junhua024-chai-02-full-061

developer_uid: junhua024

submission_id: junhua024-chai-02-full-061_v3

model_name: junhua024-chai-02-full-061_v3

model_group: junhua024/chai_02_full_0

status: torndown

timestamp: 2025-07-16T14:55:46+00:00

num_battles: 8414

num_wins: 4239

celo_rating: 1280.21

family_friendly_score: 0.5466

family_friendly_standard_error: 0.007040290334922275

submission_type: basic

model_repo: junhua024/chai_02_full_061

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': 0.589091401698753, 'latency_mean': 1.6973541712760924, 'latency_p50': 1.7036101818084717, 'latency_p90': 1.8762961149215698}, {'batch_size': 3, 'throughput': 1.058034677928193, 'latency_mean': 2.8300935196876527, 'latency_p50': 2.825405716896057, 'latency_p90': 3.090511989593506}, {'batch_size': 5, 'throughput': 1.269202688451542, 'latency_mean': 3.912174826860428, 'latency_p50': 3.8987027406692505, 'latency_p90': 4.402765011787414}, {'batch_size': 6, 'throughput': 1.33227389342312, 'latency_mean': 4.482679985761642, 'latency_p50': 4.490136623382568, 'latency_p90': 4.996345639228821}, {'batch_size': 8, 'throughput': 1.395807400639789, 'latency_mean': 5.699820981025696, 'latency_p50': 5.727339029312134, 'latency_p90': 6.395721673965454}, {'batch_size': 10, 'throughput': 1.4298123746582374, 'latency_mean': 6.943011775016784, 'latency_p50': 6.924413681030273, 'latency_p90': 7.95951783657074}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-02-full-061_v3

is_internal_developer: False

language_model: junhua024/chai_02_full_061

model_size: 13B

ranking_group: single

throughput_3p7s: 1.25

us_pacific_date: 2025-07-16

win_ratio: 0.5038031851675778

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-061-v3-mkmlizer
Waiting for job on junhua024-chai-02-full-061-v3-mkmlizer to finish
junhua024-chai-02-full-061-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-02-full-061-v3-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-061-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-02-full-061-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-02-full-061-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-02-full-061-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-02-full-061-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-02-full-061-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-02-full-061-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-02-full-061-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-02-full-061-v3-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-061-v3-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-02-full-061-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-02-full-061-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-02-full-061-v3-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-02-full-061-v3-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-061-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-02-full-061-v3-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-02-full-061-v3-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-061-v3-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-02-full-061-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-02-full-061-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-02-full-061-v3-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-061-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-02-full-061-v3-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-061-v3-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-061-v3-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-061-v3-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-061-v3-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-061-v3-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-061-v3-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-061-v3-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-061-v3-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-061-v3-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-061-v3-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-061-v3-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-061-v3-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-061-v3-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-061-v3-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-061-v3-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-061-v3-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`
Unable to record family friendly update due to error: HTTPConnectionPool(host='chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by ConnectTimeoutError(<urllib3.connection.HTTPConnection object at 0x7242447783d0>, 'Connection to chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com timed out. (connect timeout=12.0)'))
junhua024-chai-02-full-061-v3-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-061-v3-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-061-v3-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-061-v3-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-061-v3-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-061-v3-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-061-v3-mkmlizer: Downloaded to shared memory in 75.390s
junhua024-chai-02-full-061-v3-mkmlizer: Checking if junhua024/chai_02_full_061 already exists in ChaiML
junhua024-chai-02-full-061-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2mvoiazu, device:0
junhua024-chai-02-full-061-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-02-full-061-v3-mkmlizer: quantized model in 30.893s
junhua024-chai-02-full-061-v3-mkmlizer: Processed model junhua024/chai_02_full_061 in 106.364s
junhua024-chai-02-full-061-v3-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-02-full-061-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-02-full-061-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-02-full-061-v3/nvidia
junhua024-chai-02-full-061-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-02-full-061-v3/nvidia/config.json
junhua024-chai-02-full-061-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-02-full-061-v3/nvidia/special_tokens_map.json
junhua024-chai-02-full-061-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-02-full-061-v3/nvidia/tokenizer_config.json
junhua024-chai-02-full-061-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-02-full-061-v3/nvidia/tokenizer.json
junhua024-chai-02-full-061-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-02-full-061-v3/nvidia/flywheel_model.0.safetensors
junhua024-chai-02-full-061-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:24, 14.72it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:21, 16.98it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:12, 28.11it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:11, 29.76it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 32.95it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 46.79it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:09, 34.66it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:09, 34.21it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:07, 39.49it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:09, 33.90it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:09, 32.71it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 33.19it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:08, 33.02it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:08, 34.30it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:08, 32.77it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 37.51it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 37.14it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:06, 38.15it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 38.01it/s]
Loading 0:  29%|██▉       | 105/363 [00:03<00:07, 35.89it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:05, 42.58it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:06, 35.59it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:06, 35.04it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:06, 36.25it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:06, 34.96it/s]
Loading 0:  38%|███▊      | 138/363 [00:03<00:06, 35.70it/s]
Loading 0:  39%|███▉      | 143/363 [00:04<00:06, 35.59it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 36.12it/s]
Loading 0:  43%|████▎     | 157/363 [00:04<00:04, 45.68it/s]
Loading 0:  45%|████▍     | 162/363 [00:04<00:05, 35.09it/s]
Loading 0:  46%|████▌     | 167/363 [00:04<00:05, 35.81it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:04, 42.53it/s]
Loading 0:  50%|████▉     | 181/363 [00:05<00:05, 35.99it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 35.14it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:04, 37.00it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:04, 35.96it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 36.74it/s]
Loading 0:  57%|█████▋    | 206/363 [00:05<00:04, 34.74it/s]
Loading 0:  58%|█████▊    | 212/363 [00:05<00:04, 35.54it/s]
Loading 0:  60%|██████    | 219/363 [00:06<00:03, 42.92it/s]
Loading 0:  62%|██████▏   | 224/363 [00:06<00:03, 38.86it/s]
Loading 0:  63%|██████▎   | 229/363 [00:06<00:03, 37.15it/s]
Loading 0:  64%|██████▍   | 234/363 [00:06<00:03, 40.02it/s]
Loading 0:  66%|██████▌   | 239/363 [00:06<00:03, 40.36it/s]
Loading 0:  67%|██████▋   | 244/363 [00:06<00:03, 33.27it/s]
Loading 0:  68%|██████▊   | 248/363 [00:06<00:03, 33.34it/s]
Loading 0:  70%|██████▉   | 254/363 [00:07<00:03, 35.82it/s]
Loading 0:  71%|███████   | 258/363 [00:07<00:03, 34.14it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 35.07it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 35.01it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 35.93it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:01, 45.69it/s]
Loading 0:  79%|███████▉  | 288/363 [00:08<00:02, 35.00it/s]
Loading 0:  81%|████████  | 293/363 [00:08<00:01, 35.54it/s]
Loading 0:  83%|████████▎ | 302/363 [00:08<00:01, 43.48it/s]
Loading 0:  85%|████████▍ | 307/363 [00:08<00:01, 36.65it/s]
Loading 0:  86%|████████▌ | 312/363 [00:08<00:01, 37.32it/s]
Loading 0:  87%|████████▋ | 317/363 [00:08<00:01, 35.95it/s]
Loading 0:  88%|████████▊ | 321/363 [00:08<00:01, 34.30it/s]
Loading 0:  90%|█████████ | 327/363 [00:09<00:01, 34.07it/s]
Loading 0:  91%|█████████▏| 332/363 [00:09<00:00, 33.93it/s]
Loading 0:  93%|█████████▎| 338/363 [00:09<00:00, 34.80it/s]
Loading 0:  95%|█████████▍| 344/363 [00:09<00:00, 40.07it/s]
Loading 0:  96%|█████████▌| 349/363 [00:09<00:00, 26.86it/s]
Loading 0:  97%|█████████▋| 353/363 [00:10<00:00, 24.31it/s]
Loading 0:  98%|█████████▊| 357/363 [00:10<00:00, 25.89it/s]
                                                            
Job junhua024-chai-02-full-061-v3-mkmlizer completed after 128.41s with status: succeeded
Stopping job with name junhua024-chai-02-full-061-v3-mkmlizer
Pipeline stage MKMLizer completed in 128.91s
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-02-full-061-v3
Waiting for inference service junhua024-chai-02-full-061-v3 to be ready
Failed to get response for submission junhua024-chai-02-full-062_v2: HTTPConnectionPool(host='junhua024-chai-02-full-062-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission zmeeks-capitanito-50-1600_v3: HTTPConnectionPool(host='zmeeks-capitanito-50-1600-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission zmeeks-capitanito-50-1600_v2: HTTPConnectionPool(host='zmeeks-capitanito-50-1600-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-02-full-061-v3 ready after 271.2517066001892s
Pipeline stage MKMLDeployer completed in 271.83s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.320078134536743s
Received healthy response to inference request in 1.7800109386444092s
Received healthy response to inference request in 1.9419276714324951s
Received healthy response to inference request in 7.105423212051392s
Received healthy response to inference request in 2.1118669509887695s
5 requests
0 failed requests
5th percentile: 1.8123942852020263
10th percentile: 1.8447776317596436
20th percentile: 1.909544324874878
30th percentile: 1.97591552734375
40th percentile: 2.0438912391662596
50th percentile: 2.1118669509887695
60th percentile: 2.195151424407959
70th percentile: 2.2784358978271486
80th percentile: 3.277147150039674
90th percentile: 5.191285181045533
95th percentile: 6.148354196548461
99th percentile: 6.914009408950806
mean time: 3.051861381530762
Pipeline stage StressChecker completed in 16.89s
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 0.91s
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 0.74s
Shutdown handler de-registered
junhua024-chai-02-full-061_v3 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 4027.54s
Shutdown handler de-registered
junhua024-chai-02-full-061_v3 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-02-full-061_v3 status is now torndown due to DeploymentManager action
junhua024-chai-02-full-061_v3 status is now torndown due to DeploymentManager action