junhua024-chai-06-full-01

developer_uid: junhua024
submission_id: junhua024-chai-06-full-01_v2
model_name: junhua024-chai-06-full-01_v2
model_group: junhua024/chai_06_full_0
status: torndown
timestamp: 2025-07-16T21:19:05+00:00
num_battles: 7555
num_wins: 1254
celo_rating: 953.78
family_friendly_score: 0.8168
family_friendly_standard_error: 0.005470608010084437
submission_type: basic
model_repo: junhua024/chai_06_full_01
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': 0.5906926877107518, 'latency_mean': 1.6928289914131165, 'latency_p50': 1.6930640935897827, 'latency_p90': 1.8504194259643554}, {'batch_size': 3, 'throughput': 1.0520906495318856, 'latency_mean': 2.8401381039619444, 'latency_p50': 2.859230399131775, 'latency_p90': 3.1366130113601685}, {'batch_size': 5, 'throughput': 1.264998136630538, 'latency_mean': 3.933378293514252, 'latency_p50': 3.9304169416427612, 'latency_p90': 4.493533492088318}, {'batch_size': 6, 'throughput': 1.3174559195031086, 'latency_mean': 4.529885220527649, 'latency_p50': 4.52136754989624, 'latency_p90': 5.085692143440246}, {'batch_size': 8, 'throughput': 1.3911332627480004, 'latency_mean': 5.717405757904053, 'latency_p50': 5.672692060470581, 'latency_p90': 6.5117512226104735}, {'batch_size': 10, 'throughput': 1.4029604095489838, 'latency_mean': 7.076728774309158, 'latency_p50': 7.041540741920471, 'latency_p90': 8.050608229637145}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: junhua024-chai-06-full-01_v2
is_internal_developer: False
language_model: junhua024/chai_06_full_01
model_size: 13B
ranking_group: single
throughput_3p7s: 1.24
us_pacific_date: 2025-07-16
win_ratio: 0.16598279285241563
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-01-v2-mkmlizer
Waiting for job on junhua024-chai-06-full-01-v2-mkmlizer to finish
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): Read timed out. (read timeout=12.0)
junhua024-chai-06-full-01-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-06-full-01-v2-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-01-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-06-full-01-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-06-full-01-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-06-full-01-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-06-full-01-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-06-full-01-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-06-full-01-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-06-full-01-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-06-full-01-v2-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-01-v2-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-06-full-01-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-06-full-01-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-06-full-01-v2-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-06-full-01-v2-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-01-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-06-full-01-v2-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-06-full-01-v2-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-01-v2-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-06-full-01-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-06-full-01-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-06-full-01-v2-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-01-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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): Read timed out. (read timeout=12.0)
junhua024-chai-06-full-01-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-01-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-01-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-01-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-01-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-01-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-01-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-01-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-01-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-01-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-01-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-01-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-01-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-01-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-01-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-01-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-01-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-01-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-01-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-01-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-01-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-01-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-01-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-01-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-01-v2-mkmlizer: Downloaded to shared memory in 136.170s
junhua024-chai-06-full-01-v2-mkmlizer: Checking if junhua024/chai_06_full_01 already exists in ChaiML
junhua024-chai-06-full-01-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpv_7zkvze, device:0
junhua024-chai-06-full-01-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-06-full-01-v2-mkmlizer: quantized model in 31.410s
junhua024-chai-06-full-01-v2-mkmlizer: Processed model junhua024/chai_06_full_01 in 167.682s
junhua024-chai-06-full-01-v2-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-06-full-01-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-06-full-01-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-06-full-01-v2/nvidia
junhua024-chai-06-full-01-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-06-full-01-v2/nvidia/config.json
junhua024-chai-06-full-01-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-06-full-01-v2/nvidia/special_tokens_map.json
junhua024-chai-06-full-01-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-06-full-01-v2/nvidia/flywheel_model.0.safetensors
junhua024-chai-06-full-01-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:21, 16.47it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:18, 18.99it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 29.86it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:11, 30.92it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 33.83it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:06, 47.74it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:08, 37.75it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:08, 37.70it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:07, 42.37it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:08, 36.06it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:08, 34.81it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 36.97it/s]
Loading 0:  19%|█▉        | 69/363 [00:01<00:08, 35.31it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:08, 35.02it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:08, 33.68it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 39.02it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 38.41it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:07, 35.73it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:07, 34.24it/s]
Loading 0:  29%|██▉       | 105/363 [00:03<00:08, 30.91it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:06, 39.44it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:08, 30.22it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:07, 32.18it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:06, 34.04it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:07, 31.99it/s]
Loading 0:  38%|███▊      | 138/363 [00:03<00:06, 33.46it/s]
Loading 0:  39%|███▉      | 143/363 [00:04<00:06, 34.03it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:06, 34.39it/s]
Loading 0:  43%|████▎     | 155/363 [00:04<00:05, 39.59it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 37.68it/s]
Loading 0:  45%|████▌     | 164/363 [00:04<00:05, 37.46it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:05, 33.75it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:04, 40.33it/s]
Loading 0:  50%|████▉     | 181/363 [00:05<00:05, 34.72it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 33.09it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:05, 34.06it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:05, 32.58it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 34.36it/s]
Loading 0:  57%|█████▋    | 206/363 [00:05<00:04, 34.51it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:04, 35.36it/s]
Loading 0:  61%|██████    | 220/363 [00:06<00:03, 44.95it/s]
Loading 0:  62%|██████▏   | 225/363 [00:06<00:03, 34.64it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:03, 34.87it/s]
Loading 0:  66%|██████▌   | 239/363 [00:06<00:02, 43.22it/s]
Loading 0:  67%|██████▋   | 244/363 [00:06<00:03, 37.27it/s]
Loading 0:  69%|██████▊   | 249/363 [00:06<00:02, 38.05it/s]
Loading 0:  70%|██████▉   | 254/363 [00:07<00:02, 37.28it/s]
Loading 0:  71%|███████   | 258/363 [00:07<00:02, 35.89it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 35.38it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 32.82it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 32.59it/s]
Loading 0:  77%|███████▋  | 281/363 [00:07<00:02, 36.27it/s]
Loading 0:  79%|███████▉  | 286/363 [00:08<00:02, 34.28it/s]
Loading 0:  80%|███████▉  | 290/363 [00:08<00:02, 33.63it/s]
Loading 0:  81%|████████  | 294/363 [00:08<00:02, 31.59it/s]
Loading 0:  83%|████████▎ | 302/363 [00:08<00:01, 37.75it/s]
Loading 0:  84%|████████▍ | 306/363 [00:08<00:01, 29.23it/s]
Loading 0:  86%|████████▌ | 311/363 [00:08<00:01, 30.35it/s]
Loading 0:  87%|████████▋ | 317/363 [00:09<00:01, 31.39it/s]
Loading 0:  88%|████████▊ | 321/363 [00:09<00:01, 30.64it/s]
Loading 0:  90%|████████▉ | 326/363 [00:09<00:01, 34.22it/s]
Loading 0:  91%|█████████ | 330/363 [00:09<00:00, 33.90it/s]
Loading 0:  92%|█████████▏| 334/363 [00:09<00:01, 28.08it/s]
Loading 0:  93%|█████████▎| 338/363 [00:09<00:00, 27.46it/s]
Loading 0:  95%|█████████▍| 344/363 [00:09<00:00, 33.34it/s]
Loading 0:  96%|█████████▌| 349/363 [00:10<00:00, 24.36it/s]
Loading 0:  97%|█████████▋| 352/363 [00:10<00:00, 22.05it/s]
Loading 0:  98%|█████████▊| 357/363 [00:10<00:00, 25.99it/s]
                                                            
Job junhua024-chai-06-full-01-v2-mkmlizer completed after 191.38s with status: succeeded
Stopping job with name junhua024-chai-06-full-01-v2-mkmlizer
Pipeline stage MKMLizer completed in 191.95s
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-06-full-01-v2
Waiting for inference service junhua024-chai-06-full-01-v2 to be ready
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): Read timed out. (read timeout=12.0)
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): Read timed out. (read timeout=12.0)
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): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-06-full-01-v2 ready after 271.69947504997253s
Pipeline stage MKMLDeployer completed in 272.60s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4329707622528076s
Received healthy response to inference request in 1.6492719650268555s
Received healthy response to inference request in 1.7207303047180176s
Received healthy response to inference request in 1.657343864440918s
Received healthy response to inference request in 1.7869620323181152s
5 requests
0 failed requests
5th percentile: 1.650886344909668
10th percentile: 1.6525007247924806
20th percentile: 1.6557294845581054
30th percentile: 1.670021152496338
40th percentile: 1.6953757286071778
50th percentile: 1.7207303047180176
60th percentile: 1.7472229957580567
70th percentile: 1.7737156867980957
80th percentile: 1.9161637783050538
90th percentile: 2.1745672702789305
95th percentile: 2.303769016265869
99th percentile: 2.40713041305542
mean time: 1.8494557857513427
Pipeline stage StressChecker completed in 10.81s
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 0.81s
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-06-full-01_v2 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
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 10499.06s
Shutdown handler de-registered
junhua024-chai-06-full-01_v2 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-06-full-01_v2 status is now torndown due to DeploymentManager action
junhua024-chai-06-full-01_v2 status is now torndown due to DeploymentManager action