junhua024-chai-1-full-002

developer_uid: junhua024
submission_id: junhua024-chai-1-full-002_v32
model_name: junhua024-chai-1-full-002_v32
model_group: junhua024/chai_1-full_00
status: torndown
timestamp: 2025-06-29T12:11:48+00:00
num_battles: 8461
num_wins: 3823
celo_rating: 1242.8
family_friendly_score: 0.6028
family_friendly_standard_error: 0.006920002312138343
submission_type: basic
model_repo: junhua024/chai_1-full_002
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.5946243472597659, 'latency_mean': 1.6815389609336853, 'latency_p50': 1.689046025276184, 'latency_p90': 1.8374887704849243}, {'batch_size': 3, 'throughput': 1.0810004086228162, 'latency_mean': 2.7725738143920897, 'latency_p50': 2.7802902460098267, 'latency_p90': 3.0882397890090942}, {'batch_size': 5, 'throughput': 1.3036169699941835, 'latency_mean': 3.8209215354919435, 'latency_p50': 3.8397927284240723, 'latency_p90': 4.370351934432983}, {'batch_size': 6, 'throughput': 1.3514115551599721, 'latency_mean': 4.412258355617523, 'latency_p50': 4.432705402374268, 'latency_p90': 4.993784832954407}, {'batch_size': 8, 'throughput': 1.4328254375160736, 'latency_mean': 5.55453287601471, 'latency_p50': 5.559803128242493, 'latency_p90': 6.18997642993927}, {'batch_size': 10, 'throughput': 1.4442642106873254, 'latency_mean': 6.866716797351837, 'latency_p50': 6.918136835098267, 'latency_p90': 7.650470829010009}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: junhua024-chai-1-full-002_v32
is_internal_developer: False
language_model: junhua024/chai_1-full_002
model_size: 13B
ranking_group: single
throughput_3p7s: 1.29
us_pacific_date: 2025-06-29
win_ratio: 0.4518378442264508
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.2, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, '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': True}
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 junhua024-chai-1-full-002-v32-mkmlizer
Waiting for job on junhua024-chai-1-full-002-v32-mkmlizer to finish
junhua024-chai-1-full-002-v32-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-1-full-002-v32-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v32-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-1-full-002-v32-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-1-full-002-v32-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-1-full-002-v32-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-1-full-002-v32-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-1-full-002-v32-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-1-full-002-v32-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-1-full-002-v32-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-1-full-002-v32-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v32-mkmlizer: ║  Version: 0.29.3                                                    ║
junhua024-chai-1-full-002-v32-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-1-full-002-v32-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-1-full-002-v32-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-1-full-002-v32-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v32-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-1-full-002-v32-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-1-full-002-v32-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v32-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-1-full-002-v32-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-1-full-002-v32-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-1-full-002-v32-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v32-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-1-full-002-v32-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v32-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v32-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v32-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v32-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v32-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v32-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v32-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v32-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v32-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v32-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v32-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v32-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v32-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v32-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v32-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v32-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v32-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v32-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v32-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v32-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v32-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v32-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v32-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v32-mkmlizer: Downloaded to shared memory in 75.897s
junhua024-chai-1-full-002-v32-mkmlizer: Checking if junhua024/chai_1-full_002 already exists in ChaiML
junhua024-chai-1-full-002-v32-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmput3ej453, device:0
junhua024-chai-1-full-002-v32-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-1-full-002-v32-mkmlizer: quantized model in 32.754s
junhua024-chai-1-full-002-v32-mkmlizer: Processed model junhua024/chai_1-full_002 in 108.745s
junhua024-chai-1-full-002-v32-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-1-full-002-v32-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-1-full-002-v32-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-1-full-002-v32
junhua024-chai-1-full-002-v32-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v32/config.json
junhua024-chai-1-full-002-v32-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v32/special_tokens_map.json
junhua024-chai-1-full-002-v32-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v32/tokenizer_config.json
junhua024-chai-1-full-002-v32-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v32/tokenizer.json
junhua024-chai-1-full-002-v32-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-1-full-002-v32/flywheel_model.0.safetensors
junhua024-chai-1-full-002-v32-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:23, 15.21it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:20, 17.63it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 27.74it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:13, 26.23it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:13, 25.95it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:11, 29.95it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:08, 39.70it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:09, 34.18it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:09, 33.72it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:09, 33.64it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:08, 37.56it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:10, 30.39it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:09, 32.44it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:08, 33.86it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:08, 33.09it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:07, 36.50it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:07, 36.88it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:08, 31.94it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:08, 33.13it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 33.11it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:07, 34.28it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:07, 34.47it/s]
Loading 0:  29%|██▉       | 105/363 [00:03<00:07, 32.47it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:06, 38.08it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:08, 30.29it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:07, 31.66it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:07, 33.37it/s]
Loading 0:  36%|███▋      | 132/363 [00:04<00:07, 32.77it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:06, 36.21it/s]
Loading 0:  39%|███▉      | 141/363 [00:04<00:06, 36.35it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:06, 31.94it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:06, 31.11it/s]
Loading 0:  43%|████▎     | 155/363 [00:04<00:05, 37.07it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 35.67it/s]
Loading 0:  45%|████▌     | 164/363 [00:04<00:05, 35.45it/s]
Loading 0:  46%|████▋     | 168/363 [00:05<00:06, 31.80it/s]
Loading 0:  48%|████▊     | 173/363 [00:05<00:05, 35.96it/s]
Loading 0:  49%|████▉     | 177/363 [00:05<00:06, 29.66it/s]
Loading 0:  50%|████▉     | 181/363 [00:05<00:06, 29.17it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:06, 28.57it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:05, 29.60it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:05, 28.65it/s]
Loading 0:  55%|█████▌    | 200/363 [00:06<00:05, 32.05it/s]
Loading 0:  56%|█████▌    | 204/363 [00:06<00:04, 32.66it/s]
Loading 0:  57%|█████▋    | 208/363 [00:06<00:05, 28.08it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:05, 27.14it/s]
Loading 0:  60%|██████    | 218/363 [00:06<00:04, 33.13it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:04, 31.35it/s]
Loading 0:  63%|██████▎   | 227/363 [00:07<00:04, 31.48it/s]
Loading 0:  64%|██████▎   | 231/363 [00:07<00:04, 29.54it/s]
Loading 0:  65%|██████▌   | 237/363 [00:07<00:03, 35.78it/s]
Loading 0:  66%|██████▋   | 241/363 [00:07<00:04, 29.96it/s]
Loading 0:  67%|██████▋   | 245/363 [00:07<00:03, 30.29it/s]
Loading 0:  69%|██████▊   | 249/363 [00:07<00:03, 29.73it/s]
Loading 0:  70%|██████▉   | 254/363 [00:07<00:03, 28.99it/s]
Loading 0:  71%|███████   | 258/363 [00:08<00:03, 28.70it/s]
Loading 0:  72%|███████▏  | 263/363 [00:08<00:03, 32.68it/s]
Loading 0:  74%|███████▎  | 267/363 [00:08<00:02, 33.42it/s]
Loading 0:  75%|███████▍  | 271/363 [00:08<00:03, 28.51it/s]
Loading 0:  76%|███████▌  | 275/363 [00:08<00:03, 28.05it/s]
Loading 0:  77%|███████▋  | 281/363 [00:08<00:02, 33.38it/s]
Loading 0:  79%|███████▉  | 286/363 [00:08<00:02, 31.13it/s]
Loading 0:  80%|███████▉  | 290/363 [00:09<00:02, 31.39it/s]
Loading 0:  81%|████████  | 294/363 [00:09<00:02, 29.62it/s]
Loading 0:  83%|████████▎ | 300/363 [00:09<00:01, 36.42it/s]
Loading 0:  84%|████████▎ | 304/363 [00:09<00:01, 29.93it/s]
Loading 0:  85%|████████▍ | 308/363 [00:09<00:01, 31.02it/s]
Loading 0:  86%|████████▌ | 312/363 [00:09<00:01, 30.11it/s]
Loading 0:  87%|████████▋ | 317/363 [00:09<00:01, 28.89it/s]
Loading 0:  88%|████████▊ | 321/363 [00:10<00:01, 28.71it/s]
Loading 0:  90%|████████▉ | 326/363 [00:10<00:01, 31.97it/s]
Loading 0:  91%|█████████ | 330/363 [00:10<00:01, 32.83it/s]
Loading 0:  92%|█████████▏| 334/363 [00:10<00:01, 28.64it/s]
Loading 0:  93%|█████████▎| 338/363 [00:10<00:00, 28.02it/s]
Loading 0:  95%|█████████▍| 344/363 [00:10<00:00, 33.94it/s]
Loading 0:  96%|█████████▌| 349/363 [00:11<00:00, 23.19it/s]
Loading 0:  97%|█████████▋| 352/363 [00:11<00:00, 19.84it/s]
Loading 0:  98%|█████████▊| 357/363 [00:11<00:00, 23.24it/s]
                                                            
Job junhua024-chai-1-full-002-v32-mkmlizer completed after 137.34s with status: succeeded
Stopping job with name junhua024-chai-1-full-002-v32-mkmlizer
Pipeline stage MKMLizer completed in 137.91s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-1-full-002-v32
Waiting for inference service junhua024-chai-1-full-002-v32 to be ready
Inference service junhua024-chai-1-full-002-v32 ready after 180.70377850532532s
Pipeline stage MKMLDeployer completed in 181.31s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5142531394958496s
Received healthy response to inference request in 1.7187178134918213s
Received healthy response to inference request in 1.6207196712493896s
Received healthy response to inference request in 1.8630881309509277s
Received healthy response to inference request in 1.4116771221160889s
5 requests
0 failed requests
5th percentile: 1.453485631942749
10th percentile: 1.4952941417694092
20th percentile: 1.5789111614227296
30th percentile: 1.640319299697876
40th percentile: 1.6795185565948487
50th percentile: 1.7187178134918213
60th percentile: 1.776465940475464
70th percentile: 1.8342140674591063
80th percentile: 1.9933211326599123
90th percentile: 2.253787136077881
95th percentile: 2.384020137786865
99th percentile: 2.488206539154053
mean time: 1.8256911754608154
Pipeline stage StressChecker completed in 10.94s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.70s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.65s
Shutdown handler de-registered
junhua024-chai-1-full-002_v32 status is now deployed due to DeploymentManager action
Failed to get response for submission junhua024-chai-1-full-002_v30: HTTPConnectionPool(host='junhua024-chai-1-full-002-v30-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service junhua024-chai-1-full-002-v32-profiler
Waiting for inference service junhua024-chai-1-full-002-v32-profiler to be ready
Inference service junhua024-chai-1-full-002-v32-profiler ready after 182.18133211135864s
Pipeline stage MKMLProfilerDeployer completed in 182.96s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/junhua024-chai-1-fule83bc3a6a5026efc3fe9c153f30720ea-deplovwmgn:/code/chaiverse_profiler_1751199706 --namespace tenant-chaiml-guanaco
kubectl exec -it junhua024-chai-1-fule83bc3a6a5026efc3fe9c153f30720ea-deplovwmgn --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751199706 && python profiles.py profile --best_of_n 8 --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_1751199706/summary.json'
kubectl exec -it junhua024-chai-1-fule83bc3a6a5026efc3fe9c153f30720ea-deplovwmgn --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1751199706/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1111.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service junhua024-chai-1-full-002-v32-profiler is running
Tearing down inference service junhua024-chai-1-full-002-v32-profiler
Service junhua024-chai-1-full-002-v32-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.94s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4676.39s
Shutdown handler de-registered
junhua024-chai-1-full-002_v32 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-1-full-002_v32 status is now torndown due to DeploymentManager action