developer_uid: azuruce
submission_id: chaiml-nemo-20241014-mer_6851_v1
model_name: chaiml-nemo-20241014-mer_6851_v1
model_group: ChaiML/nemo-20241014_mer
status: torndown
timestamp: 2024-10-15T17:35:15+00:00
num_battles: 6509
num_wins: 3585
celo_rating: 1282.92
family_friendly_score: 0.5715201025148167
family_friendly_standard_error: 0.006229866160889379
submission_type: basic
model_repo: ChaiML/nemo-20241014_merge_v6_w325-albert
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: chaiml-nemo-20241014-mer_6851_v1
is_internal_developer: True
language_model: ChaiML/nemo-20241014_merge_v6_w325-albert
model_size: 13B
ranking_group: single
us_pacific_date: 2024-10-15
win_ratio: 0.5507758488247042
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': 8, '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-20241014-mer-6851-v1-mkmlizer
Waiting for job on chaiml-nemo-20241014-mer-6851-v1-mkmlizer to finish
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: Downloaded to shared memory in 51.314s
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7dhs2kd7, device:0
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: quantized model in 38.116s
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: Processed model ChaiML/nemo-20241014_merge_v6_w325-albert in 89.430s
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241014-mer-6851-v1
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241014-mer-6851-v1/config.json
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241014-mer-6851-v1/special_tokens_map.json
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241014-mer-6851-v1/tokenizer_config.json
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241014-mer-6851-v1/tokenizer.json
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241014-mer-6851-v1/flywheel_model.0.safetensors
chaiml-nemo-20241014-mer-6851-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:22,  3.06s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:55,  1.21it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:45,  3.33it/s]
Loading 0:   5%|▍         | 18/363 [00:06<01:05,  5.30it/s]
Loading 0:   7%|▋         | 24/363 [00:06<00:42,  8.04it/s]
Loading 0:   9%|▉         | 32/363 [00:06<00:25, 13.12it/s]
Loading 0:  10%|█         | 38/363 [00:06<00:19, 17.02it/s]
Loading 0:  12%|█▏        | 43/363 [00:07<00:18, 17.11it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:13, 23.05it/s]
Loading 0:  15%|█▌        | 56/363 [00:07<00:11, 26.65it/s]
Loading 0:  17%|█▋        | 61/363 [00:07<00:10, 29.73it/s]
Loading 0:  19%|█▊        | 68/363 [00:07<00:08, 36.11it/s]
Loading 0:  20%|██        | 74/363 [00:07<00:07, 38.44it/s]
Loading 0:  22%|██▏       | 79/363 [00:07<00:07, 39.41it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:06, 44.30it/s]
Loading 0:  25%|██▌       | 91/363 [00:08<00:06, 44.71it/s]
Loading 0:  26%|██▋       | 96/363 [00:08<00:07, 37.62it/s]
Loading 0:  29%|██▊       | 104/363 [00:08<00:05, 45.87it/s]
Loading 0:  30%|███       | 110/363 [00:08<00:05, 44.54it/s]
Loading 0:  32%|███▏      | 115/363 [00:08<00:05, 42.16it/s]
Loading 0:  33%|███▎      | 121/363 [00:09<00:07, 31.39it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:07, 30.70it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:06, 35.14it/s]
Loading 0:  37%|███▋      | 135/363 [00:09<00:06, 35.66it/s]
Loading 0:  38%|███▊      | 139/363 [00:09<00:06, 35.95it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:06, 34.13it/s]
Loading 0:  40%|████      | 147/363 [00:09<00:06, 34.52it/s]
Loading 0:  42%|████▏     | 151/363 [00:09<00:06, 33.06it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:05, 38.56it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:05, 36.25it/s]
Loading 0:  46%|████▌     | 166/363 [00:10<00:05, 38.53it/s]
Loading 0:  47%|████▋     | 170/363 [00:10<00:05, 35.97it/s]
Loading 0:  48%|████▊     | 175/363 [00:10<00:05, 36.85it/s]
Loading 0:  49%|████▉     | 179/363 [00:10<00:05, 34.42it/s]
Loading 0:  51%|█████     | 184/363 [00:10<00:05, 35.60it/s]
Loading 0:  52%|█████▏    | 188/363 [00:10<00:05, 33.90it/s]
Loading 0:  53%|█████▎    | 193/363 [00:11<00:04, 35.70it/s]
Loading 0:  54%|█████▍    | 197/363 [00:11<00:04, 33.53it/s]
Loading 0:  56%|█████▌    | 202/363 [00:11<00:06, 24.77it/s]
Loading 0:  56%|█████▋    | 205/363 [00:11<00:06, 24.27it/s]
Loading 0:  58%|█████▊    | 209/363 [00:11<00:05, 27.42it/s]
Loading 0:  59%|█████▊    | 213/363 [00:11<00:05, 26.66it/s]
Loading 0:  61%|██████    | 220/363 [00:12<00:04, 34.07it/s]
Loading 0:  62%|██████▏   | 224/363 [00:12<00:04, 33.19it/s]
Loading 0:  63%|██████▎   | 229/363 [00:12<00:03, 35.98it/s]
Loading 0:  64%|██████▍   | 233/363 [00:12<00:03, 34.59it/s]
Loading 0:  66%|██████▌   | 238/363 [00:12<00:03, 37.30it/s]
Loading 0:  67%|██████▋   | 242/363 [00:12<00:03, 35.45it/s]
Loading 0:  68%|██████▊   | 247/363 [00:12<00:03, 37.22it/s]
Loading 0:  69%|██████▉   | 251/363 [00:12<00:03, 35.36it/s]
Loading 0:  71%|███████   | 256/363 [00:13<00:02, 37.64it/s]
Loading 0:  72%|███████▏  | 260/363 [00:13<00:02, 35.75it/s]
Loading 0:  73%|███████▎  | 265/363 [00:13<00:02, 37.70it/s]
Loading 0:  74%|███████▍  | 269/363 [00:13<00:02, 35.80it/s]
Loading 0:  75%|███████▌  | 274/363 [00:13<00:02, 38.42it/s]
Loading 0:  77%|███████▋  | 278/363 [00:13<00:02, 36.34it/s]
Loading 0:  78%|███████▊  | 283/363 [00:13<00:03, 25.73it/s]
Loading 0:  79%|███████▉  | 287/363 [00:14<00:02, 27.01it/s]
Loading 0:  80%|████████  | 292/363 [00:14<00:02, 31.04it/s]
Loading 0:  82%|████████▏ | 296/363 [00:14<00:02, 30.69it/s]
Loading 0:  83%|████████▎ | 301/363 [00:14<00:01, 34.09it/s]
Loading 0:  84%|████████▍ | 305/363 [00:14<00:01, 33.15it/s]
Loading 0:  85%|████████▌ | 310/363 [00:14<00:01, 35.37it/s]
Loading 0:  87%|████████▋ | 314/363 [00:14<00:01, 33.79it/s]
Loading 0:  88%|████████▊ | 318/363 [00:14<00:01, 34.80it/s]
Loading 0:  89%|████████▊ | 322/363 [00:15<00:01, 31.48it/s]
Loading 0:  90%|█████████ | 328/363 [00:15<00:00, 36.67it/s]
Loading 0:  91%|█████████▏| 332/363 [00:15<00:00, 34.58it/s]
Loading 0:  93%|█████████▎| 337/363 [00:15<00:00, 36.80it/s]
Loading 0:  94%|█████████▍| 341/363 [00:15<00:00, 35.04it/s]
Loading 0:  95%|█████████▌| 346/363 [00:15<00:00, 37.60it/s]
Loading 0:  96%|█████████▋| 350/363 [00:15<00:00, 35.58it/s]
Loading 0:  98%|█████████▊| 355/363 [00:15<00:00, 38.69it/s]
Loading 0:  99%|█████████▉| 359/363 [00:16<00:00, 36.78it/s]
                                                            

Job chaiml-nemo-20241014-mer-6851-v1-mkmlizer completed after 115.3s with status: succeeded
Stopping job with name chaiml-nemo-20241014-mer-6851-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.88s
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-20241014-mer-6851-v1
Waiting for inference service chaiml-nemo-20241014-mer-6851-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-nemo-20241014-mer-6851-v1 ready after 160.69407415390015s
Pipeline stage MKMLDeployer completed in 161.27s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0329854488372803s
Received healthy response to inference request in 1.4894928932189941s
Received healthy response to inference request in 1.5103545188903809s
Received healthy response to inference request in 1.5399737358093262s
Received healthy response to inference request in 1.4197876453399658s
5 requests
0 failed requests
5th percentile: 1.4337286949157715
10th percentile: 1.4476697444915771
20th percentile: 1.4755518436431885
30th percentile: 1.4936652183532715
40th percentile: 1.5020098686218262
50th percentile: 1.5103545188903809
60th percentile: 1.522202205657959
70th percentile: 1.534049892425537
80th percentile: 1.638576078414917
90th percentile: 1.8357807636260988
95th percentile: 1.9343831062316894
99th percentile: 2.013264980316162
mean time: 1.5985188484191895
Pipeline stage StressChecker completed in 9.38s
Shutdown handler de-registered
chaiml-nemo-20241014-mer_6851_v1 status is now deployed due to DeploymentManager action
chaiml-nemo-20241014-mer_6851_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241014-mer_6851_v1 status is now torndown due to DeploymentManager action