developer_uid: chai_backend_admin
submission_id: chaiml-nemo-20241010-ti_5991_v26
model_name: chaiml-nemo-20241010-ti_5991_v26
model_group: ChaiML/nemo-20241010_tie
status: torndown
timestamp: 2024-10-12T12:00:41+00:00
num_battles: 6487
num_wins: 3296
celo_rating: 1259.56
family_friendly_score: 0.5750865973887556
family_friendly_standard_error: 0.006235079739738786
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_v26
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: 0.5080931092955141
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-v26-mkmlizer
Waiting for job on chaiml-nemo-20241010-ti-5991-v26-mkmlizer to finish
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: Downloaded to shared memory in 28.735s
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp90if8nsk, device:0
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: quantized model in 36.396s
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: Processed model ChaiML/nemo-20241010_tier_merge_v4-albert in 65.131s
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v26
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v26/config.json
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v26/special_tokens_map.json
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v26/tokenizer_config.json
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v26/tokenizer.json
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v26/flywheel_model.0.safetensors
chaiml-nemo-20241010-ti-5991-v26-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:11,  3.02s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:51,  1.22it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:08,  2.75it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:21,  4.28it/s]
Loading 0:   6%|▌         | 22/363 [00:06<00:42,  7.96it/s]
Loading 0:   7%|▋         | 27/363 [00:06<00:30, 10.90it/s]
Loading 0:   9%|▉         | 32/363 [00:06<00:22, 14.50it/s]
Loading 0:  10%|█         | 38/363 [00:06<00:17, 18.64it/s]
Loading 0:  12%|█▏        | 43/363 [00:07<00:18, 17.77it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:13, 23.22it/s]
Loading 0:  15%|█▍        | 54/363 [00:07<00:11, 26.78it/s]
Loading 0:  16%|█▋        | 59/363 [00:07<00:10, 30.18it/s]
Loading 0:  18%|█▊        | 64/363 [00:07<00:08, 34.06it/s]
Loading 0:  19%|█▉        | 69/363 [00:07<00:09, 31.16it/s]
Loading 0:  21%|██        | 76/363 [00:08<00:07, 37.81it/s]
Loading 0:  22%|██▏       | 81/363 [00:08<00:07, 39.01it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:06, 40.22it/s]
Loading 0:  25%|██▌       | 92/363 [00:08<00:06, 39.35it/s]
Loading 0:  27%|██▋       | 97/363 [00:08<00:06, 39.10it/s]
Loading 0:  28%|██▊       | 103/363 [00:08<00:06, 42.73it/s]
Loading 0:  30%|██▉       | 108/363 [00:08<00:05, 42.61it/s]
Loading 0:  31%|███       | 113/363 [00:08<00:05, 42.67it/s]
Loading 0:  33%|███▎      | 118/363 [00:09<00:05, 43.18it/s]
Loading 0:  34%|███▍      | 123/363 [00:09<00:09, 25.96it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:06, 33.50it/s]
Loading 0:  37%|███▋      | 135/363 [00:09<00:06, 35.17it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:06, 36.91it/s]
Loading 0:  40%|███▉      | 145/363 [00:09<00:05, 39.26it/s]
Loading 0:  41%|████▏     | 150/363 [00:10<00:06, 34.54it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:04, 41.79it/s]
Loading 0:  45%|████▍     | 162/363 [00:10<00:04, 40.94it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:04, 41.81it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:04, 42.27it/s]
Loading 0:  49%|████▉     | 177/363 [00:10<00:05, 34.77it/s]
Loading 0:  51%|█████     | 184/363 [00:10<00:04, 40.94it/s]
Loading 0:  52%|█████▏    | 189/363 [00:10<00:04, 41.24it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:03, 42.66it/s]
Loading 0:  55%|█████▍    | 199/363 [00:11<00:03, 43.13it/s]
Loading 0:  56%|█████▌    | 204/363 [00:11<00:05, 26.58it/s]
Loading 0:  58%|█████▊    | 211/363 [00:11<00:04, 34.35it/s]
Loading 0:  60%|█████▉    | 216/363 [00:11<00:04, 36.39it/s]
Loading 0:  61%|██████    | 221/363 [00:11<00:03, 38.30it/s]
Loading 0:  63%|██████▎   | 227/363 [00:12<00:03, 38.07it/s]
Loading 0:  64%|██████▍   | 232/363 [00:12<00:03, 38.57it/s]
Loading 0:  66%|██████▌   | 238/363 [00:12<00:03, 41.58it/s]
Loading 0:  67%|██████▋   | 243/363 [00:12<00:02, 42.05it/s]
Loading 0:  68%|██████▊   | 248/363 [00:12<00:02, 41.56it/s]
Loading 0:  70%|██████▉   | 253/363 [00:12<00:02, 43.42it/s]
Loading 0:  71%|███████   | 258/363 [00:12<00:02, 37.19it/s]
Loading 0:  73%|███████▎  | 265/363 [00:12<00:02, 44.07it/s]
Loading 0:  74%|███████▍  | 270/363 [00:13<00:02, 43.17it/s]
Loading 0:  76%|███████▌  | 275/363 [00:13<00:02, 43.80it/s]
Loading 0:  77%|███████▋  | 281/363 [00:13<00:01, 41.39it/s]
Loading 0:  79%|███████▉  | 286/363 [00:13<00:02, 29.33it/s]
Loading 0:  80%|████████  | 292/363 [00:13<00:02, 35.05it/s]
Loading 0:  82%|████████▏ | 297/363 [00:13<00:01, 36.91it/s]
Loading 0:  83%|████████▎ | 302/363 [00:13<00:01, 38.55it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:01, 38.31it/s]
Loading 0:  86%|████████▌ | 313/363 [00:14<00:01, 38.03it/s]
Loading 0:  88%|████████▊ | 319/363 [00:14<00:01, 42.76it/s]
Loading 0:  89%|████████▉ | 324/363 [00:14<00:00, 42.64it/s]
Loading 0:  91%|█████████ | 329/363 [00:14<00:00, 43.13it/s]
Loading 0:  92%|█████████▏| 334/363 [00:14<00:00, 44.90it/s]
Loading 0:  93%|█████████▎| 339/363 [00:14<00:00, 37.51it/s]
Loading 0:  95%|█████████▌| 346/363 [00:14<00:00, 44.69it/s]
Loading 0:  97%|█████████▋| 351/363 [00:15<00:00, 44.49it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 44.84it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 42.09it/s]
                                                            

Job chaiml-nemo-20241010-ti-5991-v26-mkmlizer completed after 93.67s with status: succeeded
Stopping job with name chaiml-nemo-20241010-ti-5991-v26-mkmlizer
Pipeline stage MKMLizer completed in 94.19s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-20241010-ti-5991-v26
Waiting for inference service chaiml-nemo-20241010-ti-5991-v26 to be ready
Inference service chaiml-nemo-20241010-ti-5991-v26 ready after 150.5300726890564s
Pipeline stage MKMLDeployer completed in 151.04s
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 2.100229263305664s
Received healthy response to inference request in 1.216867208480835s
Received healthy response to inference request in 1.666748046875s
Received healthy response to inference request in 1.5289719104766846s
5 requests
1 failed requests
5th percentile: 1.279288148880005
10th percentile: 1.3417090892791748
20th percentile: 1.4665509700775146
30th percentile: 1.5565271377563477
40th percentile: 1.6116375923156738
50th percentile: 1.666748046875
60th percentile: 1.8401405334472656
70th percentile: 2.013533020019531
80th percentile: 5.712375164031986
90th percentile: 12.936666965484621
95th percentile: 16.548812866210934
99th percentile: 19.43852958679199
mean time: 5.3347550392150875
%s, retrying in %s seconds...
Received healthy response to inference request in 1.4052600860595703s
Received healthy response to inference request in 1.4717812538146973s
Received healthy response to inference request in 1.379969835281372s
Received healthy response to inference request in 1.5949103832244873s
Received healthy response to inference request in 1.417579174041748s
5 requests
0 failed requests
5th percentile: 1.3850278854370117
10th percentile: 1.3900859355926514
20th percentile: 1.4002020359039307
30th percentile: 1.4077239036560059
40th percentile: 1.412651538848877
50th percentile: 1.417579174041748
60th percentile: 1.4392600059509277
70th percentile: 1.4609408378601074
80th percentile: 1.4964070796966553
90th percentile: 1.5456587314605712
95th percentile: 1.5702845573425293
99th percentile: 1.5899852180480958
mean time: 1.453900146484375
Pipeline stage StressChecker completed in 37.16s
Shutdown handler de-registered
chaiml-nemo-20241010-ti_5991_v26 status is now deployed due to DeploymentManager action
chaiml-nemo-20241010-ti_5991_v26 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241010-ti_5991_v26 status is now torndown due to DeploymentManager action