developer_uid: shiroe40
submission_id: cycy233-nemo-p-e-v3-c3_v1
model_name: auto
model_group: cycy233/nemo-p-e-v3-c3
status: torndown
timestamp: 2024-09-24T03:41:37+00:00
num_battles: 21067
num_wins: 11836
celo_rating: 1282.9
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/nemo-p-e-v3-c3
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6081385997801666, 'latency_mean': 1.644265273809433, 'latency_p50': 1.6503911018371582, 'latency_p90': 1.8188803672790528}, {'batch_size': 3, 'throughput': 1.0690599244678265, 'latency_mean': 2.7988870668411256, 'latency_p50': 2.7967071533203125, 'latency_p90': 3.1371275186538696}, {'batch_size': 5, 'throughput': 1.227206550193427, 'latency_mean': 4.055158026218415, 'latency_p50': 4.053181052207947, 'latency_p90': 4.49225013256073}, {'batch_size': 6, 'throughput': 1.2523300825083286, 'latency_mean': 4.771094799041748, 'latency_p50': 4.796989679336548, 'latency_p90': 5.4098138332366945}, {'batch_size': 8, 'throughput': 1.2346134317412385, 'latency_mean': 6.444566783905029, 'latency_p50': 6.446216702461243, 'latency_p90': 7.332075595855713}, {'batch_size': 10, 'throughput': 1.2028888312929618, 'latency_mean': 8.256282178163529, 'latency_p50': 8.336342692375183, 'latency_p90': 9.275464725494384}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: auto
is_internal_developer: False
language_model: cycy233/nemo-p-e-v3-c3
model_size: 13B
ranking_group: single
throughput_3p7s: 1.2
us_pacific_date: 2024-09-23
win_ratio: 0.56182655337732
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-e-v3-c3-v1-mkmlizer
Waiting for job on cycy233-nemo-p-e-v3-c3-v1-mkmlizer to finish
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
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: ║ _____ __ __ ║
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: ║ /___/ ║
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: ║ ║
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: ║ Version: 0.10.1 ║
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: ║ ║
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: ║ belonging to: ║
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: ║ ║
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: ║ ║
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: Downloaded to shared memory in 51.113s
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppux4jdj5, device:0
cycy233-nemo-p-e-v3-c3-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
Failed to get response for submission blend_gilel_2024-09-20: ('http://chaiml-elo-alignment-run-3-v44-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:58952->127.0.0.1:8080: read: connection reset by peer\n')
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: quantized model in 37.347s
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: Processed model cycy233/nemo-p-e-v3-c3 in 88.461s
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-nemo-p-e-v3-c3-v1
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-nemo-p-e-v3-c3-v1/config.json
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-nemo-p-e-v3-c3-v1/special_tokens_map.json
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-nemo-p-e-v3-c3-v1/tokenizer_config.json
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-nemo-p-e-v3-c3-v1/tokenizer.json
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-nemo-p-e-v3-c3-v1/flywheel_model.0.safetensors
cycy233-nemo-p-e-v3-c3-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 28.76it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:07, 45.76it/s] Loading 0: 5%|▍ | 18/363 [00:00<00:08, 42.72it/s] Loading 0: 6%|▋ | 23/363 [00:00<00:10, 32.44it/s] Loading 0: 8%|▊ | 30/363 [00:00<00:08, 41.40it/s] Loading 0: 10%|▉ | 35/363 [00:00<00:08, 40.92it/s] Loading 0: 11%|█ | 40/363 [00:01<00:07, 41.35it/s] Loading 0: 13%|█▎ | 46/363 [00:01<00:07, 40.64it/s] Loading 0: 14%|█▍ | 51/363 [00:01<00:07, 40.41it/s] Loading 0: 16%|█▋ | 59/363 [00:01<00:06, 49.43it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:09, 29.94it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:08, 35.89it/s] Loading 0: 21%|██ | 77/363 [00:02<00:07, 36.91it/s] Loading 0: 23%|██▎ | 82/363 [00:02<00:08, 32.88it/s] Loading 0: 25%|██▍ | 89/363 [00:02<00:06, 40.29it/s] Loading 0: 26%|██▌ | 94/363 [00:02<00:06, 41.42it/s] Loading 0: 27%|██▋ | 99/363 [00:02<00:06, 42.84it/s] Loading 0: 29%|██▊ | 104/363 [00:02<00:05, 43.95it/s] Loading 0: 30%|███ | 110/363 [00:02<00:05, 43.04it/s] Loading 0: 32%|███▏ | 115/363 [00:02<00:05, 44.44it/s] Loading 0: 33%|███▎ | 120/363 [00:03<00:05, 42.54it/s] Loading 0: 35%|███▍ | 126/363 [00:03<00:05, 44.21it/s] Loading 0: 36%|███▌ | 131/363 [00:03<00:05, 45.33it/s] Loading 0: 37%|███▋ | 136/363 [00:03<00:05, 39.33it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 32.90it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 33.84it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 33.24it/s] Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 38.53it/s] Loading 0: 44%|████▍ | 161/363 [00:04<00:05, 40.07it/s] Loading 0: 46%|████▌ | 166/363 [00:04<00:04, 40.90it/s] Loading 0: 47%|████▋ | 172/363 [00:04<00:04, 41.26it/s] Loading 0: 49%|████▉ | 177/363 [00:04<00:04, 40.95it/s] Loading 0: 50%|█████ | 183/363 [00:04<00:03, 45.58it/s] Loading 0: 52%|█████▏ | 188/363 [00:04<00:03, 46.02it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 46.39it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 44.76it/s] Loading 0: 56%|█████▌ | 204/363 [00:05<00:03, 41.90it/s] Loading 0: 58%|█████▊ | 210/363 [00:05<00:03, 45.88it/s] Loading 0: 59%|█████▉ | 215/363 [00:05<00:03, 43.53it/s] Loading 0: 61%|██████ | 221/363 [00:05<00:03, 47.27it/s] Loading 0: 62%|██████▏ | 226/363 [00:05<00:05, 27.22it/s] Loading 0: 63%|██████▎ | 230/363 [00:05<00:04, 26.83it/s] Loading 0: 65%|██████▌ | 237/363 [00:06<00:03, 33.41it/s] Loading 0: 67%|██████▋ | 242/363 [00:06<00:03, 34.71it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:03, 36.33it/s] Loading 0: 69%|██████▉ | 252/363 [00:06<00:02, 37.97it/s] Loading 0: 71%|███████ | 257/363 [00:06<00:03, 30.79it/s] Loading 0: 73%|███████▎ | 264/363 [00:06<00:02, 37.51it/s] Loading 0: 74%|███████▍ | 269/363 [00:06<00:02, 37.44it/s] Loading 0: 75%|███████▌ | 274/363 [00:07<00:02, 37.81it/s] Loading 0: 77%|███████▋ | 279/363 [00:07<00:02, 39.80it/s] Loading 0: 78%|███████▊ | 284/363 [00:07<00:02, 33.38it/s] Loading 0: 80%|████████ | 291/363 [00:07<00:01, 39.81it/s] Loading 0: 82%|████████▏ | 296/363 [00:07<00:01, 39.11it/s] Loading 0: 83%|████████▎ | 301/363 [00:07<00:01, 40.81it/s] Loading 0: 84%|████████▍ | 306/363 [00:14<00:23, 2.40it/s] Loading 0: 85%|████████▌ | 310/363 [00:14<00:17, 3.11it/s] Loading 0: 87%|████████▋ | 314/363 [00:14<00:12, 4.08it/s] Loading 0: 88%|████████▊ | 320/363 [00:15<00:07, 6.09it/s] Loading 0: 90%|████████▉ | 326/363 [00:15<00:04, 8.56it/s] Loading 0: 91%|█████████ | 330/363 [00:15<00:03, 10.48it/s] Loading 0: 93%|█████████▎| 338/363 [00:15<00:01, 16.16it/s] Loading 0: 95%|█████████▍| 344/363 [00:15<00:00, 19.99it/s] Loading 0: 96%|█████████▌| 349/363 [00:15<00:00, 23.21it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 29.52it/s] Loading 0: 99%|█████████▉| 361/363 [00:15<00:00, 33.02it/s]
Job cycy233-nemo-p-e-v3-c3-v1-mkmlizer completed after 114.83s with status: succeeded
Stopping job with name cycy233-nemo-p-e-v3-c3-v1-mkmlizer
Pipeline stage MKMLizer completed in 117.45s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-nemo-p-e-v3-c3-v1
Waiting for inference service cycy233-nemo-p-e-v3-c3-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
Inference service cycy233-nemo-p-e-v3-c3-v1 ready after 201.98053169250488s
Pipeline stage MKMLDeployer completed in 202.38s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.4648077487945557s
Received healthy response to inference request in 2.31524658203125s
Received healthy response to inference request in 1.788050889968872s
Received healthy response to inference request in 1.9831466674804688s
Received healthy response to inference request in 3.601731538772583s
5 requests
0 failed requests
5th percentile: 1.8270700454711915
10th percentile: 1.8660892009735108
20th percentile: 1.9441275119781494
30th percentile: 2.049566650390625
40th percentile: 2.1824066162109377
50th percentile: 2.31524658203125
60th percentile: 2.775071048736572
70th percentile: 3.2348955154418944
80th percentile: 3.492192506790161
90th percentile: 3.546962022781372
95th percentile: 3.5743467807769775
99th percentile: 3.596254587173462
mean time: 2.6305966854095457
Pipeline stage StressChecker completed in 14.39s
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
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.55s
Shutdown handler de-registered
cycy233-nemo-p-e-v3-c3_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 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cycy233-nemo-p-e-v3-c3-v1-profiler
Waiting for inference service cycy233-nemo-p-e-v3-c3-v1-profiler to be ready
Inference service cycy233-nemo-p-e-v3-c3-v1-profiler ready after 200.46299147605896s
Pipeline stage MKMLProfilerDeployer completed in 200.86s
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-v3-c3-v1-profiler-predictor-00001-deploymx2d7j:/code/chaiverse_profiler_1727149893 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-nemo-p-e-v3-c3-v1-profiler-predictor-00001-deploymx2d7j --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727149893 && 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_1727149893/summary.json'
kubectl exec -it cycy233-nemo-p-e-v3-c3-v1-profiler-predictor-00001-deploymx2d7j --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727149893/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1172.42s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-nemo-p-e-v3-c3-v1-profiler is running
Tearing down inference service cycy233-nemo-p-e-v3-c3-v1-profiler
Service cycy233-nemo-p-e-v3-c3-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.17s
Shutdown handler de-registered
cycy233-nemo-p-e-v3-c3_v1 status is now inactive due to auto deactivation removed underperforming models
cycy233-nemo-p-e-v3-c3_v1 status is now torndown due to DeploymentManager action