chaiml-elite-feed-convo-_5606

submission_id: chaiml-elite-feed-convo-_5606_v3

developer_uid: zonemercy

alignment_samples: 11022

alignment_score: 0.10761356097629605

best_of: 8

celo_rating: 1249.01

display_name: chaiml-elite-feed-convo-_5606_v3

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}</s>', 'user_template': '{user_name}: {message}</s>', 'response_template': '{bot_name}:', 'truncate_by_message': True}

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}

gpu_counts: {'NVIDIA RTX A5000': 1}

is_internal_developer: True

language_model: ChaiML/Elite-Feed-Convo-v1-1e5

latencies: [{'batch_size': 1, 'throughput': 0.6155382641480155, 'latency_mean': 1.6245025408267975, 'latency_p50': 1.62218177318573, 'latency_p90': 1.807719874382019}, {'batch_size': 3, 'throughput': 0.9889528661300029, 'latency_mean': 3.0288898479938506, 'latency_p50': 2.928057074546814, 'latency_p90': 3.5108341455459593}, {'batch_size': 5, 'throughput': 1.2373459880482605, 'latency_mean': 4.024719533920288, 'latency_p50': 4.052057981491089, 'latency_p90': 4.502264165878295}, {'batch_size': 6, 'throughput': 1.2566519867056336, 'latency_mean': 4.753232181072235, 'latency_p50': 4.743093848228455, 'latency_p90': 5.377752447128296}, {'batch_size': 8, 'throughput': 1.2250413148389219, 'latency_mean': 6.476557787656784, 'latency_p50': 6.482583045959473, 'latency_p90': 7.451122879981995}, {'batch_size': 10, 'throughput': 1.198125945760679, 'latency_mean': 8.294080123901367, 'latency_p50': 8.322778105735779, 'latency_p90': 9.336544442176818}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: ChaiML/Elite-Feed-Convo-

model_name: chaiml-elite-feed-convo-_5606_v3

model_num_parameters: 12772070400.0

model_repo: ChaiML/Elite-Feed-Convo-v1-1e5

model_size: 13B

num_battles: 11022

num_wins: 5608

propriety_score: 0.7619553666312433

propriety_total_count: 941.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 1.18

timestamp: 2024-09-11T21:30:09+00:00

us_pacific_date: 2024-09-11

win_ratio: 0.5088005806568681

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 chaiml-elite-feed-convo-5606-v3-mkmlizer
Waiting for job on chaiml-elite-feed-convo-5606-v3-mkmlizer to finish
chaiml-elite-feed-convo-5606-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elite-feed-convo-5606-v3-mkmlizer: ║     _____            __           __                                ║
chaiml-elite-feed-convo-5606-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-elite-feed-convo-5606-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-elite-feed-convo-5606-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-elite-feed-convo-5606-v3-mkmlizer: ║       /___/                                                         ║
chaiml-elite-feed-convo-5606-v3-mkmlizer: ║                                                                     ║
chaiml-elite-feed-convo-5606-v3-mkmlizer: ║  Version: 0.10.1                                                    ║
chaiml-elite-feed-convo-5606-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-elite-feed-convo-5606-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-elite-feed-convo-5606-v3-mkmlizer: ║                                                                     ║
chaiml-elite-feed-convo-5606-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-elite-feed-convo-5606-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-elite-feed-convo-5606-v3-mkmlizer: ║                                                                     ║
chaiml-elite-feed-convo-5606-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-elite-feed-convo-5606-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-elite-feed-convo-5606-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-elite-feed-convo-5606-v3-mkmlizer: ║                                                                     ║
chaiml-elite-feed-convo-5606-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-elite-feed-convo-5606-v3-mkmlizer: Downloaded to shared memory in 28.339s
chaiml-elite-feed-convo-5606-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjio18f67, device:0
chaiml-elite-feed-convo-5606-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elite-feed-convo-5606-v3-mkmlizer: quantized model in 34.578s
chaiml-elite-feed-convo-5606-v3-mkmlizer: Processed model ChaiML/Elite-Feed-Convo-v1-1e5 in 62.917s
chaiml-elite-feed-convo-5606-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elite-feed-convo-5606-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elite-feed-convo-5606-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elite-feed-convo-5606-v3
chaiml-elite-feed-convo-5606-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elite-feed-convo-5606-v3/special_tokens_map.json
chaiml-elite-feed-convo-5606-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elite-feed-convo-5606-v3/config.json
chaiml-elite-feed-convo-5606-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elite-feed-convo-5606-v3/tokenizer_config.json
chaiml-elite-feed-convo-5606-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elite-feed-convo-5606-v3/tokenizer.json
chaiml-elite-feed-convo-5606-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elite-feed-convo-5606-v3/flywheel_model.0.safetensors
chaiml-elite-feed-convo-5606-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 31.78it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 54.35it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:06, 51.38it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:06, 50.24it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 52.43it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 48.49it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:06, 47.19it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:05, 52.95it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 46.17it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 35.62it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 36.63it/s]
Loading 0:  20%|██        | 73/363 [00:01<00:07, 37.63it/s]
Loading 0:  22%|██▏       | 81/363 [00:01<00:06, 45.62it/s]
Loading 0:  24%|██▍       | 87/363 [00:01<00:06, 45.06it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:06, 45.02it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:05, 49.23it/s]
Loading 0:  29%|██▉       | 105/363 [00:02<00:05, 47.07it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:04, 51.57it/s]
Loading 0:  33%|███▎      | 118/363 [00:02<00:05, 44.55it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:04, 52.14it/s]
Loading 0:  36%|███▋      | 132/363 [00:02<00:04, 49.84it/s]
Loading 0:  38%|███▊      | 138/363 [00:02<00:04, 51.30it/s]
Loading 0:  40%|███▉      | 144/363 [00:03<00:06, 34.72it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:05, 35.69it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:04, 42.23it/s]
Loading 0:  45%|████▍     | 162/363 [00:03<00:04, 45.68it/s]
Loading 0:  46%|████▋     | 168/363 [00:03<00:04, 43.58it/s]
Loading 0:  48%|████▊     | 175/363 [00:03<00:03, 49.14it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:03, 47.17it/s]
Loading 0:  52%|█████▏    | 187/363 [00:04<00:03, 47.34it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 49.09it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 48.67it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 47.05it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:02, 52.18it/s]
Loading 0:  60%|█████▉    | 217/363 [00:04<00:02, 50.61it/s]
Loading 0:  61%|██████▏   | 223/363 [00:04<00:03, 38.71it/s]
Loading 0:  63%|██████▎   | 228/363 [00:05<00:03, 37.33it/s]
Loading 0:  64%|██████▍   | 233/363 [00:05<00:03, 38.71it/s]
Loading 0:  66%|██████▌   | 239/363 [00:05<00:03, 37.89it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:02, 45.96it/s]
Loading 0:  70%|██████▉   | 253/363 [00:05<00:02, 45.06it/s]
Loading 0:  71%|███████   | 258/363 [00:05<00:02, 44.66it/s]
Loading 0:  73%|███████▎  | 265/363 [00:05<00:01, 50.29it/s]
Loading 0:  75%|███████▍  | 271/363 [00:05<00:01, 49.12it/s]
Loading 0:  76%|███████▋  | 277/363 [00:06<00:01, 49.38it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 50.98it/s]
Loading 0:  80%|███████▉  | 289/363 [00:06<00:01, 48.84it/s]
Loading 0:  81%|████████  | 294/363 [00:06<00:01, 43.59it/s]
Loading 0:  82%|████████▏ | 299/363 [00:06<00:01, 43.87it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:23,  2.56it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:16,  3.30it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:11,  4.31it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:05,  7.19it/s]
Loading 0:  90%|████████▉ | 326/363 [00:13<00:03,  9.81it/s]
Loading 0:  91%|█████████ | 331/363 [00:13<00:02, 12.50it/s]
Loading 0:  93%|█████████▎| 337/363 [00:13<00:01, 16.57it/s]
Loading 0:  94%|█████████▍| 343/363 [00:14<00:00, 21.04it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 24.61it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 31.39it/s]
Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 34.79it/s]
                                                            
Job chaiml-elite-feed-convo-5606-v3-mkmlizer completed after 85.27s with status: succeeded
Stopping job with name chaiml-elite-feed-convo-5606-v3-mkmlizer
Pipeline stage MKMLizer completed in 87.35s
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-5606-v3
Waiting for inference service chaiml-elite-feed-convo-5606-v3 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
Inference service chaiml-elite-feed-convo-5606-v3 ready after 161.25349617004395s
Pipeline stage MKMLDeployer completed in 161.84s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7282660007476807s
Failed to get response for submission chaiml-elo-alignment-run-3_v42: ('http://chaiml-llama-8b-pairwis-8189-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'readfrom tcp 127.0.0.1:47424->127.0.0.1:8080: write tcp 127.0.0.1:47424->127.0.0.1:8080: use of closed network connection\n')
Received healthy response to inference request in 1.9348127841949463s
Received healthy response to inference request in 1.8739964962005615s
Received healthy response to inference request in 1.894763708114624s
Received healthy response to inference request in 2.5219240188598633s
5 requests
0 failed requests
5th percentile: 1.878149938583374
10th percentile: 1.8823033809661864
20th percentile: 1.8906102657318116
30th percentile: 1.9027735233306884
40th percentile: 1.9187931537628173
50th percentile: 1.9348127841949463
60th percentile: 2.169657278060913
70th percentile: 2.40450177192688
80th percentile: 2.5631924152374266
90th percentile: 2.6457292079925536
95th percentile: 2.6869976043701174
99th percentile: 2.720012321472168
mean time: 2.1907526016235352
Pipeline stage StressChecker completed in 11.90s
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 5.86s
Shutdown handler de-registered
chaiml-elite-feed-convo-_5606_v3 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-elite-feed-convo-5606-v3-profiler
Waiting for inference service chaiml-elite-feed-convo-5606-v3-profiler to be ready
Inference service chaiml-elite-feed-convo-5606-v3-profiler ready after 160.390056848526s
Pipeline stage MKMLProfilerDeployer completed in 160.80s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-elite-feed-coe6e5355d8d7edf968f54fe52f2137a5d-deplosg5m7:/code/chaiverse_profiler_1726090681 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-elite-feed-coe6e5355d8d7edf968f54fe52f2137a5d-deplosg5m7 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726090681 && 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_1726090681/summary.json'
kubectl exec -it chaiml-elite-feed-coe6e5355d8d7edf968f54fe52f2137a5d-deplosg5m7 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726090681/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1185.37s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-elite-feed-convo-5606-v3-profiler is running
Tearing down inference service chaiml-elite-feed-convo-5606-v3-profiler
Service chaiml-elite-feed-convo-5606-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.89s
Shutdown handler de-registered
chaiml-elite-feed-convo-_5606_v3 status is now inactive due to auto deactivation removed underperforming models