sao10k-12b-spice-ella

developer_uid: sao10k
submission_id: sao10k-12b-spice-ella_v1
model_name: ella-spice
model_group: Sao10K/12B-Spice-Ella
status: torndown
timestamp: 2024-10-22T15:59:14+00:00
num_battles: 144521
num_wins: 75997
celo_rating: 1268.46
family_friendly_score: 0.0
submission_type: basic
model_repo: Sao10K/12B-Spice-Ella
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 512
max_output_tokens: 64
display_name: ella-spice
is_internal_developer: False
language_model: Sao10K/12B-Spice-Ella
model_size: 13B
ranking_group: single
us_pacific_date: 2024-10-22
win_ratio: 0.5258543741048014
generation_params: {'temperature': 0.75, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '\n\n', '\nYou:', '[/INST]', '<|im_end|>', '</s>'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\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 sao10k-12b-spice-ella-v1-mkmlizer
Waiting for job on sao10k-12b-spice-ella-v1-mkmlizer to finish
sao10k-12b-spice-ella-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-12b-spice-ella-v1-mkmlizer: ║     _____            __           __                                ║
sao10k-12b-spice-ella-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-12b-spice-ella-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-12b-spice-ella-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-12b-spice-ella-v1-mkmlizer: ║       /___/                                                         ║
sao10k-12b-spice-ella-v1-mkmlizer: ║                                                                     ║
sao10k-12b-spice-ella-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
sao10k-12b-spice-ella-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-12b-spice-ella-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-12b-spice-ella-v1-mkmlizer: ║                                                                     ║
sao10k-12b-spice-ella-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-12b-spice-ella-v1-mkmlizer: ║  belonging to:                                                      ║
sao10k-12b-spice-ella-v1-mkmlizer: ║                                                                     ║
sao10k-12b-spice-ella-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-12b-spice-ella-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-12b-spice-ella-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
sao10k-12b-spice-ella-v1-mkmlizer: ║                                                                     ║
sao10k-12b-spice-ella-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-12b-spice-ella-v1-mkmlizer: Downloaded to shared memory in 51.032s
sao10k-12b-spice-ella-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7vyrl1gb, device:0
sao10k-12b-spice-ella-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-12b-spice-ella-v1-mkmlizer: quantized model in 37.313s
sao10k-12b-spice-ella-v1-mkmlizer: Processed model Sao10K/12B-Spice-Ella in 88.346s
sao10k-12b-spice-ella-v1-mkmlizer: creating bucket guanaco-mkml-models
sao10k-12b-spice-ella-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-12b-spice-ella-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-12b-spice-ella-v1
sao10k-12b-spice-ella-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-12b-spice-ella-v1/config.json
sao10k-12b-spice-ella-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-12b-spice-ella-v1/special_tokens_map.json
sao10k-12b-spice-ella-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-12b-spice-ella-v1/tokenizer_config.json
sao10k-12b-spice-ella-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-12b-spice-ella-v1/tokenizer.json
sao10k-12b-spice-ella-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-12b-spice-ella-v1/flywheel_model.0.safetensors
sao10k-12b-spice-ella-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:16,  3.04s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:51,  1.22it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:44,  3.36it/s]
Loading 0:   5%|▍         | 18/363 [00:06<01:04,  5.35it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:43,  7.91it/s]
Loading 0:   8%|▊         | 29/363 [00:06<00:29, 11.51it/s]
Loading 0:   9%|▉         | 34/363 [00:06<00:21, 14.99it/s]
Loading 0:  11%|█▏        | 41/363 [00:06<00:15, 21.30it/s]
Loading 0:  13%|█▎        | 47/363 [00:07<00:12, 25.14it/s]
Loading 0:  14%|█▍        | 52/363 [00:07<00:11, 27.58it/s]
Loading 0:  16%|█▌        | 58/363 [00:07<00:11, 25.93it/s]
Loading 0:  17%|█▋        | 62/363 [00:07<00:11, 27.11it/s]
Loading 0:  18%|█▊        | 67/363 [00:07<00:09, 30.79it/s]
Loading 0:  20%|█▉        | 71/363 [00:07<00:09, 32.33it/s]
Loading 0:  21%|██        | 77/363 [00:07<00:07, 37.37it/s]
Loading 0:  23%|██▎       | 82/363 [00:08<00:06, 40.22it/s]
Loading 0:  24%|██▍       | 87/363 [00:08<00:08, 32.57it/s]
Loading 0:  25%|██▌       | 92/363 [00:08<00:07, 36.31it/s]
Loading 0:  27%|██▋       | 97/363 [00:08<00:07, 35.56it/s]
Loading 0:  28%|██▊       | 101/363 [00:08<00:07, 36.27it/s]
Loading 0:  29%|██▉       | 105/363 [00:08<00:07, 33.65it/s]
Loading 0:  31%|███       | 112/363 [00:08<00:06, 41.44it/s]
Loading 0:  32%|███▏      | 117/363 [00:08<00:06, 40.71it/s]
Loading 0:  34%|███▎      | 122/363 [00:09<00:05, 41.10it/s]
Loading 0:  35%|███▍      | 127/363 [00:09<00:05, 41.62it/s]
Loading 0:  36%|███▋      | 132/363 [00:09<00:06, 33.93it/s]
Loading 0:  38%|███▊      | 139/363 [00:09<00:05, 40.40it/s]
Loading 0:  40%|███▉      | 144/363 [00:09<00:05, 39.81it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:05, 39.17it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:05, 40.50it/s]
Loading 0:  44%|████▍     | 159/363 [00:10<00:08, 24.09it/s]
Loading 0:  46%|████▌     | 166/363 [00:10<00:06, 30.31it/s]
Loading 0:  47%|████▋     | 170/363 [00:10<00:06, 30.46it/s]
Loading 0:  48%|████▊     | 175/363 [00:10<00:05, 32.66it/s]
Loading 0:  49%|████▉     | 179/363 [00:10<00:05, 32.01it/s]
Loading 0:  51%|█████     | 184/363 [00:10<00:05, 34.17it/s]
Loading 0:  52%|█████▏    | 188/363 [00:11<00:05, 33.38it/s]
Loading 0:  53%|█████▎    | 193/363 [00:11<00:04, 34.82it/s]
Loading 0:  54%|█████▍    | 197/363 [00:11<00:04, 33.40it/s]
Loading 0:  56%|█████▌    | 202/363 [00:11<00:04, 35.43it/s]
Loading 0:  57%|█████▋    | 206/363 [00:11<00:04, 33.34it/s]
Loading 0:  58%|█████▊    | 210/363 [00:11<00:04, 34.50it/s]
Loading 0:  59%|█████▉    | 214/363 [00:11<00:04, 31.20it/s]
Loading 0:  61%|██████    | 220/363 [00:12<00:03, 36.02it/s]
Loading 0:  62%|██████▏   | 224/363 [00:12<00:03, 34.98it/s]
Loading 0:  63%|██████▎   | 229/363 [00:12<00:03, 35.63it/s]
Loading 0:  64%|██████▍   | 233/363 [00:12<00:03, 34.09it/s]
Loading 0:  66%|██████▌   | 238/363 [00:12<00:03, 35.91it/s]
Loading 0:  67%|██████▋   | 242/363 [00:12<00:03, 34.31it/s]
Loading 0:  68%|██████▊   | 246/363 [00:12<00:03, 35.12it/s]
Loading 0:  69%|██████▉   | 250/363 [00:12<00:03, 31.12it/s]
Loading 0:  70%|██████▉   | 254/363 [00:13<00:03, 32.85it/s]
Loading 0:  71%|███████   | 258/363 [00:13<00:05, 20.64it/s]
Loading 0:  72%|███████▏  | 263/363 [00:13<00:03, 25.63it/s]
Loading 0:  74%|███████▎  | 267/363 [00:13<00:03, 25.55it/s]
Loading 0:  75%|███████▍  | 272/363 [00:13<00:03, 30.13it/s]
Loading 0:  76%|███████▌  | 276/363 [00:13<00:03, 27.82it/s]
Loading 0:  77%|███████▋  | 281/363 [00:14<00:02, 32.02it/s]
Loading 0:  79%|███████▊  | 285/363 [00:14<00:02, 29.28it/s]
Loading 0:  80%|███████▉  | 290/363 [00:14<00:02, 32.90it/s]
Loading 0:  81%|████████  | 294/363 [00:14<00:02, 30.22it/s]
Loading 0:  82%|████████▏ | 299/363 [00:14<00:01, 34.14it/s]
Loading 0:  83%|████████▎ | 303/363 [00:14<00:01, 31.75it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:01, 35.80it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:01, 32.75it/s]
Loading 0:  87%|████████▋ | 317/363 [00:15<00:01, 36.09it/s]
Loading 0:  88%|████████▊ | 321/363 [00:15<00:01, 32.88it/s]
Loading 0:  90%|█████████ | 328/363 [00:15<00:00, 39.40it/s]
Loading 0:  92%|█████████▏| 333/363 [00:15<00:00, 38.41it/s]
Loading 0:  93%|█████████▎| 337/363 [00:15<00:00, 36.72it/s]
Loading 0:  94%|█████████▍| 341/363 [00:15<00:00, 34.88it/s]
Loading 0:  95%|█████████▌| 345/363 [00:15<00:00, 36.08it/s]
Loading 0:  96%|█████████▌| 349/363 [00:16<00:00, 32.74it/s]
Loading 0:  97%|█████████▋| 353/363 [00:16<00:00, 33.88it/s]
Loading 0:  98%|█████████▊| 357/363 [00:16<00:00, 22.53it/s]
                                                            
Job sao10k-12b-spice-ella-v1-mkmlizer completed after 115.05s with status: succeeded
Stopping job with name sao10k-12b-spice-ella-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.62s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sao10k-12b-spice-ella-v1
Waiting for inference service sao10k-12b-spice-ella-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service sao10k-12b-spice-ella-v1 ready after 140.53115391731262s
Pipeline stage MKMLDeployer completed in 141.12s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1793439388275146s
Received healthy response to inference request in 1.596170425415039s
Received healthy response to inference request in 1.6341042518615723s
Received healthy response to inference request in 1.6010489463806152s
Received healthy response to inference request in 1.6238694190979004s
5 requests
0 failed requests
5th percentile: 1.5971461296081544
10th percentile: 1.5981218338012695
20th percentile: 1.6000732421875
30th percentile: 1.6056130409240723
40th percentile: 1.6147412300109862
50th percentile: 1.6238694190979004
60th percentile: 1.6279633522033692
70th percentile: 1.632057285308838
80th percentile: 1.7431521892547608
90th percentile: 1.9612480640411378
95th percentile: 2.070296001434326
99th percentile: 2.1575343513488767
mean time: 1.7269073963165282
Pipeline stage StressChecker completed in 10.36s
Shutdown handler de-registered
sao10k-12b-spice-ella_v1 status is now deployed due to DeploymentManager action
sao10k-12b-spice-ella_v1 status is now inactive due to auto deactivation removed underperforming models
sao10k-12b-spice-ella_v1 status is now torndown due to DeploymentManager action