junhua024-chai-02-full-061

developer_uid: junhua024

submission_id: junhua024-chai-02-full-061_v2

model_name: junhua024-chai-02-full-061_v2

model_group: junhua024/chai_02_full_0

status: torndown

timestamp: 2025-07-16T14:08:57+00:00

num_battles: 9035

num_wins: 4454

celo_rating: 1276.07

family_friendly_score: 0.5534

family_friendly_standard_error: 0.007030625007778469

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': 0.5805506299817844, 'latency_mean': 1.7223445427417756, 'latency_p50': 1.7301477193832397, 'latency_p90': 1.8845654010772706}, {'batch_size': 3, 'throughput': 1.0337237097090546, 'latency_mean': 2.8884114134311676, 'latency_p50': 2.875040054321289, 'latency_p90': 3.174839186668396}, {'batch_size': 5, 'throughput': 1.2363987843755724, 'latency_mean': 4.027342995405197, 'latency_p50': 4.046600818634033, 'latency_p90': 4.4186502456665036}, {'batch_size': 6, 'throughput': 1.279866972810994, 'latency_mean': 4.649946960210801, 'latency_p50': 4.678068280220032, 'latency_p90': 5.165667581558227}, {'batch_size': 8, 'throughput': 1.363916150307982, 'latency_mean': 5.834952323436737, 'latency_p50': 5.792910814285278, 'latency_p90': 6.643672227859497}, {'batch_size': 10, 'throughput': 1.3969197720261612, 'latency_mean': 7.111437662839889, 'latency_p50': 7.065439820289612, 'latency_p90': 8.087024903297424}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-02-full-061_v2

is_internal_developer: False

language_model: junhua024/chai_02_full_061

model_size: 13B

ranking_group: single

throughput_3p7s: 1.2

us_pacific_date: 2025-07-16

win_ratio: 0.49297177642501383

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-v2-mkmlizer
Waiting for job on junhua024-chai-02-full-061-v2-mkmlizer to finish
junhua024-chai-02-full-061-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-02-full-061-v2-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-061-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-02-full-061-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-02-full-061-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-02-full-061-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-02-full-061-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-02-full-061-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-02-full-061-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-02-full-061-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-02-full-061-v2-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-061-v2-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-02-full-061-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-02-full-061-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-02-full-061-v2-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-02-full-061-v2-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-061-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-02-full-061-v2-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-02-full-061-v2-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-061-v2-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-02-full-061-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-02-full-061-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-02-full-061-v2-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-061-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-02-full-061-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-02-full-061-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-02-full-061-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-02-full-061-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-02-full-061-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-02-full-061-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-02-full-061-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-02-full-061-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-02-full-061-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-02-full-061-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-02-full-061-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-02-full-061-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-02-full-061-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-02-full-061-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-02-full-061-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-02-full-061-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-02-full-061-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-02-full-061-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-02-full-061-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-02-full-061-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-02-full-061-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-02-full-061-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-02-full-061-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-02-full-061-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-02-full-061-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-02-full-061-v2-mkmlizer: Downloaded to shared memory in 127.267s
junhua024-chai-02-full-061-v2-mkmlizer: Checking if junhua024/chai_02_full_061 already exists in ChaiML
junhua024-chai-02-full-061-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxzzlp37p, device:0
junhua024-chai-02-full-061-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-02-full-061-v2-mkmlizer: quantized model in 31.027s
junhua024-chai-02-full-061-v2-mkmlizer: Processed model junhua024/chai_02_full_061 in 158.380s
junhua024-chai-02-full-061-v2-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-02-full-061-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-02-full-061-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-02-full-061-v2/nvidia
junhua024-chai-02-full-061-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-02-full-061-v2/nvidia/config.json
junhua024-chai-02-full-061-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-02-full-061-v2/nvidia/special_tokens_map.json
junhua024-chai-02-full-061-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-02-full-061-v2/nvidia/tokenizer_config.json
junhua024-chai-02-full-061-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-02-full-061-v2/nvidia/tokenizer.json
junhua024-chai-02-full-061-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-02-full-061-v2/nvidia/flywheel_model.0.safetensors
junhua024-chai-02-full-061-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:25, 14.41it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:20, 17.28it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 29.49it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:11, 30.80it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 32.78it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 46.20it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:09, 36.10it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:08, 35.89it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:07, 40.43it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:08, 34.54it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:08, 34.13it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 36.00it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:08, 34.97it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:08, 34.81it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:08, 32.31it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 37.30it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 37.00it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:07, 36.72it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:07, 35.35it/s]
Loading 0:  29%|██▉       | 105/363 [00:03<00:07, 33.58it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:06, 40.45it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:07, 34.06it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:07, 32.39it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:07, 33.04it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:07, 32.49it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 33.44it/s]
Loading 0:  39%|███▉      | 143/363 [00:04<00:06, 33.65it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:06, 34.78it/s]
Loading 0:  43%|████▎     | 155/363 [00:04<00:05, 39.27it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 37.42it/s]
Loading 0:  45%|████▌     | 164/363 [00:04<00:05, 37.44it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:05, 35.13it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:04, 42.02it/s]
Loading 0:  50%|████▉     | 181/363 [00:05<00:05, 35.44it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 34.84it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:04, 36.31it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:04, 34.82it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 34.29it/s]
Loading 0:  57%|█████▋    | 206/363 [00:05<00:04, 33.78it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:04, 34.58it/s]
Loading 0:  61%|██████    | 220/363 [00:06<00:03, 43.80it/s]
Loading 0:  62%|██████▏   | 225/363 [00:06<00:04, 33.64it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:03, 33.95it/s]
Loading 0:  66%|██████▌   | 239/363 [00:06<00:03, 41.23it/s]
Loading 0:  67%|██████▋   | 244/363 [00:06<00:03, 34.96it/s]
Loading 0:  68%|██████▊   | 248/363 [00:07<00:03, 32.90it/s]
Loading 0:  70%|██████▉   | 254/363 [00:07<00:03, 33.59it/s]
Loading 0:  71%|███████   | 258/363 [00:07<00:03, 32.46it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:03, 32.43it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 32.39it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 33.71it/s]
Loading 0:  77%|███████▋  | 281/363 [00:07<00:02, 38.31it/s]
Loading 0:  79%|███████▉  | 286/363 [00:08<00:02, 37.02it/s]
Loading 0:  80%|███████▉  | 290/363 [00:08<00:01, 37.21it/s]
Loading 0:  81%|████████  | 294/363 [00:08<00:01, 35.24it/s]
Loading 0:  83%|████████▎ | 302/363 [00:08<00:01, 42.60it/s]
Loading 0:  85%|████████▍ | 307/363 [00:08<00:01, 35.03it/s]
Loading 0:  86%|████████▌ | 311/363 [00:08<00:01, 34.15it/s]
Loading 0:  87%|████████▋ | 317/363 [00:08<00:01, 36.12it/s]
Loading 0:  88%|████████▊ | 321/363 [00:09<00:01, 33.80it/s]
Loading 0:  90%|█████████ | 327/363 [00:09<00:01, 34.06it/s]
Loading 0:  91%|█████████▏| 332/363 [00:09<00:00, 34.20it/s]
Loading 0:  93%|█████████▎| 338/363 [00:09<00:00, 35.47it/s]
Loading 0:  95%|█████████▌| 346/363 [00:09<00:00, 44.76it/s]
Loading 0:  97%|█████████▋| 351/363 [00:10<00:00, 24.82it/s]
Loading 0:  98%|█████████▊| 355/363 [00:10<00:00, 27.05it/s]
Loading 0:  99%|█████████▉| 360/363 [00:10<00:00, 30.91it/s]
                                                            
Job junhua024-chai-02-full-061-v2-mkmlizer completed after 181.33s with status: succeeded
Stopping job with name junhua024-chai-02-full-061-v2-mkmlizer
Pipeline stage MKMLizer completed in 181.85s
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-v2
Waiting for inference service junhua024-chai-02-full-061-v2 to be ready
Failed to get response for submission junhua024-chai-02-full-061_v1: HTTPConnectionPool(host='junhua024-chai-02-full-061-v1-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_v4: HTTPConnectionPool(host='zmeeks-capitanito-50-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-02-full-061-v2 ready after 261.30195140838623s
Pipeline stage MKMLDeployer completed in 261.85s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.345167636871338s
Received healthy response to inference request in 1.8380424976348877s
Received healthy response to inference request in 1.675504446029663s
Received healthy response to inference request in 2.0145645141601562s
Received healthy response to inference request in 1.7233405113220215s
5 requests
0 failed requests
5th percentile: 1.6850716590881347
10th percentile: 1.6946388721466064
20th percentile: 1.7137732982635498
30th percentile: 1.7462809085845947
40th percentile: 1.7921617031097412
50th percentile: 1.8380424976348877
60th percentile: 1.908651304244995
70th percentile: 1.9792601108551025
80th percentile: 2.0806851387023926
90th percentile: 2.2129263877868652
95th percentile: 2.2790470123291016
99th percentile: 2.3319435119628906
mean time: 1.9193239212036133
Pipeline stage StressChecker completed in 11.13s
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 0.78s
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 0.79s
Shutdown handler de-registered
junhua024-chai-02-full-061_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 6137.63s
Shutdown handler de-registered
junhua024-chai-02-full-061_v2 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-02-full-061_v2 status is now torndown due to DeploymentManager action
junhua024-chai-02-full-061_v2 status is now torndown due to DeploymentManager action