chaiml-nemo-20241017-dar_4269

developer_uid: azuruce

submission_id: chaiml-nemo-20241017-dar_4269_v1

model_name: chaiml-nemo-20241017-dar_4269_v1

model_group: ChaiML/nemo-20241017-dar

status: torndown

timestamp: 2024-10-18T21:09:30+00:00

num_battles: 10528

num_wins: 5144

celo_rating: 1246.47

family_friendly_score: 0.5827986633249791

family_friendly_standard_error: 0.004907079130611738

submission_type: basic

model_repo: ChaiML/nemo-20241017-dare_ties-remerge_v2_5merge-albert

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

display_name: chaiml-nemo-20241017-dar_4269_v1

is_internal_developer: True

language_model: ChaiML/nemo-20241017-dare_ties-remerge_v2_5merge-albert

model_size: 13B

ranking_group: single

us_pacific_date: 2024-10-18

win_ratio: 0.4886018237082067

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', '</s>', '###', 'Bot:', 'User:', 'You:', '<|im_end|>'], '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-20241017-dar-4269-v1-mkmlizer
Waiting for job on chaiml-nemo-20241017-dar-4269-v1-mkmlizer to finish
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: Downloaded to shared memory in 57.588s
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp1kl8n5k0, device:0
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: quantized model in 37.458s
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: Processed model ChaiML/nemo-20241017-dare_ties-remerge_v2_5merge-albert in 95.046s
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241017-dar-4269-v1
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241017-dar-4269-v1/config.json
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241017-dar-4269-v1/special_tokens_map.json
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241017-dar-4269-v1/tokenizer_config.json
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241017-dar-4269-v1/tokenizer.json
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241017-dar-4269-v1/flywheel_model.0.safetensors
chaiml-nemo-20241017-dar-4269-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:24,  3.06s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:54,  1.21it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:09,  2.72it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:22,  4.24it/s]
Loading 0:   6%|▌         | 22/363 [00:06<00:42,  7.93it/s]
Loading 0:   7%|▋         | 27/363 [00:06<00:30, 10.90it/s]
Loading 0:   9%|▉         | 32/363 [00:06<00:23, 14.35it/s]
Loading 0:  10%|█         | 37/363 [00:07<00:18, 18.03it/s]
Loading 0:  12%|█▏        | 42/363 [00:07<00:19, 16.24it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:13, 22.74it/s]
Loading 0:  15%|█▍        | 54/363 [00:07<00:12, 25.57it/s]
Loading 0:  16%|█▋        | 59/363 [00:07<00:10, 27.92it/s]
Loading 0:  17%|█▋        | 63/363 [00:07<00:10, 29.80it/s]
Loading 0:  19%|█▊        | 68/363 [00:07<00:08, 33.44it/s]
Loading 0:  20%|██        | 73/363 [00:08<00:08, 35.39it/s]
Loading 0:  21%|██▏       | 78/363 [00:08<00:09, 31.28it/s]
Loading 0:  23%|██▎       | 85/363 [00:08<00:07, 38.19it/s]
Loading 0:  25%|██▍       | 90/363 [00:08<00:07, 38.13it/s]
Loading 0:  26%|██▌       | 95/363 [00:08<00:06, 39.30it/s]
Loading 0:  28%|██▊       | 100/363 [00:08<00:06, 40.36it/s]
Loading 0:  29%|██▉       | 105/363 [00:08<00:07, 32.94it/s]
Loading 0:  31%|███       | 112/363 [00:09<00:06, 40.25it/s]
Loading 0:  32%|███▏      | 117/363 [00:09<00:06, 39.94it/s]
Loading 0:  34%|███▎      | 122/363 [00:09<00:08, 29.12it/s]
Loading 0:  35%|███▍      | 126/363 [00:09<00:07, 30.00it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:07, 30.82it/s]
Loading 0:  37%|███▋      | 134/363 [00:09<00:07, 30.86it/s]
Loading 0:  38%|███▊      | 139/363 [00:10<00:06, 33.45it/s]
Loading 0:  39%|███▉      | 143/363 [00:10<00:06, 33.50it/s]
Loading 0:  40%|████      | 147/363 [00:10<00:06, 32.90it/s]
Loading 0:  42%|████▏     | 151/363 [00:10<00:06, 31.43it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:05, 36.95it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:05, 36.39it/s]
Loading 0:  46%|████▌     | 166/363 [00:10<00:05, 38.75it/s]
Loading 0:  47%|████▋     | 170/363 [00:10<00:05, 37.40it/s]
Loading 0:  48%|████▊     | 175/363 [00:10<00:04, 39.91it/s]
Loading 0:  50%|████▉     | 180/363 [00:11<00:04, 38.14it/s]
Loading 0:  51%|█████     | 184/363 [00:11<00:04, 36.80it/s]
Loading 0:  52%|█████▏    | 188/363 [00:11<00:04, 35.39it/s]
Loading 0:  53%|█████▎    | 193/363 [00:11<00:04, 38.23it/s]
Loading 0:  54%|█████▍    | 197/363 [00:11<00:04, 37.74it/s]
Loading 0:  56%|█████▌    | 202/363 [00:11<00:05, 28.63it/s]
Loading 0:  57%|█████▋    | 206/363 [00:11<00:05, 29.53it/s]
Loading 0:  58%|█████▊    | 211/363 [00:12<00:04, 33.55it/s]
Loading 0:  59%|█████▉    | 215/363 [00:12<00:04, 33.41it/s]
Loading 0:  60%|██████    | 219/363 [00:12<00:04, 34.99it/s]
Loading 0:  61%|██████▏   | 223/363 [00:12<00:04, 32.35it/s]
Loading 0:  63%|██████▎   | 229/363 [00:12<00:03, 38.01it/s]
Loading 0:  64%|██████▍   | 233/363 [00:12<00:03, 36.57it/s]
Loading 0:  66%|██████▌   | 238/363 [00:12<00:03, 38.50it/s]
Loading 0:  67%|██████▋   | 242/363 [00:12<00:03, 36.90it/s]
Loading 0:  68%|██████▊   | 246/363 [00:13<00:03, 37.48it/s]
Loading 0:  69%|██████▉   | 250/363 [00:13<00:03, 33.70it/s]
Loading 0:  71%|███████   | 256/363 [00:13<00:02, 38.52it/s]
Loading 0:  72%|███████▏  | 260/363 [00:13<00:02, 36.72it/s]
Loading 0:  73%|███████▎  | 265/363 [00:13<00:02, 38.27it/s]
Loading 0:  74%|███████▍  | 269/363 [00:13<00:02, 36.72it/s]
Loading 0:  75%|███████▌  | 274/363 [00:13<00:02, 38.39it/s]
Loading 0:  77%|███████▋  | 278/363 [00:13<00:02, 35.03it/s]
Loading 0:  78%|███████▊  | 283/363 [00:14<00:02, 26.92it/s]
Loading 0:  79%|███████▉  | 287/363 [00:14<00:02, 28.23it/s]
Loading 0:  80%|████████  | 292/363 [00:14<00:02, 31.76it/s]
Loading 0:  82%|████████▏ | 296/363 [00:14<00:02, 32.81it/s]
Loading 0:  83%|████████▎ | 301/363 [00:14<00:01, 36.89it/s]
Loading 0:  84%|████████▍ | 305/363 [00:14<00:01, 35.92it/s]
Loading 0:  85%|████████▌ | 310/363 [00:14<00:01, 37.71it/s]
Loading 0:  87%|████████▋ | 314/363 [00:14<00:01, 36.17it/s]
Loading 0:  88%|████████▊ | 319/363 [00:15<00:01, 39.30it/s]
Loading 0:  89%|████████▉ | 324/363 [00:15<00:00, 39.19it/s]
Loading 0:  90%|█████████ | 328/363 [00:15<00:00, 38.57it/s]
Loading 0:  91%|█████████▏| 332/363 [00:15<00:00, 36.84it/s]
Loading 0:  93%|█████████▎| 337/363 [00:15<00:00, 40.03it/s]
Loading 0:  94%|█████████▍| 342/363 [00:15<00:00, 40.01it/s]
Loading 0:  96%|█████████▌| 347/363 [00:15<00:00, 39.94it/s]
Loading 0:  97%|█████████▋| 352/363 [00:15<00:00, 40.62it/s]
Loading 0:  98%|█████████▊| 357/363 [00:16<00:00, 33.78it/s]
                                                            
Job chaiml-nemo-20241017-dar-4269-v1-mkmlizer completed after 125.06s with status: succeeded
Stopping job with name chaiml-nemo-20241017-dar-4269-v1-mkmlizer
Pipeline stage MKMLizer completed in 125.57s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-20241017-dar-4269-v1
Waiting for inference service chaiml-nemo-20241017-dar-4269-v1 to be ready
Inference service chaiml-nemo-20241017-dar-4269-v1 ready after 180.68246793746948s
Pipeline stage MKMLDeployer completed in 181.22s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9160659313201904s
Received healthy response to inference request in 2.1364498138427734s
Received healthy response to inference request in 1.6873524188995361s
Received healthy response to inference request in 1.466223955154419s
Received healthy response to inference request in 1.9339306354522705s
5 requests
0 failed requests
5th percentile: 1.5104496479034424
10th percentile: 1.5546753406524658
20th percentile: 1.6431267261505127
30th percentile: 1.733095121383667
40th percentile: 1.8245805263519288
50th percentile: 1.9160659313201904
60th percentile: 1.9232118129730225
70th percentile: 1.9303576946258545
80th percentile: 1.9744344711303712
90th percentile: 2.055442142486572
95th percentile: 2.0959459781646728
99th percentile: 2.1283490467071533
mean time: 1.8280045509338378
Pipeline stage StressChecker completed in 10.49s
Shutdown handler de-registered
chaiml-nemo-20241017-dar_4269_v1 status is now deployed due to DeploymentManager action
chaiml-nemo-20241017-dar_4269_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241017-dar_4269_v1 status is now torndown due to DeploymentManager action