junhua024-chai-02-full-01220

developer_uid: junhua024
submission_id: junhua024-chai-02-full-01220_v5
model_name: junhua024-chai-02-full-01220_v5
model_group: junhua024/chai_02_full_0
status: torndown
timestamp: 2025-07-16T20:19:52+00:00
num_battles: 6100
num_wins: 2848
celo_rating: 1271.94
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: junhua024/chai_02_full_01220
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': 0.5903711620812195, 'latency_mean': 1.6937443959712981, 'latency_p50': 1.6960129737854004, 'latency_p90': 1.852795624732971}, {'batch_size': 3, 'throughput': 1.0611135177971536, 'latency_mean': 2.8168593180179595, 'latency_p50': 2.8002727031707764, 'latency_p90': 3.0745275020599365}, {'batch_size': 5, 'throughput': 1.2669478256306956, 'latency_mean': 3.9307190096378326, 'latency_p50': 3.9360698461532593, 'latency_p90': 4.331886744499206}, {'batch_size': 6, 'throughput': 1.3181991944702125, 'latency_mean': 4.5189389288425446, 'latency_p50': 4.46697998046875, 'latency_p90': 5.106600832939148}, {'batch_size': 8, 'throughput': 1.382967636044349, 'latency_mean': 5.747125952243805, 'latency_p50': 5.7622785568237305, 'latency_p90': 6.537365341186524}, {'batch_size': 10, 'throughput': 1.4152476960322269, 'latency_mean': 6.996479612588883, 'latency_p50': 7.0021727085113525, 'latency_p90': 8.01062207221985}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: junhua024-chai-02-full-01220_v5
is_internal_developer: False
language_model: junhua024/chai_02_full_01220
model_size: 13B
ranking_group: single
throughput_3p7s: 1.24
us_pacific_date: 2025-07-16
win_ratio: 0.4668852459016393
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-01220-v5-mkmlizer
Waiting for job on junhua024-chai-02-full-01220-v5-mkmlizer to finish
junhua024-chai-02-full-01220-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-02-full-01220-v5-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-01220-v5-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-02-full-01220-v5-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-02-full-01220-v5-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-02-full-01220-v5-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-02-full-01220-v5-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-02-full-01220-v5-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-02-full-01220-v5-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-02-full-01220-v5-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-02-full-01220-v5-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-01220-v5-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-02-full-01220-v5-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-02-full-01220-v5-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-02-full-01220-v5-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-02-full-01220-v5-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-01220-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-02-full-01220-v5-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-02-full-01220-v5-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-01220-v5-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-02-full-01220-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-02-full-01220-v5-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-02-full-01220-v5-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-01220-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-02-full-01220-v5-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-01220-v5-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-01220-v5-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-01220-v5-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-01220-v5-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-01220-v5-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-01220-v5-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-01220-v5-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-01220-v5-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-01220-v5-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-01220-v5-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-01220-v5-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-01220-v5-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-01220-v5-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-01220-v5-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-01220-v5-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-01220-v5-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-01220-v5-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-01220-v5-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-01220-v5-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-01220-v5-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-01220-v5-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-01220-v5-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-01220-v5-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-01220-v5-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-01220-v5-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-01220-v5-mkmlizer: Downloaded to shared memory in 133.436s
junhua024-chai-02-full-01220-v5-mkmlizer: Checking if junhua024/chai_02_full_01220 already exists in ChaiML
junhua024-chai-02-full-01220-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmljlsgzp, device:0
junhua024-chai-02-full-01220-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-02-full-01220-v5-mkmlizer: quantized model in 30.492s
junhua024-chai-02-full-01220-v5-mkmlizer: Processed model junhua024/chai_02_full_01220 in 164.015s
junhua024-chai-02-full-01220-v5-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-02-full-01220-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-02-full-01220-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-02-full-01220-v5/nvidia
junhua024-chai-02-full-01220-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-02-full-01220-v5/nvidia/config.json
junhua024-chai-02-full-01220-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-02-full-01220-v5/nvidia/special_tokens_map.json
junhua024-chai-02-full-01220-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-02-full-01220-v5/nvidia/tokenizer_config.json
junhua024-chai-02-full-01220-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-02-full-01220-v5/nvidia/tokenizer.json
junhua024-chai-02-full-01220-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-02-full-01220-v5/nvidia/flywheel_model.0.safetensors
junhua024-chai-02-full-01220-v5-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:22, 15.94it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:19, 18.03it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:12, 28.89it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 31.52it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 33.83it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:06, 47.29it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:08, 37.40it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:08, 36.57it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:07, 40.84it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:08, 34.65it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:09, 33.63it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 34.97it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:08, 33.09it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:08, 34.09it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:08, 32.85it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 38.10it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 37.50it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:06, 38.45it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:07, 37.32it/s]
Loading 0:  29%|██▉       | 105/363 [00:02<00:07, 34.62it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:05, 41.72it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:07, 34.61it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:07, 32.50it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:06, 34.65it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:06, 33.34it/s]
Loading 0:  38%|███▊      | 138/363 [00:03<00:06, 33.19it/s]
Loading 0:  39%|███▉      | 143/363 [00:04<00:06, 33.27it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:06, 34.23it/s]
Loading 0:  43%|████▎     | 155/363 [00:04<00:05, 39.61it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 37.13it/s]
Loading 0:  45%|████▌     | 164/363 [00:04<00:05, 36.32it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:05, 33.57it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:04, 39.68it/s]
Loading 0:  50%|████▉     | 180/363 [00:05<00:05, 32.29it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 33.99it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:04, 35.94it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:04, 34.55it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 35.56it/s]
Loading 0:  57%|█████▋    | 206/363 [00:05<00:04, 35.61it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:04, 36.06it/s]
Loading 0:  61%|██████    | 220/363 [00:06<00:03, 45.55it/s]
Loading 0:  62%|██████▏   | 225/363 [00:06<00:03, 34.86it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:03, 35.34it/s]
Loading 0:  66%|██████▌   | 239/363 [00:06<00:02, 43.33it/s]
Loading 0:  67%|██████▋   | 244/363 [00:06<00:03, 36.27it/s]
Loading 0:  69%|██████▊   | 249/363 [00:06<00:03, 37.37it/s]
Loading 0:  70%|██████▉   | 254/363 [00:07<00:02, 36.95it/s]
Loading 0:  71%|███████   | 258/363 [00:07<00:02, 35.21it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 35.50it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 34.93it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 35.38it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:01, 44.99it/s]
Loading 0:  79%|███████▉  | 288/363 [00:08<00:02, 34.24it/s]
Loading 0:  81%|████████  | 293/363 [00:08<00:02, 34.84it/s]
Loading 0:  83%|████████▎ | 302/363 [00:08<00:01, 42.66it/s]
Loading 0:  85%|████████▍ | 307/363 [00:08<00:01, 36.35it/s]
Loading 0:  86%|████████▌ | 311/363 [00:08<00:01, 35.52it/s]
Loading 0:  87%|████████▋ | 317/363 [00:08<00:01, 37.25it/s]
Loading 0:  88%|████████▊ | 321/363 [00:08<00:01, 35.72it/s]
Loading 0:  90%|█████████ | 327/363 [00:09<00:01, 35.99it/s]
Loading 0:  91%|█████████▏| 332/363 [00:09<00:00, 35.58it/s]
Loading 0:  93%|█████████▎| 338/363 [00:09<00:00, 36.00it/s]
Loading 0:  95%|█████████▌| 345/363 [00:09<00:00, 43.30it/s]
Loading 0:  96%|█████████▋| 350/363 [00:09<00:00, 25.15it/s]
Loading 0:  98%|█████████▊| 354/363 [00:10<00:00, 26.85it/s]
Loading 0:  99%|█████████▊| 358/363 [00:10<00:00, 27.84it/s]
                                                            
Job junhua024-chai-02-full-01220-v5-mkmlizer completed after 190.1s with status: succeeded
Stopping job with name junhua024-chai-02-full-01220-v5-mkmlizer
Pipeline stage MKMLizer completed in 190.63s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-02-full-01220-v5
Waiting for inference service junhua024-chai-02-full-01220-v5 to be ready
Unable to record family friendly update due to error: Invalid JSON input: JSON must contain 'User Safety' and 'Response Safety' fields
Inference service junhua024-chai-02-full-01220-v5 ready after 271.9849045276642s
Pipeline stage MKMLDeployer completed in 272.92s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2428441047668457s
Received healthy response to inference request in 1.5568430423736572s
Received healthy response to inference request in 1.7871911525726318s
Received healthy response to inference request in 1.612485647201538s
Received healthy response to inference request in 1.7335944175720215s
5 requests
0 failed requests
5th percentile: 1.5679715633392335
10th percentile: 1.5791000843048095
20th percentile: 1.6013571262359618
30th percentile: 1.6367074012756349
40th percentile: 1.6851509094238282
50th percentile: 1.7335944175720215
60th percentile: 1.7550331115722657
70th percentile: 1.7764718055725097
80th percentile: 1.8783217430114747
90th percentile: 2.06058292388916
95th percentile: 2.151713514328003
99th percentile: 2.224617986679077
mean time: 1.7865916728973388
Pipeline stage StressChecker completed in 10.50s
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 0.83s
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 0.86s
Shutdown handler de-registered
junhua024-chai-02-full-01220_v5 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
Received signal 15, running shutdown handler
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
Pipeline stage OfflineFamilyFriendlyScorer completed in 4547.43s
Shutdown handler de-registered
junhua024-chai-02-full-01220_v5 status is now torndown due to DeploymentManager action
junhua024-chai-02-full-01220_v5 status is now torndown due to DeploymentManager action