chaiml-nemo-20241014-lin_6270

developer_uid: azuruce
submission_id: chaiml-nemo-20241014-lin_6270_v3
model_name: chaiml-nemo-20241014-lin_6270_v3
model_group: ChaiML/nemo-20241014_lin
status: torndown
timestamp: 2024-10-16T06:28:57+00:00
num_battles: 5882
num_wins: 3102
celo_rating: 1234.91
family_friendly_score: 0.557027027027027
family_friendly_standard_error: 0.0066265061614003695
submission_type: basic
model_repo: ChaiML/nemo-20241014_linear_v1-albert
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
display_name: chaiml-nemo-20241014-lin_6270_v3
is_internal_developer: True
language_model: ChaiML/nemo-20241014_linear_v1-albert
model_size: 13B
ranking_group: single
us_pacific_date: 2024-10-15
win_ratio: 0.527371642298538
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-20241014-lin-6270-v3-mkmlizer
Waiting for job on chaiml-nemo-20241014-lin-6270-v3-mkmlizer to finish
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: ║                                                                     ║
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: ║                                                                     ║
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: ║                                                                     ║
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: ║                                                                     ║
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: Downloaded to shared memory in 30.208s
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp59paohfn, device:0
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: quantized model in 37.505s
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: Processed model ChaiML/nemo-20241014_linear_v1-albert in 67.714s
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241014-lin-6270-v3
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241014-lin-6270-v3/config.json
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241014-lin-6270-v3/special_tokens_map.json
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241014-lin-6270-v3/tokenizer_config.json
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241014-lin-6270-v3/tokenizer.json
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241014-lin-6270-v3/flywheel_model.0.safetensors
chaiml-nemo-20241014-lin-6270-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:17,  3.04s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:54,  1.21it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:09,  2.72it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:22,  4.21it/s]
Loading 0:   6%|▌         | 22/363 [00:06<00:43,  7.82it/s]
Loading 0:   7%|▋         | 26/363 [00:06<00:33,  9.99it/s]
Loading 0:   9%|▊         | 31/363 [00:06<00:24, 13.61it/s]
Loading 0:  10%|▉         | 35/363 [00:07<00:20, 16.26it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:19, 16.27it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:17, 18.74it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:13, 23.41it/s]
Loading 0:  15%|█▍        | 53/363 [00:07<00:12, 25.18it/s]
Loading 0:  16%|█▌        | 58/363 [00:07<00:10, 29.19it/s]
Loading 0:  17%|█▋        | 62/363 [00:07<00:10, 29.75it/s]
Loading 0:  18%|█▊        | 67/363 [00:08<00:08, 33.29it/s]
Loading 0:  20%|█▉        | 71/363 [00:08<00:08, 33.57it/s]
Loading 0:  21%|██        | 76/363 [00:08<00:07, 36.03it/s]
Loading 0:  22%|██▏       | 80/363 [00:08<00:07, 35.80it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:06, 40.17it/s]
Loading 0:  25%|██▌       | 92/363 [00:08<00:06, 40.23it/s]
Loading 0:  27%|██▋       | 97/363 [00:08<00:06, 40.52it/s]
Loading 0:  29%|██▊       | 104/363 [00:08<00:05, 45.84it/s]
Loading 0:  30%|███       | 109/363 [00:08<00:05, 46.75it/s]
Loading 0:  31%|███▏      | 114/363 [00:09<00:06, 38.19it/s]
Loading 0:  33%|███▎      | 121/363 [00:09<00:07, 33.29it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:07, 32.94it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:06, 36.02it/s]
Loading 0:  37%|███▋      | 134/363 [00:09<00:06, 34.95it/s]
Loading 0:  38%|███▊      | 139/363 [00:09<00:05, 38.13it/s]
Loading 0:  40%|███▉      | 144/363 [00:10<00:05, 39.08it/s]
Loading 0:  41%|████      | 149/363 [00:10<00:05, 40.54it/s]
Loading 0:  42%|████▏     | 154/363 [00:10<00:04, 42.81it/s]
Loading 0:  44%|████▍     | 159/363 [00:10<00:05, 35.78it/s]
Loading 0:  46%|████▌     | 166/363 [00:10<00:04, 43.29it/s]
Loading 0:  47%|████▋     | 171/363 [00:10<00:04, 43.10it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:04, 43.69it/s]
Loading 0:  50%|████▉     | 181/363 [00:10<00:04, 43.27it/s]
Loading 0:  51%|█████     | 186/363 [00:11<00:05, 34.20it/s]
Loading 0:  53%|█████▎    | 193/363 [00:11<00:04, 41.94it/s]
Loading 0:  55%|█████▍    | 198/363 [00:11<00:03, 41.89it/s]
Loading 0:  56%|█████▌    | 203/363 [00:11<00:05, 30.55it/s]
Loading 0:  57%|█████▋    | 207/363 [00:11<00:04, 31.72it/s]
Loading 0:  58%|█████▊    | 211/363 [00:11<00:04, 32.88it/s]
Loading 0:  59%|█████▉    | 215/363 [00:11<00:04, 32.34it/s]
Loading 0:  60%|██████    | 219/363 [00:12<00:04, 32.77it/s]
Loading 0:  61%|██████▏   | 223/363 [00:12<00:05, 27.47it/s]
Loading 0:  63%|██████▎   | 230/363 [00:12<00:03, 35.31it/s]
Loading 0:  65%|██████▌   | 236/363 [00:12<00:03, 36.70it/s]
Loading 0:  66%|██████▌   | 240/363 [00:12<00:03, 34.87it/s]
Loading 0:  68%|██████▊   | 247/363 [00:12<00:02, 43.02it/s]
Loading 0:  69%|██████▉   | 252/363 [00:12<00:02, 41.71it/s]
Loading 0:  71%|███████   | 257/363 [00:13<00:02, 43.23it/s]
Loading 0:  72%|███████▏  | 262/363 [00:13<00:02, 44.65it/s]
Loading 0:  74%|███████▎  | 267/363 [00:13<00:02, 35.41it/s]
Loading 0:  75%|███████▌  | 274/363 [00:13<00:02, 42.08it/s]
Loading 0:  77%|███████▋  | 279/363 [00:13<00:02, 41.94it/s]
Loading 0:  78%|███████▊  | 284/363 [00:13<00:02, 30.37it/s]
Loading 0:  79%|███████▉  | 288/363 [00:13<00:02, 31.75it/s]
Loading 0:  81%|████████  | 293/363 [00:14<00:02, 34.24it/s]
Loading 0:  82%|████████▏ | 298/363 [00:14<00:01, 37.59it/s]
Loading 0:  83%|████████▎ | 303/363 [00:14<00:01, 33.42it/s]
Loading 0:  85%|████████▌ | 310/363 [00:14<00:01, 40.88it/s]
Loading 0:  87%|████████▋ | 315/363 [00:14<00:01, 40.71it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:01, 41.73it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:00, 43.21it/s]
Loading 0:  91%|█████████ | 330/363 [00:15<00:00, 35.93it/s]
Loading 0:  93%|█████████▎| 337/363 [00:15<00:00, 43.70it/s]
Loading 0:  94%|█████████▍| 342/363 [00:15<00:00, 42.64it/s]
Loading 0:  96%|█████████▌| 347/363 [00:15<00:00, 41.86it/s]
Loading 0:  97%|█████████▋| 352/363 [00:15<00:00, 41.50it/s]
Loading 0:  98%|█████████▊| 357/363 [00:15<00:00, 34.47it/s]
                                                            
Job chaiml-nemo-20241014-lin-6270-v3-mkmlizer completed after 93.78s with status: succeeded
Stopping job with name chaiml-nemo-20241014-lin-6270-v3-mkmlizer
Pipeline stage MKMLizer completed in 94.31s
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-20241014-lin-6270-v3
Waiting for inference service chaiml-nemo-20241014-lin-6270-v3 to be ready
Inference service chaiml-nemo-20241014-lin-6270-v3 ready after 170.57020807266235s
Pipeline stage MKMLDeployer completed in 171.14s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 1.9962079524993896s
Received healthy response to inference request in 1.5418660640716553s
Received healthy response to inference request in 1.4500391483306885s
Received healthy response to inference request in 1.3768880367279053s
5 requests
1 failed requests
5th percentile: 1.3915182590484618
10th percentile: 1.4061484813690186
20th percentile: 1.435408926010132
30th percentile: 1.4684045314788818
40th percentile: 1.5051352977752686
50th percentile: 1.5418660640716553
60th percentile: 1.723602819442749
70th percentile: 1.9053395748138426
80th percentile: 5.629812860488895
90th percentile: 12.897022676467898
95th percentile: 16.530627584457395
99th percentile: 19.437511510849
mean time: 5.305846738815307
%s, retrying in %s seconds...
Received healthy response to inference request in 1.3704116344451904s
Received healthy response to inference request in 1.4134862422943115s
Received healthy response to inference request in 1.5308191776275635s
Received healthy response to inference request in 1.3339223861694336s
Received healthy response to inference request in 1.359365463256836s
5 requests
0 failed requests
5th percentile: 1.339011001586914
10th percentile: 1.3440996170043946
20th percentile: 1.3542768478393554
30th percentile: 1.3615746974945069
40th percentile: 1.3659931659698485
50th percentile: 1.3704116344451904
60th percentile: 1.387641477584839
70th percentile: 1.4048713207244874
80th percentile: 1.436952829360962
90th percentile: 1.4838860034942627
95th percentile: 1.507352590560913
99th percentile: 1.5261258602142334
mean time: 1.401600980758667
Pipeline stage StressChecker completed in 35.98s
Shutdown handler de-registered
chaiml-nemo-20241014-lin_6270_v3 status is now deployed due to DeploymentManager action
chaiml-nemo-20241014-lin_6270_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241014-lin_6270_v3 status is now torndown due to DeploymentManager action