developer_uid: chai_backend_admin
submission_id: chaiml-nemo-20241010-ti_5991_v40
model_name: chaiml-nemo-20241010-ti_5991_v40
model_group: ChaiML/nemo-20241010_tie
status: torndown
timestamp: 2024-10-12T22:00:38+00:00
num_battles: 6453
num_wins: 3388
celo_rating: 1268.56
family_friendly_score: 0.5823659034719983
family_friendly_standard_error: 0.006239467947732826
submission_type: basic
model_repo: ChaiML/nemo-20241010_tier_merge_v4-albert
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
display_name: chaiml-nemo-20241010-ti_5991_v40
is_internal_developer: True
language_model: ChaiML/nemo-20241010_tier_merge_v4-albert
model_size: 13B
ranking_group: single
us_pacific_date: 2024-10-12
win_ratio: 0.5250271191693786
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}
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-20241010-ti-5991-v40-mkmlizer
Stopping job with name chaiml-nemo-20241010-ti-5991-v40-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-nemo-20241010-ti-5991-v40-mkmlizer
Waiting for job on chaiml-nemo-20241010-ti-5991-v40-mkmlizer to finish
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: Downloaded to shared memory in 33.206s
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvus2_2_f, device:0
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission chaiml-nemo-20241010-ti_5991_v38: ('http://chaiml-nemo-20241010-ti-5991-v38-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:54850->127.0.0.1:8080: read: connection reset by peer\n')
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: quantized model in 36.361s
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: Processed model ChaiML/nemo-20241010_tier_merge_v4-albert in 69.567s
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v40
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v40/config.json
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v40/special_tokens_map.json
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v40/tokenizer_config.json
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v40/tokenizer.json
Stopping job with name chaiml-nemo-20241010-ti-5991-v40-mkmlizer
%s, retrying in %s seconds...
Stopping job with name chaiml-nemo-20241010-ti-5991-v40-mkmlizer
%s, retrying in %s seconds...
Stopping job with name chaiml-nemo-20241010-ti-5991-v40-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-nemo-20241010-ti-5991-v40-mkmlizer
Waiting for job on chaiml-nemo-20241010-ti-5991-v40-mkmlizer to finish
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: Downloaded to shared memory in 28.138s
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmprsqfkls5, device:0
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: quantized model in 36.595s
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: Processed model ChaiML/nemo-20241010_tier_merge_v4-albert in 64.734s
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v40
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v40/tokenizer_config.json
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v40/tokenizer.json
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v40/flywheel_model.0.safetensors
chaiml-nemo-20241010-ti-5991-v40-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<18:02,  3.00s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:49,  1.23it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:07,  2.76it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:20,  4.31it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:39,  8.54it/s]
Loading 0:   8%|▊         | 28/363 [00:06<00:29, 11.51it/s]
Loading 0:   9%|▉         | 33/363 [00:06<00:23, 14.01it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:19, 16.15it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:17, 18.68it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:13, 23.91it/s]
Loading 0:  15%|█▌        | 56/363 [00:07<00:11, 27.32it/s]
Loading 0:  17%|█▋        | 60/363 [00:07<00:10, 28.25it/s]
Loading 0:  18%|█▊        | 67/363 [00:07<00:08, 35.17it/s]
Loading 0:  20%|█▉        | 72/363 [00:07<00:08, 35.83it/s]
Loading 0:  21%|██        | 77/363 [00:08<00:07, 36.34it/s]
Loading 0:  23%|██▎       | 82/363 [00:08<00:07, 38.96it/s]
Loading 0:  24%|██▍       | 87/363 [00:08<00:08, 32.67it/s]
Loading 0:  26%|██▌       | 94/363 [00:08<00:06, 39.85it/s]
Loading 0:  27%|██▋       | 99/363 [00:08<00:06, 40.72it/s]
Loading 0:  29%|██▊       | 104/363 [00:08<00:06, 42.10it/s]
Loading 0:  30%|███       | 109/363 [00:08<00:05, 43.42it/s]
Loading 0:  31%|███▏      | 114/363 [00:09<00:07, 35.06it/s]
Loading 0:  33%|███▎      | 121/363 [00:09<00:08, 28.84it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:08, 29.64it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:06, 34.28it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:06, 37.62it/s]
Loading 0:  39%|███▉      | 141/363 [00:09<00:06, 32.23it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:05, 39.94it/s]
Loading 0:  42%|████▏     | 153/363 [00:10<00:05, 39.73it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:05, 39.72it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:04, 41.32it/s]
Loading 0:  46%|████▋     | 168/363 [00:10<00:05, 34.53it/s]
Loading 0:  48%|████▊     | 175/363 [00:10<00:04, 41.34it/s]
Loading 0:  50%|████▉     | 180/363 [00:10<00:04, 41.05it/s]
Loading 0:  51%|█████     | 185/363 [00:10<00:04, 41.71it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:04, 42.25it/s]
Loading 0:  54%|█████▎    | 195/363 [00:11<00:04, 35.47it/s]
Loading 0:  56%|█████▌    | 202/363 [00:11<00:05, 30.48it/s]
Loading 0:  57%|█████▋    | 206/363 [00:11<00:04, 31.48it/s]
Loading 0:  58%|█████▊    | 211/363 [00:11<00:04, 34.97it/s]
Loading 0:  59%|█████▉    | 215/363 [00:11<00:04, 34.40it/s]
Loading 0:  61%|██████    | 221/363 [00:11<00:03, 38.61it/s]
Loading 0:  63%|██████▎   | 227/363 [00:12<00:03, 38.52it/s]
Loading 0:  64%|██████▍   | 232/363 [00:12<00:03, 38.78it/s]
Loading 0:  66%|██████▌   | 238/363 [00:12<00:02, 43.21it/s]
Loading 0:  67%|██████▋   | 243/363 [00:12<00:02, 42.25it/s]
Loading 0:  68%|██████▊   | 248/363 [00:12<00:02, 43.08it/s]
Loading 0:  70%|██████▉   | 253/363 [00:12<00:02, 44.44it/s]
Loading 0:  71%|███████   | 258/363 [00:12<00:02, 36.39it/s]
Loading 0:  73%|███████▎  | 265/363 [00:13<00:02, 43.61it/s]
Loading 0:  74%|███████▍  | 270/363 [00:13<00:02, 43.51it/s]
Loading 0:  76%|███████▌  | 275/363 [00:13<00:02, 43.39it/s]
Loading 0:  77%|███████▋  | 280/363 [00:13<00:01, 44.17it/s]
Loading 0:  79%|███████▊  | 285/363 [00:13<00:02, 26.01it/s]
Loading 0:  80%|████████  | 292/363 [00:13<00:02, 33.71it/s]
Loading 0:  82%|████████▏ | 297/363 [00:13<00:01, 35.57it/s]
Loading 0:  83%|████████▎ | 302/363 [00:14<00:01, 36.61it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:01, 39.40it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:01, 34.62it/s]
Loading 0:  88%|████████▊ | 319/363 [00:14<00:01, 42.15it/s]
Loading 0:  89%|████████▉ | 324/363 [00:14<00:00, 41.34it/s]
Loading 0:  91%|█████████ | 329/363 [00:14<00:00, 40.68it/s]
Loading 0:  92%|█████████▏| 334/363 [00:14<00:00, 42.67it/s]
Loading 0:  93%|█████████▎| 339/363 [00:15<00:00, 35.56it/s]
Loading 0:  95%|█████████▌| 346/363 [00:15<00:00, 43.00it/s]
Loading 0:  97%|█████████▋| 351/363 [00:15<00:00, 42.90it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 43.67it/s]
Loading 0:  99%|█████████▉| 361/363 [00:15<00:00, 44.20it/s]
                                                            

Job chaiml-nemo-20241010-ti-5991-v40-mkmlizer completed after 94.28s with status: succeeded
Stopping job with name chaiml-nemo-20241010-ti-5991-v40-mkmlizer
Pipeline stage MKMLizer completed in 189.99s
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-20241010-ti-5991-v40
Ignoring service chaiml-nemo-20241010-ti-5991-v40 already deployed
Waiting for inference service chaiml-nemo-20241010-ti-5991-v40 to be ready
Inference service chaiml-nemo-20241010-ti-5991-v40 ready after 60.34044027328491s
Pipeline stage MKMLDeployer completed in 61.00s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.568451166152954s
Received healthy response to inference request in 3.9540534019470215s
Received healthy response to inference request in 3.8058059215545654s
Received healthy response to inference request in 2.3269760608673096s
Received healthy response to inference request in 1.8623435497283936s
5 requests
0 failed requests
5th percentile: 1.9552700519561768
10th percentile: 2.04819655418396
20th percentile: 2.2340495586395264
30th percentile: 2.5752710819244387
40th percentile: 3.0718611240386964
50th percentile: 3.568451166152954
60th percentile: 3.6633930683135985
70th percentile: 3.7583349704742433
80th percentile: 3.8354554176330566
90th percentile: 3.894754409790039
95th percentile: 3.9244039058685303
99th percentile: 3.948123502731323
mean time: 3.1035260200500487
%s, retrying in %s seconds...
Received healthy response to inference request in 2.4455909729003906s
Received healthy response to inference request in 2.2506048679351807s
Received healthy response to inference request in 1.4536547660827637s
Received healthy response to inference request in 1.7170791625976562s
Received healthy response to inference request in 1.5501606464385986s
5 requests
0 failed requests
5th percentile: 1.4729559421539307
10th percentile: 1.4922571182250977
20th percentile: 1.5308594703674316
30th percentile: 1.5835443496704102
40th percentile: 1.6503117561340332
50th percentile: 1.7170791625976562
60th percentile: 1.930489444732666
70th percentile: 2.1438997268676756
80th percentile: 2.2896020889282225
90th percentile: 2.3675965309143066
95th percentile: 2.406593751907349
99th percentile: 2.437791528701782
mean time: 1.883418083190918
Pipeline stage StressChecker completed in 28.42s
Shutdown handler de-registered
chaiml-nemo-20241010-ti_5991_v40 status is now deployed due to DeploymentManager action
chaiml-nemo-20241010-ti_5991_v40 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241010-ti_5991_v40 status is now torndown due to DeploymentManager action