abacusai-bigstral-12b-32k

developer_uid: azuruce
submission_id: abacusai-bigstral-12b-32k_v1
model_name: abacusai-bigstral-12b-32k_v1
model_group: abacusai/bigstral-12b-32
status: torndown
timestamp: 2024-10-09T21:56:23+00:00
num_battles: 7101
num_wins: 2999
celo_rating: 1194.89
family_friendly_score: 0.5391708468574801
family_friendly_standard_error: 0.006025921274562161
submission_type: basic
model_repo: abacusai/bigstral-12b-32k
model_architecture: MistralForCausalLM
model_num_parameters: 12476420096.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: abacusai-bigstral-12b-32k_v1
is_internal_developer: True
language_model: abacusai/bigstral-12b-32k
model_size: 12B
ranking_group: single
us_pacific_date: 2024-10-09
win_ratio: 0.42233488241092804
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|>', '\nYou:'], '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 abacusai-bigstral-12b-32k-v1-mkmlizer
Waiting for job on abacusai-bigstral-12b-32k-v1-mkmlizer to finish
abacusai-bigstral-12b-32k-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
abacusai-bigstral-12b-32k-v1-mkmlizer: ║     _____            __           __                                ║
abacusai-bigstral-12b-32k-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
abacusai-bigstral-12b-32k-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
abacusai-bigstral-12b-32k-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
abacusai-bigstral-12b-32k-v1-mkmlizer: ║       /___/                                                         ║
abacusai-bigstral-12b-32k-v1-mkmlizer: ║                                                                     ║
abacusai-bigstral-12b-32k-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
abacusai-bigstral-12b-32k-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
abacusai-bigstral-12b-32k-v1-mkmlizer: ║  https://mk1.ai                                                     ║
abacusai-bigstral-12b-32k-v1-mkmlizer: ║                                                                     ║
abacusai-bigstral-12b-32k-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
abacusai-bigstral-12b-32k-v1-mkmlizer: ║  belonging to:                                                      ║
abacusai-bigstral-12b-32k-v1-mkmlizer: ║                                                                     ║
abacusai-bigstral-12b-32k-v1-mkmlizer: ║  Chai Research Corp.                                                ║
abacusai-bigstral-12b-32k-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
abacusai-bigstral-12b-32k-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
abacusai-bigstral-12b-32k-v1-mkmlizer: ║                                                                     ║
abacusai-bigstral-12b-32k-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
abacusai-bigstral-12b-32k-v1-mkmlizer: Downloaded to shared memory in 51.838s
abacusai-bigstral-12b-32k-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjua4hcgw, device:0
abacusai-bigstral-12b-32k-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
abacusai-bigstral-12b-32k-v1-mkmlizer: quantized model in 29.048s
abacusai-bigstral-12b-32k-v1-mkmlizer: Processed model abacusai/bigstral-12b-32k in 80.887s
abacusai-bigstral-12b-32k-v1-mkmlizer: creating bucket guanaco-mkml-models
abacusai-bigstral-12b-32k-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
abacusai-bigstral-12b-32k-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/abacusai-bigstral-12b-32k-v1
abacusai-bigstral-12b-32k-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/abacusai-bigstral-12b-32k-v1/special_tokens_map.json
abacusai-bigstral-12b-32k-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/abacusai-bigstral-12b-32k-v1/config.json
abacusai-bigstral-12b-32k-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/abacusai-bigstral-12b-32k-v1/tokenizer_config.json
abacusai-bigstral-12b-32k-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/abacusai-bigstral-12b-32k-v1/tokenizer.model
abacusai-bigstral-12b-32k-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/abacusai-bigstral-12b-32k-v1/tokenizer.json
abacusai-bigstral-12b-32k-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/abacusai-bigstral-12b-32k-v1/flywheel_model.0.safetensors
abacusai-bigstral-12b-32k-v1-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:16, 29.93it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:10, 45.56it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:10, 46.11it/s]
Loading 0:   5%|▍         | 23/507 [00:00<00:11, 41.49it/s]
Loading 0:   6%|▌         | 31/507 [00:00<00:09, 50.95it/s]
Loading 0:   7%|▋         | 37/507 [00:00<00:09, 47.77it/s]
Loading 0:   8%|▊         | 42/507 [00:00<00:10, 45.92it/s]
Loading 0:   9%|▉         | 48/507 [00:01<00:09, 49.27it/s]
Loading 0:  11%|█         | 54/507 [00:01<00:09, 47.68it/s]
Loading 0:  12%|█▏        | 59/507 [00:01<00:11, 39.12it/s]
Loading 0:  13%|█▎        | 64/507 [00:01<00:11, 40.26it/s]
Loading 0:  14%|█▎        | 69/507 [00:01<00:10, 42.10it/s]
Loading 0:  15%|█▍        | 74/507 [00:01<00:12, 35.97it/s]
Loading 0:  16%|█▌        | 81/507 [00:01<00:11, 37.44it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:09, 42.10it/s]
Loading 0:  18%|█▊        | 92/507 [00:02<00:10, 41.12it/s]
Loading 0:  19%|█▉        | 97/507 [00:02<00:09, 43.02it/s]
Loading 0:  20%|██        | 103/507 [00:02<00:09, 41.21it/s]
Loading 0:  21%|██▏       | 108/507 [00:02<00:09, 40.30it/s]
Loading 0:  23%|██▎       | 116/507 [00:02<00:08, 48.66it/s]
Loading 0:  24%|██▍       | 122/507 [00:02<00:08, 47.16it/s]
Loading 0:  25%|██▌       | 129/507 [00:02<00:07, 52.79it/s]
Loading 0:  27%|██▋       | 135/507 [00:03<00:07, 50.17it/s]
Loading 0:  28%|██▊       | 141/507 [00:03<00:07, 50.73it/s]
Loading 0:  29%|██▉       | 147/507 [00:03<00:06, 52.71it/s]
Loading 0:  30%|███       | 153/507 [00:03<00:07, 48.10it/s]
Loading 0:  32%|███▏      | 160/507 [00:03<00:06, 52.87it/s]
Loading 0:  33%|███▎      | 166/507 [00:03<00:06, 49.37it/s]
Loading 0:  34%|███▍      | 172/507 [00:03<00:06, 49.79it/s]
Loading 0:  35%|███▌      | 178/507 [00:03<00:06, 51.94it/s]
Loading 0:  36%|███▋      | 184/507 [00:04<00:06, 49.28it/s]
Loading 0:  37%|███▋      | 190/507 [00:04<00:06, 49.51it/s]
Loading 0:  39%|███▊      | 196/507 [00:04<00:06, 50.68it/s]
Loading 0:  40%|███▉      | 202/507 [00:04<00:06, 45.31it/s]
Loading 0:  41%|████      | 207/507 [00:06<00:31,  9.44it/s]
Loading 0:  42%|████▏     | 211/507 [00:06<00:26, 11.21it/s]
Loading 0:  43%|████▎     | 220/507 [00:06<00:16, 17.61it/s]
Loading 0:  44%|████▍     | 225/507 [00:06<00:13, 20.91it/s]
Loading 0:  45%|████▌     | 230/507 [00:06<00:11, 24.66it/s]
Loading 0:  47%|████▋     | 236/507 [00:06<00:10, 26.91it/s]
Loading 0:  48%|████▊     | 241/507 [00:06<00:09, 29.01it/s]
Loading 0:  49%|████▊     | 247/507 [00:06<00:07, 34.58it/s]
Loading 0:  50%|████▉     | 253/507 [00:07<00:06, 39.45it/s]
Loading 0:  51%|█████     | 258/507 [00:07<00:06, 36.48it/s]
Loading 0:  52%|█████▏    | 266/507 [00:07<00:05, 44.92it/s]
Loading 0:  54%|█████▎    | 272/507 [00:07<00:05, 43.83it/s]
Loading 0:  55%|█████▍    | 277/507 [00:07<00:05, 43.32it/s]
Loading 0:  56%|█████▌    | 284/507 [00:07<00:04, 48.65it/s]
Loading 0:  57%|█████▋    | 290/507 [00:07<00:04, 44.43it/s]
Loading 0:  58%|█████▊    | 295/507 [00:08<00:04, 42.55it/s]
Loading 0:  59%|█████▉    | 301/507 [00:08<00:04, 45.25it/s]
Loading 0:  60%|██████    | 306/507 [00:08<00:04, 45.00it/s]
Loading 0:  61%|██████▏   | 311/507 [00:08<00:04, 46.12it/s]
Loading 0:  63%|██████▎   | 317/507 [00:08<00:04, 45.07it/s]
Loading 0:  64%|██████▎   | 322/507 [00:08<00:04, 45.10it/s]
Loading 0:  65%|██████▍   | 329/507 [00:08<00:03, 50.98it/s]
Loading 0:  66%|██████▌   | 335/507 [00:08<00:03, 48.77it/s]
Loading 0:  67%|██████▋   | 340/507 [00:08<00:03, 45.25it/s]
Loading 0:  68%|██████▊   | 347/507 [00:09<00:03, 49.53it/s]
Loading 0:  70%|██████▉   | 353/507 [00:09<00:03, 42.88it/s]
Loading 0:  71%|███████   | 358/507 [00:09<00:03, 42.03it/s]
Loading 0:  72%|███████▏  | 365/507 [00:09<00:03, 40.65it/s]
Loading 0:  74%|███████▎  | 373/507 [00:09<00:02, 47.64it/s]
Loading 0:  75%|███████▍  | 379/507 [00:09<00:02, 44.23it/s]
Loading 0:  76%|███████▌  | 384/507 [00:10<00:02, 42.89it/s]
Loading 0:  77%|███████▋  | 391/507 [00:10<00:02, 48.80it/s]
Loading 0:  78%|███████▊  | 397/507 [00:10<00:02, 46.80it/s]
Loading 0:  79%|███████▉  | 402/507 [00:10<00:02, 46.10it/s]
Loading 0:  80%|████████  | 408/507 [00:10<00:03, 28.56it/s]
Loading 0:  81%|████████▏ | 412/507 [00:10<00:03, 29.29it/s]
Loading 0:  82%|████████▏ | 416/507 [00:11<00:03, 29.48it/s]
Loading 0:  84%|████████▎ | 424/507 [00:11<00:02, 38.97it/s]
Loading 0:  85%|████████▍ | 429/507 [00:11<00:01, 40.60it/s]
Loading 0:  86%|████████▌ | 435/507 [00:11<00:01, 41.52it/s]
Loading 0:  87%|████████▋ | 440/507 [00:11<00:01, 42.68it/s]
Loading 0:  88%|████████▊ | 447/507 [00:11<00:01, 48.94it/s]
Loading 0:  89%|████████▉ | 453/507 [00:11<00:01, 44.99it/s]
Loading 0:  90%|█████████ | 458/507 [00:11<00:01, 45.18it/s]
Loading 0:  92%|█████████▏| 465/507 [00:11<00:00, 50.14it/s]
Loading 0:  93%|█████████▎| 471/507 [00:12<00:00, 44.80it/s]
Loading 0:  94%|█████████▍| 476/507 [00:12<00:00, 44.06it/s]
Loading 0:  95%|█████████▌| 483/507 [00:12<00:00, 48.59it/s]
Loading 0:  96%|█████████▋| 489/507 [00:12<00:00, 44.79it/s]
Loading 0:  97%|█████████▋| 494/507 [00:12<00:00, 43.41it/s]
Loading 0:  99%|█████████▉| 501/507 [00:12<00:00, 48.41it/s]
Loading 0: 100%|█████████▉| 506/507 [00:12<00:00, 48.46it/s]
                                                            
Job abacusai-bigstral-12b-32k-v1-mkmlizer completed after 104.42s with status: succeeded
Stopping job with name abacusai-bigstral-12b-32k-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.06s
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 abacusai-bigstral-12b-32k-v1
Waiting for inference service abacusai-bigstral-12b-32k-v1 to be ready
Inference service abacusai-bigstral-12b-32k-v1 ready after 140.57186007499695s
Pipeline stage MKMLDeployer completed in 141.16s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1925833225250244s
Received healthy response to inference request in 2.0933916568756104s
Received healthy response to inference request in 1.9881815910339355s
Received healthy response to inference request in 1.715078353881836s
Received healthy response to inference request in 1.6839966773986816s
5 requests
0 failed requests
5th percentile: 1.6902130126953125
10th percentile: 1.6964293479919434
20th percentile: 1.708862018585205
30th percentile: 1.7696990013122558
40th percentile: 1.8789402961730957
50th percentile: 1.9881815910339355
60th percentile: 2.0302656173706053
70th percentile: 2.0723496437072755
80th percentile: 2.113229990005493
90th percentile: 2.152906656265259
95th percentile: 2.1727449893951416
99th percentile: 2.188615655899048
mean time: 1.9346463203430175
Pipeline stage StressChecker completed in 11.20s
Shutdown handler de-registered
abacusai-bigstral-12b-32k_v1 status is now deployed due to DeploymentManager action
abacusai-bigstral-12b-32k_v1 status is now inactive due to auto deactivation removed underperforming models
abacusai-bigstral-12b-32k_v1 status is now torndown due to DeploymentManager action