submission_id: cycy233-nemo-p-v3-c4_v1
developer_uid: shiroe40
best_of: 8
celo_rating: 1245.57
display_name: auto
family_friendly_score: 0.0
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}
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}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: cycy233/nemo-p-v3-c4
latencies: [{'batch_size': 1, 'throughput': 0.6177130128064563, 'latency_mean': 1.6187775504589081, 'latency_p50': 1.6155000925064087, 'latency_p90': 1.7834623098373412}, {'batch_size': 3, 'throughput': 1.089471158857896, 'latency_mean': 2.751804537773132, 'latency_p50': 2.7503323554992676, 'latency_p90': 3.0324568271636965}, {'batch_size': 5, 'throughput': 1.2433348638227546, 'latency_mean': 4.001860430240631, 'latency_p50': 4.018169641494751, 'latency_p90': 4.530649256706238}, {'batch_size': 6, 'throughput': 1.256247549676785, 'latency_mean': 4.752964423894882, 'latency_p50': 4.752171158790588, 'latency_p90': 5.294273018836975}, {'batch_size': 8, 'throughput': 1.244052330011944, 'latency_mean': 6.381191949844361, 'latency_p50': 6.41688346862793, 'latency_p90': 7.281610822677612}, {'batch_size': 10, 'throughput': 1.214899693714095, 'latency_mean': 8.18161514878273, 'latency_p50': 8.223394751548767, 'latency_p90': 9.304785299301146}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: cycy233/nemo-p-v3-c4
model_name: auto
model_num_parameters: 12772070400.0
model_repo: cycy233/nemo-p-v3-c4
model_size: 13B
num_battles: 11134
num_wins: 5606
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 1.22
timestamp: 2024-09-19T07:57:17+00:00
us_pacific_date: 2024-09-19
win_ratio: 0.5035027842644153
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 cycy233-nemo-p-v3-c4-v1-mkmlizer
Waiting for job on cycy233-nemo-p-v3-c4-v1-mkmlizer to finish
cycy233-nemo-p-v3-c4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-nemo-p-v3-c4-v1-mkmlizer: ║ _____ __ __ ║
cycy233-nemo-p-v3-c4-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-nemo-p-v3-c4-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-nemo-p-v3-c4-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-nemo-p-v3-c4-v1-mkmlizer: ║ /___/ ║
cycy233-nemo-p-v3-c4-v1-mkmlizer: ║ ║
cycy233-nemo-p-v3-c4-v1-mkmlizer: ║ Version: 0.10.1 ║
cycy233-nemo-p-v3-c4-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-nemo-p-v3-c4-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-nemo-p-v3-c4-v1-mkmlizer: ║ ║
cycy233-nemo-p-v3-c4-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-nemo-p-v3-c4-v1-mkmlizer: ║ belonging to: ║
cycy233-nemo-p-v3-c4-v1-mkmlizer: ║ ║
cycy233-nemo-p-v3-c4-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-nemo-p-v3-c4-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-nemo-p-v3-c4-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-nemo-p-v3-c4-v1-mkmlizer: ║ ║
cycy233-nemo-p-v3-c4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-nemo-p-v3-c4-v1-mkmlizer: Downloaded to shared memory in 49.328s
cycy233-nemo-p-v3-c4-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmprnbltabe, device:0
cycy233-nemo-p-v3-c4-v1-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
cycy233-nemo-p-v3-c4-v1-mkmlizer: quantized model in 35.811s
cycy233-nemo-p-v3-c4-v1-mkmlizer: Processed model cycy233/nemo-p-v3-c4 in 85.139s
cycy233-nemo-p-v3-c4-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-nemo-p-v3-c4-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-nemo-p-v3-c4-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-nemo-p-v3-c4-v1
cycy233-nemo-p-v3-c4-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-nemo-p-v3-c4-v1/config.json
cycy233-nemo-p-v3-c4-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-nemo-p-v3-c4-v1/special_tokens_map.json
cycy233-nemo-p-v3-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-nemo-p-v3-c4-v1/tokenizer_config.json
cycy233-nemo-p-v3-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-nemo-p-v3-c4-v1/tokenizer.json
cycy233-nemo-p-v3-c4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-nemo-p-v3-c4-v1/flywheel_model.0.safetensors
cycy233-nemo-p-v3-c4-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 4/363 [00:00<00:09, 37.20it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:05, 64.88it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:04, 84.53it/s] Loading 0: 9%|▉ | 34/363 [00:00<00:04, 80.01it/s] Loading 0: 13%|█▎ | 49/363 [00:00<00:03, 93.64it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:12, 23.43it/s] Loading 0: 21%|██ | 76/363 [00:01<00:08, 33.80it/s] Loading 0: 24%|██▍ | 88/363 [00:02<00:06, 41.84it/s] Loading 0: 28%|██▊ | 103/363 [00:02<00:04, 52.79it/s] Loading 0: 31%|███ | 112/363 [00:02<00:04, 58.27it/s] Loading 0: 34%|███▍ | 124/363 [00:02<00:03, 64.86it/s] Loading 0: 38%|███▊ | 139/363 [00:02<00:02, 76.89it/s] Loading 0: 41%|████ | 149/363 [00:03<00:07, 26.90it/s] Loading 0: 44%|████▍ | 160/363 [00:03<00:06, 33.05it/s] Loading 0: 48%|████▊ | 175/363 [00:03<00:04, 44.20it/s] Loading 0: 52%|█████▏ | 187/363 [00:04<00:03, 52.29it/s] Loading 0: 54%|█████▍ | 196/363 [00:04<00:02, 55.88it/s] Loading 0: 56%|█████▋ | 205/363 [00:04<00:02, 57.39it/s] Loading 0: 59%|█████▉ | 214/363 [00:04<00:02, 63.18it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:06, 22.76it/s] Loading 0: 64%|██████▍ | 232/363 [00:05<00:04, 28.73it/s] Loading 0: 66%|██████▋ | 241/363 [00:05<00:03, 35.60it/s] Loading 0: 69%|██████▉ | 250/363 [00:05<00:02, 43.04it/s] Loading 0: 73%|███████▎ | 265/363 [00:05<00:01, 57.17it/s] Loading 0: 76%|███████▋ | 277/363 [00:06<00:01, 65.15it/s] Loading 0: 79%|███████▉ | 286/363 [00:06<00:01, 68.73it/s] Loading 0: 81%|████████▏ | 295/363 [00:06<00:00, 72.11it/s] Loading 0: 84%|████████▎ | 304/363 [00:07<00:02, 22.69it/s] Loading 0: 87%|████████▋ | 314/363 [00:07<00:01, 29.67it/s] Loading 0: 90%|█████████ | 328/363 [00:07<00:00, 40.53it/s] Loading 0: 94%|█████████▎| 340/363 [00:07<00:00, 48.43it/s] Loading 0: 96%|█████████▌| 349/363 [00:07<00:00, 54.26it/s] Loading 0: 99%|█████████▊| 358/363 [00:08<00:00, 59.78it/s]
Job cycy233-nemo-p-v3-c4-v1-mkmlizer completed after 113.33s with status: succeeded
Stopping job with name cycy233-nemo-p-v3-c4-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.20s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-nemo-p-v3-c4-v1
Waiting for inference service cycy233-nemo-p-v3-c4-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
Inference service cycy233-nemo-p-v3-c4-v1 ready after 191.33939599990845s
Pipeline stage MKMLDeployer completed in 191.77s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3218159675598145s
Received healthy response to inference request in 1.7574317455291748s
Received healthy response to inference request in 1.7557628154754639s
Received healthy response to inference request in 2.1999266147613525s
Received healthy response to inference request in 2.113866090774536s
5 requests
0 failed requests
5th percentile: 1.756096601486206
10th percentile: 1.7564303874969482
20th percentile: 1.7570979595184326
30th percentile: 1.828718614578247
40th percentile: 1.9712923526763917
50th percentile: 2.113866090774536
60th percentile: 2.1482903003692626
70th percentile: 2.182714509963989
80th percentile: 2.2243044853210447
90th percentile: 2.2730602264404296
95th percentile: 2.2974380970001222
99th percentile: 2.316940393447876
mean time: 2.029760646820068
Pipeline stage StressChecker completed in 11.11s
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 6.11s
Shutdown handler de-registered
cycy233-nemo-p-v3-c4_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cycy233-nemo-p-v3-c4-v1-profiler
Waiting for inference service cycy233-nemo-p-v3-c4-v1-profiler to be ready
Inference service cycy233-nemo-p-v3-c4-v1-profiler ready after 200.5431890487671s
Pipeline stage MKMLProfilerDeployer completed in 200.88s
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-c4-v1-profiler-predictor-00001-deploymend6tlz:/code/chaiverse_profiler_1726733208 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-nemo-p-v3-c4-v1-profiler-predictor-00001-deploymend6tlz --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726733208 && 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_1726733208/summary.json'
kubectl exec -it cycy233-nemo-p-v3-c4-v1-profiler-predictor-00001-deploymend6tlz --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726733208/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1157.99s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-nemo-p-v3-c4-v1-profiler is running
Tearing down inference service cycy233-nemo-p-v3-c4-v1-profiler
Service cycy233-nemo-p-v3-c4-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.82s
Shutdown handler de-registered
cycy233-nemo-p-v3-c4_v1 status is now inactive due to auto deactivation removed underperforming models
cycy233-nemo-p-v3-c4_v1 status is now torndown due to DeploymentManager action
Pipeline stage MKMLDeleter completed in 4.97s
Running pipeline stage MKMLDeleter
Pipeline stage %s skipped, reason=%s
cycy233-nemo-p-v0-c3_v2 status is now torndown due to DeploymentManager action
run pipeline %s
run pipeline stage %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage MKMLModelDeleter completed in 5.00s
Pipeline stage %s skipped, reason=%s
admin requested tearing down of chaiml-0916-intent-suppo_6584_v2
admin requested tearing down of cycy233-nemo-p-v3-c4_v1
cycy233-nemo-p-v1-c1_v1 status is now torndown due to DeploymentManager action
run pipeline stage %s
Pipeline stage %s skipped, reason=%s
cycy233-nemo-p-v1-c1_v1 status is now torndown due to DeploymentManager action
Pipeline stage %s skipped, reason=%s
run pipeline stage %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
Pipeline stage MKMLDeleter completed in 6.11s
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
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