submission_id: chaiml-nemo-20241010-ti_5991_v80
developer_uid: chai_backend_admin
best_of: 4
celo_rating: 1263.12
display_name: chaiml-nemo-20241010-ti_5991_v80
family_friendly_score: 0.585053592695514
family_friendly_standard_error: 0.004883829576429595
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}
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}
is_internal_developer: True
language_model: ChaiML/nemo-20241010_tier_merge_v4-albert
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: ChaiML/nemo-20241010_tie
model_name: chaiml-nemo-20241010-ti_5991_v80
model_num_parameters: 12772070400.0
model_repo: ChaiML/nemo-20241010_tier_merge_v4-albert
model_size: 13B
num_battles: 10700
num_wins: 5527
ranking_group: single
status: torndown
submission_type: basic
timestamp: 2024-10-13T21:01:27+00:00
us_pacific_date: 2024-10-13
win_ratio: 0.5165420560747663
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-v80-mkmlizer
Waiting for job on chaiml-nemo-20241010-ti-5991-v80-mkmlizer to finish
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: Downloaded to shared memory in 27.308s
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmz77i11c, device:0
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: quantized model in 36.127s
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: Processed model ChaiML/nemo-20241010_tier_merge_v4-albert in 63.436s
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v80
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v80/config.json
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v80/special_tokens_map.json
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v80/tokenizer_config.json
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v80/tokenizer.json
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v80/flywheel_model.0.safetensors
chaiml-nemo-20241010-ti-5991-v80-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<18:00,  2.99s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:48,  1.24it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:43,  3.40it/s]
Loading 0:   5%|▍         | 17/363 [00:06<01:09,  4.97it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:41,  8.11it/s]
Loading 0:   8%|▊         | 29/363 [00:06<00:28, 11.56it/s]
Loading 0:   9%|▉         | 34/363 [00:06<00:22, 14.86it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:19, 16.73it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:16, 19.39it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:12, 24.96it/s]
Loading 0:  15%|█▌        | 56/363 [00:07<00:10, 28.25it/s]
Loading 0:  17%|█▋        | 61/363 [00:07<00:09, 30.77it/s]
Loading 0:  18%|█▊        | 67/363 [00:07<00:08, 36.42it/s]
Loading 0:  20%|█▉        | 72/363 [00:07<00:07, 38.53it/s]
Loading 0:  21%|██        | 77/363 [00:07<00:07, 39.98it/s]
Loading 0:  23%|██▎       | 82/363 [00:07<00:06, 41.40it/s]
Loading 0:  24%|██▍       | 87/363 [00:08<00:07, 35.85it/s]
Loading 0:  26%|██▌       | 94/363 [00:08<00:06, 42.16it/s]
Loading 0:  27%|██▋       | 99/363 [00:08<00:06, 42.93it/s]
Loading 0:  29%|██▊       | 104/363 [00:08<00:05, 44.14it/s]
Loading 0:  30%|███       | 110/363 [00:08<00:05, 42.22it/s]
Loading 0:  32%|███▏      | 115/363 [00:08<00:06, 41.12it/s]
Loading 0:  33%|███▎      | 121/363 [00:09<00:07, 30.92it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:07, 31.99it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:06, 36.80it/s]
Loading 0:  38%|███▊      | 137/363 [00:09<00:06, 37.41it/s]
Loading 0:  39%|███▉      | 142/363 [00:09<00:05, 37.91it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:04, 43.41it/s]
Loading 0:  43%|████▎     | 155/363 [00:09<00:04, 41.77it/s]
Loading 0:  44%|████▍     | 160/363 [00:09<00:04, 41.10it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:04, 45.92it/s]
Loading 0:  48%|████▊     | 173/363 [00:10<00:04, 43.02it/s]
Loading 0:  49%|████▉     | 178/363 [00:10<00:04, 42.14it/s]
Loading 0:  51%|█████     | 184/363 [00:10<00:03, 46.21it/s]
Loading 0:  52%|█████▏    | 189/363 [00:10<00:03, 45.31it/s]
Loading 0:  53%|█████▎    | 194/363 [00:10<00:03, 45.86it/s]
Loading 0:  55%|█████▍    | 199/363 [00:10<00:03, 46.32it/s]
Loading 0:  56%|█████▌    | 204/363 [00:11<00:05, 27.09it/s]
Loading 0:  58%|█████▊    | 211/363 [00:11<00:04, 34.38it/s]
Loading 0:  60%|█████▉    | 216/363 [00:11<00:04, 36.24it/s]
Loading 0:  61%|██████    | 221/363 [00:11<00:03, 37.72it/s]
Loading 0:  62%|██████▏   | 226/363 [00:11<00:03, 39.54it/s]
Loading 0:  64%|██████▎   | 231/363 [00:11<00:03, 33.11it/s]
Loading 0:  66%|██████▌   | 238/363 [00:11<00:03, 39.61it/s]
Loading 0:  67%|██████▋   | 243/363 [00:12<00:03, 39.55it/s]
Loading 0:  68%|██████▊   | 248/363 [00:12<00:02, 39.98it/s]
Loading 0:  70%|██████▉   | 253/363 [00:12<00:02, 41.49it/s]
Loading 0:  71%|███████   | 258/363 [00:12<00:03, 34.64it/s]
Loading 0:  73%|███████▎  | 265/363 [00:12<00:02, 41.40it/s]
Loading 0:  74%|███████▍  | 270/363 [00:12<00:02, 41.64it/s]
Loading 0:  76%|███████▌  | 275/363 [00:12<00:02, 41.98it/s]
Loading 0:  77%|███████▋  | 280/363 [00:12<00:01, 43.55it/s]
Loading 0:  79%|███████▊  | 285/363 [00:13<00:03, 25.93it/s]
Loading 0:  80%|████████  | 292/363 [00:13<00:02, 33.09it/s]
Loading 0:  82%|████████▏ | 297/363 [00:13<00:01, 34.30it/s]
Loading 0:  83%|████████▎ | 302/363 [00:13<00:01, 35.84it/s]
Loading 0:  85%|████████▍ | 307/363 [00:13<00:01, 38.47it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:01, 33.41it/s]
Loading 0:  88%|████████▊ | 319/363 [00:14<00:01, 40.50it/s]
Loading 0:  89%|████████▉ | 324/363 [00:14<00:00, 40.30it/s]
Loading 0:  91%|█████████ | 329/363 [00:14<00:00, 38.53it/s]
Loading 0:  92%|█████████▏| 334/363 [00:14<00:00, 40.67it/s]
Loading 0:  93%|█████████▎| 339/363 [00:14<00:00, 34.39it/s]
Loading 0:  95%|█████████▌| 346/363 [00:14<00:00, 41.13it/s]
Loading 0:  97%|█████████▋| 351/363 [00:14<00:00, 41.39it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 42.03it/s]
Loading 0:  99%|█████████▉| 361/363 [00:15<00:00, 43.40it/s]
                                                            

Job chaiml-nemo-20241010-ti-5991-v80-mkmlizer completed after 83.75s with status: succeeded
Stopping job with name chaiml-nemo-20241010-ti-5991-v80-mkmlizer
Pipeline stage MKMLizer completed in 84.28s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-20241010-ti-5991-v80
Waiting for inference service chaiml-nemo-20241010-ti-5991-v80 to be ready
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')
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')
Inference service chaiml-nemo-20241010-ti-5991-v80 ready after 170.81262874603271s
Pipeline stage MKMLDeployer completed in 171.34s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7176778316497803s
Received healthy response to inference request in 1.4247896671295166s
Received healthy response to inference request in 1.5684001445770264s
Received healthy response to inference request in 1.2812981605529785s
Received healthy response to inference request in 1.1662390232086182s
5 requests
0 failed requests
5th percentile: 1.1892508506774901
10th percentile: 1.2122626781463623
20th percentile: 1.2582863330841065
30th percentile: 1.3099964618682862
40th percentile: 1.3673930644989014
50th percentile: 1.4247896671295166
60th percentile: 1.4822338581085206
70th percentile: 1.5396780490875244
80th percentile: 1.5982556819915772
90th percentile: 1.6579667568206786
95th percentile: 1.6878222942352294
99th percentile: 1.7117067241668702
mean time: 1.431680965423584
Pipeline stage StressChecker completed in 8.61s
Shutdown handler de-registered
chaiml-nemo-20241010-ti_5991_v80 status is now deployed due to DeploymentManager action
chaiml-nemo-20241010-ti_5991_v80 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241010-ti_5991_v80 status is now torndown due to DeploymentManager action