chaiml-elite-feed-convo-_1831

submission_id: chaiml-elite-feed-convo-_1831_v1

developer_uid: zonemercy

alignment_samples: 10828

alignment_score: 0.2575033838072679

best_of: 8

celo_rating: 1252.93

display_name: chaiml-elite-feed-convo-_1831_v1

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-v2-1e5ep1

latencies: [{'batch_size': 1, 'throughput': 0.6125299876702663, 'latency_mean': 1.6324709224700928, 'latency_p50': 1.6429740190505981, 'latency_p90': 1.7875160694122314}, {'batch_size': 3, 'throughput': 1.091343530720679, 'latency_mean': 2.7425295996665953, 'latency_p50': 2.7402766942977905, 'latency_p90': 3.0012779235839844}, {'batch_size': 5, 'throughput': 1.2399254215560975, 'latency_mean': 4.0164690482616425, 'latency_p50': 4.028828263282776, 'latency_p90': 4.503456401824951}, {'batch_size': 6, 'throughput': 1.2711678718592725, 'latency_mean': 4.716579804420471, 'latency_p50': 4.6999441385269165, 'latency_p90': 5.332068371772766}, {'batch_size': 8, 'throughput': 1.2567427948508059, 'latency_mean': 6.33377210855484, 'latency_p50': 6.392281532287598, 'latency_p90': 7.1344249725341795}, {'batch_size': 10, 'throughput': 1.206994040195272, 'latency_mean': 8.241184388399125, 'latency_p50': 8.276776671409607, 'latency_p90': 9.402438402175903}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: ChaiML/Elite-Feed-Convo-

model_name: chaiml-elite-feed-convo-_1831_v1

model_num_parameters: 12772070400.0

model_repo: ChaiML/Elite-Feed-Convo-v2-1e5ep1

model_size: 13B

num_battles: 10827

num_wins: 5586

propriety_score: 0.7571569595261599

propriety_total_count: 1013.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 1.22

timestamp: 2024-09-12T19:52:50+00:00

us_pacific_date: 2024-09-12

win_ratio: 0.5159323912441119

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-1831-v1-mkmlizer
Waiting for job on chaiml-elite-feed-convo-1831-v1-mkmlizer to finish
chaiml-elite-feed-convo-1831-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elite-feed-convo-1831-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-elite-feed-convo-1831-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-elite-feed-convo-1831-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-elite-feed-convo-1831-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-elite-feed-convo-1831-v1-mkmlizer: ║       /___/                                                         ║
chaiml-elite-feed-convo-1831-v1-mkmlizer: ║                                                                     ║
chaiml-elite-feed-convo-1831-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
chaiml-elite-feed-convo-1831-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-elite-feed-convo-1831-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-elite-feed-convo-1831-v1-mkmlizer: ║                                                                     ║
chaiml-elite-feed-convo-1831-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-elite-feed-convo-1831-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-elite-feed-convo-1831-v1-mkmlizer: ║                                                                     ║
chaiml-elite-feed-convo-1831-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-elite-feed-convo-1831-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-elite-feed-convo-1831-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-elite-feed-convo-1831-v1-mkmlizer: ║                                                                     ║
chaiml-elite-feed-convo-1831-v1-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
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
chaiml-elite-feed-convo-1831-v1-mkmlizer: Downloaded to shared memory in 97.434s
chaiml-elite-feed-convo-1831-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmps0zo6jid, device:0
chaiml-elite-feed-convo-1831-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elite-feed-convo-1831-v1-mkmlizer: quantized model in 40.397s
chaiml-elite-feed-convo-1831-v1-mkmlizer: Processed model ChaiML/Elite-Feed-Convo-v2-1e5ep1 in 137.831s
chaiml-elite-feed-convo-1831-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elite-feed-convo-1831-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elite-feed-convo-1831-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elite-feed-convo-1831-v1
chaiml-elite-feed-convo-1831-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elite-feed-convo-1831-v1/config.json
chaiml-elite-feed-convo-1831-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elite-feed-convo-1831-v1/special_tokens_map.json
chaiml-elite-feed-convo-1831-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elite-feed-convo-1831-v1/tokenizer_config.json
chaiml-elite-feed-convo-1831-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elite-feed-convo-1831-v1/tokenizer.json
chaiml-elite-feed-convo-1831-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 23.68it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:11, 31.06it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:12, 27.57it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:08, 39.09it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:14, 23.34it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:11, 28.00it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:11, 29.25it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:10, 31.08it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:10, 30.76it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 33.65it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:09, 32.28it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:09, 32.93it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 29.11it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:11, 26.43it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:09, 31.89it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:09, 31.82it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 31.26it/s]
Loading 0:  23%|██▎       | 84/363 [00:02<00:08, 33.73it/s]
Loading 0:  24%|██▍       | 88/363 [00:02<00:08, 32.22it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:07, 34.70it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 33.05it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:09, 26.74it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:11, 22.14it/s]
Loading 0:  31%|███       | 111/363 [00:03<00:08, 30.06it/s]
Loading 0:  32%|███▏      | 115/363 [00:03<00:08, 30.05it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 32.89it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 32.53it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 35.67it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:06, 34.42it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:06, 33.90it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:07, 30.45it/s]
Loading 0:  40%|████      | 146/363 [00:04<00:07, 29.79it/s]
Loading 0:  41%|████▏     | 150/363 [00:04<00:07, 26.77it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:06, 31.86it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:06, 31.35it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:05, 34.21it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:05, 32.73it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 35.59it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 34.15it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:06, 27.11it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:07, 23.09it/s]
Loading 0:  53%|█████▎    | 192/363 [00:06<00:05, 30.50it/s]
Loading 0:  54%|█████▍    | 196/363 [00:06<00:05, 28.99it/s]
Loading 0:  55%|█████▌    | 201/363 [00:06<00:05, 32.28it/s]
Loading 0:  56%|█████▋    | 205/363 [00:06<00:04, 31.64it/s]
Loading 0:  58%|█████▊    | 210/363 [00:06<00:04, 34.27it/s]
Loading 0:  59%|█████▉    | 214/363 [00:06<00:04, 32.80it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 33.35it/s]
Loading 0:  61%|██████▏   | 223/363 [00:07<00:04, 28.17it/s]
Loading 0:  63%|██████▎   | 227/363 [00:07<00:04, 28.16it/s]
Loading 0:  63%|██████▎   | 230/363 [00:07<00:05, 24.75it/s]
Loading 0:  65%|██████▌   | 237/363 [00:07<00:03, 32.58it/s]
Loading 0:  66%|██████▋   | 241/363 [00:07<00:03, 31.75it/s]
Loading 0:  68%|██████▊   | 246/363 [00:07<00:03, 34.71it/s]
Loading 0:  69%|██████▉   | 250/363 [00:08<00:03, 32.68it/s]
Loading 0:  70%|███████   | 255/363 [00:08<00:03, 35.52it/s]
Loading 0:  71%|███████▏  | 259/363 [00:08<00:03, 33.27it/s]
Loading 0:  72%|███████▏  | 263/363 [00:08<00:03, 26.19it/s]
Loading 0:  73%|███████▎  | 266/363 [00:08<00:04, 22.94it/s]
Loading 0:  75%|███████▌  | 273/363 [00:08<00:02, 30.57it/s]
Loading 0:  76%|███████▋  | 277/363 [00:09<00:02, 30.43it/s]
Loading 0:  78%|███████▊  | 282/363 [00:09<00:02, 33.74it/s]
Loading 0:  79%|███████▉  | 286/363 [00:09<00:02, 32.52it/s]
Loading 0:  80%|████████  | 291/363 [00:09<00:02, 35.40it/s]
Loading 0:  81%|████████▏ | 295/363 [00:09<00:02, 33.86it/s]
Loading 0:  82%|████████▏ | 299/363 [00:09<00:01, 34.23it/s]
Loading 0:  84%|████████▎ | 304/363 [00:09<00:01, 29.60it/s]
Loading 0:  85%|████████▍ | 308/363 [00:10<00:01, 29.37it/s]
Loading 0:  86%|████████▌ | 312/363 [00:10<00:01, 27.41it/s]
Loading 0:  88%|████████▊ | 318/363 [00:10<00:01, 32.23it/s]
Loading 0:  89%|████████▊ | 322/363 [00:10<00:01, 31.05it/s]
Loading 0:  90%|█████████ | 327/363 [00:10<00:01, 33.10it/s]
Loading 0:  91%|█████████ | 331/363 [00:10<00:01, 30.79it/s]
Loading 0:  93%|█████████▎| 336/363 [00:10<00:00, 32.59it/s]
Loading 0:  94%|█████████▎| 340/363 [00:11<00:00, 31.20it/s]
Loading 0:  95%|█████████▍| 344/363 [00:17<00:09,  2.00it/s]
Loading 0:  96%|█████████▌| 348/363 [00:18<00:05,  2.69it/s]
Loading 0:  97%|█████████▋| 353/363 [00:18<00:02,  3.90it/s]
Loading 0:  98%|█████████▊| 357/363 [00:18<00:01,  5.05it/s]
                                                            
Job chaiml-elite-feed-convo-1831-v1-mkmlizer completed after 168.24s with status: succeeded
Stopping job with name chaiml-elite-feed-convo-1831-v1-mkmlizer
Pipeline stage MKMLizer completed in 169.22s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Connection pool is full, discarding connection: %s. Connection pool size: %s
Pipeline stage MKMLTemplater completed in 3.36s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-elite-feed-convo-1831-v1
Waiting for inference service chaiml-elite-feed-convo-1831-v1 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
Inference service chaiml-elite-feed-convo-1831-v1 ready after 181.48449516296387s
Pipeline stage MKMLDeployer completed in 183.36s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9150631427764893s
Received healthy response to inference request in 1.9154586791992188s
Received healthy response to inference request in 1.8569133281707764s
Received healthy response to inference request in 1.7013885974884033s
Received healthy response to inference request in 1.739922285079956s
5 requests
0 failed requests
5th percentile: 1.709095335006714
10th percentile: 1.7168020725250244
20th percentile: 1.7322155475616454
30th percentile: 1.7633204936981202
40th percentile: 1.8101169109344482
50th percentile: 1.8569133281707764
60th percentile: 1.8803314685821533
70th percentile: 1.9037496089935302
80th percentile: 2.115379571914673
90th percentile: 2.515221357345581
95th percentile: 2.715142250061035
99th percentile: 2.8750789642333983
mean time: 2.0257492065429688
Pipeline stage StressChecker completed in 11.13s
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 5.17s
Shutdown handler de-registered
chaiml-elite-feed-convo-_1831_v1 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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-elite-feed-convo-1831-v1-profiler
Waiting for inference service chaiml-elite-feed-convo-1831-v1-profiler to be ready
Inference service chaiml-elite-feed-convo-1831-v1-profiler ready after 170.42156386375427s
Pipeline stage MKMLProfilerDeployer completed in 170.79s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-elite-feed-co8e80779bfd2c3394b59373af0d1636a6-deplocgh4v:/code/chaiverse_profiler_1726171358 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-elite-feed-co8e80779bfd2c3394b59373af0d1636a6-deplocgh4v --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726171358 && 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_1726171358/summary.json'
kubectl exec -it chaiml-elite-feed-co8e80779bfd2c3394b59373af0d1636a6-deplocgh4v --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726171358/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1159.60s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-elite-feed-convo-1831-v1-profiler is running
Tearing down inference service chaiml-elite-feed-convo-1831-v1-profiler
Service chaiml-elite-feed-convo-1831-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.98s
Shutdown handler de-registered
chaiml-elite-feed-convo-_1831_v1 status is now inactive due to auto deactivation removed underperforming models