submission_id: chaiml-nemo-20241010-ti_5991_v32
developer_uid: chai_backend_admin
best_of: 4
celo_rating: 1267.47
display_name: chaiml-nemo-20241010-ti_5991_v32
family_friendly_score: 0.5761379737867517
family_friendly_standard_error: 0.0056773512301976055
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_v32
model_num_parameters: 12772070400.0
model_repo: ChaiML/nemo-20241010_tier_merge_v4-albert
model_size: 13B
num_battles: 7771
num_wins: 4237
ranking_group: single
status: torndown
submission_type: basic
timestamp: 2024-10-12T16:00:34+00:00
us_pacific_date: 2024-10-12
win_ratio: 0.5452322738386308
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-v32-mkmlizer
Waiting for job on chaiml-nemo-20241010-ti-5991-v32-mkmlizer to finish
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: Downloaded to shared memory in 34.660s
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppoykl_j_, device:0
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: quantized model in 37.630s
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: Processed model ChaiML/nemo-20241010_tier_merge_v4-albert in 72.291s
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v32
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v32/config.json
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v32/special_tokens_map.json
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v32/tokenizer_config.json
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v32/tokenizer.json
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v32/flywheel_model.0.safetensors
chaiml-nemo-20241010-ti-5991-v32-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:13,  3.03s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:52,  1.22it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:08,  2.74it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:21,  4.27it/s]
Loading 0:   6%|▌         | 22/363 [00:06<00:42,  7.96it/s]
Loading 0:   7%|▋         | 27/363 [00:06<00:31, 10.83it/s]
Loading 0:   9%|▉         | 32/363 [00:06<00:23, 14.14it/s]
Loading 0:  10%|▉         | 36/363 [00:06<00:19, 17.08it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:19, 16.32it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:16, 18.91it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:13, 23.48it/s]
Loading 0:  15%|█▍        | 53/363 [00:07<00:12, 25.37it/s]
Loading 0:  16%|█▌        | 58/363 [00:07<00:10, 29.72it/s]
Loading 0:  17%|█▋        | 62/363 [00:07<00:10, 29.93it/s]
Loading 0:  18%|█▊        | 67/363 [00:07<00:09, 32.66it/s]
Loading 0:  20%|█▉        | 71/363 [00:08<00:09, 32.06it/s]
Loading 0:  21%|██        | 76/363 [00:08<00:08, 35.07it/s]
Loading 0:  22%|██▏       | 80/363 [00:08<00:08, 34.35it/s]
Loading 0:  23%|██▎       | 85/363 [00:08<00:07, 36.69it/s]
Loading 0:  25%|██▍       | 89/363 [00:08<00:07, 35.76it/s]
Loading 0:  26%|██▌       | 94/363 [00:08<00:06, 38.97it/s]
Loading 0:  27%|██▋       | 99/363 [00:08<00:06, 38.97it/s]
Loading 0:  29%|██▊       | 104/363 [00:08<00:06, 39.80it/s]
Loading 0:  30%|███       | 109/363 [00:09<00:06, 39.98it/s]
Loading 0:  31%|███▏      | 114/363 [00:09<00:07, 31.89it/s]
Loading 0:  33%|███▎      | 121/363 [00:09<00:08, 27.32it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:08, 28.35it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:07, 32.25it/s]
Loading 0:  37%|███▋      | 134/363 [00:09<00:07, 32.22it/s]
Loading 0:  38%|███▊      | 139/363 [00:10<00:06, 35.20it/s]
Loading 0:  39%|███▉      | 143/363 [00:10<00:06, 34.00it/s]
Loading 0:  41%|████      | 148/363 [00:10<00:05, 37.06it/s]
Loading 0:  42%|████▏     | 152/363 [00:10<00:05, 35.80it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:05, 37.96it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:05, 35.61it/s]
Loading 0:  46%|████▌     | 166/363 [00:10<00:05, 38.79it/s]
Loading 0:  47%|████▋     | 170/363 [00:10<00:05, 37.29it/s]
Loading 0:  48%|████▊     | 175/363 [00:10<00:04, 39.93it/s]
Loading 0:  50%|████▉     | 180/363 [00:11<00:04, 38.83it/s]
Loading 0:  51%|█████     | 184/363 [00:11<00:04, 38.02it/s]
Loading 0:  52%|█████▏    | 188/363 [00:11<00:04, 36.48it/s]
Loading 0:  53%|█████▎    | 193/363 [00:11<00:04, 39.88it/s]
Loading 0:  55%|█████▍    | 198/363 [00:11<00:04, 38.78it/s]
Loading 0:  56%|█████▌    | 202/363 [00:11<00:06, 26.25it/s]
Loading 0:  57%|█████▋    | 206/363 [00:12<00:05, 27.62it/s]
Loading 0:  58%|█████▊    | 211/363 [00:12<00:04, 31.72it/s]
Loading 0:  59%|█████▉    | 215/363 [00:12<00:04, 31.05it/s]
Loading 0:  61%|██████    | 220/363 [00:12<00:04, 34.28it/s]
Loading 0:  62%|██████▏   | 224/363 [00:12<00:04, 33.28it/s]
Loading 0:  63%|██████▎   | 229/363 [00:12<00:03, 36.16it/s]
Loading 0:  64%|██████▍   | 233/363 [00:12<00:03, 34.72it/s]
Loading 0:  66%|██████▌   | 238/363 [00:12<00:03, 36.53it/s]
Loading 0:  67%|██████▋   | 242/363 [00:12<00:03, 35.17it/s]
Loading 0:  68%|██████▊   | 247/363 [00:13<00:03, 37.68it/s]
Loading 0:  69%|██████▉   | 251/363 [00:13<00:03, 34.24it/s]
Loading 0:  70%|███████   | 255/363 [00:13<00:03, 35.36it/s]
Loading 0:  71%|███████▏  | 259/363 [00:13<00:03, 31.96it/s]
Loading 0:  73%|███████▎  | 265/363 [00:13<00:02, 36.63it/s]
Loading 0:  74%|███████▍  | 269/363 [00:13<00:02, 35.30it/s]
Loading 0:  75%|███████▌  | 274/363 [00:13<00:02, 37.22it/s]
Loading 0:  77%|███████▋  | 278/363 [00:13<00:02, 35.28it/s]
Loading 0:  78%|███████▊  | 283/363 [00:14<00:03, 25.98it/s]
Loading 0:  79%|███████▉  | 287/363 [00:14<00:02, 27.42it/s]
Loading 0:  80%|████████  | 292/363 [00:14<00:02, 31.69it/s]
Loading 0:  82%|████████▏ | 296/363 [00:14<00:02, 31.78it/s]
Loading 0:  83%|████████▎ | 301/363 [00:14<00:01, 34.40it/s]
Loading 0:  84%|████████▍ | 305/363 [00:14<00:01, 33.92it/s]
Loading 0:  85%|████████▌ | 310/363 [00:15<00:01, 37.31it/s]
Loading 0:  87%|████████▋ | 314/363 [00:15<00:01, 35.54it/s]
Loading 0:  88%|████████▊ | 319/363 [00:15<00:01, 37.90it/s]
Loading 0:  89%|████████▉ | 323/363 [00:15<00:01, 36.22it/s]
Loading 0:  90%|█████████ | 328/363 [00:15<00:00, 38.83it/s]
Loading 0:  91%|█████████▏| 332/363 [00:15<00:00, 37.80it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:00, 42.18it/s]
Loading 0:  94%|█████████▍| 343/363 [00:15<00:00, 44.26it/s]
Loading 0:  96%|█████████▌| 348/363 [00:16<00:00, 34.91it/s]
Loading 0:  98%|█████████▊| 356/363 [00:16<00:00, 43.30it/s]
Loading 0:  99%|█████████▉| 361/363 [00:16<00:00, 44.75it/s]
                                                            

Job chaiml-nemo-20241010-ti-5991-v32-mkmlizer completed after 104.45s with status: succeeded
Stopping job with name chaiml-nemo-20241010-ti-5991-v32-mkmlizer
Pipeline stage MKMLizer completed in 105.01s
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-20241010-ti-5991-v32
Waiting for inference service chaiml-nemo-20241010-ti-5991-v32 to be ready
Failed to get response for submission sao10k-mn-12b-lyra-v4a1_v3: ('http://sao10k-mn-12b-lyra-v4a1-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:42302->127.0.0.1:8080: read: connection reset by peer\n')
Inference service chaiml-nemo-20241010-ti-5991-v32 ready after 150.534809589386s
Pipeline stage MKMLDeployer completed in 151.09s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8284790515899658s
Received healthy response to inference request in 1.5560989379882812s
Received healthy response to inference request in 1.3952016830444336s
Received healthy response to inference request in 1.4122421741485596s
Received healthy response to inference request in 1.595686674118042s
5 requests
0 failed requests
5th percentile: 1.3986097812652587
10th percentile: 1.402017879486084
20th percentile: 1.4088340759277345
30th percentile: 1.4410135269165039
40th percentile: 1.4985562324523927
50th percentile: 1.5560989379882812
60th percentile: 1.5719340324401856
70th percentile: 1.58776912689209
80th percentile: 1.6422451496124268
90th percentile: 1.7353621006011963
95th percentile: 1.781920576095581
99th percentile: 1.8191673564910888
mean time: 1.5575417041778565
Pipeline stage StressChecker completed in 9.39s
Shutdown handler de-registered
chaiml-nemo-20241010-ti_5991_v32 status is now deployed due to DeploymentManager action
chaiml-nemo-20241010-ti_5991_v32 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241010-ti_5991_v32 status is now torndown due to DeploymentManager action