submission_id: chaiml-nemo-20241010-t_5991_v128
developer_uid: chai_backend_admin
best_of: 4
celo_rating: 1268.34
display_name: chaiml-nemo-20241010-t_5991_v128
family_friendly_score: 0.5529612490066844
family_friendly_standard_error: 0.005856794187802684
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_v128
model_num_parameters: 12772070400.0
model_repo: ChaiML/nemo-20241010_tier_merge_v4-albert
model_size: 13B
num_battles: 7565
num_wins: 4733
ranking_group: single
status: inactive
submission_type: basic
timestamp: 2024-10-14T23:01:04+00:00
us_pacific_date: 2024-10-14
win_ratio: 0.6256444150693985
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-v128-mkmlizer
Waiting for job on chaiml-nemo-20241010-t-5991-v128-mkmlizer to finish
chaiml-nemo-20241010-t-5991-v128-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241010-t-5991-v128-mkmlizer: ║ _____ __ __ ║
chaiml-nemo-20241010-t-5991-v128-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-nemo-20241010-t-5991-v128-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-nemo-20241010-t-5991-v128-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-nemo-20241010-t-5991-v128-mkmlizer: ║ /___/ ║
chaiml-nemo-20241010-t-5991-v128-mkmlizer: ║ ║
chaiml-nemo-20241010-t-5991-v128-mkmlizer: ║ Version: 0.11.12 ║
chaiml-nemo-20241010-t-5991-v128-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-nemo-20241010-t-5991-v128-mkmlizer: ║ https://mk1.ai ║
chaiml-nemo-20241010-t-5991-v128-mkmlizer: ║ ║
chaiml-nemo-20241010-t-5991-v128-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nemo-20241010-t-5991-v128-mkmlizer: ║ belonging to: ║
chaiml-nemo-20241010-t-5991-v128-mkmlizer: ║ ║
chaiml-nemo-20241010-t-5991-v128-mkmlizer: ║ Chai Research Corp. ║
chaiml-nemo-20241010-t-5991-v128-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nemo-20241010-t-5991-v128-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-nemo-20241010-t-5991-v128-mkmlizer: ║ ║
chaiml-nemo-20241010-t-5991-v128-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241010-t-5991-v128-mkmlizer: Downloaded to shared memory in 28.684s
chaiml-nemo-20241010-t-5991-v128-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpr9976cz2, device:0
chaiml-nemo-20241010-t-5991-v128-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241010-t-5991-v128-mkmlizer: quantized model in 36.794s
chaiml-nemo-20241010-t-5991-v128-mkmlizer: Processed model ChaiML/nemo-20241010_tier_merge_v4-albert in 65.478s
chaiml-nemo-20241010-t-5991-v128-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241010-t-5991-v128-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241010-t-5991-v128-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241010-t-5991-v128
chaiml-nemo-20241010-t-5991-v128-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-t-5991-v128/config.json
chaiml-nemo-20241010-t-5991-v128-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241010-t-5991-v128/special_tokens_map.json
chaiml-nemo-20241010-t-5991-v128-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-t-5991-v128/tokenizer_config.json
chaiml-nemo-20241010-t-5991-v128-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241010-t-5991-v128/tokenizer.json
chaiml-nemo-20241010-t-5991-v128-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241010-t-5991-v128/flywheel_model.0.safetensors
chaiml-nemo-20241010-t-5991-v128-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:27, 3.07s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:55, 1.21it/s] Loading 0: 4%|▎ | 13/363 [00:06<01:45, 3.32it/s] Loading 0: 5%|▍ | 17/363 [00:06<01:11, 4.84it/s] Loading 0: 6%|▌ | 22/363 [00:06<00:46, 7.34it/s] Loading 0: 7%|▋ | 26/363 [00:06<00:34, 9.68it/s] Loading 0: 9%|▉ | 32/363 [00:06<00:23, 14.35it/s] Loading 0: 10%|█ | 38/363 [00:07<00:17, 19.01it/s] Loading 0: 12%|█▏ | 43/363 [00:07<00:18, 17.59it/s] Loading 0: 14%|█▍ | 50/363 [00:07<00:13, 23.87it/s] Loading 0: 15%|█▌ | 56/363 [00:07<00:11, 27.66it/s] Loading 0: 17%|█▋ | 61/363 [00:07<00:09, 30.30it/s] Loading 0: 18%|█▊ | 67/363 [00:07<00:08, 35.64it/s] Loading 0: 20%|█▉ | 72/363 [00:07<00:07, 37.11it/s] Loading 0: 21%|██ | 77/363 [00:08<00:07, 38.75it/s] Loading 0: 23%|██▎ | 83/363 [00:08<00:06, 40.13it/s] Loading 0: 24%|██▍ | 88/363 [00:08<00:06, 40.71it/s] Loading 0: 26%|██▌ | 95/363 [00:08<00:05, 45.32it/s] Loading 0: 28%|██▊ | 101/363 [00:08<00:05, 44.77it/s] Loading 0: 29%|██▉ | 106/363 [00:08<00:05, 44.45it/s] Loading 0: 31%|███ | 113/363 [00:08<00:05, 48.65it/s] Loading 0: 33%|███▎ | 119/363 [00:08<00:05, 46.56it/s] Loading 0: 34%|███▍ | 124/363 [00:09<00:08, 29.63it/s] Loading 0: 36%|███▌ | 131/363 [00:09<00:06, 35.70it/s] Loading 0: 38%|███▊ | 137/363 [00:09<00:06, 37.54it/s] Loading 0: 39%|███▉ | 142/363 [00:09<00:05, 37.62it/s] Loading 0: 41%|████ | 148/363 [00:09<00:05, 41.56it/s] Loading 0: 42%|████▏ | 153/363 [00:09<00:05, 40.37it/s] Loading 0: 44%|████▎ | 158/363 [00:10<00:05, 39.68it/s] Loading 0: 45%|████▍ | 163/363 [00:10<00:04, 40.64it/s] Loading 0: 46%|████▋ | 168/363 [00:10<00:05, 35.85it/s] Loading 0: 48%|████▊ | 175/363 [00:10<00:04, 43.56it/s] Loading 0: 50%|████▉ | 180/363 [00:10<00:04, 42.31it/s] Loading 0: 51%|█████ | 185/363 [00:10<00:04, 43.70it/s] Loading 0: 53%|█████▎ | 191/363 [00:10<00:04, 41.18it/s] Loading 0: 54%|█████▍ | 196/363 [00:10<00:04, 39.76it/s] Loading 0: 56%|█████▌ | 202/363 [00:11<00:05, 30.75it/s] Loading 0: 57%|█████▋ | 206/363 [00:11<00:05, 31.32it/s] Loading 0: 58%|█████▊ | 212/363 [00:11<00:04, 36.07it/s] Loading 0: 60%|█████▉ | 216/363 [00:11<00:04, 36.47it/s] Loading 0: 61%|██████ | 220/363 [00:11<00:04, 35.70it/s] Loading 0: 62%|██████▏ | 224/363 [00:11<00:03, 34.77it/s] Loading 0: 63%|██████▎ | 230/363 [00:11<00:03, 39.29it/s] Loading 0: 65%|██████▌ | 236/363 [00:12<00:03, 38.46it/s] Loading 0: 66%|██████▌ | 240/363 [00:12<00:03, 36.30it/s] Loading 0: 68%|██████▊ | 247/363 [00:12<00:02, 44.04it/s] Loading 0: 69%|██████▉ | 252/363 [00:12<00:02, 43.53it/s] Loading 0: 71%|███████ | 257/363 [00:12<00:02, 44.77it/s] Loading 0: 72%|███████▏ | 263/363 [00:12<00:02, 42.56it/s] Loading 0: 74%|███████▍ | 268/363 [00:12<00:02, 40.09it/s] Loading 0: 75%|███████▌ | 274/363 [00:13<00:02, 44.44it/s] Loading 0: 77%|███████▋ | 279/363 [00:13<00:01, 44.53it/s] Loading 0: 78%|███████▊ | 284/363 [00:13<00:02, 30.10it/s] Loading 0: 79%|███████▉ | 288/363 [00:13<00:02, 31.87it/s] Loading 0: 81%|████████ | 293/363 [00:13<00:02, 34.45it/s] Loading 0: 82%|████████▏ | 298/363 [00:13<00:01, 37.65it/s] Loading 0: 83%|████████▎ | 303/363 [00:13<00:01, 32.57it/s] Loading 0: 85%|████████▌ | 310/363 [00:14<00:01, 40.68it/s] Loading 0: 87%|████████▋ | 315/363 [00:14<00:01, 38.77it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:01, 39.87it/s] Loading 0: 90%|████████▉ | 325/363 [00:14<00:00, 42.16it/s] Loading 0: 91%|█████████ | 330/363 [00:14<00:00, 36.60it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:00, 44.99it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:00, 43.93it/s] Loading 0: 96%|█████████▌| 349/363 [00:14<00:00, 42.91it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 47.71it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 45.48it/s]
Job chaiml-nemo-20241010-t-5991-v128-mkmlizer completed after 94.25s with status: succeeded
Stopping job with name chaiml-nemo-20241010-t-5991-v128-mkmlizer
Pipeline stage MKMLizer completed in 95.06s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-20241010-t-5991-v128
Waiting for inference service chaiml-nemo-20241010-t-5991-v128 to be ready
Inference service chaiml-nemo-20241010-t-5991-v128 ready after 150.65434527397156s
Pipeline stage MKMLDeployer completed in 151.21s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.085819721221924s
Received healthy response to inference request in 1.3769276142120361s
Received healthy response to inference request in 1.4125823974609375s
Received healthy response to inference request in 1.564284086227417s
Received healthy response to inference request in 1.3565757274627686s
5 requests
0 failed requests
5th percentile: 1.3606461048126222
10th percentile: 1.3647164821624755
20th percentile: 1.3728572368621825
30th percentile: 1.3840585708618165
40th percentile: 1.398320484161377
50th percentile: 1.4125823974609375
60th percentile: 1.4732630729675293
70th percentile: 1.533943748474121
80th percentile: 1.6685912132263185
90th percentile: 1.8772054672241212
95th percentile: 1.9815125942230223
99th percentile: 2.0649582958221435
mean time: 1.5592379093170166
Pipeline stage StressChecker completed in 9.28s
Shutdown handler de-registered
chaiml-nemo-20241010-t_5991_v128 status is now deployed due to DeploymentManager action
chaiml-nemo-20241010-t_5991_v128 status is now inactive due to auto deactivation removed underperforming models