chaiml-nemo-20241014-mer_2893

developer_uid: azuruce

submission_id: chaiml-nemo-20241014-mer_2893_v1

model_name: chaiml-nemo-20241014-mer_2893_v1

model_group: ChaiML/nemo-20241014_mer

status: torndown

timestamp: 2024-10-15T17:34:44+00:00

num_battles: 6703

num_wins: 3761

celo_rating: 1288.82

family_friendly_score: 0.5726302083333333

family_friendly_standard_error: 0.006157537725550236

submission_type: basic

model_repo: ChaiML/nemo-20241014_merge_v4_w217-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_2893_v1

is_internal_developer: True

language_model: ChaiML/nemo-20241014_merge_v4_w217-albert

model_size: 13B

ranking_group: single

us_pacific_date: 2024-10-15

win_ratio: 0.5610920483365657

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-2893-v1-mkmlizer
Waiting for job on chaiml-nemo-20241014-mer-2893-v1-mkmlizer to finish
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: Downloaded to shared memory in 54.908s
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpa8gj8us_, device:0
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: quantized model in 36.673s
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: Processed model ChaiML/nemo-20241014_merge_v4_w217-albert in 91.581s
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241014-mer-2893-v1
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241014-mer-2893-v1/tokenizer_config.json
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241014-mer-2893-v1/tokenizer.json
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241014-mer-2893-v1/flywheel_model.0.safetensors
chaiml-nemo-20241014-mer-2893-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:39,  3.10s/it]
Loading 0:   2%|▏         | 6/363 [00:06<05:00,  1.19it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:11,  2.68it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:23,  4.17it/s]
Loading 0:   6%|▌         | 22/363 [00:06<00:43,  7.79it/s]
Loading 0:   7%|▋         | 27/363 [00:06<00:31, 10.71it/s]
Loading 0:   9%|▉         | 32/363 [00:06<00:23, 14.28it/s]
Loading 0:  10%|█         | 37/363 [00:07<00:17, 18.45it/s]
Loading 0:  12%|█▏        | 42/363 [00:07<00:19, 16.14it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:13, 22.83it/s]
Loading 0:  15%|█▍        | 54/363 [00:07<00:11, 26.40it/s]
Loading 0:  16%|█▋        | 59/363 [00:07<00:10, 29.86it/s]
Loading 0:  18%|█▊        | 65/363 [00:07<00:09, 32.48it/s]
Loading 0:  19%|█▉        | 70/363 [00:08<00:08, 34.03it/s]
Loading 0:  21%|██        | 76/363 [00:08<00:07, 39.30it/s]
Loading 0:  22%|██▏       | 81/363 [00:08<00:07, 39.58it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:06, 40.67it/s]
Loading 0:  25%|██▌       | 91/363 [00:08<00:06, 42.50it/s]
Loading 0:  26%|██▋       | 96/363 [00:08<00:07, 36.68it/s]
Loading 0:  29%|██▊       | 104/363 [00:08<00:05, 45.31it/s]
Loading 0:  30%|███       | 110/363 [00:08<00:05, 44.41it/s]
Loading 0:  32%|███▏      | 115/363 [00:09<00:05, 43.46it/s]
Loading 0:  33%|███▎      | 121/363 [00:09<00:07, 31.94it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:07, 32.40it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:06, 37.36it/s]
Loading 0:  38%|███▊      | 137/363 [00:09<00:05, 37.95it/s]
Loading 0:  39%|███▉      | 142/363 [00:09<00:05, 38.23it/s]
Loading 0:  41%|████      | 149/363 [00:10<00:04, 43.79it/s]
Loading 0:  43%|████▎     | 155/363 [00:10<00:04, 43.20it/s]
Loading 0:  44%|████▍     | 160/363 [00:10<00:04, 42.31it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:04, 46.94it/s]
Loading 0:  48%|████▊     | 173/363 [00:10<00:04, 44.94it/s]
Loading 0:  49%|████▉     | 178/363 [00:10<00:04, 42.69it/s]
Loading 0:  51%|█████     | 184/363 [00:10<00:03, 46.83it/s]
Loading 0:  52%|█████▏    | 189/363 [00:10<00:03, 46.51it/s]
Loading 0:  54%|█████▎    | 195/363 [00:11<00:03, 42.09it/s]
Loading 0:  56%|█████▌    | 202/363 [00:11<00:04, 34.15it/s]
Loading 0:  57%|█████▋    | 206/363 [00:11<00:04, 34.02it/s]
Loading 0:  58%|█████▊    | 212/363 [00:11<00:03, 38.56it/s]
Loading 0:  60%|██████    | 218/363 [00:11<00:03, 39.51it/s]
Loading 0:  61%|██████▏   | 223/363 [00:11<00:03, 39.50it/s]
Loading 0:  63%|██████▎   | 230/363 [00:11<00:02, 45.11it/s]
Loading 0:  65%|██████▌   | 236/363 [00:12<00:02, 44.02it/s]
Loading 0:  66%|██████▋   | 241/363 [00:12<00:02, 42.99it/s]
Loading 0:  68%|██████▊   | 247/363 [00:12<00:02, 46.55it/s]
Loading 0:  69%|██████▉   | 252/363 [00:12<00:02, 44.24it/s]
Loading 0:  71%|███████   | 257/363 [00:12<00:02, 44.75it/s]
Loading 0:  72%|███████▏  | 263/363 [00:12<00:02, 43.82it/s]
Loading 0:  74%|███████▍  | 268/363 [00:12<00:02, 42.61it/s]
Loading 0:  76%|███████▌  | 275/363 [00:12<00:01, 47.86it/s]
Loading 0:  77%|███████▋  | 281/363 [00:13<00:01, 46.14it/s]
Loading 0:  79%|███████▉  | 286/363 [00:13<00:02, 29.58it/s]
Loading 0:  80%|████████  | 292/363 [00:13<00:02, 34.75it/s]
Loading 0:  82%|████████▏ | 297/363 [00:13<00:01, 36.82it/s]
Loading 0:  83%|████████▎ | 302/363 [00:13<00:01, 38.93it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:01, 39.84it/s]
Loading 0:  86%|████████▌ | 313/363 [00:14<00:01, 39.08it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:00, 44.07it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:00, 45.44it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:00, 37.86it/s]
Loading 0:  93%|█████████▎| 337/363 [00:14<00:00, 44.63it/s]
Loading 0:  94%|█████████▍| 342/363 [00:14<00:00, 44.23it/s]
Loading 0:  96%|█████████▌| 347/363 [00:14<00:00, 44.26it/s]
Loading 0:  97%|█████████▋| 353/363 [00:14<00:00, 41.12it/s]
Loading 0:  99%|█████████▊| 358/363 [00:15<00:00, 41.21it/s]
                                                            
Job chaiml-nemo-20241014-mer-2893-v1-mkmlizer completed after 124.47s with status: succeeded
Stopping job with name chaiml-nemo-20241014-mer-2893-v1-mkmlizer
Pipeline stage MKMLizer completed in 125.03s
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-2893-v1
Waiting for inference service chaiml-nemo-20241014-mer-2893-v1 to be ready
Inference service chaiml-nemo-20241014-mer-2893-v1 ready after 160.70126748085022s
Pipeline stage MKMLDeployer completed in 161.59s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.073425769805908s
Received healthy response to inference request in 1.7019805908203125s
Received healthy response to inference request in 1.5707836151123047s
Received healthy response to inference request in 1.4778859615325928s
Received healthy response to inference request in 1.6786489486694336s
5 requests
0 failed requests
5th percentile: 1.4964654922485352
10th percentile: 1.5150450229644776
20th percentile: 1.5522040843963623
30th percentile: 1.5923566818237305
40th percentile: 1.635502815246582
50th percentile: 1.6786489486694336
60th percentile: 1.6879816055297852
70th percentile: 1.6973142623901367
80th percentile: 1.7762696266174318
90th percentile: 1.92484769821167
95th percentile: 1.9991367340087889
99th percentile: 2.0585679626464843
mean time: 1.7005449771881103
Pipeline stage StressChecker completed in 10.08s
Shutdown handler de-registered
chaiml-nemo-20241014-mer_2893_v1 status is now deployed due to DeploymentManager action
chaiml-nemo-20241014-mer_2893_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241014-mer_2893_v1 status is now torndown due to DeploymentManager action