submission_id: chaiml-nemo-20241010-t_5991_v161
developer_uid: chai_backend_admin
best_of: 4
celo_rating: 1262.3
display_name: chaiml-nemo-20241010-t_5991_v161
family_friendly_score: 0.5915211719847482
family_friendly_standard_error: 0.005369464495465135
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-t_5991_v161
model_num_parameters: 12772070400.0
model_repo: ChaiML/nemo-20241010_tier_merge_v4-albert
model_size: 13B
num_battles: 8747
num_wins: 4681
ranking_group: single
status: inactive
submission_type: basic
timestamp: 2024-10-15T15:01:13+00:00
us_pacific_date: 2024-10-15
win_ratio: 0.5351549102549445
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-t-5991-v161-mkmlizer
Waiting for job on chaiml-nemo-20241010-t-5991-v161-mkmlizer to finish
chaiml-nemo-20241010-t-5991-v161-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241010-t-5991-v161-mkmlizer: ║ _____ __ __ ║
chaiml-nemo-20241010-t-5991-v161-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-nemo-20241010-t-5991-v161-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-nemo-20241010-t-5991-v161-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-nemo-20241010-t-5991-v161-mkmlizer: ║ /___/ ║
chaiml-nemo-20241010-t-5991-v161-mkmlizer: ║ ║
chaiml-nemo-20241010-t-5991-v161-mkmlizer: ║ Version: 0.11.12 ║
chaiml-nemo-20241010-t-5991-v161-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-nemo-20241010-t-5991-v161-mkmlizer: ║ https://mk1.ai ║
chaiml-nemo-20241010-t-5991-v161-mkmlizer: ║ ║
chaiml-nemo-20241010-t-5991-v161-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nemo-20241010-t-5991-v161-mkmlizer: ║ belonging to: ║
chaiml-nemo-20241010-t-5991-v161-mkmlizer: ║ ║
chaiml-nemo-20241010-t-5991-v161-mkmlizer: ║ Chai Research Corp. ║
chaiml-nemo-20241010-t-5991-v161-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nemo-20241010-t-5991-v161-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-nemo-20241010-t-5991-v161-mkmlizer: ║ ║
chaiml-nemo-20241010-t-5991-v161-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241010-t-5991-v161-mkmlizer: Downloaded to shared memory in 28.158s
chaiml-nemo-20241010-t-5991-v161-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpsbgeprt5, device:0
chaiml-nemo-20241010-t-5991-v161-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241010-t-5991-v161-mkmlizer: quantized model in 36.745s
chaiml-nemo-20241010-t-5991-v161-mkmlizer: Processed model ChaiML/nemo-20241010_tier_merge_v4-albert in 64.903s
chaiml-nemo-20241010-t-5991-v161-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241010-t-5991-v161-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241010-t-5991-v161-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241010-t-5991-v161
chaiml-nemo-20241010-t-5991-v161-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-t-5991-v161/config.json
chaiml-nemo-20241010-t-5991-v161-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241010-t-5991-v161/special_tokens_map.json
chaiml-nemo-20241010-t-5991-v161-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-t-5991-v161/tokenizer_config.json
chaiml-nemo-20241010-t-5991-v161-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241010-t-5991-v161/tokenizer.json
chaiml-nemo-20241010-t-5991-v161-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241010-t-5991-v161/flywheel_model.0.safetensors
chaiml-nemo-20241010-t-5991-v161-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:14, 3.03s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:52, 1.22it/s] Loading 0: 4%|▎ | 13/363 [00:06<01:44, 3.35it/s] Loading 0: 5%|▍ | 17/363 [00:06<01:11, 4.86it/s] Loading 0: 6%|▌ | 22/363 [00:06<00:46, 7.36it/s] Loading 0: 7%|▋ | 26/363 [00:06<00:34, 9.67it/s] Loading 0: 9%|▉ | 32/363 [00:06<00:23, 14.21it/s] Loading 0: 10%|█ | 38/363 [00:06<00:17, 18.38it/s] Loading 0: 12%|█▏ | 43/363 [00:07<00:18, 16.98it/s] Loading 0: 13%|█▎ | 49/363 [00:07<00:14, 22.17it/s] Loading 0: 15%|█▍ | 53/363 [00:07<00:12, 24.13it/s] Loading 0: 16%|█▌ | 58/363 [00:07<00:10, 28.63it/s] Loading 0: 17%|█▋ | 63/363 [00:07<00:09, 31.70it/s] Loading 0: 19%|█▊ | 68/363 [00:07<00:08, 34.93it/s] Loading 0: 20%|██ | 73/363 [00:07<00:07, 38.40it/s] Loading 0: 21%|██▏ | 78/363 [00:08<00:08, 33.83it/s] Loading 0: 23%|██▎ | 85/363 [00:08<00:06, 40.68it/s] Loading 0: 25%|██▍ | 90/363 [00:08<00:06, 41.10it/s] Loading 0: 26%|██▌ | 95/363 [00:08<00:06, 42.01it/s] Loading 0: 28%|██▊ | 100/363 [00:08<00:05, 43.89it/s] Loading 0: 29%|██▉ | 105/363 [00:08<00:06, 37.43it/s] Loading 0: 31%|███ | 113/363 [00:08<00:05, 45.46it/s] Loading 0: 33%|███▎ | 119/363 [00:09<00:05, 43.90it/s] Loading 0: 34%|███▍ | 124/363 [00:09<00:07, 30.18it/s] Loading 0: 36%|███▌ | 131/363 [00:09<00:06, 36.12it/s] Loading 0: 38%|███▊ | 137/363 [00:09<00:06, 37.09it/s] Loading 0: 39%|███▉ | 142/363 [00:09<00:05, 37.50it/s] Loading 0: 41%|████ | 149/363 [00:09<00:04, 42.98it/s] Loading 0: 43%|████▎ | 155/363 [00:10<00:04, 42.78it/s] Loading 0: 44%|████▍ | 160/363 [00:10<00:04, 41.31it/s] Loading 0: 46%|████▌ | 167/363 [00:10<00:04, 46.28it/s] Loading 0: 48%|████▊ | 173/363 [00:10<00:04, 45.31it/s] Loading 0: 49%|████▉ | 178/363 [00:10<00:04, 43.66it/s] Loading 0: 51%|█████ | 185/363 [00:10<00:03, 47.90it/s] Loading 0: 53%|█████▎ | 191/363 [00:10<00:03, 46.13it/s] Loading 0: 54%|█████▍ | 196/363 [00:10<00:03, 44.54it/s] Loading 0: 56%|█████▌ | 202/363 [00:11<00:04, 33.51it/s] Loading 0: 57%|█████▋ | 206/363 [00:11<00:05, 30.03it/s] Loading 0: 58%|█████▊ | 210/363 [00:11<00:04, 30.94it/s] Loading 0: 59%|█████▉ | 214/363 [00:11<00:05, 26.09it/s] Loading 0: 60%|██████ | 218/363 [00:11<00:05, 26.72it/s] Loading 0: 61%|██████ | 222/363 [00:12<00:05, 24.47it/s] Loading 0: 63%|██████▎ | 227/363 [00:12<00:04, 28.12it/s] Loading 0: 64%|██████▎ | 231/363 [00:12<00:04, 27.64it/s] Loading 0: 66%|██████▌ | 238/363 [00:12<00:03, 36.14it/s] Loading 0: 67%|██████▋ | 243/363 [00:12<00:03, 38.07it/s] Loading 0: 68%|██████▊ | 248/363 [00:12<00:03, 38.22it/s] Loading 0: 70%|██████▉ | 253/363 [00:12<00:02, 40.70it/s] Loading 0: 71%|███████ | 258/363 [00:13<00:02, 35.70it/s] Loading 0: 73%|███████▎ | 265/363 [00:13<00:02, 43.09it/s] Loading 0: 74%|███████▍ | 270/363 [00:13<00:02, 42.30it/s] Loading 0: 76%|███████▌ | 275/363 [00:13<00:02, 42.20it/s] Loading 0: 77%|███████▋ | 280/363 [00:13<00:01, 43.14it/s] Loading 0: 79%|███████▊ | 285/363 [00:13<00:03, 25.87it/s] Loading 0: 80%|████████ | 292/363 [00:13<00:02, 32.53it/s] Loading 0: 82%|████████▏ | 297/363 [00:14<00:01, 34.64it/s] Loading 0: 83%|████████▎ | 302/363 [00:14<00:01, 37.00it/s] Loading 0: 85%|████████▍ | 308/363 [00:14<00:01, 38.13it/s] Loading 0: 86%|████████▌ | 313/363 [00:14<00:01, 37.13it/s] Loading 0: 88%|████████▊ | 319/363 [00:14<00:01, 40.67it/s] Loading 0: 89%|████████▉ | 324/363 [00:14<00:00, 41.63it/s] Loading 0: 91%|█████████ | 329/363 [00:14<00:00, 40.93it/s] Loading 0: 92%|█████████▏| 334/363 [00:14<00:00, 42.50it/s] Loading 0: 93%|█████████▎| 339/363 [00:15<00:00, 37.32it/s] Loading 0: 96%|█████████▌| 347/363 [00:15<00:00, 45.41it/s] Loading 0: 97%|█████████▋| 353/363 [00:15<00:00, 44.04it/s] Loading 0: 99%|█████████▊| 358/363 [00:15<00:00, 43.06it/s]
Job chaiml-nemo-20241010-t-5991-v161-mkmlizer completed after 94.38s with status: succeeded
Stopping job with name chaiml-nemo-20241010-t-5991-v161-mkmlizer
Pipeline stage MKMLizer completed in 94.99s
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-20241010-t-5991-v161
Waiting for inference service chaiml-nemo-20241010-t-5991-v161 to be ready
Inference service chaiml-nemo-20241010-t-5991-v161 ready after 160.87602400779724s
Pipeline stage MKMLDeployer completed in 161.45s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8061227798461914s
Received healthy response to inference request in 1.4995090961456299s
Received healthy response to inference request in 1.3464553356170654s
Received healthy response to inference request in 1.362736701965332s
Received healthy response to inference request in 1.5472826957702637s
5 requests
0 failed requests
5th percentile: 1.3497116088867187
10th percentile: 1.352967882156372
20th percentile: 1.3594804286956788
30th percentile: 1.3900911808013916
40th percentile: 1.4448001384735107
50th percentile: 1.4995090961456299
60th percentile: 1.5186185359954834
70th percentile: 1.5377279758453368
80th percentile: 1.5990507125854492
90th percentile: 1.7025867462158204
95th percentile: 1.754354763031006
99th percentile: 1.7957691764831543
mean time: 1.5124213218688964
Pipeline stage StressChecker completed in 9.54s
Shutdown handler de-registered
chaiml-nemo-20241010-t_5991_v161 status is now deployed due to DeploymentManager action
chaiml-nemo-20241010-t_5991_v161 status is now inactive due to auto deactivation removed underperforming models