developer_uid: chai_backend_admin
submission_id: chaiml-nemo-20241010-ti_5991_v55
model_name: chaiml-nemo-20241010-ti_5991_v55
model_group: ChaiML/nemo-20241010_tie
status: torndown
timestamp: 2024-10-13T06:00:54+00:00
num_battles: 8756
num_wins: 4477
celo_rating: 1261.91
family_friendly_score: 0.5577383124518509
family_friendly_standard_error: 0.005447976916429404
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_v55
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: 0.5113065326633166
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-v55-mkmlizer
Waiting for job on chaiml-nemo-20241010-ti-5991-v55-mkmlizer to finish
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: Downloaded to shared memory in 28.996s
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplh7x29gz, device:0
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v55
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v55/config.json
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v55/special_tokens_map.json
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v55/tokenizer_config.json
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v55/tokenizer.json
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v55/flywheel_model.0.safetensors
chaiml-nemo-20241010-ti-5991-v55-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:12,  3.03s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:52,  1.22it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:08,  2.73it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:22,  4.24it/s]
Loading 0:   6%|▌         | 22/363 [00:06<00:43,  7.87it/s]
Loading 0:   7%|▋         | 26/363 [00:06<00:33, 10.06it/s]
Loading 0:   9%|▊         | 31/363 [00:06<00:24, 13.69it/s]
Loading 0:  10%|▉         | 35/363 [00:06<00:19, 16.41it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:19, 16.32it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:16, 18.94it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:12, 24.62it/s]
Loading 0:  15%|█▍        | 54/363 [00:07<00:11, 27.33it/s]
Loading 0:  16%|█▋        | 59/363 [00:07<00:09, 30.54it/s]
Loading 0:  17%|█▋        | 63/363 [00:07<00:09, 31.98it/s]
Loading 0:  18%|█▊        | 67/363 [00:07<00:08, 33.08it/s]
Loading 0:  20%|█▉        | 71/363 [00:08<00:08, 32.77it/s]
Loading 0:  21%|██        | 76/363 [00:08<00:08, 35.81it/s]
Loading 0:  22%|██▏       | 80/363 [00:08<00:08, 34.61it/s]
Loading 0:  23%|██▎       | 85/363 [00:08<00:07, 36.80it/s]
Loading 0:  25%|██▍       | 89/363 [00:08<00:07, 36.00it/s]
Loading 0:  26%|██▌       | 94/363 [00:08<00:06, 38.83it/s]
Loading 0:  27%|██▋       | 98/363 [00:08<00:07, 37.63it/s]
Loading 0:  28%|██▊       | 103/363 [00:08<00:06, 40.61it/s]
Loading 0:  30%|██▉       | 108/363 [00:09<00:06, 40.56it/s]
Loading 0:  31%|███       | 113/363 [00:09<00:06, 38.66it/s]
Loading 0:  32%|███▏      | 117/363 [00:09<00:06, 38.31it/s]
Loading 0:  33%|███▎      | 121/363 [00:09<00:09, 26.04it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:08, 27.54it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:06, 33.27it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:06, 36.59it/s]
Loading 0:  39%|███▉      | 141/363 [00:10<00:07, 31.18it/s]
Loading 0:  41%|████      | 148/363 [00:10<00:05, 37.96it/s]
Loading 0:  42%|████▏     | 153/363 [00:10<00:05, 37.35it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:05, 37.93it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:05, 39.57it/s]
Loading 0:  46%|████▋     | 168/363 [00:10<00:05, 33.49it/s]
Loading 0:  48%|████▊     | 175/363 [00:10<00:04, 40.27it/s]
Loading 0:  50%|████▉     | 180/363 [00:11<00:04, 40.04it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:04, 40.05it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:04, 41.23it/s]
Loading 0:  54%|█████▎    | 195/363 [00:11<00:04, 34.25it/s]
Loading 0:  56%|█████▌    | 202/363 [00:11<00:05, 29.33it/s]
Loading 0:  57%|█████▋    | 206/363 [00:11<00:05, 30.17it/s]
Loading 0:  58%|█████▊    | 212/363 [00:12<00:04, 34.71it/s]
Loading 0:  60%|██████    | 218/363 [00:12<00:04, 35.31it/s]
Loading 0:  61%|██████    | 222/363 [00:12<00:04, 34.36it/s]
Loading 0:  63%|██████▎   | 229/363 [00:12<00:03, 42.14it/s]
Loading 0:  64%|██████▍   | 234/363 [00:12<00:03, 42.48it/s]
Loading 0:  66%|██████▌   | 239/363 [00:12<00:02, 43.26it/s]
Loading 0:  67%|██████▋   | 245/363 [00:12<00:02, 41.45it/s]
Loading 0:  69%|██████▉   | 250/363 [00:12<00:02, 40.84it/s]
Loading 0:  71%|███████   | 257/363 [00:13<00:02, 45.71it/s]
Loading 0:  72%|███████▏  | 262/363 [00:13<00:02, 46.61it/s]
Loading 0:  74%|███████▎  | 267/363 [00:13<00:02, 39.00it/s]
Loading 0:  76%|███████▌  | 275/363 [00:13<00:01, 46.11it/s]
Loading 0:  77%|███████▋  | 280/363 [00:13<00:01, 46.42it/s]
Loading 0:  79%|███████▊  | 285/363 [00:13<00:02, 27.75it/s]
Loading 0:  80%|████████  | 292/363 [00:14<00:02, 34.41it/s]
Loading 0:  82%|████████▏ | 297/363 [00:14<00:01, 35.61it/s]
Loading 0:  83%|████████▎ | 302/363 [00:14<00:01, 37.15it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:01, 38.67it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:01, 33.71it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:01, 41.90it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:00, 43.44it/s]
Loading 0:  91%|█████████ | 330/363 [00:15<00:00, 36.38it/s]
Loading 0:  93%|█████████▎| 337/363 [00:15<00:00, 43.72it/s]
Loading 0:  94%|█████████▍| 342/363 [00:15<00:00, 43.17it/s]
Loading 0:  96%|█████████▌| 347/363 [00:15<00:00, 42.86it/s]
Loading 0:  97%|█████████▋| 352/363 [00:15<00:00, 43.03it/s]
Loading 0:  98%|█████████▊| 357/363 [00:15<00:00, 36.01it/s]
                                                            

Job chaiml-nemo-20241010-ti-5991-v55-mkmlizer completed after 93.75s with status: succeeded
Stopping job with name chaiml-nemo-20241010-ti-5991-v55-mkmlizer
Pipeline stage MKMLizer completed in 94.39s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-20241010-ti-5991-v55
Waiting for inference service chaiml-nemo-20241010-ti-5991-v55 to be ready
Inference service chaiml-nemo-20241010-ti-5991-v55 ready after 170.7976849079132s
Pipeline stage MKMLDeployer completed in 171.38s
run pipeline stage %s
Running pipeline stage StressChecker
Failed to get response for submission chaiml-chaiml-sft-horror_v2: ('http://chaiml-chaiml-sft-horror-v2-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Received healthy response to inference request in 1.9494149684906006s
Received healthy response to inference request in 1.3420844078063965s
Received healthy response to inference request in 1.4760003089904785s
Received healthy response to inference request in 1.80023193359375s
Received healthy response to inference request in 1.8503105640411377s
5 requests
0 failed requests
5th percentile: 1.3688675880432128
10th percentile: 1.3956507682800292
20th percentile: 1.4492171287536622
30th percentile: 1.5408466339111329
40th percentile: 1.6705392837524413
50th percentile: 1.80023193359375
60th percentile: 1.820263385772705
70th percentile: 1.8402948379516602
80th percentile: 1.8701314449310302
90th percentile: 1.9097732067108155
95th percentile: 1.929594087600708
99th percentile: 1.945450792312622
mean time: 1.6836084365844726
Pipeline stage StressChecker completed in 9.80s
Shutdown handler de-registered
chaiml-nemo-20241010-ti_5991_v55 status is now deployed due to DeploymentManager action
chaiml-nemo-20241010-ti_5991_v55 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241010-ti_5991_v55 status is now torndown due to DeploymentManager action