submission_id: cycy233-nemo-p-v0-c2_v2
developer_uid: shiroe40
best_of: 8
celo_rating: 1229.72
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>', '###', 'Bot:', 'User:', 'You:', '<|im_end|>'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: cycy233/nemo-p-v0-c2
latencies: [{'batch_size': 1, 'throughput': 0.6921084834814899, 'latency_mean': 1.4447639417648315, 'latency_p50': 1.4570696353912354, 'latency_p90': 1.6075617313385009}, {'batch_size': 3, 'throughput': 1.3256137258900935, 'latency_mean': 2.2575961220264436, 'latency_p50': 2.2611751556396484, 'latency_p90': 2.47237606048584}, {'batch_size': 5, 'throughput': 1.5631463024087688, 'latency_mean': 3.1887358558177947, 'latency_p50': 3.2023565769195557, 'latency_p90': 3.537432146072388}, {'batch_size': 6, 'throughput': 1.6070075500643073, 'latency_mean': 3.7091821146011354, 'latency_p50': 3.7194809913635254, 'latency_p90': 4.255779814720153}, {'batch_size': 8, 'throughput': 1.6141419155120411, 'latency_mean': 4.937501055002213, 'latency_p50': 4.926253318786621, 'latency_p90': 5.627223062515259}, {'batch_size': 10, 'throughput': 1.5388097507056655, 'latency_mean': 6.455609947443008, 'latency_p50': 6.521261692047119, 'latency_p90': 7.207298326492309}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: cycy233/nemo-p-v0-c2
model_name: auto
model_num_parameters: 12772070400.0
model_repo: cycy233/nemo-p-v0-c2
model_size: 13B
num_battles: 11016
num_wins: 5158
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 1.62
timestamp: 2024-09-15T08:02:51+00:00
us_pacific_date: 2024-09-15
win_ratio: 0.46822803195352214
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-v0-c2-v2-mkmlizer
Waiting for job on cycy233-nemo-p-v0-c2-v2-mkmlizer to finish
cycy233-nemo-p-v0-c2-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-nemo-p-v0-c2-v2-mkmlizer: ║ _____ __ __ ║
cycy233-nemo-p-v0-c2-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-nemo-p-v0-c2-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-nemo-p-v0-c2-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-nemo-p-v0-c2-v2-mkmlizer: ║ /___/ ║
cycy233-nemo-p-v0-c2-v2-mkmlizer: ║ ║
cycy233-nemo-p-v0-c2-v2-mkmlizer: ║ Version: 0.10.1 ║
cycy233-nemo-p-v0-c2-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-nemo-p-v0-c2-v2-mkmlizer: ║ https://mk1.ai ║
cycy233-nemo-p-v0-c2-v2-mkmlizer: ║ ║
cycy233-nemo-p-v0-c2-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-nemo-p-v0-c2-v2-mkmlizer: ║ belonging to: ║
cycy233-nemo-p-v0-c2-v2-mkmlizer: ║ ║
cycy233-nemo-p-v0-c2-v2-mkmlizer: ║ Chai Research Corp. ║
cycy233-nemo-p-v0-c2-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-nemo-p-v0-c2-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-nemo-p-v0-c2-v2-mkmlizer: ║ ║
cycy233-nemo-p-v0-c2-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-nemo-p-v0-c2-v2-mkmlizer: Downloaded to shared memory in 34.379s
cycy233-nemo-p-v0-c2-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnkstp8xy, device:0
cycy233-nemo-p-v0-c2-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-nemo-p-v0-c2-v2-mkmlizer: quantized model in 35.074s
cycy233-nemo-p-v0-c2-v2-mkmlizer: Processed model cycy233/nemo-p-v0-c2 in 69.453s
cycy233-nemo-p-v0-c2-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-nemo-p-v0-c2-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-nemo-p-v0-c2-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-nemo-p-v0-c2-v2
cycy233-nemo-p-v0-c2-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-nemo-p-v0-c2-v2/config.json
cycy233-nemo-p-v0-c2-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-nemo-p-v0-c2-v2/special_tokens_map.json
cycy233-nemo-p-v0-c2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-nemo-p-v0-c2-v2/tokenizer_config.json
cycy233-nemo-p-v0-c2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-nemo-p-v0-c2-v2/tokenizer.json
cycy233-nemo-p-v0-c2-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-nemo-p-v0-c2-v2/flywheel_model.0.safetensors
cycy233-nemo-p-v0-c2-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 4/363 [00:00<00:09, 37.73it/s] Loading 0: 4%|▍ | 16/363 [00:00<00:04, 72.15it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:03, 91.77it/s] Loading 0: 12%|█▏ | 43/363 [00:00<00:03, 92.17it/s] Loading 0: 16%|█▌ | 58/363 [00:00<00:03, 100.27it/s] Loading 0: 19%|█▊ | 68/363 [00:01<00:11, 25.63it/s] Loading 0: 21%|██ | 76/363 [00:01<00:09, 30.19it/s] Loading 0: 23%|██▎ | 85/363 [00:01<00:07, 36.70it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:05, 47.02it/s] Loading 0: 29%|██▉ | 106/363 [00:02<00:04, 52.31it/s] Loading 0: 33%|███▎ | 121/363 [00:02<00:03, 65.02it/s] Loading 0: 37%|███▋ | 133/363 [00:02<00:03, 71.32it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:08, 24.71it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:05, 34.46it/s] Loading 0: 46%|████▌ | 166/363 [00:03<00:04, 40.41it/s] Loading 0: 49%|████▉ | 178/363 [00:03<00:03, 48.44it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:02, 60.86it/s] Loading 0: 56%|█████▋ | 205/363 [00:04<00:02, 67.41it/s] Loading 0: 61%|██████ | 220/363 [00:04<00:01, 78.41it/s] Loading 0: 63%|██████▎ | 230/363 [00:05<00:04, 27.69it/s] Loading 0: 66%|██████▋ | 241/363 [00:05<00:03, 33.82it/s] Loading 0: 71%|███████ | 256/363 [00:05<00:02, 45.06it/s] Loading 0: 74%|███████▍ | 268/363 [00:05<00:01, 52.55it/s] Loading 0: 78%|███████▊ | 283/363 [00:05<00:01, 64.24it/s] Loading 0: 81%|████████▏ | 295/363 [00:06<00:01, 66.02it/s] Loading 0: 84%|████████▎ | 304/363 [00:07<00:02, 25.71it/s] Loading 0: 88%|████████▊ | 319/363 [00:07<00:01, 35.26it/s] Loading 0: 91%|█████████ | 331/363 [00:07<00:00, 42.88it/s] Loading 0: 95%|█████████▌| 346/363 [00:07<00:00, 54.22it/s] Loading 0: 99%|█████████▊| 358/363 [00:07<00:00, 61.06it/s]
Job cycy233-nemo-p-v0-c2-v2-mkmlizer completed after 93.39s with status: succeeded
Stopping job with name cycy233-nemo-p-v0-c2-v2-mkmlizer
Pipeline stage MKMLizer completed in 94.63s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-nemo-p-v0-c2-v2
Waiting for inference service cycy233-nemo-p-v0-c2-v2 to be ready
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission chaiml-lexical-nemo-v4-1k1e5_v3: ('http://chaiml-lexical-nemo-v4-1k1e5-v3-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:57546->127.0.0.1:8080: read: connection reset by peer\n')
Inference service cycy233-nemo-p-v0-c2-v2 ready after 170.95992636680603s
Pipeline stage MKMLDeployer completed in 172.28s
run pipeline stage %s
Running pipeline stage StressChecker
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
Received healthy response to inference request in 2.6223225593566895s
Received healthy response to inference request in 1.61197829246521s
Received healthy response to inference request in 2.0027830600738525s
Received healthy response to inference request in 1.63374662399292s
Received healthy response to inference request in 1.824747085571289s
5 requests
0 failed requests
5th percentile: 1.6163319587707519
10th percentile: 1.620685625076294
20th percentile: 1.629392957687378
30th percentile: 1.6719467163085937
40th percentile: 1.7483469009399415
50th percentile: 1.824747085571289
60th percentile: 1.8959614753723144
70th percentile: 1.9671758651733398
80th percentile: 2.12669095993042
90th percentile: 2.3745067596435545
95th percentile: 2.498414659500122
99th percentile: 2.597540979385376
mean time: 1.9391155242919922
Pipeline stage StressChecker completed in 11.37s
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 5.24s
Shutdown handler de-registered
cycy233-nemo-p-v0-c2_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cycy233-nemo-p-v0-c2-v2-profiler
Waiting for inference service cycy233-nemo-p-v0-c2-v2-profiler to be ready
Inference service cycy233-nemo-p-v0-c2-v2-profiler ready after 170.3928506374359s
Pipeline stage MKMLProfilerDeployer completed in 170.74s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-nemo-p-v0-c2-v2-profiler-predictor-00001-deploymenf7ntq:/code/chaiverse_profiler_1726387865 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-nemo-p-v0-c2-v2-profiler-predictor-00001-deploymenf7ntq --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726387865 && 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_1726387865/summary.json'
kubectl exec -it cycy233-nemo-p-v0-c2-v2-profiler-predictor-00001-deploymenf7ntq --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726387865/summary.json'
Pipeline stage MKMLProfilerRunner completed in 952.34s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-nemo-p-v0-c2-v2-profiler is running
Tearing down inference service cycy233-nemo-p-v0-c2-v2-profiler
Service cycy233-nemo-p-v0-c2-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.80s
Shutdown handler de-registered
cycy233-nemo-p-v0-c2_v2 status is now inactive due to auto deactivation removed underperforming models
cycy233-nemo-p-v0-c2_v2 status is now torndown due to DeploymentManager action
run pipeline stage %s
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 cycy233-nemo-p-v2-c4_v1
run pipeline stage %s
Pipeline stage %s skipped, reason=%s
Shutdown handler de-registered
Pipeline stage %s skipped, reason=%s
cycy233-nemo-p-v0-c2_v2 status is now torndown due to DeploymentManager action
Running pipeline stage MKMLDeleter
run pipeline stage %s
Pipeline stage MKMLModelDeleter completed in 3.38s
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread