chaiml-nemo-20241017-mod_6892

developer_uid: azuruce

submission_id: chaiml-nemo-20241017-mod_6892_v3

model_name: chaiml-nemo-20241017-mod_6892_v3

model_group: ChaiML/nemo-20241017-mod

status: torndown

timestamp: 2024-10-18T16:02:31+00:00

num_battles: 8311

num_wins: 3845

celo_rating: 1227.95

family_friendly_score: 0.6032272879091516

family_friendly_standard_error: 0.005450387352769314

submission_type: basic

model_repo: ChaiML/nemo-20241017-model_stock-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-mod_6892_v3

is_internal_developer: True

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

model_size: 13B

ranking_group: single

us_pacific_date: 2024-10-18

win_ratio: 0.4626398748646372

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}

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-mod-6892-v3-mkmlizer
Waiting for job on chaiml-nemo-20241017-mod-6892-v3-mkmlizer to finish
chaiml-nemo-20241017-mod-6892-v3-mkmlizer: Downloaded to shared memory in 28.873s
chaiml-nemo-20241017-mod-6892-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppd7ceeen, device:0
chaiml-nemo-20241017-mod-6892-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241017-mod-6892-v3-mkmlizer: quantized model in 38.486s
chaiml-nemo-20241017-mod-6892-v3-mkmlizer: Processed model ChaiML/nemo-20241017-model_stock-remerge_v2_5merge-albert in 67.359s
chaiml-nemo-20241017-mod-6892-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241017-mod-6892-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241017-mod-6892-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241017-mod-6892-v3
chaiml-nemo-20241017-mod-6892-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241017-mod-6892-v3/special_tokens_map.json
chaiml-nemo-20241017-mod-6892-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241017-mod-6892-v3/config.json
chaiml-nemo-20241017-mod-6892-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241017-mod-6892-v3/tokenizer_config.json
chaiml-nemo-20241017-mod-6892-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241017-mod-6892-v3/tokenizer.json
chaiml-nemo-20241017-mod-6892-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241017-mod-6892-v3/flywheel_model.0.safetensors
chaiml-nemo-20241017-mod-6892-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<19:22,  3.22s/it]
Loading 0:   2%|▏         | 6/363 [00:06<05:08,  1.16it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:15,  2.60it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:25,  4.06it/s]
Loading 0:   6%|▌         | 22/363 [00:06<00:44,  7.63it/s]
Loading 0:   7%|▋         | 27/363 [00:07<00:32, 10.50it/s]
Loading 0:   9%|▉         | 32/363 [00:07<00:23, 13.87it/s]
Loading 0:  10%|█         | 37/363 [00:07<00:18, 17.90it/s]
Loading 0:  12%|█▏        | 42/363 [00:07<00:19, 16.20it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:13, 22.70it/s]
Loading 0:  15%|█▍        | 54/363 [00:07<00:11, 25.87it/s]
Loading 0:  16%|█▋        | 59/363 [00:08<00:10, 29.18it/s]
Loading 0:  18%|█▊        | 64/363 [00:08<00:09, 33.00it/s]
Loading 0:  19%|█▉        | 69/363 [00:08<00:09, 29.58it/s]
Loading 0:  21%|██        | 76/363 [00:08<00:07, 36.84it/s]
Loading 0:  22%|██▏       | 81/363 [00:08<00:07, 37.15it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:07, 38.24it/s]
Loading 0:  25%|██▌       | 91/363 [00:08<00:06, 40.05it/s]
Loading 0:  26%|██▋       | 96/363 [00:08<00:07, 34.49it/s]
Loading 0:  28%|██▊       | 103/363 [00:09<00:06, 41.87it/s]
Loading 0:  30%|██▉       | 108/363 [00:09<00:06, 41.48it/s]
Loading 0:  31%|███       | 113/363 [00:09<00:06, 41.53it/s]
Loading 0:  33%|███▎      | 118/363 [00:09<00:05, 41.11it/s]
Loading 0:  34%|███▍      | 123/363 [00:09<00:09, 24.81it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:07, 31.85it/s]
Loading 0:  37%|███▋      | 135/363 [00:10<00:06, 32.72it/s]
Loading 0:  39%|███▊      | 140/363 [00:10<00:06, 34.20it/s]
Loading 0:  40%|███▉      | 144/363 [00:10<00:06, 35.29it/s]
Loading 0:  41%|████      | 149/363 [00:10<00:05, 36.16it/s]
Loading 0:  42%|████▏     | 153/363 [00:10<00:05, 35.59it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:05, 35.07it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:05, 34.09it/s]
Loading 0:  46%|████▌     | 166/363 [00:10<00:05, 37.12it/s]
Loading 0:  47%|████▋     | 170/363 [00:11<00:05, 35.62it/s]
Loading 0:  48%|████▊     | 175/363 [00:11<00:05, 37.39it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:05, 36.23it/s]
Loading 0:  51%|█████     | 184/363 [00:11<00:04, 38.97it/s]
Loading 0:  52%|█████▏    | 188/363 [00:11<00:04, 37.31it/s]
Loading 0:  53%|█████▎    | 193/363 [00:11<00:04, 39.50it/s]
Loading 0:  54%|█████▍    | 197/363 [00:11<00:04, 37.03it/s]
Loading 0:  56%|█████▌    | 202/363 [00:12<00:06, 26.33it/s]
Loading 0:  57%|█████▋    | 206/363 [00:12<00:05, 27.77it/s]
Loading 0:  58%|█████▊    | 211/363 [00:12<00:05, 28.89it/s]
Loading 0:  59%|█████▉    | 215/363 [00:12<00:04, 29.89it/s]
Loading 0:  61%|██████    | 220/363 [00:12<00:04, 33.29it/s]
Loading 0:  62%|██████▏   | 224/363 [00:12<00:04, 34.09it/s]
Loading 0:  63%|██████▎   | 230/363 [00:12<00:03, 38.83it/s]
Loading 0:  65%|██████▍   | 235/363 [00:12<00:03, 41.52it/s]
Loading 0:  66%|██████▌   | 240/363 [00:13<00:03, 34.10it/s]
Loading 0:  68%|██████▊   | 247/363 [00:13<00:02, 41.20it/s]
Loading 0:  69%|██████▉   | 252/363 [00:13<00:02, 40.54it/s]
Loading 0:  71%|███████   | 257/363 [00:13<00:02, 40.97it/s]
Loading 0:  72%|███████▏  | 262/363 [00:13<00:02, 42.80it/s]
Loading 0:  74%|███████▎  | 267/363 [00:13<00:02, 36.13it/s]
Loading 0:  75%|███████▌  | 274/363 [00:13<00:02, 42.39it/s]
Loading 0:  77%|███████▋  | 279/363 [00:14<00:01, 42.23it/s]
Loading 0:  78%|███████▊  | 284/363 [00:14<00:02, 30.36it/s]
Loading 0:  79%|███████▉  | 288/363 [00:14<00:02, 31.67it/s]
Loading 0:  80%|████████  | 292/363 [00:14<00:02, 32.77it/s]
Loading 0:  82%|████████▏ | 296/363 [00:14<00:02, 30.66it/s]
Loading 0:  83%|████████▎ | 300/363 [00:14<00:01, 32.48it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:02, 29.09it/s]
Loading 0:  85%|████████▍ | 308/363 [00:15<00:01, 31.09it/s]
Loading 0:  86%|████████▌ | 312/363 [00:15<00:01, 30.01it/s]
Loading 0:  88%|████████▊ | 319/363 [00:15<00:01, 37.90it/s]
Loading 0:  89%|████████▉ | 323/363 [00:15<00:01, 37.00it/s]
Loading 0:  90%|█████████ | 328/363 [00:15<00:00, 40.22it/s]
Loading 0:  92%|█████████▏| 333/363 [00:15<00:00, 40.27it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:00, 39.64it/s]
Loading 0:  94%|█████████▍| 343/363 [00:15<00:00, 40.61it/s]
Loading 0:  96%|█████████▌| 348/363 [00:16<00:00, 32.97it/s]
Loading 0:  98%|█████████▊| 355/363 [00:16<00:00, 39.32it/s]
Loading 0:  99%|█████████▉| 360/363 [00:16<00:00, 38.32it/s]
                                                            
Job chaiml-nemo-20241017-mod-6892-v3-mkmlizer completed after 93.11s with status: succeeded
Stopping job with name chaiml-nemo-20241017-mod-6892-v3-mkmlizer
Pipeline stage MKMLizer completed in 93.62s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.60s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-20241017-mod-6892-v3
Waiting for inference service chaiml-nemo-20241017-mod-6892-v3 to be ready
Inference service chaiml-nemo-20241017-mod-6892-v3 ready after 170.59984135627747s
Pipeline stage MKMLDeployer completed in 171.42s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8889720439910889s
Received healthy response to inference request in 1.2125885486602783s
Received healthy response to inference request in 1.4956305027008057s
Received healthy response to inference request in 1.5832557678222656s
Received healthy response to inference request in 1.2227134704589844s
5 requests
0 failed requests
5th percentile: 1.2146135330200196
10th percentile: 1.2166385173797607
20th percentile: 1.220688486099243
30th percentile: 1.2772968769073487
40th percentile: 1.3864636898040772
50th percentile: 1.4956305027008057
60th percentile: 1.5306806087493896
70th percentile: 1.5657307147979735
80th percentile: 1.6443990230560304
90th percentile: 1.7666855335235596
95th percentile: 1.8278287887573241
99th percentile: 1.876743392944336
mean time: 1.4806320667266846
Pipeline stage StressChecker completed in 8.85s
Shutdown handler de-registered
chaiml-nemo-20241017-mod_6892_v3 status is now deployed due to DeploymentManager action
chaiml-nemo-20241017-mod_6892_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241017-mod_6892_v3 status is now torndown due to DeploymentManager action