submission_id: chaiml-nemo-20241010-ti_5991_v42
developer_uid: chai_backend_admin
best_of: 4
celo_rating: 1259.36
display_name: chaiml-nemo-20241010-ti_5991_v42
family_friendly_score: 0.5734297080741861
family_friendly_standard_error: 0.006387565659848003
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_v42
model_num_parameters: 12772070400.0
model_repo: ChaiML/nemo-20241010_tier_merge_v4-albert
model_size: 13B
num_battles: 6210
num_wins: 3162
ranking_group: single
status: torndown
submission_type: basic
timestamp: 2024-10-12T23:00:35+00:00
us_pacific_date: 2024-10-12
win_ratio: 0.5091787439613527
Download Preference Data
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-v42-mkmlizer
Waiting for job on chaiml-nemo-20241010-ti-5991-v42-mkmlizer to finish
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: ║ _____ __ __ ║
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: ║ /___/ ║
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: ║ ║
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: ║ Version: 0.11.12 ║
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: ║ https://mk1.ai ║
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: ║ ║
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: ║ belonging to: ║
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: ║ ║
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: ║ Chai Research Corp. ║
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: ║ ║
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: Downloaded to shared memory in 29.042s
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpitoo347y, device:0
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: quantized model in 36.392s
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: Processed model ChaiML/nemo-20241010_tier_merge_v4-albert in 65.434s
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v42
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v42/config.json
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v42/special_tokens_map.json
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v42/tokenizer_config.json
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v42/tokenizer.json
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v42/flywheel_model.0.safetensors
chaiml-nemo-20241010-ti-5991-v42-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:20, 3.05s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:53, 1.21it/s] Loading 0: 4%|▎ | 13/363 [00:06<01:44, 3.34it/s] Loading 0: 5%|▍ | 17/363 [00:06<01:10, 4.89it/s] Loading 0: 6%|▋ | 23/363 [00:06<00:42, 8.00it/s] Loading 0: 8%|▊ | 29/363 [00:06<00:28, 11.56it/s] Loading 0: 9%|▉ | 34/363 [00:06<00:21, 14.95it/s] Loading 0: 11%|█ | 40/363 [00:07<00:19, 16.83it/s] Loading 0: 12%|█▏ | 44/363 [00:07<00:16, 19.34it/s] Loading 0: 14%|█▍ | 50/363 [00:07<00:12, 24.88it/s] Loading 0: 15%|█▌ | 56/363 [00:07<00:10, 28.88it/s] Loading 0: 17%|█▋ | 61/363 [00:07<00:09, 31.48it/s] Loading 0: 19%|█▊ | 68/363 [00:07<00:07, 38.00it/s] Loading 0: 20%|██ | 74/363 [00:07<00:07, 39.28it/s] Loading 0: 22%|██▏ | 79/363 [00:08<00:07, 39.16it/s] Loading 0: 23%|██▎ | 85/363 [00:08<00:06, 43.31it/s] Loading 0: 25%|██▍ | 90/363 [00:08<00:06, 42.54it/s] Loading 0: 26%|██▌ | 95/363 [00:08<00:06, 43.09it/s] Loading 0: 28%|██▊ | 101/363 [00:08<00:06, 43.36it/s] Loading 0: 29%|██▉ | 106/363 [00:08<00:05, 42.98it/s] Loading 0: 31%|███ | 112/363 [00:08<00:05, 46.27it/s] Loading 0: 32%|███▏ | 117/363 [00:08<00:05, 46.20it/s] Loading 0: 34%|███▎ | 122/363 [00:09<00:07, 32.25it/s] Loading 0: 35%|███▍ | 126/363 [00:09<00:07, 33.32it/s] Loading 0: 36%|███▌ | 131/363 [00:09<00:06, 36.86it/s] Loading 0: 38%|███▊ | 137/363 [00:09<00:05, 38.79it/s] Loading 0: 39%|███▉ | 142/363 [00:09<00:05, 39.73it/s] Loading 0: 41%|████ | 149/363 [00:09<00:04, 45.58it/s] Loading 0: 43%|████▎ | 155/363 [00:09<00:04, 44.84it/s] Loading 0: 44%|████▍ | 160/363 [00:09<00:04, 43.78it/s] Loading 0: 46%|████▌ | 167/363 [00:10<00:04, 48.81it/s] Loading 0: 48%|████▊ | 173/363 [00:10<00:04, 46.75it/s] Loading 0: 49%|████▉ | 178/363 [00:10<00:04, 43.82it/s] Loading 0: 50%|█████ | 183/363 [00:10<00:04, 44.02it/s] Loading 0: 52%|█████▏ | 188/363 [00:10<00:04, 37.49it/s] Loading 0: 53%|█████▎ | 192/363 [00:10<00:04, 37.54it/s] Loading 0: 54%|█████▍ | 196/363 [00:10<00:04, 34.17it/s] Loading 0: 56%|█████▌ | 202/363 [00:11<00:05, 28.36it/s] Loading 0: 57%|█████▋ | 206/363 [00:11<00:05, 29.76it/s] Loading 0: 58%|█████▊ | 212/363 [00:11<00:04, 35.43it/s] Loading 0: 60%|██████ | 218/363 [00:11<00:03, 37.34it/s] Loading 0: 61%|██████ | 222/363 [00:11<00:03, 35.92it/s] Loading 0: 63%|██████▎ | 230/363 [00:11<00:02, 44.37it/s] Loading 0: 65%|██████▌ | 236/363 [00:11<00:02, 43.31it/s] Loading 0: 66%|██████▋ | 241/363 [00:12<00:02, 40.76it/s] Loading 0: 68%|██████▊ | 247/363 [00:12<00:02, 43.70it/s] Loading 0: 69%|██████▉ | 252/363 [00:12<00:02, 41.37it/s] Loading 0: 71%|███████ | 257/363 [00:12<00:02, 42.47it/s] Loading 0: 72%|███████▏ | 263/363 [00:12<00:02, 41.80it/s] Loading 0: 74%|███████▍ | 268/363 [00:12<00:02, 39.77it/s] Loading 0: 76%|███████▌ | 275/363 [00:12<00:01, 44.69it/s] Loading 0: 77%|███████▋ | 280/363 [00:12<00:01, 44.57it/s] Loading 0: 79%|███████▊ | 285/363 [00:13<00:02, 26.86it/s] Loading 0: 81%|████████ | 293/363 [00:13<00:02, 34.97it/s] Loading 0: 82%|████████▏ | 298/363 [00:13<00:01, 37.17it/s] Loading 0: 83%|████████▎ | 303/363 [00:13<00:01, 33.64it/s] Loading 0: 85%|████████▌ | 310/363 [00:13<00:01, 40.19it/s] Loading 0: 87%|████████▋ | 315/363 [00:13<00:01, 40.62it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:01, 41.81it/s] Loading 0: 90%|████████▉ | 325/363 [00:14<00:00, 43.21it/s] Loading 0: 91%|█████████ | 330/363 [00:14<00:00, 36.21it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:00, 43.84it/s] Loading 0: 94%|█████████▍| 343/363 [00:14<00:00, 44.89it/s] Loading 0: 96%|█████████▌| 348/363 [00:14<00:00, 37.11it/s] Loading 0: 98%|█████████▊| 355/363 [00:14<00:00, 43.71it/s] Loading 0: 99%|█████████▉| 360/363 [00:15<00:00, 42.71it/s]
Job chaiml-nemo-20241010-ti-5991-v42-mkmlizer completed after 93.85s with status: succeeded
Stopping job with name chaiml-nemo-20241010-ti-5991-v42-mkmlizer
Pipeline stage MKMLizer completed in 94.41s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-20241010-ti-5991-v42
Waiting for inference service chaiml-nemo-20241010-ti-5991-v42 to be ready
Inference service chaiml-nemo-20241010-ti-5991-v42 ready after 160.5872881412506s
Pipeline stage MKMLDeployer completed in 161.29s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9881713390350342s
Received healthy response to inference request in 1.4048659801483154s
Received healthy response to inference request in 1.5892107486724854s
Received healthy response to inference request in 1.6871888637542725s
Received healthy response to inference request in 1.3457651138305664s
5 requests
0 failed requests
5th percentile: 1.3575852870941163
10th percentile: 1.369405460357666
20th percentile: 1.3930458068847655
30th percentile: 1.4417349338531493
40th percentile: 1.5154728412628173
50th percentile: 1.5892107486724854
60th percentile: 1.6284019947052002
70th percentile: 1.667593240737915
80th percentile: 1.747385358810425
90th percentile: 1.8677783489227295
95th percentile: 1.9279748439788817
99th percentile: 1.9761320400238036
mean time: 1.6030404090881347
Pipeline stage StressChecker completed in 9.44s
Shutdown handler de-registered
chaiml-nemo-20241010-ti_5991_v42 status is now deployed due to DeploymentManager action
chaiml-nemo-20241010-ti_5991_v42 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241010-ti_5991_v42 status is now torndown due to DeploymentManager action