chaiml-nemo-20241015-dar_4058

developer_uid: azuruce

submission_id: chaiml-nemo-20241015-dar_4058_v1

model_name: chaiml-nemo-20241015-dar_4058_v1

model_group: ChaiML/nemo-20241015-dar

status: torndown

timestamp: 2024-10-16T16:41:51+00:00

num_battles: 7307

num_wins: 3779

celo_rating: 1236.1

family_friendly_score: 0.6082085971982345

family_friendly_standard_error: 0.005830680116577131

submission_type: basic

model_repo: ChaiML/nemo-20241015-dare_ties-remerge_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-20241015-dar_4058_v1

is_internal_developer: True

language_model: ChaiML/nemo-20241015-dare_ties-remerge_v1-albert

model_size: 13B

ranking_group: single

us_pacific_date: 2024-10-16

win_ratio: 0.5171753113452854

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-20241015-dar-4058-v1-mkmlizer
Waiting for job on chaiml-nemo-20241015-dar-4058-v1-mkmlizer to finish
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: Downloaded to shared memory in 51.356s
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnlopxtko, device:0
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: quantized model in 36.652s
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: Processed model ChaiML/nemo-20241015-dare_ties-remerge_v1-albert in 88.008s
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-4058-v1
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-4058-v1/config.json
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-4058-v1/special_tokens_map.json
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-4058-v1/tokenizer_config.json
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-4058-v1/tokenizer.json
chaiml-nemo-20241015-dar-4058-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-4058-v1/flywheel_model.0.safetensors
chaiml-nemo-20241015-dar-4058-v1-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<04:49,  1.23it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:43,  3.38it/s]
Loading 0:   5%|▍         | 17/363 [00:06<01:10,  4.94it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:42,  8.04it/s]
Loading 0:   8%|▊         | 28/363 [00:06<00:29, 11.18it/s]
Loading 0:   9%|▉         | 33/363 [00:06<00:23, 13.86it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:19, 16.56it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:16, 18.93it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:12, 24.26it/s]
Loading 0:  15%|█▌        | 55/363 [00:07<00:10, 28.47it/s]
Loading 0:  17%|█▋        | 60/363 [00:07<00:11, 25.98it/s]
Loading 0:  18%|█▊        | 67/363 [00:07<00:09, 32.26it/s]
Loading 0:  20%|█▉        | 72/363 [00:07<00:08, 33.94it/s]
Loading 0:  21%|██        | 77/363 [00:08<00:07, 36.35it/s]
Loading 0:  23%|██▎       | 82/363 [00:08<00:07, 37.49it/s]
Loading 0:  24%|██▍       | 87/363 [00:08<00:08, 33.06it/s]
Loading 0:  26%|██▌       | 94/363 [00:08<00:06, 40.87it/s]
Loading 0:  27%|██▋       | 99/363 [00:08<00:06, 41.55it/s]
Loading 0:  29%|██▊       | 104/363 [00:08<00:06, 43.06it/s]
Loading 0:  30%|███       | 110/363 [00:08<00:06, 42.11it/s]
Loading 0:  32%|███▏      | 115/363 [00:08<00:06, 41.13it/s]
Loading 0:  33%|███▎      | 121/363 [00:09<00:08, 30.00it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:07, 30.98it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:06, 36.02it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:05, 38.91it/s]
Loading 0:  39%|███▉      | 141/363 [00:09<00:06, 32.63it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:05, 39.93it/s]
Loading 0:  42%|████▏     | 153/363 [00:10<00:05, 39.87it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:05, 39.72it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:04, 41.25it/s]
Loading 0:  46%|████▋     | 168/363 [00:10<00:05, 36.82it/s]
Loading 0:  48%|████▊     | 175/363 [00:10<00:04, 44.22it/s]
Loading 0:  50%|████▉     | 180/363 [00:10<00:04, 43.60it/s]
Loading 0:  51%|█████     | 185/363 [00:10<00:04, 44.02it/s]
Loading 0:  53%|█████▎    | 191/363 [00:10<00:04, 42.61it/s]
Loading 0:  54%|█████▍    | 196/363 [00:11<00:04, 41.41it/s]
Loading 0:  56%|█████▌    | 202/363 [00:11<00:05, 31.75it/s]
Loading 0:  57%|█████▋    | 206/363 [00:11<00:04, 32.22it/s]
Loading 0:  58%|█████▊    | 212/363 [00:11<00:04, 37.14it/s]
Loading 0:  60%|█████▉    | 217/363 [00:11<00:03, 38.99it/s]
Loading 0:  61%|██████    | 222/363 [00:11<00:04, 32.69it/s]
Loading 0:  63%|██████▎   | 229/363 [00:12<00:03, 39.54it/s]
Loading 0:  64%|██████▍   | 234/363 [00:12<00:03, 39.49it/s]
Loading 0:  66%|██████▌   | 239/363 [00:12<00:03, 38.11it/s]
Loading 0:  67%|██████▋   | 244/363 [00:12<00:02, 40.22it/s]
Loading 0:  69%|██████▊   | 249/363 [00:12<00:03, 33.90it/s]
Loading 0:  71%|███████   | 257/363 [00:12<00:02, 42.34it/s]
Loading 0:  72%|███████▏  | 263/363 [00:12<00:02, 41.63it/s]
Loading 0:  74%|███████▍  | 268/363 [00:12<00:02, 41.28it/s]
Loading 0:  76%|███████▌  | 275/363 [00:13<00:01, 46.11it/s]
Loading 0:  77%|███████▋  | 281/363 [00:13<00:01, 44.10it/s]
Loading 0:  79%|███████▉  | 286/363 [00:13<00:02, 29.88it/s]
Loading 0:  80%|████████  | 292/363 [00:13<00:02, 34.43it/s]
Loading 0:  82%|████████▏ | 297/363 [00:13<00:01, 36.05it/s]
Loading 0:  83%|████████▎ | 302/363 [00:13<00:01, 38.47it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:01, 38.78it/s]
Loading 0:  86%|████████▌ | 313/363 [00:14<00:01, 37.51it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:01, 42.79it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:00, 42.65it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:00, 35.59it/s]
Loading 0:  92%|█████████▏| 335/363 [00:14<00:00, 38.61it/s]
Loading 0:  94%|█████████▎| 340/363 [00:14<00:00, 38.87it/s]
Loading 0:  96%|█████████▌| 347/363 [00:15<00:00, 44.29it/s]
Loading 0:  97%|█████████▋| 353/363 [00:15<00:00, 42.65it/s]
Loading 0:  99%|█████████▊| 358/363 [00:15<00:00, 42.16it/s]
                                                            
Job chaiml-nemo-20241015-dar-4058-v1-mkmlizer completed after 114.73s with status: succeeded
Stopping job with name chaiml-nemo-20241015-dar-4058-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.23s
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-20241015-dar-4058-v1
Waiting for inference service chaiml-nemo-20241015-dar-4058-v1 to be ready
Failed to get response for submission chaiml-nemo-20241010-tie_5991_v2: ('http://chaiml-nemo-20241010-tie-5991-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:42350->127.0.0.1:8080: read: connection reset by peer\n')
Inference service chaiml-nemo-20241015-dar-4058-v1 ready after 160.89704537391663s
Pipeline stage MKMLDeployer completed in 161.46s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9455640316009521s
Received healthy response to inference request in 1.5175952911376953s
Received healthy response to inference request in 1.6684396266937256s
Received healthy response to inference request in 1.3762083053588867s
Received healthy response to inference request in 1.3572824001312256s
5 requests
0 failed requests
5th percentile: 1.3610675811767579
10th percentile: 1.3648527622222901
20th percentile: 1.3724231243133544
30th percentile: 1.4044857025146484
40th percentile: 1.4610404968261719
50th percentile: 1.5175952911376953
60th percentile: 1.5779330253601074
70th percentile: 1.6382707595825194
80th percentile: 1.7238645076751709
90th percentile: 1.8347142696380616
95th percentile: 1.8901391506195069
99th percentile: 1.9344790554046631
mean time: 1.5730179309844972
Pipeline stage StressChecker completed in 9.76s
Shutdown handler de-registered
chaiml-nemo-20241015-dar_4058_v1 status is now deployed due to DeploymentManager action
chaiml-nemo-20241015-dar_4058_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241015-dar_4058_v1 status is now torndown due to DeploymentManager action