developer_uid: chai_backend_admin
submission_id: chaiml-nemo-20241010-ti_5991_v84
model_name: chaiml-nemo-20241010-ti_5991_v84
model_group: ChaiML/nemo-20241010_tie
status: torndown
timestamp: 2024-10-13T23:00:45+00:00
num_battles: 9513
num_wins: 5011
celo_rating: 1263.57
family_friendly_score: 0.5721103360336033
family_friendly_standard_error: 0.005211035684312015
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_v84
is_internal_developer: True
language_model: ChaiML/nemo-20241010_tier_merge_v4-albert
model_size: 13B
ranking_group: single
us_pacific_date: 2024-10-13
win_ratio: 0.5267528645012088
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-v84-mkmlizer
Waiting for job on chaiml-nemo-20241010-ti-5991-v84-mkmlizer to finish
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-llama-8b-pairwis_8189_v33: ('http://chaiml-llama-8b-pairwis-8189-v33-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: Downloaded to shared memory in 32.595s
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpypywzjl8, device:0
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: quantized model in 37.292s
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: Processed model ChaiML/nemo-20241010_tier_merge_v4-albert in 69.887s
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v84
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v84/special_tokens_map.json
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v84/config.json
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v84/tokenizer_config.json
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v84/tokenizer.json
chaiml-nemo-20241010-ti-5991-v84-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v84/flywheel_model.0.safetensors
chaiml-nemo-20241010-ti-5991-v84-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<04:53,  1.22it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:09,  2.73it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:21,  4.25it/s]
Loading 0:   6%|▌         | 22/363 [00:06<00:43,  7.93it/s]
Loading 0:   7%|▋         | 27/363 [00:06<00:30, 10.89it/s]
Loading 0:   9%|▉         | 32/363 [00:06<00:23, 14.29it/s]
Loading 0:  10%|█         | 37/363 [00:06<00:17, 18.33it/s]
Loading 0:  12%|█▏        | 42/363 [00:07<00:20, 15.94it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:14, 22.35it/s]
Loading 0:  15%|█▍        | 54/363 [00:07<00:12, 25.50it/s]
Loading 0:  16%|█▋        | 59/363 [00:07<00:10, 28.44it/s]
Loading 0:  18%|█▊        | 64/363 [00:07<00:09, 31.93it/s]
Loading 0:  19%|█▉        | 69/363 [00:08<00:10, 29.13it/s]
Loading 0:  21%|██        | 76/363 [00:08<00:07, 35.97it/s]
Loading 0:  22%|██▏       | 81/363 [00:08<00:07, 37.05it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:07, 37.97it/s]
Loading 0:  25%|██▌       | 91/363 [00:08<00:06, 39.86it/s]
Loading 0:  26%|██▋       | 96/363 [00:08<00:07, 33.38it/s]
Loading 0:  28%|██▊       | 103/363 [00:08<00:06, 40.22it/s]
Loading 0:  30%|██▉       | 108/363 [00:08<00:06, 39.55it/s]
Loading 0:  31%|███       | 113/363 [00:09<00:06, 39.59it/s]
Loading 0:  33%|███▎      | 118/363 [00:09<00:05, 41.19it/s]
Loading 0:  34%|███▍      | 123/363 [00:09<00:09, 24.97it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:07, 32.08it/s]
Loading 0:  37%|███▋      | 135/363 [00:09<00:06, 33.88it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:06, 35.49it/s]
Loading 0:  40%|███▉      | 145/363 [00:10<00:05, 37.97it/s]
Loading 0:  41%|████▏     | 150/363 [00:10<00:06, 32.58it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:05, 39.15it/s]
Loading 0:  45%|████▍     | 162/363 [00:10<00:05, 39.07it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:04, 39.51it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:04, 40.98it/s]
Loading 0:  49%|████▉     | 177/363 [00:10<00:05, 33.61it/s]
Loading 0:  51%|█████     | 184/363 [00:11<00:04, 40.03it/s]
Loading 0:  52%|█████▏    | 189/363 [00:11<00:04, 39.40it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:04, 40.05it/s]
Loading 0:  55%|█████▍    | 199/363 [00:11<00:03, 41.21it/s]
Loading 0:  56%|█████▌    | 204/363 [00:11<00:06, 24.92it/s]
Loading 0:  58%|█████▊    | 211/363 [00:11<00:04, 31.83it/s]
Loading 0:  60%|█████▉    | 216/363 [00:12<00:04, 31.84it/s]
Loading 0:  61%|██████    | 220/363 [00:12<00:04, 33.30it/s]
Loading 0:  62%|██████▏   | 224/363 [00:12<00:04, 33.27it/s]
Loading 0:  63%|██████▎   | 229/363 [00:12<00:03, 36.50it/s]
Loading 0:  64%|██████▍   | 233/363 [00:12<00:03, 35.72it/s]
Loading 0:  66%|██████▌   | 238/363 [00:12<00:03, 38.14it/s]
Loading 0:  67%|██████▋   | 243/363 [00:12<00:03, 38.41it/s]
Loading 0:  68%|██████▊   | 247/363 [00:12<00:03, 38.49it/s]
Loading 0:  69%|██████▉   | 251/363 [00:13<00:03, 37.12it/s]
Loading 0:  71%|███████   | 256/363 [00:13<00:02, 40.06it/s]
Loading 0:  72%|███████▏  | 261/363 [00:13<00:02, 40.08it/s]
Loading 0:  73%|███████▎  | 266/363 [00:13<00:02, 39.62it/s]
Loading 0:  75%|███████▍  | 271/363 [00:13<00:02, 40.74it/s]
Loading 0:  76%|███████▌  | 276/363 [00:13<00:02, 33.33it/s]
Loading 0:  78%|███████▊  | 283/363 [00:14<00:02, 28.71it/s]
Loading 0:  79%|███████▉  | 287/363 [00:14<00:02, 29.24it/s]
Loading 0:  80%|████████  | 292/363 [00:14<00:02, 32.94it/s]
Loading 0:  82%|████████▏ | 296/363 [00:14<00:02, 33.35it/s]
Loading 0:  83%|████████▎ | 301/363 [00:14<00:01, 36.48it/s]
Loading 0:  84%|████████▍ | 305/363 [00:14<00:01, 35.97it/s]
Loading 0:  85%|████████▌ | 310/363 [00:14<00:01, 38.61it/s]
Loading 0:  87%|████████▋ | 315/363 [00:14<00:01, 38.39it/s]
Loading 0:  88%|████████▊ | 319/363 [00:14<00:01, 38.62it/s]
Loading 0:  89%|████████▉ | 323/363 [00:15<00:01, 36.88it/s]
Loading 0:  90%|█████████ | 328/363 [00:15<00:00, 39.27it/s]
Loading 0:  91%|█████████▏| 332/363 [00:15<00:00, 37.82it/s]
Loading 0:  93%|█████████▎| 337/363 [00:15<00:00, 40.58it/s]
Loading 0:  94%|█████████▍| 342/363 [00:15<00:00, 40.41it/s]
Loading 0:  96%|█████████▌| 347/363 [00:15<00:00, 40.19it/s]
Loading 0:  97%|█████████▋| 352/363 [00:15<00:00, 41.73it/s]
Loading 0:  98%|█████████▊| 357/363 [00:15<00:00, 34.38it/s]
                                                            

Job chaiml-nemo-20241010-ti-5991-v84-mkmlizer completed after 93.85s with status: succeeded
Stopping job with name chaiml-nemo-20241010-ti-5991-v84-mkmlizer
Pipeline stage MKMLizer completed in 94.35s
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-v84
Waiting for inference service chaiml-nemo-20241010-ti-5991-v84 to be ready
Failed to get response for submission chaiml-llama-8b-pairwis_8189_v33: ('http://chaiml-llama-8b-pairwis-8189-v33-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission chaiml-llama-8b-pairwis_8189_v33: ('http://chaiml-llama-8b-pairwis-8189-v33-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Inference service chaiml-nemo-20241010-ti-5991-v84 ready after 170.5896236896515s
Pipeline stage MKMLDeployer completed in 171.17s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5558388233184814s
Received healthy response to inference request in 1.4075162410736084s
Received healthy response to inference request in 1.4247019290924072s
Received healthy response to inference request in 1.330195426940918s
Received healthy response to inference request in 1.4614791870117188s
5 requests
0 failed requests
5th percentile: 1.3456595897674561
10th percentile: 1.361123752593994
20th percentile: 1.3920520782470702
30th percentile: 1.4109533786773683
40th percentile: 1.4178276538848877
50th percentile: 1.4247019290924072
60th percentile: 1.4394128322601318
70th percentile: 1.4541237354278564
80th percentile: 1.6803511142730714
90th percentile: 2.1180949687957766
95th percentile: 2.336966896057129
99th percentile: 2.512064437866211
mean time: 1.6359463214874268
Pipeline stage StressChecker completed in 9.84s
Shutdown handler de-registered
chaiml-nemo-20241010-ti_5991_v84 status is now deployed due to DeploymentManager action
chaiml-nemo-20241010-ti_5991_v84 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241010-ti_5991_v84 status is now torndown due to DeploymentManager action