suppo_6584_v1
Running pipeline stage MKMLModelDeleter
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of cycy233-nemo-p-v3-c2_v1
run pipeline stage %s
Shutdown handler de-registered
Pipeline stage MKMLDeleter completed in 4.97s
Pipeline stage %s skipped, reason=%s
cycy233-nemo-p-v0-c3_v2 status is now torndown due to DeploymentManager action
Shutdown handler de-registered
Running pipeline stage MKMLDeleter
run pipeline %s
run pipeline stage %s
run pipeline %s
Pipeline stage MKMLModelDeleter completed in 5.00s
Pipeline stage %s skipped, reason=%s
admin requested tearing down of chaiml-0916-intent-suppo_6584_v2
Shutdown handler not registered because Python interpreter is not running in the main thread
Running pipeline stage MKMLModelDeleter
cycy233-nemo-p-v1-c1_v1 status is now torndown due to DeploymentManager action
run pipeline stage %s
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLDeleter completed in 6.15s
run pipeline stage %s
run pipeline stage %s
Running pipeline stage MKMLDeleter
run pipeline %s
Shutdown handler de-registered
Pipeline stage MKMLModelDeleter completed in 5.85s
run pipeline %s
Pipeline stage %s skipped, reason=%s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of chaiml-0916-intent-suppo_6584_v4
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of deverdever-heavenly-mouse-v20_v1
Running pipeline stage MKMLModelDeleter
run pipeline stage %s
Running pipeline stage MKMLDeleter
Running pipeline stage MKMLDeleter
Pipeline stage %s skipped, reason=%s
run pipeline stage %s
cycy233-nemo-p-v1-c2_v1 status is now torndown due to DeploymentManager action
Shutdown handler de-registered
Pipeline stage MKMLModelDeleter completed in 6.48s
run pipeline stage %s
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
admin requested tearing down of chaiml-0917-bot-dominant_6324_v2
run pipeline stage %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage %s skipped, reason=%s
admin requested tearing down of epiculous-azure-dusk-bas_2210_v1
Running pipeline stage MKMLModelDeleter
Pipeline stage %s skipped, reason=%s
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLDeleter completed in 8.17s
Running pipeline stage MKMLDeleter
cycy233-nemo-p-v1-c2_v2 status is now torndown due to DeploymentManager action
Shutdown handler de-registered
Running pipeline stage MKMLDeleter