junhua024-chai-02-full-0121

developer_uid: junhua024

submission_id: junhua024-chai-02-full-0121_v3

model_name: junhua024-chai-02-full-0121_v3

model_group: junhua024/chai_02_full_0

status: torndown

timestamp: 2025-07-16T17:32:45+00:00

num_battles: 7479

num_wins: 3735

celo_rating: 1285.04

family_friendly_score: 0.5449999999999999

family_friendly_standard_error: 0.0070423717595707765

submission_type: basic

model_repo: junhua024/chai_02_full_0121

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': 0.5908846626203731, 'latency_mean': 1.692185459136963, 'latency_p50': 1.7061322927474976, 'latency_p90': 1.873633360862732}, {'batch_size': 3, 'throughput': 1.0741569827521267, 'latency_mean': 2.779968510866165, 'latency_p50': 2.7586967945098877, 'latency_p90': 3.0762330293655396}, {'batch_size': 5, 'throughput': 1.2893544657497713, 'latency_mean': 3.8574529671669007, 'latency_p50': 3.833585262298584, 'latency_p90': 4.239443612098694}, {'batch_size': 6, 'throughput': 1.3564478054142342, 'latency_mean': 4.408238810300827, 'latency_p50': 4.3990384340286255, 'latency_p90': 4.984762644767761}, {'batch_size': 8, 'throughput': 1.4031267886092287, 'latency_mean': 5.656111882925034, 'latency_p50': 5.667257905006409, 'latency_p90': 6.376514863967896}, {'batch_size': 10, 'throughput': 1.4480798696057506, 'latency_mean': 6.8499070084095, 'latency_p50': 6.862177848815918, 'latency_p90': 7.798692393302917}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-02-full-0121_v3

is_internal_developer: False

language_model: junhua024/chai_02_full_0121

model_size: 13B

ranking_group: single

throughput_3p7s: 1.27

us_pacific_date: 2025-07-16

win_ratio: 0.4993983152827918

generation_params: {'temperature': 1.0, 'top_p': 0.88, 'min_p': 0.0, 'top_k': 10, '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': "{bot_name}'s Persona: {memory}\n####\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 junhua024-chai-02-full-0121-v3-mkmlizer
Waiting for job on junhua024-chai-02-full-0121-v3-mkmlizer to finish
junhua024-chai-02-full-0121-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-02-full-0121-v3-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-0121-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-02-full-0121-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-02-full-0121-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-02-full-0121-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-02-full-0121-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-02-full-0121-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-02-full-0121-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-02-full-0121-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-02-full-0121-v3-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-0121-v3-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-02-full-0121-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-02-full-0121-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-02-full-0121-v3-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-02-full-0121-v3-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-0121-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-02-full-0121-v3-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-02-full-0121-v3-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-0121-v3-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-02-full-0121-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-02-full-0121-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-02-full-0121-v3-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-0121-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-02-full-0121-v3-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-02-full-0121-v3-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-02-full-0121-v3-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-02-full-0121-v3-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-02-full-0121-v3-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-02-full-0121-v3-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-02-full-0121-v3-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-02-full-0121-v3-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-02-full-0121-v3-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-02-full-0121-v3-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-02-full-0121-v3-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-02-full-0121-v3-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-02-full-0121-v3-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-02-full-0121-v3-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-02-full-0121-v3-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-02-full-0121-v3-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-02-full-0121-v3-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-02-full-0121-v3-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-02-full-0121-v3-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-02-full-0121-v3-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-02-full-0121-v3-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-02-full-0121-v3-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-02-full-0121-v3-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-02-full-0121-v3-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-02-full-0121-v3-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-02-full-0121-v3-mkmlizer: Downloaded to shared memory in 79.653s
junhua024-chai-02-full-0121-v3-mkmlizer: Checking if junhua024/chai_02_full_0121 already exists in ChaiML
junhua024-chai-02-full-0121-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpdhi1_ila, device:0
junhua024-chai-02-full-0121-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-02-full-0121-v3-mkmlizer: quantized model in 31.682s
junhua024-chai-02-full-0121-v3-mkmlizer: Processed model junhua024/chai_02_full_0121 in 111.420s
junhua024-chai-02-full-0121-v3-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-02-full-0121-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-02-full-0121-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-02-full-0121-v3/nvidia
junhua024-chai-02-full-0121-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-02-full-0121-v3/nvidia/config.json
junhua024-chai-02-full-0121-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-02-full-0121-v3/nvidia/special_tokens_map.json
junhua024-chai-02-full-0121-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-02-full-0121-v3/nvidia/tokenizer_config.json
junhua024-chai-02-full-0121-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-02-full-0121-v3/nvidia/tokenizer.json
junhua024-chai-02-full-0121-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-02-full-0121-v3/nvidia/flywheel_model.0.safetensors
junhua024-chai-02-full-0121-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:24, 15.02it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:20, 17.20it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:10, 32.30it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:10, 33.55it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:11, 29.74it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:11, 29.27it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 44.45it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:09, 33.17it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:10, 31.81it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:07, 40.57it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:08, 34.25it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:09, 33.65it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 35.03it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:09, 32.52it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:08, 35.92it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:07, 35.89it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:09, 30.96it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:08, 32.30it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 33.41it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:07, 35.82it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:07, 35.73it/s]
Loading 0:  29%|██▉       | 105/363 [00:03<00:07, 32.42it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:06, 39.92it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:07, 33.79it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:07, 33.04it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:06, 35.17it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:06, 33.55it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 34.39it/s]
Loading 0:  39%|███▉      | 143/363 [00:04<00:06, 34.40it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:06, 34.33it/s]
Loading 0:  43%|████▎     | 155/363 [00:04<00:05, 39.41it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 35.91it/s]
Loading 0:  45%|████▌     | 164/363 [00:04<00:05, 35.62it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:06, 32.26it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:04, 38.33it/s]
Loading 0:  49%|████▉     | 179/363 [00:05<00:05, 31.97it/s]
Loading 0:  50%|█████     | 183/363 [00:05<00:05, 31.62it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 31.78it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:05, 29.15it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:05, 28.75it/s]
Loading 0:  55%|█████▌    | 201/363 [00:06<00:05, 31.05it/s]
Loading 0:  57%|█████▋    | 206/363 [00:06<00:04, 31.80it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:04, 33.14it/s]
Loading 0:  61%|██████    | 220/363 [00:06<00:03, 42.70it/s]
Loading 0:  62%|██████▏   | 225/363 [00:06<00:04, 33.09it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:03, 33.80it/s]
Loading 0:  66%|██████▌   | 239/363 [00:06<00:03, 41.02it/s]
Loading 0:  67%|██████▋   | 244/363 [00:07<00:03, 34.53it/s]
Loading 0:  68%|██████▊   | 248/363 [00:07<00:03, 34.05it/s]
Loading 0:  70%|██████▉   | 254/363 [00:07<00:03, 34.45it/s]
Loading 0:  71%|███████   | 258/363 [00:07<00:03, 33.47it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 33.05it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 32.90it/s]
Loading 0:  76%|███████▌  | 275/363 [00:08<00:02, 34.18it/s]
Loading 0:  78%|███████▊  | 283/363 [00:08<00:01, 43.57it/s]
Loading 0:  79%|███████▉  | 288/363 [00:08<00:02, 33.68it/s]
Loading 0:  81%|████████  | 293/363 [00:08<00:02, 33.52it/s]
Loading 0:  83%|████████▎ | 301/363 [00:08<00:01, 42.75it/s]
Loading 0:  84%|████████▍ | 306/363 [00:08<00:01, 31.40it/s]
Loading 0:  86%|████████▌ | 311/363 [00:09<00:01, 32.06it/s]
Loading 0:  87%|████████▋ | 317/363 [00:09<00:01, 32.21it/s]
Loading 0:  88%|████████▊ | 321/363 [00:09<00:01, 30.66it/s]
Loading 0:  90%|█████████ | 327/363 [00:09<00:01, 31.70it/s]
Loading 0:  91%|█████████▏| 332/363 [00:09<00:00, 32.42it/s]
Loading 0:  93%|█████████▎| 338/363 [00:09<00:00, 33.64it/s]
Loading 0:  95%|█████████▍| 344/363 [00:10<00:00, 38.27it/s]
Loading 0:  96%|█████████▌| 349/363 [00:10<00:00, 26.06it/s]
Loading 0:  97%|█████████▋| 353/363 [00:10<00:00, 24.06it/s]
Loading 0:  98%|█████████▊| 357/363 [00:10<00:00, 25.71it/s]
                                                            
Job junhua024-chai-02-full-0121-v3-mkmlizer completed after 139.27s with status: succeeded
Stopping job with name junhua024-chai-02-full-0121-v3-mkmlizer
Pipeline stage MKMLizer completed in 139.77s
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 junhua024-chai-02-full-0121-v3
Waiting for inference service junhua024-chai-02-full-0121-v3 to be ready
Inference service junhua024-chai-02-full-0121-v3 ready after 270.9202196598053s
Pipeline stage MKMLDeployer completed in 271.52s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7417733669281006s
Received healthy response to inference request in 1.7987027168273926s
Received healthy response to inference request in 2.231590509414673s
Received healthy response to inference request in 2.288760185241699s
Received healthy response to inference request in 2.052316904067993s
5 requests
0 failed requests
5th percentile: 1.8494255542755127
10th percentile: 1.9001483917236328
20th percentile: 2.001594066619873
30th percentile: 2.088171625137329
40th percentile: 2.159881067276001
50th percentile: 2.231590509414673
60th percentile: 2.2544583797454836
70th percentile: 2.277326250076294
80th percentile: 2.3793628215789795
90th percentile: 2.56056809425354
95th percentile: 2.6511707305908203
99th percentile: 2.7236528396606445
mean time: 2.2226287364959716
Pipeline stage StressChecker completed in 12.80s
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 0.84s
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 1.01s
Shutdown handler de-registered
junhua024-chai-02-full-0121_v3 status is now deployed due to DeploymentManager action
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
Pipeline stage OfflineFamilyFriendlyScorer completed in 5301.65s
Shutdown handler de-registered
junhua024-chai-02-full-0121_v3 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-02-full-0121_v3 status is now torndown due to DeploymentManager action
junhua024-chai-02-full-0121_v3 status is now torndown due to DeploymentManager action