developer_uid: azuruce
submission_id: chaiml-nemo-20241014-mer_6682_v1
model_name: chaiml-nemo-20241014-mer_6682_v1
model_group: ChaiML/nemo-20241014_mer
status: torndown
timestamp: 2024-10-15T15:05:27+00:00
num_battles: 8683
num_wins: 4876
celo_rating: 1282.3
family_friendly_score: 0.5787632451670306
family_friendly_standard_error: 0.0054161891147490645
submission_type: basic
model_repo: ChaiML/nemo-20241014_merge_v3_w127-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_6682_v1
is_internal_developer: True
language_model: ChaiML/nemo-20241014_merge_v3_w127-albert
model_size: 13B
ranking_group: single
us_pacific_date: 2024-10-15
win_ratio: 0.5615570655303467
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-6682-v1-mkmlizer
Waiting for job on chaiml-nemo-20241014-mer-6682-v1-mkmlizer to finish
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: Downloaded to shared memory in 49.198s
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2ki2bby_, device:0
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: quantized model in 37.062s
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: Processed model ChaiML/nemo-20241014_merge_v3_w127-albert in 86.260s
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241014-mer-6682-v1
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241014-mer-6682-v1/config.json
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241014-mer-6682-v1/special_tokens_map.json
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241014-mer-6682-v1/tokenizer_config.json
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241014-mer-6682-v1/tokenizer.json
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241014-mer-6682-v1/flywheel_model.0.safetensors
chaiml-nemo-20241014-mer-6682-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:23,  3.06s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:54,  1.21it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:45,  3.33it/s]
Loading 0:   5%|▍         | 17/363 [00:06<01:10,  4.87it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:42,  7.96it/s]
Loading 0:   8%|▊         | 29/363 [00:06<00:29, 11.40it/s]
Loading 0:   9%|▉         | 34/363 [00:06<00:22, 14.64it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:21, 15.09it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:18, 17.52it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:13, 22.89it/s]
Loading 0:  15%|█▌        | 56/363 [00:07<00:11, 26.12it/s]
Loading 0:  17%|█▋        | 60/363 [00:07<00:11, 26.86it/s]
Loading 0:  18%|█▊        | 67/363 [00:07<00:08, 33.74it/s]
Loading 0:  20%|█▉        | 72/363 [00:08<00:08, 35.69it/s]
Loading 0:  21%|██        | 77/363 [00:08<00:07, 36.12it/s]
Loading 0:  23%|██▎       | 82/363 [00:08<00:07, 38.42it/s]
Loading 0:  24%|██▍       | 87/363 [00:08<00:08, 33.85it/s]
Loading 0:  26%|██▌       | 94/363 [00:08<00:06, 41.54it/s]
Loading 0:  27%|██▋       | 99/363 [00:08<00:06, 42.39it/s]
Loading 0:  29%|██▊       | 104/363 [00:08<00:05, 43.50it/s]
Loading 0:  30%|███       | 109/363 [00:08<00:05, 44.89it/s]
Loading 0:  31%|███▏      | 114/363 [00:09<00:06, 37.98it/s]
Loading 0:  33%|███▎      | 121/363 [00:09<00:07, 31.95it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:07, 32.21it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:06, 36.50it/s]
Loading 0:  37%|███▋      | 135/363 [00:09<00:06, 37.19it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:05, 39.15it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:05, 39.26it/s]
Loading 0:  42%|████▏     | 151/363 [00:10<00:05, 39.50it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:04, 43.65it/s]
Loading 0:  45%|████▍     | 162/363 [00:10<00:04, 40.45it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:04, 40.91it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:04, 42.74it/s]
Loading 0:  49%|████▉     | 177/363 [00:10<00:05, 35.15it/s]
Loading 0:  51%|█████     | 184/363 [00:10<00:04, 41.91it/s]
Loading 0:  52%|█████▏    | 189/363 [00:10<00:04, 42.62it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:03, 42.88it/s]
Loading 0:  55%|█████▍    | 199/363 [00:11<00:03, 44.09it/s]
Loading 0:  56%|█████▌    | 204/363 [00:11<00:05, 26.51it/s]
Loading 0:  58%|█████▊    | 212/363 [00:11<00:04, 34.90it/s]
Loading 0:  60%|██████    | 218/363 [00:11<00:03, 36.37it/s]
Loading 0:  61%|██████▏   | 223/363 [00:11<00:03, 36.19it/s]
Loading 0:  63%|██████▎   | 230/363 [00:12<00:03, 41.38it/s]
Loading 0:  65%|██████▍   | 235/363 [00:12<00:03, 41.80it/s]
Loading 0:  66%|██████▌   | 240/363 [00:12<00:03, 34.62it/s]
Loading 0:  68%|██████▊   | 247/363 [00:12<00:02, 39.77it/s]
Loading 0:  69%|██████▉   | 252/363 [00:12<00:02, 39.66it/s]
Loading 0:  71%|███████   | 257/363 [00:12<00:02, 41.71it/s]
Loading 0:  72%|███████▏  | 263/363 [00:12<00:02, 40.90it/s]
Loading 0:  74%|███████▍  | 268/363 [00:13<00:02, 39.44it/s]
Loading 0:  75%|███████▌  | 274/363 [00:13<00:02, 43.68it/s]
Loading 0:  77%|███████▋  | 279/363 [00:13<00:02, 41.79it/s]
Loading 0:  78%|███████▊  | 284/363 [00:13<00:02, 30.12it/s]
Loading 0:  79%|███████▉  | 288/363 [00:13<00:02, 32.00it/s]
Loading 0:  81%|████████  | 293/363 [00:13<00:01, 35.26it/s]
Loading 0:  82%|████████▏ | 297/363 [00:13<00:01, 34.87it/s]
Loading 0:  83%|████████▎ | 302/363 [00:14<00:01, 37.25it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:01, 40.38it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:01, 33.80it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:01, 42.41it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:00, 44.22it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:00, 36.19it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:00, 43.66it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:00, 42.43it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 41.31it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 46.00it/s]
Loading 0:  99%|█████████▉| 361/363 [00:15<00:00, 46.21it/s]
                                                            

Job chaiml-nemo-20241014-mer-6682-v1-mkmlizer completed after 114.41s with status: succeeded
Stopping job with name chaiml-nemo-20241014-mer-6682-v1-mkmlizer
Pipeline stage MKMLizer completed in 114.92s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-20241014-mer-6682-v1
Waiting for inference service chaiml-nemo-20241014-mer-6682-v1 to be ready
Failed to get response for submission chaiml-nemo-20241010-tie_5991_v2: HTTPConnectionPool(host='chaiml-llama-8b-pairwis-8189-v27-predictor.tenant-chaiml-guanaco.k2.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x74efa0ea10a0>: Failed to establish a new connection: [Errno -5] No address associated with hostname'))
Failed to get response for submission blend_lofer_2024-10-07: HTTPConnectionPool(host='chaiml-elo-alignment-run-3-v44-predictor.tenant-chaiml-guanaco.k2.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x74eed7f71970>: Failed to establish a new connection: [Errno -5] No address associated with hostname'))
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-nemo-20241014-mer-6682-v1 ready after 160.81268501281738s
Pipeline stage MKMLDeployer completed in 161.43s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1601529121398926s
Received healthy response to inference request in 1.536207675933838s
Received healthy response to inference request in 1.6612331867218018s
Received healthy response to inference request in 1.445573329925537s
Received healthy response to inference request in 2.128525495529175s
5 requests
0 failed requests
5th percentile: 1.4637001991271972
10th percentile: 1.4818270683288575
20th percentile: 1.5180808067321778
30th percentile: 1.5612127780914307
40th percentile: 1.6112229824066162
50th percentile: 1.6612331867218018
60th percentile: 1.8481501102447508
70th percentile: 2.0350670337677
80th percentile: 2.1348509788513184
90th percentile: 2.1475019454956055
95th percentile: 2.153827428817749
99th percentile: 2.158887815475464
mean time: 1.7863385200500488
Pipeline stage StressChecker completed in 10.41s
Shutdown handler de-registered
chaiml-nemo-20241014-mer_6682_v1 status is now deployed due to DeploymentManager action
chaiml-nemo-20241014-mer_6682_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241014-mer_6682_v1 status is now torndown due to DeploymentManager action