submission_id: chaiml-nemo-20241017-ti_8098_v10
developer_uid: chai_backend_admin
best_of: 4
celo_rating: 1250.94
display_name: chaiml-nemo-20241017-ti_8098_v10
family_friendly_score: 0.5933999999999999
family_friendly_standard_error: 0.006946602622865367
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '### Response:\n{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '###', 'Bot:', 'User:', 'You:', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: True
language_model: ChaiML/nemo-20241017-ties-remerge_v2_5merge-albert
latencies: [{'batch_size': 1, 'throughput': 0.633959429555376, 'latency_mean': 1.577292459011078, 'latency_p50': 1.5735149383544922, 'latency_p90': 1.7402290105819702}, {'batch_size': 3, 'throughput': 1.2672334142125061, 'latency_mean': 2.359461485147476, 'latency_p50': 2.3438756465911865, 'latency_p90': 2.5973950386047364}, {'batch_size': 5, 'throughput': 1.5843204618785136, 'latency_mean': 3.136183439493179, 'latency_p50': 3.1420297622680664, 'latency_p90': 3.556856560707092}, {'batch_size': 6, 'throughput': 1.7026104307868808, 'latency_mean': 3.5122527861595154, 'latency_p50': 3.510942578315735, 'latency_p90': 3.913451647758484}, {'batch_size': 8, 'throughput': 1.8449001939879277, 'latency_mean': 4.315245907306672, 'latency_p50': 4.319546818733215, 'latency_p90': 4.783288097381591}, {'batch_size': 10, 'throughput': 1.9359309428063782, 'latency_mean': 5.117599799633026, 'latency_p50': 5.072981595993042, 'latency_p90': 5.85263614654541}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: ChaiML/nemo-20241017-tie
model_name: chaiml-nemo-20241017-ti_8098_v10
model_num_parameters: 12772070400.0
model_repo: ChaiML/nemo-20241017-ties-remerge_v2_5merge-albert
model_size: 13B
num_battles: 18144
num_wins: 9264
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.75
timestamp: 2024-11-13T00:17:08+00:00
us_pacific_date: 2024-11-12
win_ratio: 0.5105820105820106
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-nemo-20241017-ti-8098-v10-mkmlizer
Waiting for job on chaiml-nemo-20241017-ti-8098-v10-mkmlizer to finish
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: ║  Version: 0.11.33                                                   ║
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: Downloaded to shared memory in 34.444s
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpy5rw_lfc, device:0
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: quantized model in 36.836s
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: Processed model ChaiML/nemo-20241017-ties-remerge_v2_5merge-albert in 71.280s
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241017-ti-8098-v10
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241017-ti-8098-v10/config.json
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241017-ti-8098-v10/tokenizer.json
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241017-ti-8098-v10/flywheel_model.0.safetensors
chaiml-nemo-20241017-ti-8098-v10-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:45,  3.12s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:59,  1.19it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:46,  3.27it/s]
Loading 0:   5%|▍         | 17/363 [00:06<01:12,  4.80it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:43,  7.82it/s]
Loading 0:   8%|▊         | 28/363 [00:06<00:30, 10.91it/s]
Loading 0:   9%|▉         | 33/363 [00:07<00:24, 13.32it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:20, 15.85it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:17, 18.09it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:13, 23.28it/s]
Loading 0:  15%|█▌        | 56/363 [00:07<00:11, 26.96it/s]
Loading 0:  17%|█▋        | 60/363 [00:07<00:10, 27.66it/s]
Loading 0:  19%|█▊        | 68/363 [00:08<00:08, 36.17it/s]
Loading 0:  20%|██        | 73/363 [00:08<00:07, 38.59it/s]
Loading 0:  21%|██▏       | 78/363 [00:08<00:08, 35.07it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:06, 43.46it/s]
Loading 0:  25%|██▌       | 92/363 [00:08<00:06, 42.55it/s]
Loading 0:  27%|██▋       | 97/363 [00:08<00:06, 42.76it/s]
Loading 0:  29%|██▊       | 104/363 [00:08<00:05, 46.90it/s]
Loading 0:  30%|███       | 109/363 [00:08<00:05, 47.01it/s]
Loading 0:  31%|███▏      | 114/363 [00:09<00:06, 39.82it/s]
Loading 0:  33%|███▎      | 121/363 [00:09<00:07, 32.85it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:07, 33.14it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:06, 36.23it/s]
Loading 0:  37%|███▋      | 134/363 [00:09<00:06, 35.99it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:05, 39.87it/s]
Loading 0:  40%|███▉      | 145/363 [00:09<00:05, 41.81it/s]
Loading 0:  41%|████▏     | 150/363 [00:10<00:05, 36.97it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:04, 42.70it/s]
Loading 0:  45%|████▍     | 162/363 [00:10<00:04, 41.95it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:04, 42.22it/s]
Loading 0:  48%|████▊     | 173/363 [00:10<00:04, 39.71it/s]
Loading 0:  49%|████▉     | 178/363 [00:10<00:04, 37.44it/s]
Loading 0:  51%|█████     | 184/363 [00:10<00:04, 41.74it/s]
Loading 0:  52%|█████▏    | 189/363 [00:11<00:04, 41.44it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:04, 41.54it/s]
Loading 0:  55%|█████▍    | 199/363 [00:11<00:03, 43.22it/s]
Loading 0:  56%|█████▌    | 204/363 [00:11<00:06, 26.49it/s]
Loading 0:  58%|█████▊    | 211/363 [00:11<00:04, 34.00it/s]
Loading 0:  60%|█████▉    | 216/363 [00:11<00:04, 36.28it/s]
Loading 0:  61%|██████    | 221/363 [00:11<00:03, 38.21it/s]
Loading 0:  63%|██████▎   | 227/363 [00:12<00:03, 38.63it/s]
Loading 0:  64%|██████▍   | 232/363 [00:12<00:03, 39.02it/s]
Loading 0:  66%|██████▌   | 238/363 [00:12<00:02, 42.75it/s]
Loading 0:  67%|██████▋   | 243/363 [00:12<00:02, 43.04it/s]
Loading 0:  68%|██████▊   | 248/363 [00:12<00:02, 43.93it/s]
Loading 0:  70%|██████▉   | 253/363 [00:12<00:02, 45.32it/s]
Loading 0:  71%|███████   | 258/363 [00:12<00:02, 37.23it/s]
Loading 0:  73%|███████▎  | 266/363 [00:12<00:02, 45.24it/s]
Loading 0:  75%|███████▍  | 272/363 [00:13<00:02, 42.58it/s]
Loading 0:  76%|███████▋  | 277/363 [00:13<00:02, 40.29it/s]
Loading 0:  78%|███████▊  | 283/363 [00:13<00:02, 32.08it/s]
Loading 0:  79%|███████▉  | 287/363 [00:13<00:02, 32.49it/s]
Loading 0:  81%|████████  | 293/363 [00:13<00:01, 36.75it/s]
Loading 0:  82%|████████▏ | 298/363 [00:13<00:01, 39.16it/s]
Loading 0:  83%|████████▎ | 303/363 [00:14<00:01, 34.51it/s]
Loading 0:  86%|████████▌ | 311/363 [00:14<00:01, 42.72it/s]
Loading 0:  87%|████████▋ | 317/363 [00:14<00:01, 41.96it/s]
Loading 0:  89%|████████▊ | 322/363 [00:14<00:01, 40.05it/s]
Loading 0:  90%|█████████ | 328/363 [00:14<00:00, 44.55it/s]
Loading 0:  92%|█████████▏| 333/363 [00:14<00:00, 44.31it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:00, 44.38it/s]
Loading 0:  94%|█████████▍| 343/363 [00:14<00:00, 45.61it/s]
Loading 0:  96%|█████████▌| 348/363 [00:15<00:00, 37.84it/s]
Loading 0:  98%|█████████▊| 355/363 [00:15<00:00, 45.33it/s]
Loading 0:  99%|█████████▉| 360/363 [00:15<00:00, 44.33it/s]
                                                            

Job chaiml-nemo-20241017-ti-8098-v10-mkmlizer completed after 94.02s with status: succeeded
Stopping job with name chaiml-nemo-20241017-ti-8098-v10-mkmlizer
Pipeline stage MKMLizer completed in 94.72s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-20241017-ti-8098-v10
Waiting for inference service chaiml-nemo-20241017-ti-8098-v10 to be ready
Inference service chaiml-nemo-20241017-ti-8098-v10 ready after 190.71434950828552s
Pipeline stage MKMLDeployer completed in 191.28s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.82708740234375s
Received healthy response to inference request in 1.7051396369934082s
Received healthy response to inference request in 1.407092571258545s
Received healthy response to inference request in 1.5048937797546387s
Received healthy response to inference request in 1.4039638042449951s
5 requests
0 failed requests
5th percentile: 1.404589557647705
10th percentile: 1.405215311050415
20th percentile: 1.406466817855835
30th percentile: 1.4266528129577636
40th percentile: 1.4657732963562011
50th percentile: 1.5048937797546387
60th percentile: 1.5849921226501464
70th percentile: 1.6650904655456542
80th percentile: 1.7295291900634766
90th percentile: 1.7783082962036132
95th percentile: 1.8026978492736816
99th percentile: 1.8222094917297362
mean time: 1.5696354389190674
Pipeline stage StressChecker completed in 9.31s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
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
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 5.69s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 3.16s
Shutdown handler de-registered
chaiml-nemo-20241017-ti_8098_v10 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 0.11s
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-nemo-20241017-ti-8098-v10-profiler
Waiting for inference service chaiml-nemo-20241017-ti-8098-v10-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2413.88s
Shutdown handler de-registered
chaiml-nemo-20241017-ti_8098_v10 status is now inactive due to auto deactivation removed underperforming models