submission_id: chaiml-nemo-20241010-t_5991_v171
developer_uid: chai_backend_admin
best_of: 4
celo_rating: 1268.96
display_name: chaiml-nemo-20241010-t_5991_v171
family_friendly_score: 0.5707002801120448
family_friendly_standard_error: 0.006397116474580244
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_v171
model_num_parameters: 12772070400.0
model_repo: ChaiML/nemo-20241010_tier_merge_v4-albert
model_size: 13B
num_battles: 6234
num_wins: 3526
ranking_group: single
status: inactive
submission_type: basic
timestamp: 2024-10-15T21:00:42+00:00
us_pacific_date: 2024-10-15
win_ratio: 0.5656079563683029
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-v171-mkmlizer
Waiting for job on chaiml-nemo-20241010-t-5991-v171-mkmlizer to finish
chaiml-nemo-20241010-t-5991-v171-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241010-t-5991-v171-mkmlizer: ║ _____ __ __ ║
chaiml-nemo-20241010-t-5991-v171-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-nemo-20241010-t-5991-v171-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-nemo-20241010-t-5991-v171-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-nemo-20241010-t-5991-v171-mkmlizer: ║ /___/ ║
chaiml-nemo-20241010-t-5991-v171-mkmlizer: ║ ║
chaiml-nemo-20241010-t-5991-v171-mkmlizer: ║ Version: 0.11.12 ║
chaiml-nemo-20241010-t-5991-v171-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-nemo-20241010-t-5991-v171-mkmlizer: ║ https://mk1.ai ║
chaiml-nemo-20241010-t-5991-v171-mkmlizer: ║ ║
chaiml-nemo-20241010-t-5991-v171-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nemo-20241010-t-5991-v171-mkmlizer: ║ belonging to: ║
chaiml-nemo-20241010-t-5991-v171-mkmlizer: ║ ║
chaiml-nemo-20241010-t-5991-v171-mkmlizer: ║ Chai Research Corp. ║
chaiml-nemo-20241010-t-5991-v171-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nemo-20241010-t-5991-v171-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-nemo-20241010-t-5991-v171-mkmlizer: ║ ║
chaiml-nemo-20241010-t-5991-v171-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241010-t-5991-v171-mkmlizer: Downloaded to shared memory in 54.002s
chaiml-nemo-20241010-t-5991-v171-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpj8gzoap0, device:0
chaiml-nemo-20241010-t-5991-v171-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241010-t-5991-v171-mkmlizer: quantized model in 36.145s
chaiml-nemo-20241010-t-5991-v171-mkmlizer: Processed model ChaiML/nemo-20241010_tier_merge_v4-albert in 90.147s
chaiml-nemo-20241010-t-5991-v171-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241010-t-5991-v171-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241010-t-5991-v171-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241010-t-5991-v171
chaiml-nemo-20241010-t-5991-v171-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-t-5991-v171/config.json
chaiml-nemo-20241010-t-5991-v171-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241010-t-5991-v171/special_tokens_map.json
chaiml-nemo-20241010-t-5991-v171-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-t-5991-v171/tokenizer_config.json
chaiml-nemo-20241010-t-5991-v171-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241010-t-5991-v171/tokenizer.json
chaiml-nemo-20241010-t-5991-v171-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241010-t-5991-v171/flywheel_model.0.safetensors
chaiml-nemo-20241010-t-5991-v171-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:07, 3.01s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:50, 1.23it/s] Loading 0: 4%|▎ | 13/363 [00:06<01:43, 3.37it/s] Loading 0: 5%|▍ | 17/363 [00:06<01:10, 4.92it/s] Loading 0: 6%|▌ | 22/363 [00:06<00:45, 7.50it/s] Loading 0: 7%|▋ | 27/363 [00:06<00:31, 10.54it/s] Loading 0: 9%|▉ | 32/363 [00:06<00:23, 14.14it/s] Loading 0: 10%|█ | 38/363 [00:06<00:17, 18.41it/s] Loading 0: 12%|█▏ | 43/363 [00:07<00:18, 17.07it/s] Loading 0: 13%|█▎ | 49/363 [00:07<00:14, 22.40it/s] Loading 0: 15%|█▍ | 53/363 [00:07<00:12, 24.74it/s] Loading 0: 16%|█▌ | 58/363 [00:07<00:10, 29.19it/s] Loading 0: 17%|█▋ | 63/363 [00:07<00:09, 32.58it/s] Loading 0: 19%|█▊ | 68/363 [00:07<00:08, 34.88it/s] Loading 0: 20%|██ | 74/363 [00:07<00:08, 35.78it/s] Loading 0: 22%|██▏ | 79/363 [00:08<00:07, 36.50it/s] Loading 0: 23%|██▎ | 85/363 [00:08<00:06, 41.37it/s] Loading 0: 25%|██▍ | 90/363 [00:08<00:06, 40.94it/s] Loading 0: 26%|██▌ | 95/363 [00:08<00:06, 41.11it/s] Loading 0: 28%|██▊ | 101/363 [00:08<00:06, 40.00it/s] Loading 0: 29%|██▉ | 106/363 [00:08<00:06, 40.13it/s] Loading 0: 31%|███ | 112/363 [00:08<00:05, 44.29it/s] Loading 0: 32%|███▏ | 117/363 [00:08<00:05, 43.96it/s] Loading 0: 34%|███▎ | 122/363 [00:09<00:07, 30.13it/s] Loading 0: 35%|███▍ | 126/363 [00:09<00:07, 30.99it/s] Loading 0: 36%|███▌ | 131/363 [00:09<00:06, 34.02it/s] Loading 0: 37%|███▋ | 136/363 [00:09<00:06, 37.35it/s] Loading 0: 39%|███▉ | 141/363 [00:09<00:06, 32.38it/s] Loading 0: 41%|████ | 148/363 [00:09<00:05, 40.37it/s] Loading 0: 42%|████▏ | 153/363 [00:10<00:05, 41.25it/s] Loading 0: 44%|████▎ | 158/363 [00:10<00:04, 41.97it/s] Loading 0: 45%|████▌ | 164/363 [00:10<00:04, 40.80it/s] Loading 0: 47%|████▋ | 169/363 [00:10<00:04, 40.97it/s] Loading 0: 48%|████▊ | 175/363 [00:10<00:04, 45.19it/s] Loading 0: 50%|████▉ | 180/363 [00:10<00:04, 44.81it/s] Loading 0: 51%|█████ | 185/363 [00:10<00:03, 45.00it/s] Loading 0: 52%|█████▏ | 190/363 [00:10<00:03, 46.10it/s] Loading 0: 54%|█████▎ | 195/363 [00:11<00:04, 35.58it/s] Loading 0: 56%|█████▌ | 202/363 [00:11<00:05, 30.35it/s] Loading 0: 57%|█████▋ | 206/363 [00:11<00:05, 31.08it/s] Loading 0: 58%|█████▊ | 212/363 [00:11<00:04, 35.87it/s] Loading 0: 60%|██████ | 218/363 [00:11<00:03, 36.57it/s] Loading 0: 61%|██████ | 222/363 [00:11<00:03, 35.41it/s] Loading 0: 63%|██████▎ | 230/363 [00:11<00:03, 43.65it/s] Loading 0: 65%|██████▌ | 236/363 [00:12<00:03, 41.55it/s] Loading 0: 66%|██████▋ | 241/363 [00:12<00:02, 40.71it/s] Loading 0: 68%|██████▊ | 247/363 [00:12<00:02, 44.93it/s] Loading 0: 69%|██████▉ | 252/363 [00:12<00:02, 45.13it/s] Loading 0: 71%|███████ | 257/363 [00:12<00:02, 45.74it/s] Loading 0: 72%|███████▏ | 263/363 [00:12<00:02, 43.29it/s] Loading 0: 74%|███████▍ | 268/363 [00:12<00:02, 42.34it/s] Loading 0: 76%|███████▌ | 275/363 [00:12<00:01, 46.79it/s] Loading 0: 77%|███████▋ | 281/363 [00:13<00:01, 43.94it/s] Loading 0: 79%|███████▉ | 286/363 [00:13<00:02, 30.68it/s] Loading 0: 81%|████████ | 293/363 [00:13<00:01, 36.73it/s] Loading 0: 82%|████████▏ | 299/363 [00:13<00:01, 36.92it/s] Loading 0: 84%|████████▎ | 304/363 [00:13<00:01, 36.53it/s] Loading 0: 85%|████████▌ | 310/363 [00:13<00:01, 40.91it/s] Loading 0: 87%|████████▋ | 315/363 [00:14<00:01, 41.28it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:01, 42.79it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:00, 41.32it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:00, 40.90it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:00, 46.04it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:00, 43.92it/s] Loading 0: 96%|█████████▌| 349/363 [00:14<00:00, 43.01it/s] Loading 0: 98%|█████████▊| 356/363 [00:14<00:00, 47.44it/s] Loading 0: 99%|█████████▉| 361/363 [00:15<00:00, 48.03it/s]
Job chaiml-nemo-20241010-t-5991-v171-mkmlizer completed after 113.9s with status: succeeded
Stopping job with name chaiml-nemo-20241010-t-5991-v171-mkmlizer
Pipeline stage MKMLizer completed in 114.40s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-20241010-t-5991-v171
Waiting for inference service chaiml-nemo-20241010-t-5991-v171 to be ready
Inference service chaiml-nemo-20241010-t-5991-v171 ready after 170.5899257659912s
Pipeline stage MKMLDeployer completed in 171.19s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.554597854614258s
Received healthy response to inference request in 1.3706765174865723s
Received healthy response to inference request in 1.5469982624053955s
Received healthy response to inference request in 1.6267433166503906s
Received healthy response to inference request in 1.361403226852417s
5 requests
0 failed requests
5th percentile: 1.363257884979248
10th percentile: 1.365112543106079
20th percentile: 1.3688218593597412
30th percentile: 1.405940866470337
40th percentile: 1.4764695644378663
50th percentile: 1.5469982624053955
60th percentile: 1.5788962841033936
70th percentile: 1.6107943058013916
80th percentile: 1.8123142242431642
90th percentile: 2.183456039428711
95th percentile: 2.369026947021484
99th percentile: 2.517483673095703
mean time: 1.6920838356018066
Pipeline stage StressChecker completed in 9.90s
Shutdown handler de-registered
chaiml-nemo-20241010-t_5991_v171 status is now deployed due to DeploymentManager action
chaiml-nemo-20241010-t_5991_v171 status is now inactive due to auto deactivation removed underperforming models