cycy233-nemo-p-v0-c1

submission_id: cycy233-nemo-p-v0-c1_v2

developer_uid: shiroe40

best_of: 8

celo_rating: 1228.71

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-c1

latencies: [{'batch_size': 1, 'throughput': 0.6963016688385947, 'latency_mean': 1.4360660791397095, 'latency_p50': 1.427552342414856, 'latency_p90': 1.5976887941360474}, {'batch_size': 3, 'throughput': 1.3241324270071235, 'latency_mean': 2.257511019706726, 'latency_p50': 2.234301447868347, 'latency_p90': 2.5056326627731322}, {'batch_size': 5, 'throughput': 1.560364623118732, 'latency_mean': 3.186424843072891, 'latency_p50': 3.1821110248565674, 'latency_p90': 3.553792452812195}, {'batch_size': 6, 'throughput': 1.6256989601575336, 'latency_mean': 3.673662030696869, 'latency_p50': 3.681315064430237, 'latency_p90': 4.184092998504639}, {'batch_size': 8, 'throughput': 1.6077108780578009, 'latency_mean': 4.939994498491287, 'latency_p50': 4.954593300819397, 'latency_p90': 5.64493248462677}, {'batch_size': 10, 'throughput': 1.5451408368484443, 'latency_mean': 6.437673147916794, 'latency_p50': 6.445868730545044, 'latency_p90': 7.433190965652466}]

max_input_tokens: 512

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: cycy233/nemo-p-v0-c1

model_name: auto

model_num_parameters: 12772070400.0

model_repo: cycy233/nemo-p-v0-c1

model_size: 13B

num_battles: 11017

num_wins: 5139

ranking_group: single

status: torndown

submission_type: basic

throughput_3p7s: 1.63

timestamp: 2024-09-15T08:02:37+00:00

us_pacific_date: 2024-09-15

win_ratio: 0.4664609240265045

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-c1-v2-mkmlizer
Waiting for job on cycy233-nemo-p-v0-c1-v2-mkmlizer to finish
cycy233-nemo-p-v0-c1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-nemo-p-v0-c1-v2-mkmlizer: ║     _____            __           __                                ║
cycy233-nemo-p-v0-c1-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-nemo-p-v0-c1-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-nemo-p-v0-c1-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-nemo-p-v0-c1-v2-mkmlizer: ║       /___/                                                         ║
cycy233-nemo-p-v0-c1-v2-mkmlizer: ║                                                                     ║
cycy233-nemo-p-v0-c1-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
cycy233-nemo-p-v0-c1-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-nemo-p-v0-c1-v2-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-nemo-p-v0-c1-v2-mkmlizer: ║                                                                     ║
cycy233-nemo-p-v0-c1-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-nemo-p-v0-c1-v2-mkmlizer: ║  belonging to:                                                      ║
cycy233-nemo-p-v0-c1-v2-mkmlizer: ║                                                                     ║
cycy233-nemo-p-v0-c1-v2-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-nemo-p-v0-c1-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-nemo-p-v0-c1-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-nemo-p-v0-c1-v2-mkmlizer: ║                                                                     ║
cycy233-nemo-p-v0-c1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-nemo-p-v0-c1-v2-mkmlizer: Downloaded to shared memory in 33.018s
cycy233-nemo-p-v0-c1-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpna7bm8y4, device:0
cycy233-nemo-p-v0-c1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-nemo-p-v0-c1-v2-mkmlizer: quantized model in 36.228s
cycy233-nemo-p-v0-c1-v2-mkmlizer: Processed model cycy233/nemo-p-v0-c1 in 69.246s
cycy233-nemo-p-v0-c1-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-nemo-p-v0-c1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-nemo-p-v0-c1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-nemo-p-v0-c1-v2
cycy233-nemo-p-v0-c1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-nemo-p-v0-c1-v2/config.json
cycy233-nemo-p-v0-c1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-nemo-p-v0-c1-v2/special_tokens_map.json
cycy233-nemo-p-v0-c1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-nemo-p-v0-c1-v2/tokenizer_config.json
cycy233-nemo-p-v0-c1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-nemo-p-v0-c1-v2/tokenizer.json
cycy233-nemo-p-v0-c1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-nemo-p-v0-c1-v2/flywheel_model.0.safetensors
cycy233-nemo-p-v0-c1-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 39.23it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:05, 68.60it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:04, 76.35it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:04, 81.43it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:04, 78.44it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:04, 71.42it/s]
Loading 0:  16%|█▌        | 58/363 [00:00<00:04, 67.30it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:16, 17.75it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:14, 19.77it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 26.81it/s]
Loading 0:  24%|██▍       | 88/363 [00:02<00:08, 34.34it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:06, 42.27it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:05, 50.21it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:04, 58.21it/s]
Loading 0:  34%|███▍      | 124/363 [00:02<00:03, 65.16it/s]
Loading 0:  37%|███▋      | 133/363 [00:02<00:03, 69.47it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:10, 20.12it/s]
Loading 0:  42%|████▏     | 151/363 [00:04<00:08, 25.82it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:06, 31.72it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 37.96it/s]
Loading 0:  49%|████▉     | 178/363 [00:04<00:04, 43.64it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:03, 53.26it/s]
Loading 0:  54%|█████▍    | 196/363 [00:04<00:02, 57.72it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:02, 72.61it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:05, 25.36it/s]
Loading 0:  64%|██████▍   | 232/363 [00:06<00:04, 30.69it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 36.96it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 49.17it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:01, 54.76it/s]
Loading 0:  76%|███████▌  | 275/363 [00:06<00:01, 62.85it/s]
Loading 0:  79%|███████▉  | 286/363 [00:06<00:01, 66.31it/s]
Loading 0:  83%|████████▎ | 301/363 [00:06<00:00, 76.59it/s]
Loading 0:  85%|████████▌ | 310/363 [00:08<00:02, 24.23it/s]
Loading 0:  89%|████████▊ | 322/363 [00:08<00:01, 31.48it/s]
Loading 0:  93%|█████████▎| 337/363 [00:08<00:00, 42.47it/s]
Loading 0:  96%|█████████▌| 349/363 [00:08<00:00, 49.95it/s]
Loading 0: 100%|██████████| 363/363 [00:14<00:00,  6.07it/s]
                                                            
Job cycy233-nemo-p-v0-c1-v2-mkmlizer completed after 94.95s with status: succeeded
Stopping job with name cycy233-nemo-p-v0-c1-v2-mkmlizer
Pipeline stage MKMLizer completed in 95.98s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-nemo-p-v0-c1-v2
Waiting for inference service cycy233-nemo-p-v0-c1-v2 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
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', '')
Inference service cycy233-nemo-p-v0-c1-v2 ready after 170.70151090621948s
Pipeline stage MKMLDeployer completed in 171.08s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6319684982299805s
Received healthy response to inference request in 2.3214261531829834s
Received healthy response to inference request in 2.3220558166503906s
Received healthy response to inference request in 2.594550609588623s
Received healthy response to inference request in 2.3338639736175537s
5 requests
0 failed requests
5th percentile: 2.3215520858764647
10th percentile: 2.3216780185699464
20th percentile: 2.3219298839569094
30th percentile: 2.3244174480438233
40th percentile: 2.3291407108306883
50th percentile: 2.3338639736175537
60th percentile: 2.4381386280059814
70th percentile: 2.542413282394409
80th percentile: 2.6020341873168946
90th percentile: 2.6170013427734373
95th percentile: 2.624484920501709
99th percentile: 2.6304717826843262
mean time: 2.4407730102539062
Pipeline stage StressChecker completed in 15.87s
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 5.65s
Shutdown handler de-registered
cycy233-nemo-p-v0-c1_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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cycy233-nemo-p-v0-c1-v2-profiler
Waiting for inference service cycy233-nemo-p-v0-c1-v2-profiler to be ready
Inference service cycy233-nemo-p-v0-c1-v2-profiler ready after 160.3837535381317s
Pipeline stage MKMLProfilerDeployer completed in 160.86s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-nemo-p-v0-c1-v2-profiler-predictor-00001-deploymenqn629:/code/chaiverse_profiler_1726387860 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-nemo-p-v0-c1-v2-profiler-predictor-00001-deploymenqn629 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726387860 && 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_1726387860/summary.json'
kubectl exec -it cycy233-nemo-p-v0-c1-v2-profiler-predictor-00001-deploymenqn629 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726387860/summary.json'
Pipeline stage MKMLProfilerRunner completed in 951.67s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-nemo-p-v0-c1-v2-profiler is running
Tearing down inference service cycy233-nemo-p-v0-c1-v2-profiler
Service cycy233-nemo-p-v0-c1-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.84s
Shutdown handler de-registered
cycy233-nemo-p-v0-c1_v2 status is now inactive due to auto deactivation removed underperforming models
cycy233-nemo-p-v0-c1_v2 status is now torndown due to DeploymentManager action
Shutdown handler de-registered
Running pipeline stage MKMLDeleter
Pipeline stage MKMLModelDeleter completed in 3.26s
run pipeline stage %s
run pipeline %s
Running pipeline stage MKMLModelDeleter
run pipeline stage %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of cycy233-nemo-p-v0-c1_v2
Pipeline stage MKMLDeleter completed in 3.23s
Pipeline stage %s skipped, reason=%s
cycy233-l3-p-v4-c4_v1 status is now torndown due to DeploymentManager action
cycy233-l3-p-v4-c4_v1 status is now torndown due to DeploymentManager action
Pipeline stage MKMLModelDeleter completed in 3.45s
Shutdown handler de-registered
Running pipeline stage MKMLDeleter
run pipeline stage %s
Running pipeline stage MKMLModelDeleter
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 3.16s
admin requested tearing down of cycy233-nemo-p-v0-c2_v1
Pipeline stage %s skipped, reason=%s
Shutdown handler de-registered
Running pipeline stage MKMLDeleter
Pipeline stage MKMLModelDeleter completed in 3.29s
cycy233-l3-p-v5-c1_v3 status is now torndown due to DeploymentManager action
run pipeline %s
Running pipeline stage MKMLModelDeleter
run pipeline stage %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage MKMLDeleter completed in 3.02s
admin requested tearing down of cycy233-nemo-p-v0-c2_v2
cycy233-l3-p-v5-c2_v3 status is now torndown due to DeploymentManager action
Pipeline stage %s skipped, reason=%s
Shutdown handler de-registered
Pipeline stage MKMLModelDeleter completed in 3.49s
Running pipeline stage MKMLDeleter
run pipeline stage %s
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLModelDeleter
run pipeline %s
run pipeline stage %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of cycy233-nemo-p-v0-c3_v1
Pipeline stage MKMLDeleter completed in 3.57s
cycy233-l3-p-v5-c3_v3 status is now torndown due to DeploymentManager action
Shutdown handler de-registered
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLDeleter
Pipeline stage MKMLModelDeleter completed in 3.69s
Pipeline stage %s skipped, reason=%s
run pipeline stage %s
Running pipeline stage MKMLModelDeleter
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of cycy233-nemo-p-v0-c3_v2
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 3.48s
Pipeline stage %s skipped, reason=%s
cycy233-l3-p-v5-c4_v3 status is now torndown due to DeploymentManager action
Shutdown handler de-registered
Pipeline stage MKMLModelDeleter completed in 3.42s
Running pipeline stage MKMLDeleter
Pipeline stage %s skipped, reason=%s
run pipeline stage %s
run pipeline %s
Running pipeline stage MKMLModelDeleter
admin requested tearing down of cycy233-nemo-p-v1-c1_v1
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 3.40s
cycy233-nemo-p-e-v0-c1_v1 status is now torndown due to DeploymentManager action
Shutdown handler de-registered
Pipeline stage MKMLModelDeleter completed in 3.27s
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLDeleter
run pipeline stage %s
Pipeline stage %s skipped, reason=%s
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline stage %s
Shutdown handler de-registered
Pipeline stage MKMLDeleter completed in 3.93s
cycy233-nemo-p-e-v0-c2_v1 status is now torndown due to DeploymentManager action
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLDeleter
Pipeline stage MKMLModelDeleter completed in 3.97s
run pipeline stage %s
run pipeline %s
Pipeline stage %s skipped, reason=%s
admin requested tearing down of cycy233-nemo-p-v1-c2_v2
cycy233-nemo-p-e-v0-c3_v1 status is now torndown due to DeploymentManager action
run pipeline stage %s
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLDeleter completed in 3.93s
Shutdown handler de-registered
Running pipeline stage MKMLDeleter
run pipeline stage %s
Pipeline stage MKMLModelDeleter completed in 3.93s
run pipeline %s
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLModelDeleter
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage MKMLDeleter completed in 2.99s
run pipeline stage %s
cycy233-nemo-p-e-v0-c4_v1 status is now torndown due to DeploymentManager action
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLDeleter
Shutdown handler de-registered
run pipeline stage %s
Pipeline stage MKMLModelDeleter completed in 3.49s
Pipeline stage %s skipped, reason=%s
run pipeline %s
run pipeline stage %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Running pipeline stage MKMLModelDeleter
admin requested tearing down of cycy233-nemo-p-v1-c4_v2
Pipeline stage MKMLDeleter completed in 3.54s
Running pipeline stage MKMLDeleter
cycy233-nemo-p-v0-c1_v1 status is now torndown due to DeploymentManager action
Shutdown handler de-registered
Pipeline stage MKMLModelDeleter completed in 3.34s
run pipeline stage %s
Running pipeline stage MKMLModelDeleter
run pipeline %s
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLDeleter completed in 3.22s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of cycy233-nemo-p-v2-c2_v1
run pipeline stage %s
Pipeline stage %s skipped, reason=%s
Shutdown handler de-registered
run pipeline %s
Running pipeline stage MKMLModelDeleter
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLDeleter completed in 3.22s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of cycy233-nemo-p-v2-c2_v1
Pipeline stage %s skipped, reason=%s
Shutdown handler de-registered
cycy233-nemo-p-v0-c1_v2 status is now torndown due to DeploymentManager action
Running pipeline stage MKMLDeleter
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLModelDeleter completed in 3.61s