chaiml-elite-feed-convo-_7085

developer_uid: zonemercy

submission_id: chaiml-elite-feed-convo-_7085_v2

model_name: chaiml-elite-feed-convo-_7085_v2

model_group: ChaiML/Elite-Feed-Convo-

status: torndown

timestamp: 2024-09-12T16:35:59+00:00

num_battles: 10869

num_wins: 5618

celo_rating: 1256.68

family_friendly_score: 0.0

submission_type: basic

model_repo: ChaiML/Elite-Feed-Convo-v2-1e5ep2

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6136136289667327, 'latency_mean': 1.6295950305461884, 'latency_p50': 1.627041220664978, 'latency_p90': 1.7920935869216919}, {'batch_size': 3, 'throughput': 1.083715594656152, 'latency_mean': 2.7596682691574097, 'latency_p50': 2.787343382835388, 'latency_p90': 3.0381842136383055}, {'batch_size': 5, 'throughput': 1.2236901775336786, 'latency_mean': 4.07181068778038, 'latency_p50': 4.063044428825378, 'latency_p90': 4.580924224853516}, {'batch_size': 6, 'throughput': 1.2513496251392788, 'latency_mean': 4.778708422183991, 'latency_p50': 4.797297120094299, 'latency_p90': 5.465224170684815}, {'batch_size': 8, 'throughput': 1.231450418626903, 'latency_mean': 6.4618465769290925, 'latency_p50': 6.475474238395691, 'latency_p90': 7.283308315277099}, {'batch_size': 10, 'throughput': 1.20351007742247, 'latency_mean': 8.261807507276535, 'latency_p50': 8.329431891441345, 'latency_p90': 9.321661853790284}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-elite-feed-convo-_7085_v2

is_internal_developer: True

language_model: ChaiML/Elite-Feed-Convo-v2-1e5ep2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.2

us_pacific_date: 2024-09-12

win_ratio: 0.5168828779096513

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>', 'Bot:', 'User:', 'You:', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "Bot's name: {bot_name}\nBot never initiate sex act unless User started first in the conversation\n####\n", 'prompt_template': '', 'bot_template': 'Bot: {message}</s>', 'user_template': 'User: {message}</s>', 'response_template': 'Bot:', 'truncate_by_message': True}

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 chaiml-elite-feed-convo-7085-v2-mkmlizer
Waiting for job on chaiml-elite-feed-convo-7085-v2-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
chaiml-elite-feed-convo-7085-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elite-feed-convo-7085-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-elite-feed-convo-7085-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-elite-feed-convo-7085-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-elite-feed-convo-7085-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-elite-feed-convo-7085-v2-mkmlizer: ║       /___/                                                         ║
chaiml-elite-feed-convo-7085-v2-mkmlizer: ║                                                                     ║
chaiml-elite-feed-convo-7085-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
chaiml-elite-feed-convo-7085-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-elite-feed-convo-7085-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-elite-feed-convo-7085-v2-mkmlizer: ║                                                                     ║
chaiml-elite-feed-convo-7085-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-elite-feed-convo-7085-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-elite-feed-convo-7085-v2-mkmlizer: ║                                                                     ║
chaiml-elite-feed-convo-7085-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-elite-feed-convo-7085-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-elite-feed-convo-7085-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-elite-feed-convo-7085-v2-mkmlizer: ║                                                                     ║
chaiml-elite-feed-convo-7085-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-elite-feed-convo-7085-v2-mkmlizer: Downloaded to shared memory in 69.547s
chaiml-elite-feed-convo-7085-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpen8fjpyr, device:0
chaiml-elite-feed-convo-7085-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elite-feed-convo-7085-v2-mkmlizer: quantized model in 40.699s
chaiml-elite-feed-convo-7085-v2-mkmlizer: Processed model ChaiML/Elite-Feed-Convo-v2-1e5ep2 in 110.246s
chaiml-elite-feed-convo-7085-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elite-feed-convo-7085-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elite-feed-convo-7085-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elite-feed-convo-7085-v2
chaiml-elite-feed-convo-7085-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elite-feed-convo-7085-v2/tokenizer_config.json
chaiml-elite-feed-convo-7085-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elite-feed-convo-7085-v2/tokenizer.json
chaiml-elite-feed-convo-7085-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elite-feed-convo-7085-v2/flywheel_model.0.safetensors
chaiml-elite-feed-convo-7085-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:14, 24.45it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 29.29it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 25.34it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:10, 31.90it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:14, 23.60it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:16, 20.78it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:12, 26.61it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:11, 27.91it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 28.59it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 28.10it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.99it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 29.75it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 29.02it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 25.74it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 22.79it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:09, 29.44it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:10, 28.30it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:10, 26.37it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:09, 29.13it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 26.29it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 33.03it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 30.77it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 24.18it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:11, 21.94it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:08, 28.52it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:08, 28.17it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 30.39it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 29.43it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 31.87it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 30.48it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 30.19it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 26.26it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:08, 24.67it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 23.48it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:06, 30.22it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:06, 29.11it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.20it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 29.47it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 31.68it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 30.29it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 24.60it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:08, 21.69it/s]
Loading 0:  52%|█████▏    | 190/363 [00:06<00:06, 26.97it/s]
Loading 0:  53%|█████▎    | 194/363 [00:07<00:06, 25.06it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 31.71it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 30.13it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 32.05it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:04, 30.06it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 30.32it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 26.20it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 24.86it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 23.36it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 29.66it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 28.73it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 31.11it/s]
Loading 0:  69%|██████▉   | 250/363 [00:08<00:03, 29.42it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 31.29it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 30.15it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 24.61it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 22.24it/s]
Loading 0:  75%|███████▌  | 273/363 [00:09<00:03, 29.04it/s]
Loading 0:  76%|███████▋  | 277/363 [00:09<00:03, 28.60it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 31.18it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 29.25it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 31.40it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 29.70it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 29.57it/s]
Loading 0:  84%|████████▎ | 304/363 [00:10<00:02, 26.33it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 25.11it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 23.67it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 30.56it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 29.82it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 31.45it/s]
Loading 0:  91%|█████████ | 331/363 [00:11<00:01, 30.74it/s]
Loading 0:  93%|█████████▎| 336/363 [00:11<00:00, 32.78it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 30.49it/s]
Loading 0:  95%|█████████▍| 344/363 [00:18<00:09,  1.99it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.68it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.88it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  5.04it/s]
                                                            
Job chaiml-elite-feed-convo-7085-v2-mkmlizer completed after 127.03s with status: succeeded
Stopping job with name chaiml-elite-feed-convo-7085-v2-mkmlizer
Pipeline stage MKMLizer completed in 129.57s
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 chaiml-elite-feed-convo-7085-v2
Waiting for inference service chaiml-elite-feed-convo-7085-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
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 chaiml-elite-feed-convo-7085-v2 ready after 171.17728853225708s
Pipeline stage MKMLDeployer completed in 172.96s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4553475379943848s
Received healthy response to inference request in 2.513639211654663s
Received healthy response to inference request in 1.618938684463501s
Received healthy response to inference request in 2.108443021774292s
Received healthy response to inference request in 1.7369091510772705s
LLM-Router throws exception AssertionError('LLM-Router predict returns error 504') for ising
5 requests
0 failed requests
5th percentile: 1.6425327777862548
10th percentile: 1.6661268711090087
20th percentile: 1.7133150577545166
30th percentile: 1.8112159252166748
40th percentile: 1.9598294734954833
50th percentile: 2.108443021774292
60th percentile: 2.247204828262329
70th percentile: 2.3859666347503663
80th percentile: 2.4670058727264403
90th percentile: 2.490322542190552
95th percentile: 2.5019808769226075
99th percentile: 2.511307544708252
mean time: 2.086655521392822
Pipeline stage StressChecker completed in 12.54s
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 6.48s
Shutdown handler de-registered
chaiml-elite-feed-convo-_7085_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 chaiml-elite-feed-convo-7085-v2-profiler
Waiting for inference service chaiml-elite-feed-convo-7085-v2-profiler to be ready
Inference service chaiml-elite-feed-convo-7085-v2-profiler ready after 170.40781497955322s
Pipeline stage MKMLProfilerDeployer completed in 170.78s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-elite-feed-co7e1b7d0baecf50c85378c2633376b409-deplov84c7:/code/chaiverse_profiler_1726159492 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-elite-feed-co7e1b7d0baecf50c85378c2633376b409-deplov84c7 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726159492 && 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_1726159492/summary.json'
kubectl exec -it chaiml-elite-feed-co7e1b7d0baecf50c85378c2633376b409-deplov84c7 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726159492/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1188.69s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-elite-feed-convo-7085-v2-profiler is running
Tearing down inference service chaiml-elite-feed-convo-7085-v2-profiler
Service chaiml-elite-feed-convo-7085-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.90s
Shutdown handler de-registered
chaiml-elite-feed-convo-_7085_v2 status is now inactive due to auto deactivation removed underperforming models
Pipeline stage MKMLDeleter completed in 14.01s
Shutdown handler de-registered
Tearing down inference service chaiml-elite-feed-convo-1137-v2
Running pipeline stage MKMLModelDeleter
Pipeline stage MKMLDeleter completed in 13.86s
Pipeline stage MKMLModelDeleter completed in 9.38s
Checking if service chaiml-elite-feed-convo-1831-v1 is running
Running pipeline stage MKMLDeleter
Pipeline stage MKMLDeleter completed in 12.51s
Shutdown handler de-registered
run pipeline stage %s
run pipeline %s
admin requested tearing down of chaiml-elite-feed-convo-_7085_v2
run pipeline stage %s
chaiml-albert-sft-intent_3850_v1 status is now torndown due to DeploymentManager action
chaiml-albert-sft-intent_3850_v1 status is now torndown due to DeploymentManager action
Cleaning model data from model cache
Cleaning model data from S3
run pipeline stage %s
chaiml-elite-feed-convo-_7085_v2 status is now torndown due to DeploymentManager action
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLModelDeleter completed in 3.98s
Pipeline stage %s skipped, reason=%s
chaiml-elite-feed-convo-_7085_v1 status is now torndown due to DeploymentManager action
Running pipeline stage MKMLDeleter
run pipeline stage %s
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
chaiml-elite-feed-convo-_7085_v2 status is now torndown due to DeploymentManager action
admin requested tearing down of chaiml-llama-8b-pairwis_8189_v24
run pipeline stage %s
chaiml-elite-feed-convo-_7085_v1 status is now torndown due to DeploymentManager action
Pipeline stage MKMLDeleter completed in 3.54s
Running pipeline stage MKMLDeleter
admin requested tearing down of chaiml-lexical-nemo-v4-1k1e5_v7
Pipeline stage MKMLModelDeleter completed in 3.96s
Pipeline stage %s skipped, reason=%s
run pipeline stage %s
chaiml-elite-feed-convo-_7085_v3 status is now torndown due to DeploymentManager action
Pipeline stage MKMLDeleter completed in 3.73s
chaiml-elite-feed-convo-_7085_v2 status is now torndown due to DeploymentManager action
run pipeline %s
run pipeline stage %s
Pipeline stage %s skipped, reason=%s
Shutdown handler not registered because Python interpreter is not running in the main thread