junhua024-chai-06-full-02102

developer_uid: junhua024

submission_id: junhua024-chai-06-full-02102_v2

model_name: junhua024-chai-06-full-02102_v2

model_group: junhua024/chai_06_full_0

status: torndown

timestamp: 2025-07-16T21:56:53+00:00

num_battles: 8200

num_wins: 3993

celo_rating: 1277.3

family_friendly_score: 0.5571999999999999

family_friendly_standard_error: 0.007024644617345421

submission_type: basic

model_repo: junhua024/chai_06_full_02102

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': 0.6055686426850403, 'latency_mean': 1.6512118577957153, 'latency_p50': 1.647855520248413, 'latency_p90': 1.8299378395080566}, {'batch_size': 3, 'throughput': 1.0898533581137908, 'latency_mean': 2.744297993183136, 'latency_p50': 2.7487770318984985, 'latency_p90': 3.043213725090027}, {'batch_size': 5, 'throughput': 1.3122338011144268, 'latency_mean': 3.800742495059967, 'latency_p50': 3.8317933082580566, 'latency_p90': 4.169006371498108}, {'batch_size': 6, 'throughput': 1.371476480966504, 'latency_mean': 4.341777079105377, 'latency_p50': 4.365132570266724, 'latency_p90': 4.845104336738586}, {'batch_size': 8, 'throughput': 1.4499152860933469, 'latency_mean': 5.486571710109711, 'latency_p50': 5.509141206741333, 'latency_p90': 6.164325594902039}, {'batch_size': 10, 'throughput': 1.4773022419981736, 'latency_mean': 6.725628020763398, 'latency_p50': 6.706896901130676, 'latency_p90': 7.580688619613648}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-06-full-02102_v2

is_internal_developer: False

language_model: junhua024/chai_06_full_02102

model_size: 13B

ranking_group: single

throughput_3p7s: 1.3

us_pacific_date: 2025-07-16

win_ratio: 0.4869512195121951

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-02102-v2-mkmlizer
Waiting for job on junhua024-chai-06-full-02102-v2-mkmlizer to finish
junhua024-chai-06-full-02102-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-06-full-02102-v2-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-02102-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-06-full-02102-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-06-full-02102-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-06-full-02102-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-06-full-02102-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-06-full-02102-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-06-full-02102-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-06-full-02102-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-06-full-02102-v2-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-02102-v2-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-06-full-02102-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-06-full-02102-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-06-full-02102-v2-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-06-full-02102-v2-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-02102-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-06-full-02102-v2-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-06-full-02102-v2-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-02102-v2-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-06-full-02102-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-06-full-02102-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-06-full-02102-v2-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-02102-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-06-full-02102-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-06-full-02102-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-06-full-02102-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-06-full-02102-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-06-full-02102-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-06-full-02102-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-06-full-02102-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-06-full-02102-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-06-full-02102-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-06-full-02102-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-06-full-02102-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-06-full-02102-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-06-full-02102-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-06-full-02102-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-06-full-02102-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-06-full-02102-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-06-full-02102-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-06-full-02102-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-06-full-02102-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-06-full-02102-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-06-full-02102-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-06-full-02102-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-06-full-02102-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-06-full-02102-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-06-full-02102-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-06-full-02102-v2-mkmlizer: Downloaded to shared memory in 130.596s
junhua024-chai-06-full-02102-v2-mkmlizer: Checking if junhua024/chai_06_full_02102 already exists in ChaiML
junhua024-chai-06-full-02102-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpws58i861, device:0
junhua024-chai-06-full-02102-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-06-full-02102-v2-mkmlizer: quantized model in 30.324s
junhua024-chai-06-full-02102-v2-mkmlizer: Processed model junhua024/chai_06_full_02102 in 161.017s
junhua024-chai-06-full-02102-v2-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-06-full-02102-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-06-full-02102-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-06-full-02102-v2/nvidia
junhua024-chai-06-full-02102-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-06-full-02102-v2/nvidia/config.json
junhua024-chai-06-full-02102-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-06-full-02102-v2/nvidia/special_tokens_map.json
junhua024-chai-06-full-02102-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-06-full-02102-v2/nvidia/tokenizer_config.json
junhua024-chai-06-full-02102-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-06-full-02102-v2/nvidia/tokenizer.json
junhua024-chai-06-full-02102-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-06-full-02102-v2/nvidia/flywheel_model.0.safetensors
junhua024-chai-06-full-02102-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:21, 16.48it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:18, 19.19it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 31.89it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 33.98it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:09, 36.15it/s]
Loading 0:   9%|▉         | 33/363 [00:00<00:07, 46.58it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:08, 39.95it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:08, 39.10it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:07, 43.71it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:08, 37.28it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:08, 36.63it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:07, 38.63it/s]
Loading 0:  19%|█▉        | 69/363 [00:01<00:07, 37.24it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:07, 36.20it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:08, 34.55it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 40.12it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:06, 39.77it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:06, 40.72it/s]
Loading 0:  28%|██▊       | 102/363 [00:02<00:06, 38.75it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:06, 38.45it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:05, 43.41it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:06, 36.61it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:06, 35.42it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:06, 37.69it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:06, 36.72it/s]
Loading 0:  38%|███▊      | 138/363 [00:03<00:06, 36.45it/s]
Loading 0:  39%|███▉      | 143/363 [00:03<00:06, 36.40it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:05, 37.55it/s]
Loading 0:  43%|████▎     | 157/363 [00:04<00:04, 46.79it/s]
Loading 0:  45%|████▍     | 162/363 [00:04<00:05, 35.37it/s]
Loading 0:  46%|████▌     | 167/363 [00:04<00:05, 36.04it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:04, 44.14it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 37.27it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 38.41it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:04, 37.21it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:04, 36.00it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 35.73it/s]
Loading 0:  57%|█████▋    | 206/363 [00:05<00:04, 35.83it/s]
Loading 0:  58%|█████▊    | 212/363 [00:05<00:04, 36.70it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 46.24it/s]
Loading 0:  62%|██████▏   | 225/363 [00:05<00:03, 35.72it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:03, 36.35it/s]
Loading 0:  66%|██████▌   | 239/363 [00:06<00:02, 43.14it/s]
Loading 0:  67%|██████▋   | 244/363 [00:06<00:03, 36.12it/s]
Loading 0:  68%|██████▊   | 248/363 [00:06<00:03, 35.00it/s]
Loading 0:  70%|██████▉   | 254/363 [00:06<00:02, 36.76it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 35.28it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 35.74it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 35.50it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 36.16it/s]
Loading 0:  77%|███████▋  | 281/363 [00:07<00:01, 41.37it/s]
Loading 0:  79%|███████▉  | 286/363 [00:07<00:01, 39.32it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 37.95it/s]
Loading 0:  81%|████████▏ | 295/363 [00:07<00:01, 37.68it/s]
Loading 0:  83%|████████▎ | 302/363 [00:07<00:01, 42.31it/s]
Loading 0:  85%|████████▍ | 307/363 [00:08<00:01, 35.81it/s]
Loading 0:  86%|████████▌ | 311/363 [00:08<00:01, 35.31it/s]
Loading 0:  87%|████████▋ | 317/363 [00:08<00:01, 36.74it/s]
Loading 0:  88%|████████▊ | 321/363 [00:08<00:01, 35.02it/s]
Loading 0:  90%|█████████ | 327/363 [00:08<00:01, 35.72it/s]
Loading 0:  91%|█████████▏| 332/363 [00:08<00:00, 35.92it/s]
Loading 0:  93%|█████████▎| 338/363 [00:09<00:00, 36.09it/s]
Loading 0:  96%|█████████▌| 347/363 [00:09<00:00, 47.61it/s]
Loading 0:  97%|█████████▋| 353/363 [00:09<00:00, 25.23it/s]
Loading 0:  98%|█████████▊| 357/363 [00:09<00:00, 26.54it/s]
                                                            
Job junhua024-chai-06-full-02102-v2-mkmlizer completed after 190.2s with status: succeeded
Stopping job with name junhua024-chai-06-full-02102-v2-mkmlizer
Pipeline stage MKMLizer completed in 190.77s
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-06-full-02102-v2
Waiting for inference service junhua024-chai-06-full-02102-v2 to be ready
Failed to get response for submission junhua024-chai-06-full-02098_v2: HTTPConnectionPool(host='junhua024-chai-06-full-02098-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-06-full-02102-v2 ready after 261.194185256958s
Pipeline stage MKMLDeployer completed in 261.81s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3860068321228027s
Received healthy response to inference request in 1.7324368953704834s
Received healthy response to inference request in 1.6253695487976074s
Received healthy response to inference request in 1.6296038627624512s
Received healthy response to inference request in 2.1773030757904053s
5 requests
0 failed requests
5th percentile: 1.6262164115905762
10th percentile: 1.627063274383545
20th percentile: 1.6287569999694824
30th percentile: 1.6501704692840575
40th percentile: 1.6913036823272705
50th percentile: 1.7324368953704834
60th percentile: 1.910383367538452
70th percentile: 2.0883298397064207
80th percentile: 2.219043827056885
90th percentile: 2.3025253295898436
95th percentile: 2.344266080856323
99th percentile: 2.377658681869507
mean time: 1.91014404296875
Pipeline stage StressChecker completed in 11.40s
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 0.72s
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 0.71s
Shutdown handler de-registered
junhua024-chai-06-full-02102_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 8856.22s
Shutdown handler de-registered
junhua024-chai-06-full-02102_v2 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-06-full-02102_v2 status is now torndown due to DeploymentManager action
run pipeline stage %s
junhua024-chai-06-full-02102_v2 status is now torndown due to DeploymentManager action