submission_id: cycy233-nemo-p-v1-c2_v2
developer_uid: shiroe40
best_of: 8
celo_rating: 1233.56
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': 512, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: cycy233/nemo-p-v1-c2
latencies: [{'batch_size': 1, 'throughput': 0.6836448490612167, 'latency_mean': 1.462681667804718, 'latency_p50': 1.467315912246704, 'latency_p90': 1.6152836561203003}, {'batch_size': 3, 'throughput': 1.3101246077308077, 'latency_mean': 2.282876043319702, 'latency_p50': 2.2756210565567017, 'latency_p90': 2.543252730369568}, {'batch_size': 5, 'throughput': 1.5323651193865484, 'latency_mean': 3.2482148027420044, 'latency_p50': 3.2518198490142822, 'latency_p90': 3.6768850326538085}, {'batch_size': 6, 'throughput': 1.5855263263839516, 'latency_mean': 3.771814466714859, 'latency_p50': 3.7761868238449097, 'latency_p90': 4.231075429916381}, {'batch_size': 8, 'throughput': 1.575778391301235, 'latency_mean': 5.036806298494339, 'latency_p50': 5.086249351501465, 'latency_p90': 5.679666972160339}, {'batch_size': 10, 'throughput': 1.5301859964787952, 'latency_mean': 6.4929718124866485, 'latency_p50': 6.5314013957977295, 'latency_p90': 7.4537567615509035}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: cycy233/nemo-p-v1-c2
model_name: auto
model_num_parameters: 12772070400.0
model_repo: cycy233/nemo-p-v1-c2
model_size: 13B
num_battles: 10129
num_wins: 4799
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 1.58
timestamp: 2024-09-18T01:46:58+00:00
us_pacific_date: 2024-09-17
win_ratio: 0.47378813308322637
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-v1-c2-v2-mkmlizer
Waiting for job on cycy233-nemo-p-v1-c2-v2-mkmlizer to finish
cycy233-nemo-p-v1-c2-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-nemo-p-v1-c2-v2-mkmlizer: ║ _____ __ __ ║
cycy233-nemo-p-v1-c2-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-nemo-p-v1-c2-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-nemo-p-v1-c2-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-nemo-p-v1-c2-v2-mkmlizer: ║ /___/ ║
cycy233-nemo-p-v1-c2-v2-mkmlizer: ║ ║
cycy233-nemo-p-v1-c2-v2-mkmlizer: ║ Version: 0.10.1 ║
cycy233-nemo-p-v1-c2-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-nemo-p-v1-c2-v2-mkmlizer: ║ https://mk1.ai ║
cycy233-nemo-p-v1-c2-v2-mkmlizer: ║ ║
cycy233-nemo-p-v1-c2-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-nemo-p-v1-c2-v2-mkmlizer: ║ belonging to: ║
cycy233-nemo-p-v1-c2-v2-mkmlizer: ║ ║
cycy233-nemo-p-v1-c2-v2-mkmlizer: ║ Chai Research Corp. ║
cycy233-nemo-p-v1-c2-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-nemo-p-v1-c2-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-nemo-p-v1-c2-v2-mkmlizer: ║ ║
cycy233-nemo-p-v1-c2-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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-v1-c2-v2-mkmlizer: Downloaded to shared memory in 35.763s
cycy233-nemo-p-v1-c2-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpg7wsy9t0, device:0
cycy233-nemo-p-v1-c2-v2-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
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-v1-c2-v2-mkmlizer: quantized model in 36.166s
cycy233-nemo-p-v1-c2-v2-mkmlizer: Processed model cycy233/nemo-p-v1-c2 in 71.930s
cycy233-nemo-p-v1-c2-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-nemo-p-v1-c2-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-nemo-p-v1-c2-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-nemo-p-v1-c2-v2
cycy233-nemo-p-v1-c2-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-nemo-p-v1-c2-v2/config.json
cycy233-nemo-p-v1-c2-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-nemo-p-v1-c2-v2/special_tokens_map.json
cycy233-nemo-p-v1-c2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-nemo-p-v1-c2-v2/tokenizer_config.json
cycy233-nemo-p-v1-c2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-nemo-p-v1-c2-v2/tokenizer.json
cycy233-nemo-p-v1-c2-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-nemo-p-v1-c2-v2/flywheel_model.0.safetensors
cycy233-nemo-p-v1-c2-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 4/363 [00:00<00:10, 33.93it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:05, 63.63it/s] Loading 0: 6%|▌ | 22/363 [00:00<00:04, 71.78it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:04, 69.68it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:03, 82.50it/s] Loading 0: 14%|█▍ | 51/363 [00:00<00:04, 73.53it/s] Loading 0: 16%|█▋ | 59/363 [00:00<00:04, 75.12it/s] Loading 0: 18%|█▊ | 67/363 [00:01<00:15, 19.24it/s] Loading 0: 21%|██ | 76/363 [00:02<00:11, 25.38it/s] Loading 0: 23%|██▎ | 85/363 [00:02<00:08, 31.38it/s] Loading 0: 26%|██▌ | 94/363 [00:02<00:06, 38.51it/s] Loading 0: 29%|██▉ | 106/363 [00:02<00:05, 47.03it/s] Loading 0: 33%|███▎ | 121/363 [00:02<00:03, 60.63it/s] Loading 0: 37%|███▋ | 133/363 [00:02<00:03, 67.60it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:09, 23.24it/s] Loading 0: 42%|████▏ | 151/363 [00:04<00:07, 28.71it/s] Loading 0: 44%|████▍ | 160/363 [00:04<00:05, 34.26it/s] Loading 0: 47%|████▋ | 169/363 [00:04<00:04, 40.13it/s] Loading 0: 49%|████▉ | 178/363 [00:04<00:04, 45.85it/s] Loading 0: 52%|█████▏ | 187/363 [00:04<00:03, 51.29it/s] Loading 0: 56%|█████▌ | 202/363 [00:04<00:02, 65.57it/s] Loading 0: 59%|█████▉ | 214/363 [00:04<00:02, 70.40it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:05, 23.74it/s] Loading 0: 64%|██████▍ | 232/363 [00:06<00:04, 28.55it/s] Loading 0: 66%|██████▋ | 241/363 [00:06<00:03, 33.16it/s] Loading 0: 69%|██████▉ | 250/363 [00:06<00:02, 39.19it/s] Loading 0: 71%|███████▏ | 259/363 [00:06<00:02, 45.49it/s] Loading 0: 74%|███████▍ | 268/363 [00:06<00:01, 49.19it/s] Loading 0: 78%|███████▊ | 283/363 [00:06<00:01, 63.06it/s] Loading 0: 81%|████████▏ | 295/363 [00:06<00:00, 69.62it/s] Loading 0: 84%|████████▎ | 304/363 [00:07<00:02, 24.48it/s] Loading 0: 88%|████████▊ | 319/363 [00:08<00:01, 34.65it/s] Loading 0: 91%|█████████ | 331/363 [00:08<00:00, 42.43it/s] Loading 0: 94%|█████████▎| 340/363 [00:08<00:00, 48.37it/s] Loading 0: 96%|█████████▌| 349/363 [00:08<00:00, 54.14it/s] Loading 0: 100%|██████████| 363/363 [00:14<00:00, 5.58it/s]
Job cycy233-nemo-p-v1-c2-v2-mkmlizer completed after 105.34s with status: succeeded
Stopping job with name cycy233-nemo-p-v1-c2-v2-mkmlizer
Pipeline stage MKMLizer completed in 106.59s
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-v1-c2-v2
Waiting for inference service cycy233-nemo-p-v1-c2-v2 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
Failed to get response for submission function_sabet_2024-09-10: ('http://chaiml-llama-8b-pairwis-8189-v27-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:43142->127.0.0.1:8080: read: connection reset by peer\n')
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-v1-c2-v2 ready after 181.140643119812s
Pipeline stage MKMLDeployer completed in 182.06s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.04421067237854s
Received healthy response to inference request in 2.524914026260376s
Received healthy response to inference request in 2.3206236362457275s
Received healthy response to inference request in 2.1821646690368652s
Received healthy response to inference request in 2.104914426803589s
5 requests
0 failed requests
5th percentile: 2.120364475250244
10th percentile: 2.1358145236968995
20th percentile: 2.16671462059021
30th percentile: 2.209856462478638
40th percentile: 2.2652400493621827
50th percentile: 2.3206236362457275
60th percentile: 2.402339792251587
70th percentile: 2.4840559482574465
80th percentile: 2.6287733554840087
90th percentile: 2.8364920139312746
95th percentile: 2.9403513431549073
99th percentile: 3.0234388065338136
mean time: 2.4353654861450194
Pipeline stage StressChecker completed in 12.96s
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 5.68s
Shutdown handler de-registered
cycy233-nemo-p-v1-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 0.14s
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-v1-c2-v2-profiler
Waiting for inference service cycy233-nemo-p-v1-c2-v2-profiler to be ready
Inference service cycy233-nemo-p-v1-c2-v2-profiler ready after 190.4679775238037s
Pipeline stage MKMLProfilerDeployer completed in 190.86s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-nemo-p-v1-c2-v2-profiler-predictor-00001-deploymenbvz4g:/code/chaiverse_profiler_1726624559 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-nemo-p-v1-c2-v2-profiler-predictor-00001-deploymenbvz4g --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726624559 && 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_1726624559/summary.json'
kubectl exec -it cycy233-nemo-p-v1-c2-v2-profiler-predictor-00001-deploymenbvz4g --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726624559/summary.json'
Pipeline stage MKMLProfilerRunner completed in 963.82s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-nemo-p-v1-c2-v2-profiler is running
Tearing down inference service cycy233-nemo-p-v1-c2-v2-profiler
Service cycy233-nemo-p-v1-c2-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.92s
Shutdown handler de-registered
cycy233-nemo-p-v1-c2_v2 status is now inactive due to auto deactivation removed underperforming models
cycy233-nemo-p-v1-c2_v2 status is now torndown due to DeploymentManager action
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