developer_uid: azuruce
submission_id: chaiml-nemo-20241017-del_1301_v5
model_name: chaiml-nemo-20241017-del_1301_v5
model_group: ChaiML/nemo-20241017-del
status: torndown
timestamp: 2024-10-18T20:41:19+00:00
num_battles: 6975
num_wins: 3390
celo_rating: 1245.23
family_friendly_score: 0.5907617908066607
family_friendly_standard_error: 0.005994316873164727
submission_type: basic
model_repo: ChaiML/nemo-20241017-della-remerge_v2_5merge-albert
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
display_name: chaiml-nemo-20241017-del_1301_v5
is_internal_developer: True
language_model: ChaiML/nemo-20241017-della-remerge_v2_5merge-albert
model_size: 13B
ranking_group: single
us_pacific_date: 2024-10-18
win_ratio: 0.4860215053763441
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}
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}
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-del-1301-v5-mkmlizer
Waiting for job on chaiml-nemo-20241017-del-1301-v5-mkmlizer to finish
chaiml-nemo-20241017-del-1301-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241017-del-1301-v5-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241017-del-1301-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241017-del-1301-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241017-del-1301-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241017-del-1301-v5-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241017-del-1301-v5-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-del-1301-v5-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241017-del-1301-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241017-del-1301-v5-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241017-del-1301-v5-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-del-1301-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241017-del-1301-v5-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241017-del-1301-v5-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-del-1301-v5-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241017-del-1301-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241017-del-1301-v5-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-nemo-20241017-del-1301-v5-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-del-1301-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241017-del-1301-v5-mkmlizer: Downloaded to shared memory in 30.534s
chaiml-nemo-20241017-del-1301-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpc8z8ku03, device:0
chaiml-nemo-20241017-del-1301-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241017-del-1301-v5-mkmlizer: quantized model in 36.564s
chaiml-nemo-20241017-del-1301-v5-mkmlizer: Processed model ChaiML/nemo-20241017-della-remerge_v2_5merge-albert in 67.098s
chaiml-nemo-20241017-del-1301-v5-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241017-del-1301-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241017-del-1301-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241017-del-1301-v5
chaiml-nemo-20241017-del-1301-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241017-del-1301-v5/config.json
chaiml-nemo-20241017-del-1301-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241017-del-1301-v5/special_tokens_map.json
chaiml-nemo-20241017-del-1301-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241017-del-1301-v5/tokenizer_config.json
chaiml-nemo-20241017-del-1301-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241017-del-1301-v5/tokenizer.json
chaiml-nemo-20241017-del-1301-v5-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:35,  3.09s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:57,  1.20it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:10,  2.70it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:22,  4.21it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:40,  8.36it/s]
Loading 0:   8%|▊         | 28/363 [00:06<00:29, 11.29it/s]
Loading 0:   9%|▉         | 33/363 [00:07<00:24, 13.61it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:20, 16.03it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:17, 18.11it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:14, 21.99it/s]
Loading 0:  15%|█▍        | 53/363 [00:07<00:13, 23.61it/s]
Loading 0:  16%|█▌        | 58/363 [00:07<00:11, 27.31it/s]
Loading 0:  17%|█▋        | 62/363 [00:07<00:10, 28.76it/s]
Loading 0:  18%|█▊        | 67/363 [00:08<00:09, 32.35it/s]
Loading 0:  20%|█▉        | 71/363 [00:08<00:09, 32.14it/s]
Loading 0:  21%|██        | 76/363 [00:08<00:08, 34.87it/s]
Loading 0:  22%|██▏       | 80/363 [00:08<00:08, 33.44it/s]
Loading 0:  23%|██▎       | 85/363 [00:08<00:07, 36.22it/s]
Loading 0:  25%|██▍       | 89/363 [00:08<00:08, 33.75it/s]
Loading 0:  26%|██▌       | 94/363 [00:08<00:07, 36.75it/s]
Loading 0:  27%|██▋       | 98/363 [00:08<00:07, 36.10it/s]
Loading 0:  28%|██▊       | 103/363 [00:09<00:06, 39.56it/s]
Loading 0:  30%|██▉       | 108/363 [00:09<00:06, 39.76it/s]
Loading 0:  31%|███       | 113/363 [00:09<00:06, 40.15it/s]
Loading 0:  33%|███▎      | 119/363 [00:09<00:06, 40.27it/s]
Loading 0:  34%|███▍      | 124/363 [00:09<00:08, 27.97it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:07, 32.71it/s]
Loading 0:  37%|███▋      | 134/363 [00:09<00:07, 32.37it/s]
Loading 0:  38%|███▊      | 138/363 [00:10<00:06, 33.47it/s]
Loading 0:  39%|███▉      | 142/363 [00:10<00:06, 31.85it/s]
Loading 0:  41%|████      | 148/363 [00:10<00:05, 38.25it/s]
Loading 0:  42%|████▏     | 153/363 [00:10<00:05, 40.15it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:04, 41.59it/s]
Loading 0:  45%|████▌     | 164/363 [00:10<00:04, 42.39it/s]
Loading 0:  47%|████▋     | 169/363 [00:10<00:04, 42.13it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:03, 46.76it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:04, 44.02it/s]
Loading 0:  52%|█████▏    | 187/363 [00:11<00:04, 41.32it/s]
Loading 0:  53%|█████▎    | 193/363 [00:11<00:03, 44.50it/s]
Loading 0:  55%|█████▍    | 198/363 [00:11<00:03, 44.11it/s]
Loading 0:  56%|█████▌    | 203/363 [00:11<00:05, 31.29it/s]
Loading 0:  57%|█████▋    | 207/363 [00:11<00:04, 32.96it/s]
Loading 0:  58%|█████▊    | 212/363 [00:11<00:04, 35.70it/s]
Loading 0:  60%|██████    | 218/363 [00:12<00:03, 38.02it/s]
Loading 0:  61%|██████▏   | 223/363 [00:12<00:03, 38.87it/s]
Loading 0:  63%|██████▎   | 229/363 [00:12<00:03, 43.81it/s]
Loading 0:  64%|██████▍   | 234/363 [00:12<00:02, 43.73it/s]
Loading 0:  66%|██████▌   | 239/363 [00:12<00:02, 44.63it/s]
Loading 0:  67%|██████▋   | 245/363 [00:12<00:02, 42.34it/s]
Loading 0:  69%|██████▉   | 250/363 [00:12<00:02, 40.83it/s]
Loading 0:  71%|███████   | 256/363 [00:12<00:02, 43.58it/s]
Loading 0:  72%|███████▏  | 261/363 [00:13<00:02, 42.50it/s]
Loading 0:  73%|███████▎  | 266/363 [00:13<00:02, 43.82it/s]
Loading 0:  75%|███████▍  | 271/363 [00:13<00:02, 45.07it/s]
Loading 0:  76%|███████▌  | 276/363 [00:13<00:02, 36.75it/s]
Loading 0:  78%|███████▊  | 283/363 [00:13<00:02, 31.70it/s]
Loading 0:  79%|███████▉  | 287/363 [00:13<00:02, 32.71it/s]
Loading 0:  81%|████████  | 293/363 [00:13<00:01, 37.13it/s]
Loading 0:  82%|████████▏ | 298/363 [00:14<00:01, 39.49it/s]
Loading 0:  83%|████████▎ | 303/363 [00:14<00:01, 34.90it/s]
Loading 0:  86%|████████▌ | 311/363 [00:14<00:01, 43.25it/s]
Loading 0:  87%|████████▋ | 317/363 [00:14<00:01, 43.33it/s]
Loading 0:  89%|████████▊ | 322/363 [00:14<00:00, 41.79it/s]
Loading 0:  91%|█████████ | 329/363 [00:14<00:00, 46.34it/s]
Loading 0:  92%|█████████▏| 335/363 [00:14<00:00, 45.21it/s]
Loading 0:  94%|█████████▎| 340/363 [00:15<00:00, 43.60it/s]
Loading 0:  95%|█████████▌| 346/363 [00:15<00:00, 45.87it/s]
Loading 0:  97%|█████████▋| 351/363 [00:15<00:00, 44.83it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 44.46it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 42.60it/s]
                                                            

Job chaiml-nemo-20241017-del-1301-v5-mkmlizer completed after 94.27s with status: succeeded
Stopping job with name chaiml-nemo-20241017-del-1301-v5-mkmlizer
Pipeline stage MKMLizer completed in 94.83s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-20241017-del-1301-v5
Waiting for inference service chaiml-nemo-20241017-del-1301-v5 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-nemo-20241017-del-1301-v5 ready after 181.51644253730774s
Pipeline stage MKMLDeployer completed in 182.05s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8851909637451172s
Received healthy response to inference request in 1.4660518169403076s
Received healthy response to inference request in 1.4292500019073486s
Received healthy response to inference request in 1.3812179565429688s
Received healthy response to inference request in 1.4716370105743408s
5 requests
0 failed requests
5th percentile: 1.3908243656158448
10th percentile: 1.4004307746887208
20th percentile: 1.4196435928344726
30th percentile: 1.4366103649139403
40th percentile: 1.451331090927124
50th percentile: 1.4660518169403076
60th percentile: 1.468285894393921
70th percentile: 1.4705199718475341
80th percentile: 1.5543478012084961
90th percentile: 1.7197693824768068
95th percentile: 1.8024801731109619
99th percentile: 1.8686488056182862
mean time: 1.5266695499420166
Pipeline stage StressChecker completed in 9.31s
Shutdown handler de-registered
chaiml-nemo-20241017-del_1301_v5 status is now deployed due to DeploymentManager action
chaiml-nemo-20241017-del_1301_v5 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241017-del_1301_v5 status is now torndown due to DeploymentManager action