submission_id: chaiml-nemo-20241010-ti_5991_v23
developer_uid: chai_backend_admin
best_of: 4
celo_rating: 1262.17
display_name: chaiml-nemo-20241010-ti_5991_v23
family_friendly_score: 0.5672588167478908
family_friendly_standard_error: 0.006187390179593036
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', '<|eot_id|>', '<|end_of_text|>', 'You:'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}
is_internal_developer: True
language_model: ChaiML/nemo-20241010_tier_merge_v4-albert
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: ChaiML/nemo-20241010_tie
model_name: chaiml-nemo-20241010-ti_5991_v23
model_num_parameters: 12772070400.0
model_repo: ChaiML/nemo-20241010_tier_merge_v4-albert
model_size: 13B
num_battles: 6643
num_wins: 3413
ranking_group: single
status: torndown
submission_type: basic
timestamp: 2024-10-12T11:00:40+00:00
us_pacific_date: 2024-10-12
win_ratio: 0.5137738973355411
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-nemo-20241010-ti-5991-v23-mkmlizer
Waiting for job on chaiml-nemo-20241010-ti-5991-v23-mkmlizer to finish
chaiml-nemo-20241010-ti-5991-v23-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241010-ti-5991-v23-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241010-ti-5991-v23-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241010-ti-5991-v23-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241010-ti-5991-v23-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241010-ti-5991-v23-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241010-ti-5991-v23-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v23-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241010-ti-5991-v23-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241010-ti-5991-v23-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241010-ti-5991-v23-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v23-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241010-ti-5991-v23-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241010-ti-5991-v23-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v23-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241010-ti-5991-v23-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241010-ti-5991-v23-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-nemo-20241010-ti-5991-v23-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v23-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241010-ti-5991-v23-mkmlizer: Downloaded to shared memory in 28.480s
chaiml-nemo-20241010-ti-5991-v23-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmptmuc9xwr, device:0
chaiml-nemo-20241010-ti-5991-v23-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-nemo-20241010-ti-5991-v23-mkmlizer: quantized model in 35.685s
chaiml-nemo-20241010-ti-5991-v23-mkmlizer: Processed model ChaiML/nemo-20241010_tier_merge_v4-albert in 64.165s
chaiml-nemo-20241010-ti-5991-v23-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241010-ti-5991-v23-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241010-ti-5991-v23-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v23
chaiml-nemo-20241010-ti-5991-v23-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v23/tokenizer.json
chaiml-nemo-20241010-ti-5991-v23-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v23/flywheel_model.0.safetensors
chaiml-nemo-20241010-ti-5991-v23-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<17:52,  2.97s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:46,  1.25it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:05,  2.80it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:19,  4.37it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:39,  8.67it/s]
Loading 0:   8%|▊         | 29/363 [00:06<00:27, 12.09it/s]
Loading 0:   9%|▉         | 34/363 [00:06<00:21, 15.40it/s]
Loading 0:  11%|█         | 40/363 [00:06<00:18, 17.25it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:16, 19.79it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:12, 25.00it/s]
Loading 0:  15%|█▌        | 56/363 [00:07<00:10, 28.37it/s]
Loading 0:  17%|█▋        | 61/363 [00:07<00:09, 30.46it/s]
Loading 0:  19%|█▊        | 68/363 [00:07<00:08, 36.71it/s]
Loading 0:  20%|██        | 74/363 [00:07<00:07, 37.64it/s]
Loading 0:  22%|██▏       | 79/363 [00:07<00:07, 38.49it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:06, 43.75it/s]
Loading 0:  25%|██▌       | 91/363 [00:08<00:06, 44.72it/s]
Loading 0:  26%|██▋       | 96/363 [00:08<00:06, 38.26it/s]
Loading 0:  29%|██▊       | 104/363 [00:08<00:05, 46.01it/s]
Loading 0:  30%|███       | 109/363 [00:08<00:05, 46.55it/s]
Loading 0:  31%|███▏      | 114/363 [00:08<00:06, 38.69it/s]
Loading 0:  33%|███▎      | 121/363 [00:08<00:07, 32.94it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:07, 33.88it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:06, 38.45it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:05, 40.31it/s]
Loading 0:  39%|███▉      | 141/363 [00:09<00:06, 34.02it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:05, 40.90it/s]
Loading 0:  42%|████▏     | 153/363 [00:09<00:05, 41.77it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:05, 37.76it/s]
Loading 0:  45%|████▌     | 164/363 [00:10<00:05, 36.87it/s]
Loading 0:  46%|████▋     | 168/363 [00:10<00:05, 34.70it/s]
Loading 0:  48%|████▊     | 175/363 [00:10<00:04, 42.11it/s]
Loading 0:  50%|████▉     | 180/363 [00:10<00:04, 42.72it/s]
Loading 0:  51%|█████     | 185/363 [00:10<00:04, 43.77it/s]
Loading 0:  53%|█████▎    | 191/363 [00:10<00:04, 42.21it/s]
Loading 0:  54%|█████▍    | 196/363 [00:10<00:03, 42.06it/s]
Loading 0:  56%|█████▌    | 202/363 [00:11<00:04, 32.45it/s]
Loading 0:  57%|█████▋    | 206/363 [00:11<00:04, 33.35it/s]
Loading 0:  58%|█████▊    | 212/363 [00:11<00:03, 37.83it/s]
Loading 0:  60%|██████    | 218/363 [00:11<00:03, 37.96it/s]
Loading 0:  61%|██████▏   | 223/363 [00:11<00:03, 38.02it/s]
Loading 0:  63%|██████▎   | 229/363 [00:11<00:03, 42.04it/s]
Loading 0:  64%|██████▍   | 234/363 [00:11<00:03, 42.90it/s]
Loading 0:  66%|██████▌   | 239/363 [00:11<00:02, 43.60it/s]
Loading 0:  67%|██████▋   | 245/363 [00:12<00:02, 40.31it/s]
Loading 0:  69%|██████▉   | 250/363 [00:12<00:02, 40.33it/s]
Loading 0:  71%|███████   | 257/363 [00:12<00:02, 45.54it/s]
Loading 0:  72%|███████▏  | 263/363 [00:12<00:02, 42.87it/s]
Loading 0:  74%|███████▍  | 268/363 [00:12<00:02, 41.95it/s]
Loading 0:  76%|███████▌  | 275/363 [00:12<00:01, 46.47it/s]
Loading 0:  77%|███████▋  | 281/363 [00:12<00:01, 43.66it/s]
Loading 0:  79%|███████▉  | 286/363 [00:13<00:02, 30.60it/s]
Loading 0:  80%|████████  | 292/363 [00:13<00:01, 35.69it/s]
Loading 0:  82%|████████▏ | 297/363 [00:13<00:01, 37.76it/s]
Loading 0:  83%|████████▎ | 302/363 [00:13<00:01, 38.30it/s]
Loading 0:  85%|████████▍ | 307/363 [00:13<00:01, 40.86it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:01, 33.91it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:01, 42.35it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:00, 40.94it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:00, 40.51it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:00, 45.43it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 42.97it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 41.89it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 46.38it/s]
Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 43.82it/s]
                                                            

Job chaiml-nemo-20241010-ti-5991-v23-mkmlizer completed after 83.36s with status: succeeded
Stopping job with name chaiml-nemo-20241010-ti-5991-v23-mkmlizer
Pipeline stage MKMLizer completed in 83.94s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-20241010-ti-5991-v23
Waiting for inference service chaiml-nemo-20241010-ti-5991-v23 to be ready
Inference service chaiml-nemo-20241010-ti-5991-v23 ready after 160.78880834579468s
Pipeline stage MKMLDeployer completed in 161.28s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.150940418243408s
Received healthy response to inference request in 2.2717204093933105s
Received healthy response to inference request in 1.9332938194274902s
Received healthy response to inference request in 1.6198031902313232s
5 requests
1 failed requests
5th percentile: 1.6825013160705566
10th percentile: 1.74519944190979
20th percentile: 1.8705956935882568
30th percentile: 1.9768231391906739
40th percentile: 2.063881778717041
50th percentile: 2.150940418243408
60th percentile: 2.199252414703369
70th percentile: 2.24756441116333
80th percentile: 5.853239059448246
90th percentile: 13.016276359558107
95th percentile: 16.597795009613034
99th percentile: 19.46300992965698
mean time: 5.6310142993927
%s, retrying in %s seconds...
Received healthy response to inference request in 2.1627724170684814s
Received healthy response to inference request in 1.4491939544677734s
Received healthy response to inference request in 1.4862444400787354s
Received healthy response to inference request in 1.4479336738586426s
Received healthy response to inference request in 1.533341884613037s
5 requests
0 failed requests
5th percentile: 1.4481857299804688
10th percentile: 1.448437786102295
20th percentile: 1.4489418983459472
30th percentile: 1.4566040515899659
40th percentile: 1.4714242458343505
50th percentile: 1.4862444400787354
60th percentile: 1.5050834178924561
70th percentile: 1.5239223957061767
80th percentile: 1.659227991104126
90th percentile: 1.9110002040863039
95th percentile: 2.0368863105773927
99th percentile: 2.1375951957702637
mean time: 1.615897274017334
Pipeline stage StressChecker completed in 39.85s
Shutdown handler de-registered
chaiml-nemo-20241010-ti_5991_v23 status is now deployed due to DeploymentManager action
chaiml-nemo-20241010-ti_5991_v23 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241010-ti_5991_v23 status is now torndown due to DeploymentManager action