junhua024-chai-02-full-02

developer_uid: junhua024

submission_id: junhua024-chai-02-full-02_v2

model_name: junhua024-chai-02-full-02_v2

model_group: junhua024/chai_02-full_0

status: torndown

timestamp: 2025-07-12T09:32:10+00:00

num_battles: 20645

num_wins: 9974

celo_rating: 1252.78

family_friendly_score: 0.6148

family_friendly_standard_error: 0.006882164775708295

submission_type: basic

model_repo: junhua024/chai_02-full_02

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': 0.6019740697695735, 'latency_mean': 1.6610744297504425, 'latency_p50': 1.6454737186431885, 'latency_p90': 1.8479472160339356}, {'batch_size': 3, 'throughput': 1.0919499656313874, 'latency_mean': 2.7339113473892214, 'latency_p50': 2.726212739944458, 'latency_p90': 3.009710907936096}, {'batch_size': 5, 'throughput': 1.30370839753343, 'latency_mean': 3.8229453790187837, 'latency_p50': 3.80659019947052, 'latency_p90': 4.309958434104919}, {'batch_size': 6, 'throughput': 1.3661966344097383, 'latency_mean': 4.359936852455139, 'latency_p50': 4.323907852172852, 'latency_p90': 4.885182642936706}, {'batch_size': 8, 'throughput': 1.436373424221168, 'latency_mean': 5.527081809043884, 'latency_p50': 5.509459495544434, 'latency_p90': 6.195692110061645}, {'batch_size': 10, 'throughput': 1.461719151266233, 'latency_mean': 6.770459427833557, 'latency_p50': 6.749459385871887, 'latency_p90': 7.527002143859863}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-02-full-02_v2

is_internal_developer: False

language_model: junhua024/chai_02-full_02

model_size: 13B

ranking_group: single

throughput_3p7s: 1.29

us_pacific_date: 2025-07-12

win_ratio: 0.48311939937030757

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 5, '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-02-v2-mkmlizer
Waiting for job on junhua024-chai-02-full-02-v2-mkmlizer to finish
junhua024-chai-02-full-02-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-02-full-02-v2-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-02-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-02-full-02-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-02-full-02-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-02-full-02-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-02-full-02-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-02-full-02-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-02-full-02-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-02-full-02-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-02-full-02-v2-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-02-v2-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-02-full-02-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-02-full-02-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-02-full-02-v2-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-02-full-02-v2-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-02-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-02-full-02-v2-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-02-full-02-v2-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-02-v2-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-02-full-02-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-02-full-02-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-02-full-02-v2-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-02-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-02-full-02-v2-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-02-v2-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-02-v2-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-02-v2-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-02-v2-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-02-v2-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-02-v2-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-02-v2-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-02-v2-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-02-v2-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-02-v2-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-02-v2-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-02-v2-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-02-v2-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-02-v2-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-02-v2-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-02-v2-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-02-v2-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-02-v2-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-02-v2-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-02-v2-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-02-v2-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-02-v2-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-02-v2-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-02-v2-mkmlizer: Downloaded to shared memory in 115.657s
junhua024-chai-02-full-02-v2-mkmlizer: Checking if junhua024/chai_02-full_02 already exists in ChaiML
junhua024-chai-02-full-02-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplg2cpr88, device:0
junhua024-chai-02-full-02-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-02-full-02-v2-mkmlizer: quantized model in 31.780s
junhua024-chai-02-full-02-v2-mkmlizer: Processed model junhua024/chai_02-full_02 in 147.509s
junhua024-chai-02-full-02-v2-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-02-full-02-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-02-full-02-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-02-full-02-v2/nvidia
junhua024-chai-02-full-02-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-02-full-02-v2/nvidia/config.json
junhua024-chai-02-full-02-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-02-full-02-v2/nvidia/special_tokens_map.json
junhua024-chai-02-full-02-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-02-full-02-v2/nvidia/tokenizer_config.json
junhua024-chai-02-full-02-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-02-full-02-v2/nvidia/flywheel_model.0.safetensors
junhua024-chai-02-full-02-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:23, 15.23it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:19, 17.97it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:10, 33.42it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:10, 32.51it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:10, 34.02it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:10, 32.46it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 42.23it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:10, 31.01it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:09, 32.29it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:07, 40.27it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:08, 34.25it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:09, 33.62it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 34.79it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:08, 34.00it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:07, 37.39it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:07, 37.66it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:08, 32.18it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:07, 36.31it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 33.94it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:07, 34.47it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:07, 34.20it/s]
Loading 0:  29%|██▉       | 105/363 [00:03<00:08, 30.82it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:06, 37.25it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:08, 30.51it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:07, 32.32it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:06, 33.98it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:06, 33.38it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:06, 37.11it/s]
Loading 0:  39%|███▉      | 141/363 [00:04<00:05, 37.76it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:06, 32.61it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:06, 31.32it/s]
Loading 0:  43%|████▎     | 155/363 [00:04<00:05, 37.20it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 35.22it/s]
Loading 0:  45%|████▌     | 164/363 [00:04<00:05, 34.29it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:06, 32.11it/s]
Loading 0:  48%|████▊     | 176/363 [00:05<00:04, 38.21it/s]
Loading 0:  50%|████▉     | 180/363 [00:05<00:05, 30.71it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 32.11it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:05, 33.13it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:05, 32.35it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:05, 32.05it/s]
Loading 0:  57%|█████▋    | 206/363 [00:06<00:04, 31.50it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:04, 32.92it/s]
Loading 0:  60%|██████    | 218/363 [00:06<00:03, 38.00it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:03, 36.04it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:03, 35.17it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 32.84it/s]
Loading 0:  66%|██████▌   | 238/363 [00:06<00:03, 41.12it/s]
Loading 0:  67%|██████▋   | 243/363 [00:07<00:03, 30.31it/s]
Loading 0:  68%|██████▊   | 248/363 [00:07<00:03, 32.45it/s]
Loading 0:  70%|██████▉   | 254/363 [00:07<00:03, 33.98it/s]
Loading 0:  71%|███████   | 258/363 [00:07<00:03, 33.30it/s]
Loading 0:  72%|███████▏  | 263/363 [00:07<00:02, 36.99it/s]
Loading 0:  74%|███████▎  | 267/363 [00:07<00:02, 36.78it/s]
Loading 0:  75%|███████▍  | 271/363 [00:08<00:02, 32.17it/s]
Loading 0:  76%|███████▌  | 275/363 [00:08<00:02, 31.08it/s]
Loading 0:  77%|███████▋  | 281/363 [00:08<00:02, 37.68it/s]
Loading 0:  79%|███████▉  | 286/363 [00:08<00:02, 36.02it/s]
Loading 0:  80%|███████▉  | 290/363 [00:08<00:02, 35.83it/s]
Loading 0:  81%|████████  | 294/363 [00:08<00:02, 33.17it/s]
Loading 0:  83%|████████▎ | 301/363 [00:08<00:01, 41.98it/s]
Loading 0:  84%|████████▍ | 306/363 [00:09<00:01, 30.82it/s]
Loading 0:  86%|████████▌ | 311/363 [00:09<00:01, 32.80it/s]
Loading 0:  87%|████████▋ | 317/363 [00:09<00:01, 34.24it/s]
Loading 0:  88%|████████▊ | 321/363 [00:09<00:01, 33.73it/s]
Loading 0:  90%|█████████ | 327/363 [00:09<00:01, 33.94it/s]
Loading 0:  91%|█████████▏| 332/363 [00:09<00:00, 33.48it/s]
Loading 0:  93%|█████████▎| 338/363 [00:09<00:00, 34.86it/s]
Loading 0:  95%|█████████▍| 344/363 [00:10<00:00, 39.80it/s]
Loading 0:  96%|█████████▌| 349/363 [00:10<00:00, 26.98it/s]
Loading 0:  97%|█████████▋| 353/363 [00:10<00:00, 24.73it/s]
Loading 0:  98%|█████████▊| 357/363 [00:10<00:00, 26.40it/s]
                                                            
Job junhua024-chai-02-full-02-v2-mkmlizer completed after 167.99s with status: succeeded
Stopping job with name junhua024-chai-02-full-02-v2-mkmlizer
Pipeline stage MKMLizer completed in 168.50s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-02-full-02-v2
Waiting for inference service junhua024-chai-02-full-02-v2 to be ready
Inference service junhua024-chai-02-full-02-v2 ready after 210.7060899734497s
Pipeline stage MKMLDeployer completed in 211.55s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1817727088928223s
Received healthy response to inference request in 1.6000564098358154s
Received healthy response to inference request in 1.6607277393341064s
Received healthy response to inference request in 1.4992315769195557s
Received healthy response to inference request in 1.246321439743042s
5 requests
0 failed requests
5th percentile: 1.2969034671783448
10th percentile: 1.3474854946136474
20th percentile: 1.4486495494842528
30th percentile: 1.5193965435028076
40th percentile: 1.5597264766693115
50th percentile: 1.6000564098358154
60th percentile: 1.6243249416351317
70th percentile: 1.6485934734344483
80th percentile: 1.7649367332458497
90th percentile: 1.973354721069336
95th percentile: 2.077563714981079
99th percentile: 2.1609309101104737
mean time: 1.6376219749450684
Pipeline stage StressChecker completed in 9.55s
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 0.68s
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 0.81s
Shutdown handler de-registered
junhua024-chai-02-full-02_v2 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2998.72s
Shutdown handler de-registered
junhua024-chai-02-full-02_v2 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-02-full-02_v2 status is now torndown due to DeploymentManager action