junhua024-chai-06-full-_16215

developer_uid: junhua024

submission_id: junhua024-chai-06-full-_16215_v5

model_name: junhua024-chai-06-full-_16215_v5

model_group: junhua024/chai_06_full_0

status: torndown

timestamp: 2025-07-17T10:22:17+00:00

num_battles: 6544

num_wins: 3284

celo_rating: 1271.25

family_friendly_score: 0.5498000000000001

family_friendly_standard_error: 0.007035907333102107

submission_type: basic

model_repo: junhua024/chai_06_full_02102_2028

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': 0.598825253968668, 'latency_mean': 1.6698046457767486, 'latency_p50': 1.676387906074524, 'latency_p90': 1.8428762674331665}, {'batch_size': 3, 'throughput': 1.0827882988281579, 'latency_mean': 2.7608867740631102, 'latency_p50': 2.7632559537887573, 'latency_p90': 3.031319785118103}, {'batch_size': 5, 'throughput': 1.3056611465245422, 'latency_mean': 3.8162983977794647, 'latency_p50': 3.814833402633667, 'latency_p90': 4.265791225433349}, {'batch_size': 6, 'throughput': 1.3537570797993577, 'latency_mean': 4.409351575374603, 'latency_p50': 4.384177088737488, 'latency_p90': 5.013801884651184}, {'batch_size': 8, 'throughput': 1.4170556404898638, 'latency_mean': 5.6071514630317685, 'latency_p50': 5.623749494552612, 'latency_p90': 6.318415713310242}, {'batch_size': 10, 'throughput': 1.45693497049924, 'latency_mean': 6.816953164339066, 'latency_p50': 6.8498581647872925, 'latency_p90': 7.661300945281982}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-06-full-_16215_v5

is_internal_developer: False

language_model: junhua024/chai_06_full_02102_2028

model_size: 13B

ranking_group: single

throughput_3p7s: 1.29

us_pacific_date: 2025-07-17

win_ratio: 0.5018337408312958

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-06-full-16215-v5-mkmlizer
Waiting for job on junhua024-chai-06-full-16215-v5-mkmlizer to finish
junhua024-chai-06-full-16215-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-06-full-16215-v5-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-16215-v5-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-06-full-16215-v5-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-06-full-16215-v5-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-06-full-16215-v5-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-06-full-16215-v5-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-06-full-16215-v5-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-06-full-16215-v5-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-06-full-16215-v5-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-06-full-16215-v5-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-16215-v5-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-06-full-16215-v5-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-06-full-16215-v5-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-06-full-16215-v5-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-06-full-16215-v5-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-16215-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-06-full-16215-v5-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-06-full-16215-v5-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-16215-v5-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-06-full-16215-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-06-full-16215-v5-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-06-full-16215-v5-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-16215-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-06-full-16215-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-06-full-16215-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-06-full-16215-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-06-full-16215-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-06-full-16215-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-06-full-16215-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-06-full-16215-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-06-full-16215-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-06-full-16215-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-06-full-16215-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-06-full-16215-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-06-full-16215-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-06-full-16215-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-06-full-16215-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-06-full-16215-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-06-full-16215-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-06-full-16215-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-06-full-16215-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-06-full-16215-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-06-full-16215-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-06-full-16215-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-06-full-16215-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-06-full-16215-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-06-full-16215-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-06-full-16215-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-06-full-16215-v5-mkmlizer: Downloaded to shared memory in 75.221s
junhua024-chai-06-full-16215-v5-mkmlizer: Checking if junhua024/chai_06_full_02102_2028 already exists in ChaiML
junhua024-chai-06-full-16215-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpy4tlu6ve, device:0
junhua024-chai-06-full-16215-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-06-full-16215-v5-mkmlizer: quantized model in 32.575s
junhua024-chai-06-full-16215-v5-mkmlizer: Processed model junhua024/chai_06_full_02102_2028 in 107.875s
junhua024-chai-06-full-16215-v5-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-06-full-16215-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-06-full-16215-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-06-full-16215-v5/nvidia
junhua024-chai-06-full-16215-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-06-full-16215-v5/nvidia/special_tokens_map.json
junhua024-chai-06-full-16215-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-06-full-16215-v5/nvidia/config.json
junhua024-chai-06-full-16215-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-06-full-16215-v5/nvidia/tokenizer_config.json
junhua024-chai-06-full-16215-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-06-full-16215-v5/nvidia/flywheel_model.0.safetensors
junhua024-chai-06-full-16215-v5-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:24, 14.85it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:20, 17.18it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:11, 31.97it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:10, 33.11it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:13, 26.21it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:13, 25.91it/s]
Loading 0:   8%|▊         | 29/363 [00:00<00:10, 33.11it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:10, 30.87it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 30.63it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:11, 28.03it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:10, 30.14it/s]
Loading 0:  14%|█▍        | 51/363 [00:01<00:10, 28.76it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:10, 28.40it/s]
Loading 0:  16%|█▋        | 59/363 [00:02<00:11, 26.72it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:09, 30.99it/s]
Loading 0:  19%|█▊        | 68/363 [00:02<00:12, 23.75it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:10, 28.68it/s]
Loading 0:  21%|██        | 77/363 [00:02<00:10, 28.48it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:11, 24.46it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:11, 25.33it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 30.04it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 32.17it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:08, 31.74it/s]
Loading 0:  29%|██▉       | 105/363 [00:03<00:08, 29.54it/s]
Loading 0:  30%|███       | 110/363 [00:03<00:07, 33.83it/s]
Loading 0:  31%|███▏      | 114/363 [00:03<00:08, 29.58it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:08, 29.14it/s]
Loading 0:  34%|███▎      | 122/363 [00:04<00:08, 28.74it/s]
Loading 0:  35%|███▌      | 128/363 [00:04<00:07, 31.68it/s]
Loading 0:  36%|███▋      | 132/363 [00:04<00:07, 29.51it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:07, 30.98it/s]
Loading 0:  39%|███▉      | 143/363 [00:04<00:06, 31.81it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:06, 32.79it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:04, 42.22it/s]
Loading 0:  45%|████▍     | 162/363 [00:05<00:06, 32.59it/s]
Loading 0:  46%|████▌     | 167/363 [00:05<00:05, 33.33it/s]
Loading 0:  48%|████▊     | 176/363 [00:05<00:04, 41.47it/s]
Loading 0:  50%|████▉     | 181/363 [00:05<00:05, 35.48it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:05, 34.22it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:04, 35.94it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:04, 34.14it/s]
Loading 0:  55%|█████▌    | 201/363 [00:06<00:04, 34.82it/s]
Loading 0:  57%|█████▋    | 206/363 [00:06<00:04, 34.63it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:04, 35.24it/s]
Loading 0:  61%|██████    | 220/363 [00:06<00:03, 44.43it/s]
Loading 0:  62%|██████▏   | 225/363 [00:07<00:04, 34.30it/s]
Loading 0:  63%|██████▎   | 230/363 [00:07<00:03, 34.16it/s]
Loading 0:  66%|██████▌   | 239/363 [00:07<00:02, 42.01it/s]
Loading 0:  67%|██████▋   | 244/363 [00:07<00:03, 36.01it/s]
Loading 0:  68%|██████▊   | 248/363 [00:07<00:03, 35.04it/s]
Loading 0:  70%|██████▉   | 254/363 [00:07<00:02, 36.61it/s]
Loading 0:  71%|███████   | 258/363 [00:08<00:02, 35.28it/s]
Loading 0:  73%|███████▎  | 264/363 [00:08<00:02, 34.85it/s]
Loading 0:  74%|███████▍  | 269/363 [00:08<00:02, 34.59it/s]
Loading 0:  76%|███████▌  | 275/363 [00:08<00:02, 34.99it/s]
Loading 0:  78%|███████▊  | 283/363 [00:08<00:01, 44.05it/s]
Loading 0:  79%|███████▉  | 288/363 [00:08<00:02, 33.62it/s]
Loading 0:  81%|████████  | 293/363 [00:09<00:02, 34.11it/s]
Loading 0:  83%|████████▎ | 302/363 [00:09<00:01, 41.79it/s]
Loading 0:  85%|████████▍ | 307/363 [00:09<00:01, 35.66it/s]
Loading 0:  86%|████████▌ | 311/363 [00:09<00:01, 34.14it/s]
Loading 0:  87%|████████▋ | 317/363 [00:09<00:01, 35.76it/s]
Loading 0:  88%|████████▊ | 321/363 [00:09<00:01, 34.49it/s]
Loading 0:  90%|█████████ | 327/363 [00:09<00:01, 34.76it/s]
Loading 0:  91%|█████████▏| 332/363 [00:10<00:00, 34.45it/s]
Loading 0:  93%|█████████▎| 338/363 [00:10<00:00, 35.25it/s]
Loading 0:  95%|█████████▍| 344/363 [00:10<00:00, 40.23it/s]
Loading 0:  96%|█████████▌| 349/363 [00:10<00:00, 27.19it/s]
Loading 0:  97%|█████████▋| 353/363 [00:10<00:00, 24.37it/s]
Loading 0:  98%|█████████▊| 357/363 [00:11<00:00, 25.37it/s]
                                                            
Job junhua024-chai-06-full-16215-v5-mkmlizer completed after 138.69s with status: succeeded
Stopping job with name junhua024-chai-06-full-16215-v5-mkmlizer
Pipeline stage MKMLizer completed in 139.38s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-06-full-16215-v5
Waiting for inference service junhua024-chai-06-full-16215-v5 to be ready
Inference service junhua024-chai-06-full-16215-v5 ready after 272.41653323173523s
Pipeline stage MKMLDeployer completed in 273.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3168599605560303s
Received healthy response to inference request in 1.548692226409912s
Received healthy response to inference request in 1.6554386615753174s
Received healthy response to inference request in 1.6712870597839355s
Received healthy response to inference request in 1.637406587600708s
5 requests
0 failed requests
5th percentile: 1.5664350986480713
10th percentile: 1.5841779708862305
20th percentile: 1.6196637153625488
30th percentile: 1.64101300239563
40th percentile: 1.6482258319854737
50th percentile: 1.6554386615753174
60th percentile: 1.6617780208587647
70th percentile: 1.668117380142212
80th percentile: 1.8004016399383547
90th percentile: 2.0586308002471925
95th percentile: 2.187745380401611
99th percentile: 2.2910370445251464
mean time: 1.7659368991851807
Pipeline stage StressChecker completed in 10.96s
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 0.79s
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 0.77s
Shutdown handler de-registered
junhua024-chai-06-full-_16215_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 4837.26s
Shutdown handler de-registered
junhua024-chai-06-full-_16215_v5 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-06-full-_16215_v5 status is now torndown due to DeploymentManager action
junhua024-chai-06-full-_16215_v5 status is now torndown due to DeploymentManager action