azuruce-chaiml-stf-horror

developer_uid: azuruce
submission_id: azuruce-chaiml-stf-horror_v1
model_name: ebony-horror-sft
model_group: azuruce/chaiml-stf-horro
status: torndown
timestamp: 2024-09-17T00:51:04+00:00
num_battles: 10933
num_wins: 5419
celo_rating: 1245.46
family_friendly_score: 0.0
submission_type: basic
model_repo: azuruce/chaiml-stf-horror
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6309487724074696, 'latency_mean': 1.5848544669151305, 'latency_p50': 1.5893526077270508, 'latency_p90': 1.757510495185852}, {'batch_size': 3, 'throughput': 1.2271035048385237, 'latency_mean': 2.434993795156479, 'latency_p50': 2.4107691049575806, 'latency_p90': 2.668763542175293}, {'batch_size': 5, 'throughput': 1.499854966419478, 'latency_mean': 3.308322715759277, 'latency_p50': 3.30946147441864, 'latency_p90': 3.73819317817688}, {'batch_size': 6, 'throughput': 1.5964211486667215, 'latency_mean': 3.737236016988754, 'latency_p50': 3.7244728803634644, 'latency_p90': 4.1849364042282104}, {'batch_size': 8, 'throughput': 1.7051539912295048, 'latency_mean': 4.658945647478103, 'latency_p50': 4.658034682273865, 'latency_p90': 5.294794011116028}, {'batch_size': 10, 'throughput': 1.7415898156585223, 'latency_mean': 5.707991654872894, 'latency_p50': 5.694512724876404, 'latency_p90': 6.4174947977066035}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: ebony-horror-sft
is_internal_developer: True
language_model: azuruce/chaiml-stf-horror
model_size: 13B
ranking_group: single
throughput_3p7s: 1.6
us_pacific_date: 2024-09-16
win_ratio: 0.4956553553461996
generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n', '</s>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n##Try to make the conversation scary while stay in character##\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{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 azuruce-chaiml-stf-horror-v1-mkmlizer
Waiting for job on azuruce-chaiml-stf-horror-v1-mkmlizer to finish
azuruce-chaiml-stf-horror-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
azuruce-chaiml-stf-horror-v1-mkmlizer: ║     _____            __           __                                ║
azuruce-chaiml-stf-horror-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
azuruce-chaiml-stf-horror-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
azuruce-chaiml-stf-horror-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
azuruce-chaiml-stf-horror-v1-mkmlizer: ║       /___/                                                         ║
azuruce-chaiml-stf-horror-v1-mkmlizer: ║                                                                     ║
azuruce-chaiml-stf-horror-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
azuruce-chaiml-stf-horror-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
azuruce-chaiml-stf-horror-v1-mkmlizer: ║  https://mk1.ai                                                     ║
azuruce-chaiml-stf-horror-v1-mkmlizer: ║                                                                     ║
azuruce-chaiml-stf-horror-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
azuruce-chaiml-stf-horror-v1-mkmlizer: ║  belonging to:                                                      ║
azuruce-chaiml-stf-horror-v1-mkmlizer: ║                                                                     ║
azuruce-chaiml-stf-horror-v1-mkmlizer: ║  Chai Research Corp.                                                ║
azuruce-chaiml-stf-horror-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
azuruce-chaiml-stf-horror-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
azuruce-chaiml-stf-horror-v1-mkmlizer: ║                                                                     ║
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
azuruce-chaiml-stf-horror-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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-chaiml-stf-horror-9847-v1-mkmlizer
Waiting for job on chaiml-chaiml-stf-horror-9847-v1-mkmlizer to finish
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: ║       /___/                                                         ║
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: ║                                                                     ║
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: ║                                                                     ║
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: ║                                                                     ║
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: ║                                                                     ║
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
azuruce-chaiml-stf-horror-v1-mkmlizer: Downloaded to shared memory in 96.179s
azuruce-chaiml-stf-horror-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpdpstrqo9, device:0
azuruce-chaiml-stf-horror-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: Downloaded to shared memory in 90.574s
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwg9tvsca, device:0
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
azuruce-chaiml-stf-horror-v1-mkmlizer: quantized model in 50.265s
azuruce-chaiml-stf-horror-v1-mkmlizer: Processed model azuruce/chaiml-stf-horror in 146.444s
azuruce-chaiml-stf-horror-v1-mkmlizer: creating bucket guanaco-mkml-models
azuruce-chaiml-stf-horror-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
azuruce-chaiml-stf-horror-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/azuruce-chaiml-stf-horror-v1
azuruce-chaiml-stf-horror-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/azuruce-chaiml-stf-horror-v1/tokenizer.json
azuruce-chaiml-stf-horror-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/azuruce-chaiml-stf-horror-v1/flywheel_model.0.safetensors
azuruce-chaiml-stf-horror-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 37.37it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:13, 25.80it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:13, 26.25it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:15, 23.03it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:11, 30.04it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:15, 21.52it/s]
Loading 0:   7%|▋         | 27/363 [00:01<00:16, 20.22it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:14, 23.08it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:13, 23.63it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:12, 26.94it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:13, 24.05it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 28.41it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:12, 25.24it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:11, 27.56it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 23.63it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:14, 20.11it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:11, 25.12it/s]
Loading 0:  20%|█▉        | 72/363 [00:02<00:12, 23.14it/s]
Loading 0:  21%|██        | 76/363 [00:03<00:11, 25.98it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:10, 25.91it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:09, 28.58it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:10, 27.11it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:09, 29.60it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:09, 27.62it/s]
Loading 0:  28%|██▊       | 101/363 [00:04<00:11, 23.13it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:13, 19.75it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 26.43it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 23.75it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 27.52it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 24.14it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:08, 27.19it/s]
Loading 0:  36%|███▌      | 130/363 [00:05<00:08, 26.68it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 25.63it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:08, 26.20it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:09, 23.48it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 22.05it/s]
Loading 0:  41%|████      | 148/363 [00:05<00:09, 23.05it/s]
Loading 0:  42%|████▏     | 151/363 [00:06<00:08, 23.82it/s]
Loading 0:  43%|████▎     | 156/363 [00:06<00:07, 27.41it/s]
Loading 0:  44%|████▍     | 159/363 [00:06<00:08, 24.54it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 27.72it/s]
Loading 0:  46%|████▌     | 166/363 [00:06<00:07, 27.34it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:07, 26.40it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.08it/s]
Loading 0:  49%|████▉     | 177/363 [00:07<00:07, 24.98it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:08, 21.63it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:09, 18.68it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 24.17it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:06, 24.50it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 24.88it/s]
Loading 0:  55%|█████▌    | 201/363 [00:08<00:05, 28.08it/s]
Loading 0:  56%|█████▌    | 204/363 [00:08<00:06, 24.83it/s]
Loading 0:  57%|█████▋    | 208/363 [00:08<00:05, 28.12it/s]
Loading 0:  58%|█████▊    | 212/363 [00:08<00:06, 23.77it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:05, 28.15it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 24.15it/s]
Loading 0:  62%|██████▏   | 226/363 [00:09<00:06, 22.40it/s]
Loading 0:  63%|██████▎   | 229/363 [00:09<00:05, 23.30it/s]
Loading 0:  64%|██████▍   | 232/363 [00:09<00:05, 23.17it/s]
Loading 0:  65%|██████▌   | 237/363 [00:09<00:04, 25.77it/s]
Loading 0:  66%|██████▌   | 240/363 [00:09<00:05, 23.40it/s]
Loading 0:  68%|██████▊   | 246/363 [00:09<00:04, 28.38it/s]
Loading 0:  69%|██████▊   | 249/363 [00:09<00:04, 25.33it/s]
Loading 0:  70%|███████   | 255/363 [00:10<00:03, 29.58it/s]
Loading 0:  71%|███████▏  | 259/363 [00:10<00:03, 27.72it/s]
Loading 0:  72%|███████▏  | 263/363 [00:10<00:04, 22.29it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:05, 19.26it/s]
Loading 0:  75%|███████▌  | 273/363 [00:10<00:03, 25.50it/s]
Loading 0:  76%|███████▌  | 276/363 [00:11<00:03, 23.18it/s]
Loading 0:  78%|███████▊  | 282/363 [00:11<00:02, 27.38it/s]
Loading 0:  79%|███████▊  | 285/363 [00:11<00:03, 24.40it/s]
Loading 0:  80%|███████▉  | 289/363 [00:11<00:02, 27.37it/s]
Loading 0:  80%|████████  | 292/363 [00:11<00:02, 27.21it/s]
Loading 0:  81%|████████▏ | 295/363 [00:11<00:02, 26.90it/s]
Loading 0:  82%|████████▏ | 299/363 [00:11<00:02, 27.48it/s]
Loading 0:  84%|████████▎ | 304/363 [00:12<00:02, 22.48it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 21.04it/s]
Loading 0:  85%|████████▌ | 310/363 [00:12<00:02, 22.29it/s]
Loading 0:  86%|████████▌ | 313/363 [00:12<00:02, 22.54it/s]
Loading 0:  88%|████████▊ | 318/363 [00:12<00:01, 25.56it/s]
Loading 0:  88%|████████▊ | 321/363 [00:12<00:01, 23.79it/s]
Loading 0:  90%|█████████ | 327/363 [00:13<00:01, 28.25it/s]
Loading 0:  91%|█████████ | 330/363 [00:13<00:01, 24.87it/s]
Loading 0:  93%|█████████▎| 336/363 [00:13<00:00, 29.26it/s]
Loading 0:  93%|█████████▎| 339/363 [00:13<00:00, 26.19it/s]
Loading 0:  95%|█████████▍| 344/363 [00:21<00:10,  1.76it/s]
Loading 0:  96%|█████████▌| 347/363 [00:21<00:07,  2.24it/s]
Loading 0:  96%|█████████▋| 350/363 [00:21<00:04,  2.88it/s]
Loading 0:  97%|█████████▋| 353/363 [00:21<00:02,  3.71it/s]
Loading 0:  98%|█████████▊| 356/363 [00:21<00:01,  4.85it/s]
Loading 0:  99%|█████████▉| 359/363 [00:22<00:00,  6.24it/s]
                                                            
Job azuruce-chaiml-stf-horror-v1-mkmlizer completed after 166.79s with status: succeeded
Stopping job with name azuruce-chaiml-stf-horror-v1-mkmlizer
Pipeline stage MKMLizer completed in 168.65s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service azuruce-chaiml-stf-horror-v1
Waiting for inference service azuruce-chaiml-stf-horror-v1 to be ready
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: quantized model in 40.142s
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: Processed model ChaiML/chaiml-stf-horror-2fifth-train in 130.716s
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-chaiml-stf-horror-9847-v1
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-chaiml-stf-horror-9847-v1/special_tokens_map.json
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-chaiml-stf-horror-9847-v1/config.json
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-chaiml-stf-horror-9847-v1/tokenizer_config.json
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-chaiml-stf-horror-9847-v1/tokenizer.json
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-chaiml-stf-horror-9847-v1/flywheel_model.0.safetensors
chaiml-chaiml-stf-horror-9847-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.85it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:11, 29.59it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 26.14it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 37.46it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:14, 22.65it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:12, 27.32it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:11, 28.71it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:10, 30.29it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:10, 29.30it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.07it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 29.73it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:10, 29.66it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 25.76it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 22.31it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:09, 29.51it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:09, 29.28it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 28.39it/s]
Loading 0:  23%|██▎       | 84/363 [00:02<00:08, 31.43it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 29.62it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 31.90it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 30.24it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 25.90it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:11, 22.57it/s]
Loading 0:  31%|███       | 111/363 [00:03<00:08, 29.96it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:08, 29.50it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 32.21it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 30.88it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 33.17it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 31.40it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 31.24it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:08, 27.26it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:08, 25.09it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:08, 23.92it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:06, 30.90it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:07, 28.97it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.31it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.48it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 31.93it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 30.62it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 25.79it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:07, 22.35it/s]
Loading 0:  53%|█████▎    | 192/363 [00:06<00:05, 29.82it/s]
Loading 0:  54%|█████▍    | 196/363 [00:06<00:05, 29.15it/s]
Loading 0:  55%|█████▌    | 201/363 [00:06<00:05, 32.07it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 30.00it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 32.07it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:04, 30.29it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 30.87it/s]
Loading 0:  61%|██████▏   | 223/363 [00:07<00:05, 26.96it/s]
Loading 0:  62%|██████▏   | 226/363 [00:07<00:05, 25.16it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 23.34it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 30.52it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 29.59it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 32.38it/s]
Loading 0:  69%|██████▉   | 250/363 [00:08<00:03, 30.56it/s]
Loading 0:  70%|███████   | 255/363 [00:08<00:03, 32.94it/s]
Loading 0:  71%|███████▏  | 259/363 [00:08<00:03, 31.05it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:03, 25.31it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 22.14it/s]
Loading 0:  75%|███████▌  | 273/363 [00:09<00:03, 29.27it/s]
Loading 0:  76%|███████▋  | 277/363 [00:09<00:02, 28.83it/s]
Loading 0:  78%|███████▊  | 282/363 [00:09<00:02, 31.70it/s]
Loading 0:  79%|███████▉  | 286/363 [00:09<00:02, 30.23it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 32.93it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 31.31it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 31.38it/s]
Loading 0:  84%|████████▎ | 304/363 [00:10<00:02, 26.16it/s]
Loading 0:  85%|████████▍ | 307/363 [00:10<00:02, 24.54it/s]
Loading 0:  86%|████████▌ | 311/363 [00:10<00:02, 23.16it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 29.89it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 28.99it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 31.18it/s]
Loading 0:  91%|█████████ | 331/363 [00:11<00:01, 29.40it/s]
Loading 0:  93%|█████████▎| 336/363 [00:11<00:00, 31.89it/s]
Loading 0:  94%|█████████▎| 340/363 [00:11<00:00, 30.15it/s]
Loading 0:  95%|█████████▍| 344/363 [00:18<00:09,  1.97it/s]
Loading 0:  96%|█████████▌| 348/363 [00:18<00:05,  2.65it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.86it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  4.99it/s]
                                                            
Job chaiml-chaiml-stf-horror-9847-v1-mkmlizer completed after 159.19s with status: succeeded
Stopping job with name chaiml-chaiml-stf-horror-9847-v1-mkmlizer
Pipeline stage MKMLizer completed in 159.74s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-chaiml-stf-horror-9847-v1
Waiting for inference service chaiml-chaiml-stf-horror-9847-v1 to be ready
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service azuruce-chaiml-stf-horror-v1 ready after 170.94344902038574s
Pipeline stage MKMLDeployer completed in 172.38s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5225565433502197s
Received healthy response to inference request in 2.0252437591552734s
Received healthy response to inference request in 2.4961678981781006s
Received healthy response to inference request in 1.7820351123809814s
Received healthy response to inference request in 2.0433013439178467s
5 requests
0 failed requests
5th percentile: 1.8306768417358399
10th percentile: 1.8793185710906983
20th percentile: 1.976602029800415
30th percentile: 2.0288552761077883
40th percentile: 2.0360783100128175
50th percentile: 2.0433013439178467
60th percentile: 2.2244479656219482
70th percentile: 2.40559458732605
80th percentile: 2.5014456272125245
90th percentile: 2.512001085281372
95th percentile: 2.517278814315796
99th percentile: 2.521500997543335
mean time: 2.1738609313964843
Pipeline stage StressChecker completed in 15.81s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.64s
Shutdown handler de-registered
azuruce-chaiml-stf-horror_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service azuruce-chaiml-stf-horror-v1-profiler
Waiting for inference service azuruce-chaiml-stf-horror-v1-profiler to be ready
Inference service azuruce-chaiml-stf-horror-v1-profiler ready after 170.39422702789307s
Pipeline stage MKMLProfilerDeployer completed in 170.82s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/azuruce-chaiml-stf-h5e51d6ac0c47f7f7baff7a01765e42b0-deplol89d5:/code/chaiverse_profiler_1726534846 --namespace tenant-chaiml-guanaco
kubectl exec -it azuruce-chaiml-stf-h5e51d6ac0c47f7f7baff7a01765e42b0-deplol89d5 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726534846 && python profiles.py profile --best_of_n 4 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1726534846/summary.json'
kubectl exec -it azuruce-chaiml-stf-h5e51d6ac0c47f7f7baff7a01765e42b0-deplol89d5 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726534846/summary.json'
Pipeline stage MKMLProfilerRunner completed in 975.73s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service azuruce-chaiml-stf-horror-v1-profiler is running
Tearing down inference service azuruce-chaiml-stf-horror-v1-profiler
Service azuruce-chaiml-stf-horror-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.99s
Shutdown handler de-registered
azuruce-chaiml-stf-horror_v1 status is now inactive due to auto deactivation removed underperforming models
run pipeline stage %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of azuruce-chaiml-stf-horror_v1
Running pipeline stage MKMLDeleter
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of bbchicago-brt-8b-l3-v1-9_2176_v3
%s, retrying in %s seconds...
run pipeline stage %s
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of blend_johuf_2024-09-11
%s, retrying in %s seconds...
Running pipeline stage MKMLDeleter
run pipeline stage %s
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of blend_lehof_2024-09-13
Checking if service akjindal53244-llama-3-1-2851-v1 is running
Checking if service arcee-ai-llama-3-1-super-4127-v1 is running
Checking if service arlineka-pharaoh-8b-v3 is running
Running pipeline stage MKMLDeleter
run pipeline stage %s
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of blend_nefuf_2024-09-18
Checking if service azuruce-chaiml-stf-horror-v1 is running
Running pipeline stage MKMLDeleter
Shutdown handler de-registered
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of blend_nihos_2024-09-13
Checking if service bbchicago-brt-8b-l3-v1-9-2176-v3 is running
blend_johuf_2024-09-11 status is now torndown due to DeploymentManager action
Shutdown handler de-registered
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of blend_nujer_2024-09-13
blend_lehof_2024-09-13 status is now torndown due to DeploymentManager action
Shutdown handler de-registered
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of blend_nujon_2024-09-11
Shutdown handler de-registered
blend_nefuf_2024-09-18 status is now torndown due to DeploymentManager action
run pipeline %s
Tearing down inference service arlineka-pharaoh-8b-v3
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of blend_sifuf_2024-09-19
Tearing down inference service azuruce-chaiml-stf-horror-v1
blend_nihos_2024-09-13 status is now torndown due to DeploymentManager action
Shutdown handler de-registered
run pipeline %s
Service arlineka-pharaoh-8b-v3 has been torndown
Tearing down inference service akjindal53244-llama-3-1-2851-v1
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of blend_tutim_2024-09-17
Tearing down inference service arcee-ai-llama-3-1-super-4127-v1
Tearing down inference service bbchicago-brt-8b-l3-v1-9-2176-v3
Shutdown handler de-registered
Service azuruce-chaiml-stf-horror-v1 has been torndown
blend_nujer_2024-09-13 status is now torndown due to DeploymentManager action
Pipeline stage MKMLDeleter completed in 5.34s
Service akjindal53244-llama-3-1-2851-v1 has been torndown
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of chaiml-0916-intent-roman_3299_v1
Service bbchicago-brt-8b-l3-v1-9-2176-v3 has been torndown
Service arcee-ai-llama-3-1-super-4127-v1 has been torndown
blend_nujon_2024-09-11 status is now torndown due to DeploymentManager action
Pipeline stage MKMLDeleter completed in 5.53s
run pipeline stage %s
Shutdown handler de-registered
Pipeline stage MKMLDeleter completed in 7.40s
run pipeline %s
admin requested tearing down of akjindal53244-llama-3-1-_2851_v1
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of chaiml-0916-intent-roman_3299_v2
Pipeline stage MKMLDeleter completed in 5.71s
Pipeline stage MKMLDeleter completed in 8.00s
run pipeline stage %s
Running pipeline stage MKMLModelDeleter
run pipeline stage %s
blend_sifuf_2024-09-19 status is now torndown due to DeploymentManager action
Shutdown handler de-registered
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of arcee-ai-llama-3-1-super_4127_v1
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline stage %s
admin requested tearing down of chaiml-0916-intent-roman_3299_v3
run pipeline stage %s
Running pipeline stage MKMLModelDeleter
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
run pipeline stage %s
blend_tutim_2024-09-17 status is now torndown due to DeploymentManager action
run pipeline %s
Running pipeline stage MKMLModelDeleter
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of arlineka-pharaoh-8b_v3
Shutdown handler not registered because Python interpreter is not running in the main thread
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from S3
admin requested tearing down of chaiml-0916-intent-suppo_6584_v1
Cleaning model data from model cache
Running pipeline stage MKMLDeleter
run pipeline stage %s
run pipeline stage %s
Cleaning model data from S3
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
admin requested tearing down of azuruce-chaiml-stf-horror_v1
Cleaning model data from S3
Cleaning model data from model cache
Cleaning model data from model cache
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of chaiml-0916-intent-suppo_6584_v2
Running pipeline stage MKMLDeleter
Checking if service chaiml-0916-intent-roman-3299-v1 is running
Running pipeline stage MKMLDeleter
Cleaning model data from model cache
run pipeline stage %s
run pipeline %s
run pipeline stage %s
Cleaning model data from model cache
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of bbchicago-brt-8b-l3-v1-9_2176_v3
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage %s skipped, reason=%s
admin requested tearing down of chaiml-0916-intent-suppo_6584_v4
Checking if service chaiml-0916-intent-roman-3299-v2 is running
Running pipeline stage MKMLDeleter
run pipeline stage %s
Running pipeline stage MKMLDeleter
run pipeline stage %s
run pipeline %s
Pipeline stage MKMLDeleter completed in 4.64s
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
admin requested tearing down of blend_johuf_2024-09-11
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of chaiml-0917-bot-dominant_6324_v2
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLDeleter
Checking if service chaiml-0916-intent-roman-3299-v3 is running
Running pipeline stage MKMLDeleter
run pipeline stage %s
run pipeline stage %s
run pipeline %s
run pipeline stage %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of blend_lehof_2024-09-13
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage MKMLDeleter completed in 6.43s
Pipeline stage %s skipped, reason=%s
admin requested tearing down of chaiml-0917-bot-dominant_6324_v3
Running pipeline stage MKMLDeleter
Checking if service chaiml-0916-intent-suppo-6584-v1 is running
Running pipeline stage MKMLModelDeleter
run pipeline stage %s
Running pipeline stage MKMLDeleter
run pipeline %s
run pipeline stage %s
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
Tearing down inference service chaiml-0916-intent-roman-3299-v1
admin requested tearing down of blend_nefuf_2024-09-18
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 8.34s
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage %s skipped, reason=%s
Tearing down inference service chaiml-0916-intent-roman-3299-v3
Cleaning model data from S3
Running pipeline stage MKMLDeleter
Tearing down inference service chaiml-0916-intent-roman-3299-v2
admin requested tearing down of chaiml-0917-bot-dominant_6324_v4
Shutdown handler de-registered
Checking if service chaiml-0916-intent-suppo-6584-v2 is running
Running pipeline stage MKMLDeleter
run pipeline %s
run pipeline stage %s
Service chaiml-0916-intent-roman-3299-v1 has been torndown
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of blend_nihos_2024-09-13
Running pipeline stage MKMLModelDeleter
run pipeline stage %s
run pipeline %s
Pipeline stage MKMLDeleter completed in 9.98s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Service chaiml-0916-intent-roman-3299-v3 has been torndown
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Tearing down inference service chaiml-0916-intent-suppo-6584-v1
Deleting key azuruce-chaiml-stf-horror-v1/config.json from bucket guanaco-mkml-models
Deleting key akjindal53244-llama-3-1-2851-v1/config.json from bucket guanaco-mkml-models
Deleting key arcee-ai-llama-3-1-super-4127-v1/config.json from bucket guanaco-mkml-models
Deleting key arlineka-pharaoh-8b-v3/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-9-2176-v3/config.json from bucket guanaco-mkml-models
admin requested tearing down of akjindal53244-llama-3-1-_2851_v1
admin requested tearing down of akjindal53244-llama-3-1-_2851_v1
admin requested tearing down of chaiml-0916-intent-roman_3299_v3