chaiml-elite-feed-convo-_7085

submission_id: chaiml-elite-feed-convo-_7085_v4

developer_uid: zonemercy

alignment_samples: 11109

alignment_score: 0.5387203166579698

best_of: 8

celo_rating: 1251.23

display_name: chaiml-elite-feed-convo-_7085_v4

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-v2-1e5ep2

latencies: [{'batch_size': 1, 'throughput': 0.6176247531878721, 'latency_mean': 1.6190432763099671, 'latency_p50': 1.6097140312194824, 'latency_p90': 1.800191879272461}, {'batch_size': 3, 'throughput': 1.0910652362039786, 'latency_mean': 2.744591031074524, 'latency_p50': 2.738669991493225, 'latency_p90': 2.975286674499512}, {'batch_size': 5, 'throughput': 1.2448738599070044, 'latency_mean': 4.005738962888717, 'latency_p50': 4.002012848854065, 'latency_p90': 4.473245406150817}, {'batch_size': 6, 'throughput': 1.2680646663929813, 'latency_mean': 4.712986624240875, 'latency_p50': 4.7148120403289795, 'latency_p90': 5.301339483261108}, {'batch_size': 8, 'throughput': 1.2351421625025223, 'latency_mean': 6.44363685131073, 'latency_p50': 6.474738359451294, 'latency_p90': 7.167217206954956}, {'batch_size': 10, 'throughput': 1.2131207981157013, 'latency_mean': 8.200356632471085, 'latency_p50': 8.264753580093384, 'latency_p90': 9.329721021652222}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: ChaiML/Elite-Feed-Convo-

model_name: chaiml-elite-feed-convo-_7085_v4

model_num_parameters: 12772070400.0

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

model_size: 13B

num_battles: 11108

num_wins: 5703

propriety_score: 0.7425742574257426

propriety_total_count: 1010.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 1.22

timestamp: 2024-09-12T19:51:56+00:00

us_pacific_date: 2024-09-12

win_ratio: 0.5134137558516385

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-7085-v4-mkmlizer
Waiting for job on chaiml-elite-feed-convo-7085-v4-mkmlizer to finish
chaiml-elite-feed-convo-7085-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elite-feed-convo-7085-v4-mkmlizer: ║     _____            __           __                                ║
chaiml-elite-feed-convo-7085-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-elite-feed-convo-7085-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-elite-feed-convo-7085-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-elite-feed-convo-7085-v4-mkmlizer: ║       /___/                                                         ║
chaiml-elite-feed-convo-7085-v4-mkmlizer: ║                                                                     ║
chaiml-elite-feed-convo-7085-v4-mkmlizer: ║  Version: 0.10.1                                                    ║
chaiml-elite-feed-convo-7085-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-elite-feed-convo-7085-v4-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-elite-feed-convo-7085-v4-mkmlizer: ║                                                                     ║
chaiml-elite-feed-convo-7085-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-elite-feed-convo-7085-v4-mkmlizer: ║  belonging to:                                                      ║
chaiml-elite-feed-convo-7085-v4-mkmlizer: ║                                                                     ║
chaiml-elite-feed-convo-7085-v4-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-elite-feed-convo-7085-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-elite-feed-convo-7085-v4-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-elite-feed-convo-7085-v4-mkmlizer: ║                                                                     ║
chaiml-elite-feed-convo-7085-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-elite-feed-convo-7085-v4-mkmlizer: Downloaded to shared memory in 55.416s
chaiml-elite-feed-convo-7085-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2h5uaz8_, device:0
chaiml-elite-feed-convo-7085-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elite-feed-convo-7085-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elite-feed-convo-7085-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elite-feed-convo-7085-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elite-feed-convo-7085-v4
chaiml-elite-feed-convo-7085-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elite-feed-convo-7085-v4/config.json
chaiml-elite-feed-convo-7085-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elite-feed-convo-7085-v4/special_tokens_map.json
chaiml-elite-feed-convo-7085-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elite-feed-convo-7085-v4/tokenizer_config.json
chaiml-elite-feed-convo-7085-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elite-feed-convo-7085-v4/tokenizer.json
chaiml-elite-feed-convo-7085-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elite-feed-convo-7085-v4/flywheel_model.0.safetensors
chaiml-elite-feed-convo-7085-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.51it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 27.86it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 24.19it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:11, 30.78it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:14, 23.21it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:16, 20.35it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:12, 25.76it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:12, 26.69it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 27.37it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:12, 24.87it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:11, 27.86it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:11, 28.26it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 27.33it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 28.10it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:09, 30.92it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:15, 19.24it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:11, 26.44it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:10, 27.29it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:10, 27.55it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:09, 30.47it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 29.63it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 32.20it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 30.94it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 25.68it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:11, 22.33it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:08, 29.56it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:08, 29.36it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 32.77it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 31.18it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 32.49it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 29.58it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 29.85it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 26.04it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:08, 24.58it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 23.33it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:06, 29.99it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:07, 28.40it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 30.87it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 29.05it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 31.60it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 30.12it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 24.11it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:08, 21.16it/s]
Loading 0:  52%|█████▏    | 190/363 [00:06<00:06, 26.40it/s]
Loading 0:  53%|█████▎    | 194/363 [00:07<00:07, 23.94it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 30.81it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 29.37it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 30.99it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:05, 29.14it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 29.39it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 25.60it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 23.78it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 22.49it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 29.30it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 27.89it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 29.83it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:03, 28.66it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 30.58it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 28.53it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 24.02it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 21.22it/s]
Loading 0:  75%|███████▌  | 273/363 [00:10<00:03, 27.78it/s]
Loading 0:  76%|███████▌  | 276/363 [00:10<00:03, 25.53it/s]
Loading 0:  77%|███████▋  | 280/363 [00:10<00:02, 28.10it/s]
Loading 0:  78%|███████▊  | 284/363 [00:10<00:03, 24.73it/s]
Loading 0:  80%|███████▉  | 289/363 [00:10<00:02, 29.49it/s]
Loading 0:  81%|████████  | 293/363 [00:10<00:02, 25.59it/s]
Loading 0:  82%|████████▏ | 298/363 [00:10<00:02, 30.43it/s]
Loading 0:  83%|████████▎ | 303/363 [00:11<00:01, 31.80it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 22.95it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 22.78it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 29.65it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 29.50it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 32.45it/s]
Loading 0:  91%|█████████ | 331/363 [00:12<00:01, 31.46it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 33.67it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 31.57it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  2.00it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.67it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.86it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  4.97it/s]
Loading 0: 100%|█████████▉| 362/363 [00:19<00:00,  7.08it/s]
                                                            
Job chaiml-elite-feed-convo-7085-v4-mkmlizer completed after 127.27s with status: succeeded
Stopping job with name chaiml-elite-feed-convo-7085-v4-mkmlizer
Pipeline stage MKMLizer completed in 128.13s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-elite-feed-convo-7085-v4
Waiting for inference service chaiml-elite-feed-convo-7085-v4 to be ready
Inference service chaiml-elite-feed-convo-7085-v4 ready after 171.364173412323s
Pipeline stage MKMLDeployer completed in 172.34s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7448348999023438s
Received healthy response to inference request in 1.8004341125488281s
Received healthy response to inference request in 1.9104998111724854s
Received healthy response to inference request in 1.907010793685913s
Received healthy response to inference request in 1.809581995010376s
5 requests
0 failed requests
5th percentile: 1.8022636890411377
10th percentile: 1.8040932655334472
20th percentile: 1.8077524185180665
30th percentile: 1.8290677547454834
40th percentile: 1.8680392742156982
50th percentile: 1.907010793685913
60th percentile: 1.908406400680542
70th percentile: 1.909802007675171
80th percentile: 2.077366828918457
90th percentile: 2.4111008644104004
95th percentile: 2.577967882156372
99th percentile: 2.7114614963531496
mean time: 2.0344723224639893
Pipeline stage StressChecker completed in 10.82s
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 5.72s
Shutdown handler de-registered
chaiml-elite-feed-convo-_7085_v4 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-elite-feed-convo-7085-v4-profiler
Waiting for inference service chaiml-elite-feed-convo-7085-v4-profiler to be ready
Inference service chaiml-elite-feed-convo-7085-v4-profiler ready after 170.40256071090698s
Pipeline stage MKMLProfilerDeployer completed in 171.86s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-elite-feed-cocda7aaa89807166beed472db16d972c7-deplo97jcw:/code/chaiverse_profiler_1726171250 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-elite-feed-cocda7aaa89807166beed472db16d972c7-deplo97jcw --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726171250 && 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_1726171250/summary.json'
kubectl exec -it chaiml-elite-feed-cocda7aaa89807166beed472db16d972c7-deplo97jcw --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726171250/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1160.40s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-elite-feed-convo-7085-v4-profiler is running
Tearing down inference service chaiml-elite-feed-convo-7085-v4-profiler
Service chaiml-elite-feed-convo-7085-v4-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.75s
Shutdown handler de-registered
chaiml-elite-feed-convo-_7085_v4 status is now inactive due to auto deactivation removed underperforming models