developer_uid: azuruce
submission_id: chaiml-nemo-comm-2alinea_5104_v1
model_name: chaiml-nemo-comm-2alinea_5104_v1
model_group: ChaiML/nemo-comm-2alinea
status: torndown
timestamp: 2024-10-01T20:08:21+00:00
num_battles: 3180
num_wins: 1592
celo_rating: 1256.24
family_friendly_score: 0.5838172043010752
family_friendly_standard_error: 0.00884301573274265
submission_type: basic
model_repo: ChaiML/nemo-comm-2alinear-albert
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: chaiml-nemo-comm-2alinea_5104_v1
ineligible_reason: num_battles<5000
is_internal_developer: True
language_model: ChaiML/nemo-comm-2alinear-albert
model_size: 13B
ranking_group: single
us_pacific_date: 2024-10-01
win_ratio: 0.5006289308176101
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|>'], 'max_input_tokens': 1024, 'best_of': 8, '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-comm-2alinea-5104-v1-mkmlizer
Waiting for job on chaiml-nemo-comm-2alinea-5104-v1-mkmlizer to finish
chaiml-nemo-comm-2abio-m-6915-v1-mkmlizer: Downloaded to shared memory in 51.796s
chaiml-nemo-comm-2abio-m-6915-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmtu5t7_j, device:0
chaiml-nemo-comm-2abio-m-6915-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-lyra-rica-2l-4135-v1-mkmlizer: quantized model in 37.538s
chaiml-nemo-lyra-rica-2l-4135-v1-mkmlizer: Processed model ChaiML/nemo-lyra-rica-2linear-albert in 91.359s
chaiml-nemo-lyra-rica-2l-4135-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-lyra-rica-2l-4135-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-lyra-rica-2l-4135-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-lyra-rica-2l-4135-v1
chaiml-nemo-lyra-rica-2l-4135-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-lyra-rica-2l-4135-v1/config.json
chaiml-nemo-lyra-rica-2l-4135-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-lyra-rica-2l-4135-v1/special_tokens_map.json
chaiml-nemo-lyra-rica-2l-4135-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-lyra-rica-2l-4135-v1/tokenizer_config.json
chaiml-nemo-lyra-rica-2l-4135-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-lyra-rica-2l-4135-v1/tokenizer.json
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-comm-2blinea-9021-v1-mkmlizer
Waiting for job on chaiml-nemo-comm-2blinea-9021-v1-mkmlizer to finish
chaiml-nemo-lyra-rica-2l-4135-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-lyra-rica-2l-4135-v1/flywheel_model.0.safetensors
chaiml-nemo-lyra-rica-2l-4135-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:07,  3.01s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:51,  1.23it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:07,  2.75it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:20,  4.31it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:39,  8.55it/s]
Loading 0:   8%|▊         | 28/363 [00:06<00:28, 11.61it/s]
Loading 0:   9%|▉         | 33/363 [00:06<00:22, 14.36it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:18, 17.88it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:15, 20.26it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:12, 25.67it/s]
Loading 0:  15%|█▌        | 56/363 [00:07<00:10, 29.44it/s]
Loading 0:  17%|█▋        | 61/363 [00:07<00:09, 31.25it/s]
Loading 0:  18%|█▊        | 67/363 [00:07<00:08, 36.76it/s]
Loading 0:  20%|█▉        | 72/363 [00:07<00:07, 37.90it/s]
Loading 0:  21%|██        | 77/363 [00:07<00:07, 39.32it/s]
Loading 0:  23%|██▎       | 82/363 [00:08<00:06, 40.34it/s]
Loading 0:  24%|██▍       | 87/363 [00:08<00:08, 34.22it/s]
Loading 0:  26%|██▌       | 94/363 [00:08<00:06, 42.11it/s]
Loading 0:  27%|██▋       | 99/363 [00:08<00:06, 41.12it/s]
Loading 0:  29%|██▊       | 104/363 [00:08<00:06, 42.74it/s]
Loading 0:  30%|███       | 110/363 [00:08<00:06, 41.55it/s]
Loading 0:  32%|███▏      | 115/363 [00:08<00:06, 40.29it/s]
Loading 0:  33%|███▎      | 121/363 [00:09<00:07, 32.53it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:07, 32.67it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:06, 37.22it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:05, 39.15it/s]
Loading 0:  39%|███▉      | 141/363 [00:09<00:06, 32.85it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:06, 35.36it/s]
Loading 0:  41%|████▏     | 150/363 [00:09<00:06, 34.49it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:04, 42.79it/s]
Loading 0:  45%|████▍     | 162/363 [00:10<00:04, 43.84it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:04, 44.11it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:04, 43.70it/s]
Loading 0:  49%|████▉     | 177/363 [00:10<00:05, 32.38it/s]
Loading 0:  50%|█████     | 182/363 [00:10<00:05, 36.08it/s]
Loading 0:  52%|█████▏    | 187/363 [00:10<00:04, 35.62it/s]
Loading 0:  53%|█████▎    | 193/363 [00:10<00:04, 40.03it/s]
Loading 0:  55%|█████▍    | 198/363 [00:11<00:04, 39.59it/s]
Loading 0:  56%|█████▌    | 203/363 [00:11<00:05, 28.21it/s]
Loading 0:  57%|█████▋    | 207/363 [00:11<00:05, 30.00it/s]
Loading 0:  58%|█████▊    | 211/363 [00:11<00:04, 31.42it/s]
Loading 0:  59%|█████▉    | 215/363 [00:11<00:04, 32.09it/s]
Loading 0:  61%|██████    | 220/363 [00:11<00:03, 36.10it/s]
Loading 0:  62%|██████▏   | 224/363 [00:11<00:03, 35.76it/s]
Loading 0:  63%|██████▎   | 229/363 [00:12<00:03, 39.40it/s]
Loading 0:  64%|██████▍   | 234/363 [00:12<00:03, 40.27it/s]
Loading 0:  66%|██████▌   | 239/363 [00:12<00:02, 41.38it/s]
Loading 0:  67%|██████▋   | 244/363 [00:12<00:02, 42.39it/s]
Loading 0:  69%|██████▊   | 249/363 [00:12<00:03, 34.39it/s]
Loading 0:  70%|██████▉   | 254/363 [00:12<00:02, 37.93it/s]
Loading 0:  71%|███████▏  | 259/363 [00:12<00:02, 37.53it/s]
Loading 0:  73%|███████▎  | 265/363 [00:12<00:02, 41.68it/s]
Loading 0:  74%|███████▍  | 270/363 [00:13<00:02, 41.09it/s]
Loading 0:  76%|███████▌  | 275/363 [00:13<00:02, 41.82it/s]
Loading 0:  77%|███████▋  | 280/363 [00:13<00:01, 43.55it/s]
Loading 0:  79%|███████▊  | 285/363 [00:13<00:03, 25.56it/s]
Loading 0:  80%|███████▉  | 290/363 [00:13<00:02, 29.83it/s]
Loading 0:  81%|████████  | 294/363 [00:13<00:02, 29.06it/s]
Loading 0:  83%|████████▎ | 301/363 [00:14<00:01, 35.79it/s]
Loading 0:  84%|████████▍ | 306/363 [00:14<00:01, 36.35it/s]
Loading 0:  86%|████████▌ | 311/363 [00:14<00:01, 36.45it/s]
Loading 0:  87%|████████▋ | 315/363 [00:14<00:01, 36.43it/s]
Loading 0:  88%|████████▊ | 319/363 [00:14<00:01, 36.68it/s]
Loading 0:  89%|████████▉ | 323/363 [00:14<00:01, 35.15it/s]
Loading 0:  90%|█████████ | 327/363 [00:14<00:01, 35.25it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:01, 28.72it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:00, 36.93it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:00, 39.03it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 39.59it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 45.08it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 42.74it/s]
                                                            

chaiml-nemo-lyra-rica-2l-4135-v2-mkmlizer: Downloaded to shared memory in 42.906s
chaiml-nemo-lyra-rica-2l-4135-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpy1ood8of, device:0
chaiml-nemo-lyra-rica-2l-4135-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
Job chaiml-nemo-lyra-rica-2l-4135-v1-mkmlizer completed after 135.1s with status: succeeded
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: ║  belonging to:                                                      ║
Stopping job with name chaiml-nemo-lyra-rica-2l-4135-v1-mkmlizer
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: ║                                                                     ║
Pipeline stage MKMLizer completed in 135.80s
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: ║  Chai Research Corp.                                                ║
run pipeline stage %s
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
Running pipeline stage MKMLTemplater
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: ║                                                                     ║
Pipeline stage MKMLTemplater completed in 0.40s
Shutdown handler not registered because Python interpreter is not running in the main thread
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
run pipeline stage %s
run pipeline %s
Running pipeline stage MKMLDeployer
chaiml-nemo-comm-2abio-m-6915-v1-mkmlizer: creating bucket guanaco-mkml-models
run pipeline stage %s
Creating inference service chaiml-nemo-lyra-rica-2l-4135-v1
chaiml-nemo-comm-2abio-m-6915-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
Running pipeline stage MKMLizer
chaiml-nemo-comm-2abio-m-6915-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-comm-2abio-m-6915-v1
Waiting for inference service chaiml-nemo-lyra-rica-2l-4135-v1 to be ready
Starting job with name chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer
chaiml-nemo-comm-2abio-m-6915-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-comm-2abio-m-6915-v1/special_tokens_map.json
Waiting for job on chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer to finish
chaiml-nemo-comm-2abio-m-6915-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-comm-2abio-m-6915-v1/config.json
chaiml-nemo-comm-2abio-m-6915-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-comm-2abio-m-6915-v1/tokenizer_config.json
chaiml-nemo-comm-2abio-m-6915-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-comm-2abio-m-6915-v1/tokenizer.json
chaiml-nemo-comm-2abio-m-6915-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-comm-2abio-m-6915-v1/flywheel_model.0.safetensors
chaiml-nemo-comm-2abio-m-6915-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<17:51,  2.97s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:45,  1.25it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:42,  3.42it/s]
Loading 0:   5%|▍         | 17/363 [00:06<01:09,  5.00it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:41,  8.15it/s]
Loading 0:   8%|▊         | 29/363 [00:06<00:28, 11.64it/s]
Loading 0:   9%|▉         | 34/363 [00:06<00:21, 15.01it/s]
Loading 0:  11%|█         | 40/363 [00:06<00:18, 17.24it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:16, 19.67it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:12, 25.24it/s]
Loading 0:  15%|█▌        | 56/363 [00:07<00:10, 28.63it/s]
Loading 0:  17%|█▋        | 61/363 [00:07<00:09, 31.14it/s]
Loading 0:  18%|█▊        | 67/363 [00:07<00:08, 36.08it/s]
Loading 0:  20%|█▉        | 72/363 [00:07<00:07, 38.15it/s]
Loading 0:  21%|██        | 77/363 [00:07<00:07, 39.60it/s]
Loading 0:  23%|██▎       | 82/363 [00:07<00:06, 41.88it/s]
Loading 0:  24%|██▍       | 87/363 [00:08<00:07, 36.39it/s]
Loading 0:  26%|██▌       | 95/363 [00:08<00:06, 44.54it/s]
Loading 0:  28%|██▊       | 101/363 [00:08<00:06, 43.12it/s]
Loading 0:  29%|██▉       | 106/363 [00:08<00:05, 43.17it/s]
Loading 0:  31%|███       | 112/363 [00:08<00:05, 45.50it/s]
Loading 0:  32%|███▏      | 117/363 [00:08<00:05, 45.50it/s]
Loading 0:  34%|███▎      | 122/363 [00:08<00:07, 33.19it/s]
Loading 0:  35%|███▌      | 128/363 [00:09<00:06, 34.86it/s]
Loading 0:  36%|███▋      | 132/363 [00:09<00:06, 34.19it/s]
Loading 0:  38%|███▊      | 139/363 [00:09<00:05, 41.64it/s]
Loading 0:  40%|███▉      | 144/363 [00:09<00:05, 42.26it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:04, 43.55it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:04, 44.88it/s]
Loading 0:  44%|████▍     | 159/363 [00:09<00:05, 37.48it/s]
Loading 0:  46%|████▌     | 167/363 [00:09<00:04, 45.52it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:04, 46.05it/s]
Loading 0:  49%|████▉     | 177/363 [00:10<00:04, 37.38it/s]
Loading 0:  51%|█████     | 184/363 [00:10<00:04, 44.48it/s]
Loading 0:  52%|█████▏    | 189/363 [00:10<00:03, 43.96it/s]
Loading 0:  53%|█████▎    | 194/363 [00:10<00:03, 43.35it/s]
Loading 0:  55%|█████▌    | 200/363 [00:10<00:03, 41.77it/s]
Loading 0:  56%|█████▋    | 205/363 [00:11<00:05, 29.93it/s]
Loading 0:  58%|█████▊    | 211/363 [00:11<00:04, 35.47it/s]
Loading 0:  60%|█████▉    | 216/363 [00:11<00:03, 37.49it/s]
Loading 0:  61%|██████    | 221/363 [00:11<00:03, 39.03it/s]
Loading 0:  63%|██████▎   | 227/363 [00:11<00:03, 38.89it/s]
Loading 0:  64%|██████▍   | 232/363 [00:11<00:03, 39.38it/s]
Loading 0:  66%|██████▌   | 238/363 [00:11<00:02, 43.84it/s]
Loading 0:  67%|██████▋   | 243/363 [00:11<00:02, 44.08it/s]
Loading 0:  68%|██████▊   | 248/363 [00:11<00:02, 44.82it/s]
Loading 0:  70%|██████▉   | 254/363 [00:12<00:02, 42.45it/s]
Loading 0:  71%|███████▏  | 259/363 [00:12<00:02, 41.64it/s]
Loading 0:  73%|███████▎  | 265/363 [00:12<00:02, 45.98it/s]
Loading 0:  74%|███████▍  | 270/363 [00:12<00:02, 46.02it/s]
Loading 0:  76%|███████▌  | 275/363 [00:12<00:01, 46.19it/s]
Loading 0:  77%|███████▋  | 281/363 [00:12<00:01, 43.82it/s]
Loading 0:  79%|███████▉  | 286/363 [00:13<00:02, 29.53it/s]
Loading 0:  81%|████████  | 293/363 [00:13<00:01, 35.93it/s]
Loading 0:  82%|████████▏ | 299/363 [00:13<00:01, 36.99it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:01, 37.91it/s]
Loading 0:  86%|████████▌ | 311/363 [00:13<00:01, 43.24it/s]
Loading 0:  87%|████████▋ | 317/363 [00:13<00:01, 42.28it/s]
Loading 0:  89%|████████▊ | 322/363 [00:13<00:00, 42.39it/s]
Loading 0:  90%|█████████ | 328/363 [00:13<00:00, 46.45it/s]
Loading 0:  92%|█████████▏| 333/363 [00:14<00:00, 46.21it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:00, 46.82it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 44.39it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 43.15it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 47.58it/s]
Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 44.33it/s]
                                                            

chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
Job chaiml-nemo-comm-2abio-m-6915-v1-mkmlizer completed after 116.9s with status: succeeded
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
Stopping job with name chaiml-nemo-comm-2abio-m-6915-v1-mkmlizer
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: ║                                                                     ║
Pipeline stage MKMLizer completed in 117.81s
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
run pipeline stage %s
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
Running pipeline stage MKMLTemplater
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: ║  https://mk1.ai                                                     ║
Pipeline stage MKMLTemplater completed in 0.38s
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: ║                                                                     ║
run pipeline stage %s
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
Running pipeline stage MKMLDeployer
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: ║  belonging to:                                                      ║
Creating inference service chaiml-nemo-comm-2abio-m-6915-v1
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: ║                                                                     ║
Waiting for inference service chaiml-nemo-comm-2abio-m-6915-v1 to be ready
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: Downloaded to shared memory in 51.211s
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpsu_ouidn, device:0
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-lyra-rica-2l-4135-v2-mkmlizer: quantized model in 37.754s
chaiml-nemo-lyra-rica-2l-4135-v2-mkmlizer: Processed model ChaiML/nemo-lyra-rica-2linear-albert in 80.661s
chaiml-nemo-lyra-rica-2l-4135-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-lyra-rica-2l-4135-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-lyra-rica-2l-4135-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-lyra-rica-2l-4135-v2
chaiml-nemo-lyra-rica-2l-4135-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-lyra-rica-2l-4135-v2/config.json
chaiml-nemo-lyra-rica-2l-4135-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-lyra-rica-2l-4135-v2/special_tokens_map.json
chaiml-nemo-lyra-rica-2l-4135-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-lyra-rica-2l-4135-v2/tokenizer_config.json
chaiml-nemo-lyra-rica-2l-4135-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-lyra-rica-2l-4135-v2/tokenizer.json
chaiml-nemo-lyra-rica-2l-4135-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-lyra-rica-2l-4135-v2/flywheel_model.0.safetensors
Inference service chaiml-nemo-lyra-rica-2b-8403-v1 ready after 140.31981587409973s
chaiml-nemo-lyra-rica-2l-4135-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:09,  3.02s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:51,  1.23it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:08,  2.75it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:21,  4.27it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:40,  8.48it/s]
Loading 0:   8%|▊         | 28/363 [00:06<00:29, 11.47it/s]
Loading 0:   9%|▉         | 33/363 [00:06<00:23, 13.93it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:19, 16.85it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:16, 19.09it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:13, 23.28it/s]
Loading 0:  15%|█▍        | 53/363 [00:07<00:12, 25.35it/s]
Loading 0:  16%|█▌        | 58/363 [00:07<00:10, 29.82it/s]
Loading 0:  17%|█▋        | 63/363 [00:07<00:09, 31.96it/s]
Loading 0:  19%|█▊        | 68/363 [00:07<00:08, 34.59it/s]
Loading 0:  20%|██        | 73/363 [00:07<00:07, 37.86it/s]
Loading 0:  21%|██▏       | 78/363 [00:08<00:08, 33.11it/s]
Loading 0:  23%|██▎       | 85/363 [00:08<00:06, 40.21it/s]
Loading 0:  25%|██▍       | 90/363 [00:08<00:07, 38.93it/s]
Loading 0:  26%|██▌       | 95/363 [00:08<00:06, 38.39it/s]
Loading 0:  28%|██▊       | 100/363 [00:08<00:06, 38.53it/s]
Loading 0:  29%|██▉       | 105/363 [00:08<00:08, 31.46it/s]
Loading 0:  31%|███       | 112/363 [00:09<00:06, 37.53it/s]
Loading 0:  32%|███▏      | 117/363 [00:09<00:06, 37.71it/s]
Loading 0:  34%|███▎      | 122/363 [00:09<00:09, 25.85it/s]
Loading 0:  35%|███▍      | 126/363 [00:09<00:08, 27.23it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:07, 29.34it/s]
Loading 0:  37%|███▋      | 134/363 [00:09<00:07, 29.53it/s]
Loading 0:  38%|███▊      | 139/363 [00:09<00:06, 32.58it/s]
Loading 0:  39%|███▉      | 143/363 [00:10<00:06, 32.20it/s]
Loading 0:  41%|████      | 148/363 [00:10<00:06, 35.24it/s]
Loading 0:  42%|████▏     | 152/363 [00:10<00:06, 34.16it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:05, 36.39it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:05, 34.77it/s]
Loading 0:  46%|████▌     | 166/363 [00:10<00:05, 36.52it/s]
Loading 0:  47%|████▋     | 170/363 [00:10<00:05, 34.51it/s]
Loading 0:  48%|████▊     | 175/363 [00:10<00:05, 36.44it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:05, 35.11it/s]
Loading 0:  51%|█████     | 184/363 [00:11<00:04, 37.56it/s]
Loading 0:  52%|█████▏    | 188/363 [00:11<00:04, 35.70it/s]
Loading 0:  53%|█████▎    | 193/363 [00:11<00:04, 38.49it/s]
Loading 0:  54%|█████▍    | 197/363 [00:11<00:04, 36.92it/s]
Loading 0:  56%|█████▌    | 202/363 [00:11<00:05, 26.95it/s]
Loading 0:  57%|█████▋    | 206/363 [00:11<00:05, 28.16it/s]
Loading 0:  58%|█████▊    | 211/363 [00:12<00:04, 31.93it/s]
Loading 0:  59%|█████▉    | 215/363 [00:12<00:04, 31.75it/s]
Loading 0:  61%|██████    | 220/363 [00:12<00:04, 34.64it/s]
Loading 0:  62%|██████▏   | 224/363 [00:12<00:04, 33.97it/s]
Loading 0:  63%|██████▎   | 229/363 [00:12<00:03, 36.79it/s]
Loading 0:  64%|██████▍   | 233/363 [00:12<00:03, 35.49it/s]
Loading 0:  66%|██████▌   | 238/363 [00:12<00:03, 37.81it/s]
Loading 0:  67%|██████▋   | 242/363 [00:12<00:03, 35.51it/s]
Loading 0:  68%|██████▊   | 247/363 [00:13<00:03, 38.08it/s]
Loading 0:  69%|██████▉   | 251/363 [00:13<00:03, 36.01it/s]
Loading 0:  71%|███████   | 256/363 [00:13<00:02, 38.49it/s]
Loading 0:  72%|███████▏  | 260/363 [00:13<00:02, 37.68it/s]
Loading 0:  73%|███████▎  | 265/363 [00:13<00:02, 40.63it/s]
Loading 0:  74%|███████▍  | 270/363 [00:13<00:02, 40.96it/s]
Loading 0:  76%|███████▌  | 275/363 [00:13<00:02, 41.72it/s]
Loading 0:  77%|███████▋  | 280/363 [00:13<00:01, 41.61it/s]
Loading 0:  79%|███████▊  | 285/363 [00:14<00:03, 25.76it/s]
Loading 0:  80%|████████  | 292/363 [00:14<00:02, 32.88it/s]
Loading 0:  82%|████████▏ | 297/363 [00:14<00:01, 34.15it/s]
Loading 0:  83%|████████▎ | 302/363 [00:14<00:01, 34.86it/s]
Loading 0:  84%|████████▍ | 306/363 [00:14<00:01, 35.62it/s]
Loading 0:  86%|████████▌ | 311/363 [00:14<00:01, 37.90it/s]
Loading 0:  87%|████████▋ | 316/363 [00:14<00:01, 40.23it/s]
Loading 0:  88%|████████▊ | 321/363 [00:15<00:01, 35.66it/s]
Loading 0:  90%|█████████ | 328/363 [00:15<00:00, 43.66it/s]
Loading 0:  92%|█████████▏| 333/363 [00:15<00:00, 44.07it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:00, 44.91it/s]
Loading 0:  94%|█████████▍| 343/363 [00:15<00:00, 45.48it/s]
Loading 0:  96%|█████████▌| 348/363 [00:15<00:00, 35.92it/s]
Loading 0:  98%|█████████▊| 355/363 [00:15<00:00, 43.39it/s]
Loading 0:  99%|█████████▉| 360/363 [00:15<00:00, 42.50it/s]
                                                            

Pipeline stage MKMLDeployer completed in 141.32s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1429383754730225s
Received healthy response to inference request in 1.7333347797393799s
Received healthy response to inference request in 1.664153814315796s
Received healthy response to inference request in 1.4861140251159668s
Received healthy response to inference request in 1.4907402992248535s
5 requests
0 failed requests
5th percentile: 1.487039279937744
10th percentile: 1.4879645347595214
20th percentile: 1.4898150444030762
30th percentile: 1.525423002243042
40th percentile: 1.594788408279419
50th percentile: 1.664153814315796
60th percentile: 1.6918262004852296
70th percentile: 1.719498586654663
80th percentile: 1.8152554988861085
90th percentile: 1.9790969371795655
95th percentile: 2.061017656326294
99th percentile: 2.1265542316436767
mean time: 1.7034562587738038
Pipeline stage StressChecker completed in 14.55s
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: Downloaded to shared memory in 52.117s
run pipeline stage %s
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpp8sqng4q, device:0
Running pipeline stage TriggerMKMLProfilingPipeline
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 3.28s
Shutdown handler de-registered
chaiml-nemo-lyra-rica-2b_8403_v1 status is now deployed due to DeploymentManager action
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: quantized model in 39.295s
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: Processed model ChaiML/nemo-comm-2alinear-albert in 90.507s
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-comm-2alinea-5104-v1
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-comm-2alinea-5104-v1/config.json
Job chaiml-nemo-lyra-rica-2l-4135-v2-mkmlizer completed after 131.68s with status: succeeded
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-comm-2alinea-5104-v1/special_tokens_map.json
Stopping job with name chaiml-nemo-lyra-rica-2l-4135-v2-mkmlizer
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-comm-2alinea-5104-v1/tokenizer_config.json
Pipeline stage MKMLizer completed in 132.77s
chaiml-nemo-comm-2alinea-5104-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-comm-2alinea-5104-v1/tokenizer.json
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.30s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-lyra-rica-2l-4135-v2
Waiting for inference service chaiml-nemo-lyra-rica-2l-4135-v2 to be ready
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: Downloaded to shared memory in 51.832s
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpehf_p5ld, device:0
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Job chaiml-nemo-comm-2alinea-5104-v1-mkmlizer completed after 118.86s with status: succeeded
Stopping job with name chaiml-nemo-comm-2alinea-5104-v1-mkmlizer
Pipeline stage MKMLizer completed in 119.92s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.30s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-comm-2alinea-5104-v1
Waiting for inference service chaiml-nemo-comm-2alinea-5104-v1 to be ready
admin requested tearing down of zonemercy-virgo-edit-v1-1e5_v17
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLDeleter
Checking if service zonemercy-virgo-edit-v1-1e5-v17 is running
Tearing down inference service zonemercy-virgo-edit-v1-1e5-v17
Service zonemercy-virgo-edit-v1-1e5-v17 has been torndown
Pipeline stage MKMLDeleter completed in 2.44s
run pipeline stage %s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key zonemercy-virgo-edit-v1-1e5-v17/config.json from bucket guanaco-mkml-models
Deleting key zonemercy-virgo-edit-v1-1e5-v17/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key zonemercy-virgo-edit-v1-1e5-v17/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key zonemercy-virgo-edit-v1-1e5-v17/tokenizer.json from bucket guanaco-mkml-models
Deleting key zonemercy-virgo-edit-v1-1e5-v17/tokenizer_config.json from bucket guanaco-mkml-models
Pipeline stage MKMLModelDeleter completed in 3.87s
Shutdown handler de-registered
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: quantized model in 36.545s
zonemercy-virgo-edit-v1-1e5_v17 status is now torndown due to DeploymentManager action
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: Processed model ChaiML/nemo-comm-2blinear-albert in 88.662s
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-comm-2blinea-9021-v1
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-comm-2blinea-9021-v1/config.json
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-comm-2blinea-9021-v1/special_tokens_map.json
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-comm-2blinea-9021-v1/tokenizer_config.json
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-comm-2blinea-9021-v1/tokenizer.json
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-comm-2blinea-9021-v1/flywheel_model.0.safetensors
chaiml-nemo-comm-2blinea-9021-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<17:50,  2.96s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:46,  1.25it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:06,  2.79it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:20,  4.34it/s]
Loading 0:   6%|▌         | 22/363 [00:06<00:42,  8.11it/s]
Loading 0:   7%|▋         | 27/363 [00:06<00:30, 11.17it/s]
Loading 0:   9%|▉         | 32/363 [00:06<00:22, 14.87it/s]
Loading 0:  10%|█         | 38/363 [00:06<00:16, 19.23it/s]
Loading 0:  12%|█▏        | 43/363 [00:07<00:17, 18.53it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:12, 24.98it/s]
Loading 0:  15%|█▌        | 56/363 [00:07<00:10, 27.94it/s]
Loading 0:  17%|█▋        | 61/363 [00:07<00:10, 30.07it/s]
Loading 0:  18%|█▊        | 67/363 [00:07<00:08, 35.73it/s]
Loading 0:  20%|█▉        | 72/363 [00:07<00:07, 37.72it/s]
Loading 0:  21%|██        | 77/363 [00:07<00:07, 39.49it/s]
Loading 0:  23%|██▎       | 83/363 [00:08<00:07, 39.44it/s]
Loading 0:  24%|██▍       | 88/363 [00:08<00:07, 39.28it/s]
Loading 0:  26%|██▌       | 95/363 [00:08<00:06, 44.53it/s]
Loading 0:  28%|██▊       | 100/363 [00:08<00:05, 45.79it/s]
Loading 0:  29%|██▉       | 105/363 [00:08<00:06, 37.42it/s]
Loading 0:  31%|███       | 112/363 [00:08<00:05, 43.50it/s]
Loading 0:  32%|███▏      | 117/363 [00:08<00:05, 41.64it/s]
Loading 0:  34%|███▎      | 122/363 [00:09<00:07, 31.04it/s]
Loading 0:  35%|███▍      | 127/363 [00:09<00:06, 34.35it/s]
Loading 0:  36%|███▋      | 132/363 [00:09<00:06, 33.08it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:05, 41.25it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:05, 40.94it/s]
Loading 0:  42%|████▏     | 151/363 [00:09<00:05, 40.15it/s]
Loading 0:  43%|████▎     | 157/363 [00:09<00:04, 44.64it/s]
Loading 0:  45%|████▍     | 162/363 [00:09<00:04, 43.67it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:04, 42.01it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:04, 43.00it/s]
Loading 0:  49%|████▉     | 177/363 [00:10<00:05, 37.06it/s]
Loading 0:  51%|█████     | 184/363 [00:10<00:04, 44.60it/s]
Loading 0:  52%|█████▏    | 189/363 [00:10<00:03, 44.60it/s]
Loading 0:  53%|█████▎    | 194/363 [00:10<00:03, 45.34it/s]
Loading 0:  55%|█████▌    | 200/363 [00:10<00:03, 43.75it/s]
Loading 0:  56%|█████▋    | 205/363 [00:11<00:05, 29.99it/s]
Loading 0:  58%|█████▊    | 211/363 [00:11<00:04, 35.70it/s]
Loading 0:  60%|█████▉    | 216/363 [00:11<00:03, 38.07it/s]
Loading 0:  61%|██████    | 221/363 [00:11<00:03, 39.94it/s]
Loading 0:  62%|██████▏   | 226/363 [00:11<00:03, 41.89it/s]
Loading 0:  64%|██████▎   | 231/363 [00:11<00:03, 35.27it/s]
Loading 0:  66%|██████▌   | 238/363 [00:11<00:02, 43.13it/s]
Loading 0:  67%|██████▋   | 243/363 [00:12<00:02, 41.49it/s]
Loading 0:  68%|██████▊   | 248/363 [00:12<00:02, 42.37it/s]
Loading 0:  70%|██████▉   | 254/363 [00:12<00:02, 42.11it/s]
Loading 0:  71%|███████▏  | 259/363 [00:12<00:02, 42.21it/s]
Loading 0:  73%|███████▎  | 265/363 [00:12<00:02, 46.51it/s]
Loading 0:  74%|███████▍  | 270/363 [00:12<00:02, 46.06it/s]
Loading 0:  76%|███████▌  | 275/363 [00:12<00:01, 46.65it/s]
Loading 0:  77%|███████▋  | 281/363 [00:12<00:01, 44.63it/s]
Loading 0:  79%|███████▉  | 286/363 [00:13<00:02, 30.36it/s]
Loading 0:  81%|████████  | 293/363 [00:13<00:01, 36.93it/s]
Loading 0:  82%|████████▏ | 299/363 [00:13<00:01, 36.55it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:01, 35.10it/s]
Loading 0:  85%|████████▌ | 310/363 [00:13<00:01, 39.16it/s]
Loading 0:  87%|████████▋ | 315/363 [00:13<00:01, 40.02it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:01, 42.11it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:00, 42.90it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:00, 37.30it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:00, 45.44it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 43.59it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 41.81it/s]
Loading 0:  98%|█████████▊| 355/363 [00:14<00:00, 44.29it/s]
Loading 0:  99%|█████████▉| 360/363 [00:14<00:00, 43.56it/s]
                                                            

Job chaiml-nemo-comm-2blinea-9021-v1-mkmlizer completed after 120.34s with status: succeeded
Stopping job with name chaiml-nemo-comm-2blinea-9021-v1-mkmlizer
Pipeline stage MKMLizer completed in 121.60s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.39s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-comm-2blinea-9021-v1
Waiting for inference service chaiml-nemo-comm-2blinea-9021-v1 to be ready
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: quantized model in 35.443s
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: Processed model ChaiML/nemo-comm-2bbio-merge-albert in 87.275s
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-comm-2bbio-m-2877-v1
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-comm-2bbio-m-2877-v1/config.json
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-comm-2bbio-m-2877-v1/special_tokens_map.json
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-comm-2bbio-m-2877-v1/tokenizer_config.json
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-comm-2bbio-m-2877-v1/tokenizer.json
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-comm-2bbio-m-2877-v1/flywheel_model.0.safetensors
chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<17:47,  2.96s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:45,  1.25it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:42,  3.43it/s]
Loading 0:   5%|▍         | 17/363 [00:06<01:09,  4.99it/s]
Loading 0:   6%|▌         | 22/363 [00:06<00:44,  7.61it/s]
Loading 0:   7%|▋         | 27/363 [00:06<00:30, 10.84it/s]
Loading 0:   9%|▉         | 33/363 [00:06<00:22, 14.79it/s]
Loading 0:  11%|█         | 40/363 [00:06<00:17, 17.96it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:15, 20.39it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:12, 26.03it/s]
Loading 0:  15%|█▌        | 56/363 [00:07<00:10, 30.07it/s]
Loading 0:  17%|█▋        | 61/363 [00:07<00:09, 32.20it/s]
Loading 0:  19%|█▊        | 68/363 [00:07<00:07, 38.25it/s]
Loading 0:  20%|██        | 73/363 [00:07<00:07, 40.82it/s]
Loading 0:  21%|██▏       | 78/363 [00:07<00:08, 34.49it/s]
Loading 0:  23%|██▎       | 85/363 [00:07<00:06, 40.44it/s]
Loading 0:  25%|██▍       | 90/363 [00:08<00:06, 40.00it/s]
Loading 0:  26%|██▌       | 95/363 [00:08<00:06, 40.78it/s]
Loading 0:  28%|██▊       | 101/363 [00:08<00:06, 42.19it/s]
Loading 0:  29%|██▉       | 106/363 [00:08<00:05, 43.07it/s]
Loading 0:  31%|███       | 112/363 [00:08<00:05, 47.03it/s]
Loading 0:  32%|███▏      | 117/363 [00:08<00:05, 45.09it/s]
Loading 0:  34%|███▎      | 122/363 [00:08<00:07, 30.83it/s]
Loading 0:  35%|███▍      | 126/363 [00:09<00:07, 32.39it/s]
Loading 0:  36%|███▋      | 132/363 [00:09<00:06, 33.75it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:05, 42.50it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:05, 43.00it/s]
Loading 0:  42%|████▏     | 151/363 [00:09<00:04, 43.26it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:04, 48.18it/s]
Loading 0:  45%|████▌     | 164/363 [00:09<00:04, 47.14it/s]
Loading 0:  47%|████▋     | 169/363 [00:09<00:04, 46.30it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:03, 50.60it/s]
Loading 0:  50%|█████     | 182/363 [00:10<00:03, 48.97it/s]
Loading 0:  52%|█████▏    | 187/363 [00:10<00:03, 45.78it/s]
Loading 0:  53%|█████▎    | 194/363 [00:10<00:03, 47.25it/s]
Loading 0:  55%|█████▌    | 200/363 [00:10<00:03, 46.63it/s]
Loading 0:  56%|█████▋    | 205/363 [00:10<00:04, 33.24it/s]
Loading 0:  58%|█████▊    | 211/363 [00:11<00:04, 37.38it/s]
Loading 0:  60%|█████▉    | 216/363 [00:11<00:03, 39.22it/s]
Loading 0:  61%|██████    | 221/363 [00:11<00:03, 41.64it/s]
Loading 0:  63%|██████▎   | 227/363 [00:11<00:03, 42.42it/s]
Loading 0:  64%|██████▍   | 232/363 [00:11<00:03, 42.23it/s]
Loading 0:  66%|██████▌   | 239/363 [00:11<00:02, 47.40it/s]
Loading 0:  67%|██████▋   | 245/363 [00:11<00:02, 46.71it/s]
Loading 0:  69%|██████▉   | 250/363 [00:11<00:02, 45.90it/s]
Loading 0:  71%|███████   | 257/363 [00:11<00:02, 49.50it/s]
Loading 0:  72%|███████▏  | 263/363 [00:12<00:02, 45.55it/s]
Loading 0:  74%|███████▍  | 268/363 [00:12<00:02, 44.35it/s]
Loading 0:  76%|███████▌  | 275/363 [00:12<00:01, 48.41it/s]
Loading 0:  77%|███████▋  | 281/363 [00:12<00:01, 46.41it/s]
Loading 0:  79%|███████▉  | 286/363 [00:12<00:02, 32.14it/s]
Loading 0:  81%|████████  | 293/363 [00:12<00:01, 38.36it/s]
Loading 0:  82%|████████▏ | 299/363 [00:13<00:01, 39.45it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:01, 39.17it/s]
Loading 0:  85%|████████▌ | 309/363 [00:13<00:01, 41.47it/s]
Loading 0:  87%|████████▋ | 314/363 [00:13<00:01, 40.99it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:00, 45.04it/s]
Loading 0:  90%|████████▉ | 326/363 [00:13<00:00, 43.67it/s]
Loading 0:  91%|█████████ | 331/363 [00:13<00:00, 43.69it/s]
Loading 0:  93%|█████████▎| 338/363 [00:13<00:00, 49.45it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 47.00it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 42.41it/s]
Loading 0:  98%|█████████▊| 355/363 [00:14<00:00, 46.68it/s]
Loading 0:  99%|█████████▉| 360/363 [00:14<00:00, 45.55it/s]
                                                            

Job chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer completed after 111.36s with status: succeeded
Stopping job with name chaiml-nemo-comm-2bbio-m-2877-v1-mkmlizer
Pipeline stage MKMLizer completed in 113.08s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.34s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-comm-2bbio-m-2877-v1
Waiting for inference service chaiml-nemo-comm-2bbio-m-2877-v1 to be ready
Inference service chaiml-nemo-lyra-rica-2l-4135-v1 ready after 140.32526564598083s
Pipeline stage MKMLDeployer completed in 141.91s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.053893804550171s
Received healthy response to inference request in 1.8128771781921387s
Received healthy response to inference request in 1.648629903793335s
Received healthy response to inference request in 1.4651131629943848s
Received healthy response to inference request in 1.6960840225219727s
5 requests
0 failed requests
5th percentile: 1.5018165111541748
10th percentile: 1.5385198593139648
20th percentile: 1.611926555633545
30th percentile: 1.6581207275390626
40th percentile: 1.6771023750305176
50th percentile: 1.6960840225219727
60th percentile: 1.7428012847900392
70th percentile: 1.7895185470581054
Inference service chaiml-nemo-comm-2abio-m-6915-v1 ready after 140.40478682518005s
80th percentile: 1.8610805034637452
Pipeline stage MKMLDeployer completed in 141.78s
90th percentile: 1.957487154006958
run pipeline stage %s
95th percentile: 2.0056904792785644
Running pipeline stage StressChecker
99th percentile: 2.0442531394958494
mean time: 1.7353196144104004
Pipeline stage StressChecker completed in 15.69s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Received healthy response to inference request in 2.209772825241089s
Pipeline stage TriggerMKMLProfilingPipeline completed in 2.67s
Shutdown handler de-registered
chaiml-nemo-lyra-rica-2l_4135_v1 status is now deployed due to DeploymentManager action
Received healthy response to inference request in 1.994039535522461s
Received healthy response to inference request in 1.8315038681030273s
Received healthy response to inference request in 1.7383065223693848s
Received healthy response to inference request in 1.767585277557373s
5 requests
0 failed requests
5th percentile: 1.7441622734069824
10th percentile: 1.75001802444458
20th percentile: 1.7617295265197754
30th percentile: 1.7803689956665039
40th percentile: 1.8059364318847657
50th percentile: 1.8315038681030273
60th percentile: 1.8965181350708007
70th percentile: 1.9615324020385743
80th percentile: 2.0371861934661863
90th percentile: 2.1234795093536376
95th percentile: 2.1666261672973635
99th percentile: 2.201143493652344
mean time: 1.908241605758667
Pipeline stage StressChecker completed in 15.80s
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 2.17s
Shutdown handler de-registered
chaiml-nemo-comm-2abio-m_6915_v1 status is now deployed due to DeploymentManager action
Inference service chaiml-nemo-lyra-rica-2l-4135-v2 ready after 140.37117099761963s
Pipeline stage MKMLDeployer completed in 141.51s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1581437587738037s
Received healthy response to inference request in 1.5772523880004883s
Received healthy response to inference request in 1.7644906044006348s
Received healthy response to inference request in 1.8408780097961426s
Inference service chaiml-nemo-comm-2alinea-5104-v1 ready after 140.41578197479248s
Pipeline stage MKMLDeployer completed in 141.56s
Received healthy response to inference request in 2.2019307613372803s
run pipeline stage %s
5 requests
Running pipeline stage StressChecker
0 failed requests
5th percentile: 1.6147000312805175
10th percentile: 1.6521476745605468
20th percentile: 1.7270429611206055
30th percentile: 1.7797680854797364
40th percentile: 1.8103230476379395
50th percentile: 1.8408780097961426
60th percentile: 1.967784309387207
70th percentile: 2.0946906089782713
80th percentile: 2.166901159286499
90th percentile: 2.1844159603118896
Received healthy response to inference request in 2.1060848236083984s
95th percentile: 2.193173360824585
99th percentile: 2.200179281234741
mean time: 1.90853910446167
Pipeline stage StressChecker completed in 14.42s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Received healthy response to inference request in 1.8384015560150146s
Pipeline stage TriggerMKMLProfilingPipeline completed in 2.15s
Shutdown handler de-registered
chaiml-nemo-lyra-rica-2l_4135_v2 status is now deployed due to DeploymentManager action
Received healthy response to inference request in 1.7227599620819092s
Received healthy response to inference request in 1.1884765625s
Received healthy response to inference request in 1.6881577968597412s
5 requests
0 failed requests
5th percentile: 1.2884128093719482
10th percentile: 1.3883490562438965
20th percentile: 1.588221549987793
30th percentile: 1.695078229904175
40th percentile: 1.708919095993042
50th percentile: 1.7227599620819092
60th percentile: 1.7690165996551515
70th percentile: 1.8152732372283935
80th percentile: 1.8919382095336914
90th percentile: 1.999011516571045
95th percentile: 2.0525481700897217
99th percentile: 2.095377492904663
mean time: 1.7087761402130126
Pipeline stage StressChecker completed in 12.89s
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 2.24s
Shutdown handler de-registered
chaiml-nemo-comm-2alinea_5104_v1 status is now deployed due to DeploymentManager action
chaiml-nemo-comm-2alinea_5104_v1 status is now inactive due to auto deactivation removed underperforming models
Deleting key chaiml-nemo-chai-4bio-me-9462-v1/tokenizer_config.json from bucket guanaco-mkml-models
admin requested tearing down of chaiml-nemo-comm-2alinea_5104_v1
Shutdown handler de-registered
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage MKMLModelDeleter completed in 3.49s
chaiml-nemo-all-10_v1 status is now torndown due to DeploymentManager action
run pipeline %s
Shutdown handler de-registered
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of chaiml-nemo-comm-2blinea_9021_v1
run pipeline stage %s
chaiml-nemo-chai-4bio-me_9462_v1 status is now torndown due to DeploymentManager action
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of chaiml-nemo-community-2_v1
Running pipeline stage MKMLDeleter
run pipeline stage %s
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
Checking if service chaiml-nemo-comm-2alinea-5104-v1 is running
Running pipeline stage MKMLDeleter
run pipeline %s
run pipeline stage %s
Checking if service chaiml-nemo-comm-2bbio-m-2877-v1 is running
run pipeline stage %s
Running pipeline stage MKMLDeleter
Tearing down inference service chaiml-nemo-comm-2alinea-5104-v1
Running pipeline stage MKMLDeleter
Checking if service chaiml-nemo-comm-2blinea-9021-v1 is running
Service chaiml-nemo-comm-2alinea-5104-v1 has been torndown
Tearing down inference service chaiml-nemo-comm-2bbio-m-2877-v1
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLDeleter completed in 5.26s
Service chaiml-nemo-comm-2bbio-m-2877-v1 has been torndown
Pipeline stage MKMLDeleter completed in 2.17s
Tearing down inference service chaiml-nemo-comm-2blinea-9021-v1
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 5.47s
run pipeline stage %s
Service chaiml-nemo-comm-2blinea-9021-v1 has been torndown
Running pipeline stage MKMLModelDeleter
run pipeline stage %s
Running pipeline stage MKMLModelDeleter
Pipeline stage MKMLDeleter completed in 6.21s
Cleaning model data from S3
Running pipeline stage MKMLModelDeleter
Pipeline stage %s skipped, reason=%s
run pipeline stage %s
Cleaning model data from model cache
Cleaning model data from S3
Pipeline stage MKMLModelDeleter completed in 2.71s
Running pipeline stage MKMLModelDeleter
Deleting key chaiml-nemo-comm-2alinea-5104-v1/config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Shutdown handler de-registered
Cleaning model data from S3
Deleting key chaiml-nemo-comm-2alinea-5104-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-nemo-comm-2bbio-m-2877-v1/config.json from bucket guanaco-mkml-models
chaiml-nemo-community-2_v1 status is now torndown due to DeploymentManager action
Cleaning model data from model cache
Deleting key chaiml-nemo-comm-2bbio-m-2877-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-nemo-comm-2blinea-9021-v1/config.json from bucket guanaco-mkml-models
Deleting key chaiml-nemo-comm-2alinea-5104-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-nemo-comm-2blinea-9021-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-nemo-comm-2alinea-5104-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-nemo-comm-2bbio-m-2877-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-nemo-comm-2alinea-5104-v1/tokenizer_config.json from bucket guanaco-mkml-models
Deleting key chaiml-nemo-comm-2bbio-m-2877-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-nemo-comm-2blinea-9021-v1/special_tokens_map.json from bucket guanaco-mkml-models
Pipeline stage MKMLModelDeleter completed in 10.21s
Deleting key chaiml-nemo-comm-2bbio-m-2877-v1/tokenizer_config.json from bucket guanaco-mkml-models
Deleting key chaiml-nemo-comm-2blinea-9021-v1/tokenizer.json from bucket guanaco-mkml-models
Shutdown handler de-registered
Pipeline stage MKMLModelDeleter completed in 9.31s
Deleting key chaiml-nemo-comm-2blinea-9021-v1/tokenizer_config.json from bucket guanaco-mkml-models
Pipeline stage MKMLModelDeleter completed in 9.31s
Deleting key chaiml-nemo-comm-2blinea-9021-v1/tokenizer_config.json from bucket guanaco-mkml-models
chaiml-nemo-comm-2alinea_5104_v1 status is now torndown due to DeploymentManager action
Shutdown handler de-registered