junhua024-chai-1-full-002

developer_uid: junhua024

submission_id: junhua024-chai-1-full-002_v24

model_name: junhua024-chai-1-full-002_v24

model_group: junhua024/chai_1-full_00

status: torndown

timestamp: 2025-06-29T09:16:45+00:00

num_battles: 8669

num_wins: 4082

celo_rating: 1249.15

family_friendly_score: 0.5871999999999999

family_friendly_standard_error: 0.006962702923434261

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': 0.5940240600645547, 'latency_mean': 1.6832630610466004, 'latency_p50': 1.6918134689331055, 'latency_p90': 1.8488735914230348}, {'batch_size': 3, 'throughput': 1.0499462270739117, 'latency_mean': 2.850105633735657, 'latency_p50': 2.86212420463562, 'latency_p90': 3.129744553565979}, {'batch_size': 5, 'throughput': 1.2610209819299125, 'latency_mean': 3.9443762719631197, 'latency_p50': 3.955245852470398, 'latency_p90': 4.416755366325378}, {'batch_size': 6, 'throughput': 1.3138697316961092, 'latency_mean': 4.531992794275284, 'latency_p50': 4.534365892410278, 'latency_p90': 5.076489591598511}, {'batch_size': 8, 'throughput': 1.377610074575083, 'latency_mean': 5.7721087038517, 'latency_p50': 5.753625154495239, 'latency_p90': 6.4609229326248165}, {'batch_size': 10, 'throughput': 1.4166252980871994, 'latency_mean': 7.001122416257858, 'latency_p50': 7.014553070068359, 'latency_p90': 7.880729794502258}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-1-full-002_v24

is_internal_developer: False

language_model: junhua024/chai_1-full_002

model_size: 13B

ranking_group: single

throughput_3p7s: 1.23

us_pacific_date: 2025-06-29

win_ratio: 0.4708732264390356

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.18, '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': "{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-1-full-002-v24-mkmlizer
Waiting for job on junhua024-chai-1-full-002-v24-mkmlizer to finish
junhua024-chai-1-full-002-v24-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-1-full-002-v24-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v24-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-1-full-002-v24-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-1-full-002-v24-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-1-full-002-v24-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-1-full-002-v24-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-1-full-002-v24-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-1-full-002-v24-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-1-full-002-v24-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-1-full-002-v24-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v24-mkmlizer: ║  Version: 0.29.3                                                    ║
junhua024-chai-1-full-002-v24-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-1-full-002-v24-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-1-full-002-v24-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-1-full-002-v24-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v24-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-1-full-002-v24-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-1-full-002-v24-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v24-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-1-full-002-v24-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-1-full-002-v24-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-1-full-002-v24-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v24-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-1-full-002-v24-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-v24-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-v24-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-v24-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-v24-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-v24-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-v24-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-v24-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-v24-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-v24-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-v24-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-v24-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-v24-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-v24-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-v24-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-v24-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-v24-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-v24-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-v24-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-v24-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-v24-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-v24-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-v24-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-v24-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-v24-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-v24-mkmlizer: Downloaded to shared memory in 74.194s
junhua024-chai-1-full-002-v24-mkmlizer: Checking if junhua024/chai_1-full_002 already exists in ChaiML
junhua024-chai-1-full-002-v24-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5lgb6qel, device:0
junhua024-chai-1-full-002-v24-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-1-full-002-v24-mkmlizer: quantized model in 31.742s
junhua024-chai-1-full-002-v24-mkmlizer: Processed model junhua024/chai_1-full_002 in 106.028s
junhua024-chai-1-full-002-v24-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-1-full-002-v24-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-1-full-002-v24-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-1-full-002-v24
junhua024-chai-1-full-002-v24-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v24/config.json
junhua024-chai-1-full-002-v24-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v24/special_tokens_map.json
junhua024-chai-1-full-002-v24-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v24/tokenizer_config.json
junhua024-chai-1-full-002-v24-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v24/tokenizer.json
junhua024-chai-1-full-002-v24-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-1-full-002-v24/flywheel_model.0.safetensors
junhua024-chai-1-full-002-v24-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:22, 15.75it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:19, 18.08it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:12, 28.65it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:11, 29.86it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 32.45it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 43.48it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:10, 31.33it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:10, 31.98it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:07, 39.35it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:09, 33.82it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:09, 33.19it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 33.95it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:08, 33.44it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:08, 33.34it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:08, 31.61it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 36.50it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 36.51it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:07, 36.48it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:07, 36.23it/s]
Loading 0:  29%|██▉       | 105/363 [00:03<00:07, 32.99it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:06, 41.04it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:08, 28.56it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:07, 30.63it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:07, 32.04it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:07, 31.33it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:06, 34.52it/s]
Loading 0:  39%|███▉      | 141/363 [00:04<00:06, 35.29it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:07, 30.71it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:07, 29.87it/s]
Loading 0:  43%|████▎     | 155/363 [00:04<00:05, 36.24it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:06, 33.18it/s]
Loading 0:  45%|████▌     | 164/363 [00:04<00:06, 32.92it/s]
Loading 0:  46%|████▋     | 168/363 [00:05<00:06, 31.27it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:04, 37.83it/s]
Loading 0:  49%|████▉     | 179/363 [00:05<00:05, 33.08it/s]
Loading 0:  50%|█████     | 183/363 [00:05<00:05, 33.36it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 34.05it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:05, 30.92it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:05, 30.93it/s]
Loading 0:  55%|█████▌    | 200/363 [00:05<00:04, 35.31it/s]
Loading 0:  56%|█████▌    | 204/363 [00:06<00:04, 35.69it/s]
Loading 0:  57%|█████▋    | 208/363 [00:06<00:04, 31.20it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:04, 30.85it/s]
Loading 0:  60%|██████    | 218/363 [00:06<00:03, 37.54it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:04, 34.80it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:03, 34.94it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 32.58it/s]
Loading 0:  66%|██████▌   | 238/363 [00:07<00:03, 41.60it/s]
Loading 0:  67%|██████▋   | 243/363 [00:07<00:03, 30.35it/s]
Loading 0:  68%|██████▊   | 248/363 [00:07<00:03, 32.64it/s]
Loading 0:  70%|██████▉   | 254/363 [00:07<00:03, 34.02it/s]
Loading 0:  71%|███████   | 258/363 [00:07<00:03, 33.27it/s]
Loading 0:  72%|███████▏  | 263/363 [00:07<00:02, 36.74it/s]
Loading 0:  74%|███████▎  | 267/363 [00:07<00:02, 36.52it/s]
Loading 0:  75%|███████▍  | 271/363 [00:08<00:02, 31.93it/s]
Loading 0:  76%|███████▌  | 275/363 [00:08<00:02, 31.17it/s]
Loading 0:  77%|███████▋  | 281/363 [00:08<00:02, 37.56it/s]
Loading 0:  79%|███████▉  | 286/363 [00:08<00:02, 35.87it/s]
Loading 0:  80%|███████▉  | 290/363 [00:08<00:02, 35.72it/s]
Loading 0:  81%|████████  | 294/363 [00:08<00:02, 33.17it/s]
Loading 0:  83%|████████▎ | 301/363 [00:08<00:01, 42.07it/s]
Loading 0:  84%|████████▍ | 306/363 [00:09<00:01, 30.83it/s]
Loading 0:  86%|████████▌ | 311/363 [00:09<00:01, 32.52it/s]
Loading 0:  87%|████████▋ | 317/363 [00:09<00:01, 34.04it/s]
Loading 0:  88%|████████▊ | 321/363 [00:09<00:01, 33.46it/s]
Loading 0:  90%|█████████ | 327/363 [00:09<00:01, 33.39it/s]
Loading 0:  91%|█████████▏| 332/363 [00:09<00:00, 32.67it/s]
Loading 0:  93%|█████████▎| 338/363 [00:10<00:00, 34.01it/s]
Loading 0:  95%|█████████▍| 344/363 [00:10<00:00, 38.70it/s]
Loading 0:  96%|█████████▌| 349/363 [00:10<00:00, 26.68it/s]
Loading 0:  97%|█████████▋| 353/363 [00:10<00:00, 24.56it/s]
Loading 0:  98%|█████████▊| 357/363 [00:10<00:00, 25.35it/s]
                                                            
Job junhua024-chai-1-full-002-v24-mkmlizer completed after 128.14s with status: succeeded
Stopping job with name junhua024-chai-1-full-002-v24-mkmlizer
Pipeline stage MKMLizer completed in 128.75s
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-1-full-002-v24
Waiting for inference service junhua024-chai-1-full-002-v24 to be ready
Inference service junhua024-chai-1-full-002-v24 ready after 181.24746251106262s
Pipeline stage MKMLDeployer completed in 181.90s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.539687156677246s
Received healthy response to inference request in 1.4395983219146729s
Received healthy response to inference request in 1.7141344547271729s
Received healthy response to inference request in 1.8599953651428223s
Received healthy response to inference request in 0.8314568996429443s
5 requests
0 failed requests
5th percentile: 0.95308518409729
10th percentile: 1.0747134685516357
20th percentile: 1.3179700374603271
30th percentile: 1.4945055484771728
40th percentile: 1.6043200016021728
50th percentile: 1.7141344547271729
60th percentile: 1.7724788188934326
70th percentile: 1.8308231830596924
80th percentile: 1.9959337234497072
90th percentile: 2.2678104400634767
95th percentile: 2.403748798370361
99th percentile: 2.5124994850158693
mean time: 1.6769744396209716
Pipeline stage StressChecker completed in 9.74s
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 0.65s
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 0.70s
Shutdown handler de-registered
junhua024-chai-1-full-002_v24 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 5633.38s
Shutdown handler de-registered
junhua024-chai-1-full-002_v24 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-1-full-002_v24 status is now torndown due to DeploymentManager action