submission_id: cycy233-nemo-p-e-v2-c1_v1
developer_uid: shiroe40
best_of: 8
celo_rating: 1284.56
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-e-v2-c1
latencies: [{'batch_size': 1, 'throughput': 0.6157030043312697, 'latency_mean': 1.6240981066226958, 'latency_p50': 1.6247248649597168, 'latency_p90': 1.7989083528518677}, {'batch_size': 3, 'throughput': 1.074057626500257, 'latency_mean': 2.7824566531181336, 'latency_p50': 2.802143096923828, 'latency_p90': 3.049704670906067}, {'batch_size': 5, 'throughput': 1.2291073830723338, 'latency_mean': 4.051647454500198, 'latency_p50': 4.044126391410828, 'latency_p90': 4.516828346252441}, {'batch_size': 6, 'throughput': 1.2555862033788199, 'latency_mean': 4.76076096534729, 'latency_p50': 4.785235166549683, 'latency_p90': 5.314118790626526}, {'batch_size': 8, 'throughput': 1.2384445593480615, 'latency_mean': 6.4318801939487455, 'latency_p50': 6.461148381233215, 'latency_p90': 7.370098376274108}, {'batch_size': 10, 'throughput': 1.2024477699880125, 'latency_mean': 8.26293199777603, 'latency_p50': 8.292901992797852, 'latency_p90': 9.294572496414185}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: cycy233/nemo-p-e-v2-c1
model_name: auto
model_num_parameters: 12772070400.0
model_repo: cycy233/nemo-p-e-v2-c1
model_size: 13B
num_battles: 64800
num_wins: 36031
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 1.2
timestamp: 2024-09-23T06:39:13+00:00
us_pacific_date: 2024-09-22
win_ratio: 0.556033950617284
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-e-v2-c1-v1-mkmlizer
Waiting for job on cycy233-nemo-p-e-v2-c1-v1-mkmlizer to finish
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: ║ _____ __ __ ║
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: ║ /___/ ║
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: ║ ║
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: ║ Version: 0.10.1 ║
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
Failed to get response for submission mistralai-mixtral-8x7b_3473_v136: ('http://mistralai-mixtral-8x7b-3473-v136-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:52004->127.0.0.1:8080: read: connection reset by peer\n')
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: ║ ║
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: ║ belonging to: ║
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: ║ ║
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: ║ ║
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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-e-v2-c1-v1-mkmlizer: Downloaded to shared memory in 47.580s
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5wietj6k, device:0
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: quantized model in 34.813s
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: Processed model cycy233/nemo-p-e-v2-c1 in 82.393s
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-nemo-p-e-v2-c1-v1
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-nemo-p-e-v2-c1-v1/special_tokens_map.json
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-nemo-p-e-v2-c1-v1/config.json
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-nemo-p-e-v2-c1-v1/tokenizer_config.json
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-nemo-p-e-v2-c1-v1/tokenizer.json
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-nemo-p-e-v2-c1-v1/flywheel_model.0.safetensors
cycy233-nemo-p-e-v2-c1-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:11, 29.89it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 52.12it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:06, 49.79it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:06, 51.12it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 53.77it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 51.46it/s] Loading 0: 12%|█▏ | 43/363 [00:00<00:06, 52.08it/s] Loading 0: 14%|█▍ | 50/363 [00:01<00:06, 48.31it/s] Loading 0: 17%|█▋ | 60/363 [00:01<00:05, 55.83it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:07, 37.58it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 41.51it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:06, 42.07it/s] Loading 0: 23%|██▎ | 83/363 [00:01<00:06, 41.56it/s] Loading 0: 25%|██▍ | 89/363 [00:01<00:06, 45.50it/s] Loading 0: 26%|██▌ | 94/363 [00:02<00:06, 44.68it/s] Loading 0: 27%|██▋ | 99/363 [00:02<00:05, 45.47it/s] Loading 0: 29%|██▉ | 105/363 [00:02<00:05, 44.48it/s] Loading 0: 31%|███ | 112/363 [00:02<00:05, 49.16it/s] Loading 0: 33%|███▎ | 118/363 [00:02<00:05, 42.91it/s] Loading 0: 34%|███▍ | 125/363 [00:02<00:04, 49.02it/s] Loading 0: 36%|███▌ | 131/363 [00:02<00:04, 49.20it/s] Loading 0: 38%|███▊ | 137/363 [00:02<00:05, 43.63it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 35.21it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 35.44it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 35.08it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:04, 41.64it/s] Loading 0: 45%|████▍ | 163/363 [00:03<00:04, 41.13it/s] Loading 0: 46%|████▋ | 168/363 [00:03<00:04, 41.70it/s] Loading 0: 48%|████▊ | 175/363 [00:03<00:04, 46.97it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:04, 44.89it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:04, 43.29it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 48.13it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 46.63it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 45.46it/s] Loading 0: 58%|█████▊ | 210/363 [00:04<00:03, 48.39it/s] Loading 0: 59%|█████▉ | 215/363 [00:04<00:03, 48.34it/s] Loading 0: 61%|██████ | 222/363 [00:04<00:02, 48.52it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:03, 34.11it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:03, 33.52it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:03, 39.79it/s] Loading 0: 67%|██████▋ | 244/363 [00:05<00:02, 41.03it/s] Loading 0: 69%|██████▊ | 249/363 [00:05<00:02, 41.12it/s] Loading 0: 71%|███████ | 256/363 [00:05<00:02, 46.54it/s] Loading 0: 72%|███████▏ | 262/363 [00:05<00:02, 45.85it/s] Loading 0: 74%|███████▎ | 267/363 [00:06<00:02, 44.30it/s] Loading 0: 75%|███████▌ | 274/363 [00:06<00:01, 48.72it/s] Loading 0: 77%|███████▋ | 280/363 [00:06<00:01, 46.41it/s] Loading 0: 79%|███████▊ | 285/363 [00:06<00:01, 44.97it/s] Loading 0: 80%|████████ | 291/363 [00:06<00:01, 47.61it/s] Loading 0: 82%|████████▏ | 296/363 [00:06<00:01, 45.45it/s] Loading 0: 83%|████████▎ | 302/363 [00:06<00:01, 48.66it/s] Loading 0: 85%|████████▍ | 307/363 [00:13<00:21, 2.58it/s] Loading 0: 86%|████████▌ | 312/363 [00:13<00:14, 3.51it/s] Loading 0: 88%|████████▊ | 320/363 [00:13<00:07, 5.60it/s] Loading 0: 90%|████████▉ | 326/363 [00:13<00:04, 7.57it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:03, 9.69it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 13.70it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:01, 17.42it/s] Loading 0: 96%|█████████▋| 350/363 [00:14<00:00, 21.79it/s] Loading 0: 98%|█████████▊| 357/363 [00:14<00:00, 26.17it/s]
Job cycy233-nemo-p-e-v2-c1-v1-mkmlizer completed after 114.56s with status: succeeded
Stopping job with name cycy233-nemo-p-e-v2-c1-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.07s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.76s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-nemo-p-e-v2-c1-v1
Waiting for inference service cycy233-nemo-p-e-v2-c1-v1 to be ready
Inference service cycy233-nemo-p-e-v2-c1-v1 ready after 191.4507155418396s
Pipeline stage MKMLDeployer completed in 191.91s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8067824840545654s
Received healthy response to inference request in 1.7944707870483398s
Received healthy response to inference request in 2.072047233581543s
Received healthy response to inference request in 2.6845107078552246s
Received healthy response to inference request in 1.8798456192016602s
5 requests
0 failed requests
5th percentile: 1.8115457534790038
10th percentile: 1.828620719909668
20th percentile: 1.8627706527709962
30th percentile: 1.9182859420776368
40th percentile: 1.9951665878295899
50th percentile: 2.072047233581543
60th percentile: 2.3170326232910154
70th percentile: 2.5620180130004884
80th percentile: 2.7089650630950928
90th percentile: 2.757873773574829
95th percentile: 2.7823281288146973
99th percentile: 2.8018916130065916
mean time: 2.247531366348267
Pipeline stage StressChecker completed in 14.25s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%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
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.20s
Shutdown handler de-registered
cycy233-nemo-p-e-v2-c1_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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cycy233-nemo-p-e-v2-c1-v1-profiler
Waiting for inference service cycy233-nemo-p-e-v2-c1-v1-profiler to be ready
Inference service cycy233-nemo-p-e-v2-c1-v1-profiler ready after 200.46189546585083s
Pipeline stage MKMLProfilerDeployer completed in 200.84s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-nemo-p-e-v2-c1-v1-profiler-predictor-00001-deploymftkzt:/code/chaiverse_profiler_1727074117 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-nemo-p-e-v2-c1-v1-profiler-predictor-00001-deploymftkzt --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727074117 && 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_1727074117/summary.json'
kubectl exec -it cycy233-nemo-p-e-v2-c1-v1-profiler-predictor-00001-deploymftkzt --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727074117/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1165.70s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-nemo-p-e-v2-c1-v1-profiler is running
Tearing down inference service cycy233-nemo-p-e-v2-c1-v1-profiler
Service cycy233-nemo-p-e-v2-c1-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.16s
Shutdown handler de-registered
cycy233-nemo-p-e-v2-c1_v1 status is now inactive due to auto deactivation removed underperforming models
cycy233-nemo-p-e-v2-c4_v1 status is now torndown due to DeploymentManager action
Shutdown handler de-registered
Stopping job with name rica40325-mistral-test1-v6-mkmlizer
Shutdown handler de-registered
cycy233-nemo-p-e-v1-c2_v1 status is now torndown due to DeploymentManager action
cycy233-nemo-p-e-v2-c1_v1 status is now torndown due to DeploymentManager action
Pipeline stage MKMLizer completed in 139.69s