junhua024-chai-1-full-002

developer_uid: junhua024

submission_id: junhua024-chai-1-full-002_v2

model_name: junhua024-chai-1-full-002_v2

model_group: junhua024/chai_1-full_00

status: torndown

timestamp: 2025-06-28T15:26:34+00:00

num_battles: 7650

num_wins: 3481

celo_rating: 1244.32

family_friendly_score: 0.5942000000000001

family_friendly_standard_error: 0.006944441806221721

submission_type: basic

model_repo: junhua024/chai_1-full_002

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': 0.6042727442010001, 'latency_mean': 1.6547674882411956, 'latency_p50': 1.641147494316101, 'latency_p90': 1.8377117395401001}, {'batch_size': 3, 'throughput': 1.0752262279991547, 'latency_mean': 2.776823569536209, 'latency_p50': 2.7944469451904297, 'latency_p90': 3.0706460237503053}, {'batch_size': 5, 'throughput': 1.288468317246162, 'latency_mean': 3.863211381435394, 'latency_p50': 3.8133766651153564, 'latency_p90': 4.2991711616516115}, {'batch_size': 6, 'throughput': 1.3419081962743769, 'latency_mean': 4.434663654565811, 'latency_p50': 4.393494606018066, 'latency_p90': 5.0383291959762575}, {'batch_size': 8, 'throughput': 1.4120830691354342, 'latency_mean': 5.623407427072525, 'latency_p50': 5.590296030044556, 'latency_p90': 6.355752873420715}, {'batch_size': 10, 'throughput': 1.4333757526328326, 'latency_mean': 6.932324928045273, 'latency_p50': 6.939852595329285, 'latency_p90': 7.766206359863281}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-1-full-002_v2

is_internal_developer: False

language_model: junhua024/chai_1-full_002

model_size: 13B

ranking_group: single

throughput_3p7s: 1.27

us_pacific_date: 2025-06-28

win_ratio: 0.4550326797385621

generation_params: {'temperature': 0.8, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n', '<|im_end|>'], '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-1-full-002-v2-mkmlizer
Waiting for job on junhua024-chai-1-full-002-v2-mkmlizer to finish
junhua024-chai-1-full-002-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-1-full-002-v2-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-1-full-002-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-1-full-002-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-1-full-002-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-1-full-002-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-1-full-002-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-1-full-002-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-1-full-002-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-1-full-002-v2-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v2-mkmlizer: ║  Version: 0.29.3                                                    ║
junhua024-chai-1-full-002-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-1-full-002-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-1-full-002-v2-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-1-full-002-v2-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-1-full-002-v2-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-1-full-002-v2-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v2-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-1-full-002-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-1-full-002-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-1-full-002-v2-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-v2-mkmlizer: Downloaded to shared memory in 128.134s
junhua024-chai-1-full-002-v2-mkmlizer: Checking if junhua024/chai_1-full_002 already exists in ChaiML
junhua024-chai-1-full-002-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphpuu5jdi, device:0
junhua024-chai-1-full-002-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-1-full-002-v2-mkmlizer: quantized model in 31.416s
junhua024-chai-1-full-002-v2-mkmlizer: Processed model junhua024/chai_1-full_002 in 159.636s
junhua024-chai-1-full-002-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-1-full-002-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-1-full-002-v2
junhua024-chai-1-full-002-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v2/config.json
junhua024-chai-1-full-002-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v2/special_tokens_map.json
junhua024-chai-1-full-002-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v2/tokenizer_config.json
junhua024-chai-1-full-002-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v2/tokenizer.json
junhua024-chai-1-full-002-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-1-full-002-v2/flywheel_model.0.safetensors
junhua024-chai-1-full-002-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:24, 14.62it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:20, 17.75it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:12, 28.76it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:11, 29.90it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 32.25it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 43.33it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:10, 32.11it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:09, 33.01it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:07, 40.13it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:08, 34.74it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:08, 33.97it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 33.79it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:08, 33.21it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:07, 36.79it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:07, 37.40it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:08, 31.56it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:08, 33.41it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 34.26it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:07, 33.62it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:07, 33.65it/s]
Loading 0:  29%|██▉       | 105/363 [00:03<00:08, 31.54it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:06, 37.64it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:08, 30.59it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:07, 32.59it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:06, 34.43it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:06, 33.70it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:06, 37.24it/s]
Loading 0:  39%|███▉      | 141/363 [00:04<00:05, 37.46it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:06, 32.20it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:06, 31.22it/s]
Loading 0:  43%|████▎     | 155/363 [00:04<00:05, 37.94it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 36.03it/s]
Loading 0:  45%|████▌     | 164/363 [00:04<00:05, 35.27it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:05, 32.91it/s]
Loading 0:  48%|████▊     | 175/363 [00:05<00:04, 41.55it/s]
Loading 0:  50%|████▉     | 180/363 [00:05<00:06, 30.31it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 31.71it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:05, 33.27it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:05, 32.69it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 32.89it/s]
Loading 0:  57%|█████▋    | 206/363 [00:06<00:04, 32.30it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:04, 33.40it/s]
Loading 0:  60%|██████    | 218/363 [00:06<00:03, 37.50it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:04, 33.90it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:04, 33.20it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 31.49it/s]
Loading 0:  66%|██████▌   | 239/363 [00:07<00:03, 37.81it/s]
Loading 0:  67%|██████▋   | 243/363 [00:07<00:03, 31.47it/s]
Loading 0:  68%|██████▊   | 248/363 [00:07<00:03, 33.82it/s]
Loading 0:  70%|██████▉   | 254/363 [00:07<00:03, 35.12it/s]
Loading 0:  71%|███████   | 258/363 [00:07<00:03, 34.07it/s]
Loading 0:  72%|███████▏  | 263/363 [00:07<00:02, 37.68it/s]
Loading 0:  74%|███████▎  | 267/363 [00:07<00:02, 37.97it/s]
Loading 0:  75%|███████▍  | 271/363 [00:07<00:02, 32.99it/s]
Loading 0:  76%|███████▌  | 275/363 [00:08<00:02, 31.53it/s]
Loading 0:  77%|███████▋  | 281/363 [00:08<00:02, 38.14it/s]
Loading 0:  79%|███████▉  | 286/363 [00:08<00:02, 34.69it/s]
Loading 0:  80%|███████▉  | 290/363 [00:08<00:02, 34.38it/s]
Loading 0:  81%|████████  | 294/363 [00:08<00:02, 31.91it/s]
Loading 0:  82%|████████▏ | 299/363 [00:08<00:01, 36.09it/s]
Loading 0:  83%|████████▎ | 303/363 [00:08<00:01, 32.51it/s]
Loading 0:  85%|████████▍ | 307/363 [00:09<00:01, 32.19it/s]
Loading 0:  86%|████████▌ | 311/363 [00:09<00:01, 31.57it/s]
Loading 0:  87%|████████▋ | 317/363 [00:09<00:01, 33.47it/s]
Loading 0:  88%|████████▊ | 321/363 [00:09<00:01, 33.20it/s]
Loading 0:  90%|█████████ | 327/363 [00:09<00:01, 33.17it/s]
Loading 0:  91%|█████████▏| 332/363 [00:09<00:00, 32.33it/s]
Loading 0:  93%|█████████▎| 338/363 [00:09<00:00, 33.54it/s]
Loading 0:  94%|█████████▍| 343/363 [00:10<00:00, 36.70it/s]
Loading 0:  96%|█████████▌| 348/363 [00:10<00:00, 39.39it/s]
Loading 0:  97%|█████████▋| 353/363 [00:10<00:00, 22.18it/s]
Loading 0:  98%|█████████▊| 357/363 [00:10<00:00, 24.05it/s]
                                                            
Job junhua024-chai-1-full-002-v2-mkmlizer completed after 187.92s with status: succeeded
Stopping job with name junhua024-chai-1-full-002-v2-mkmlizer
Pipeline stage MKMLizer completed in 188.43s
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-1-full-002-v2
Waiting for inference service junhua024-chai-1-full-002-v2 to be ready
Failed to get response for submission junhua024-chai-1-full-002_v1: HTTPConnectionPool(host='junhua024-chai-1-full-002-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission junhua024-chai-1-full-002_v1: HTTPConnectionPool(host='junhua024-chai-1-full-002-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-1-full-002-v2 ready after 160.6670548915863s
Pipeline stage MKMLDeployer completed in 161.22s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.560549736022949s
Received healthy response to inference request in 1.6306116580963135s
Received healthy response to inference request in 1.6450037956237793s
Received healthy response to inference request in 1.542442798614502s
Received healthy response to inference request in 1.660041093826294s
5 requests
0 failed requests
5th percentile: 1.5600765705108643
10th percentile: 1.5777103424072265
20th percentile: 1.612977886199951
30th percentile: 1.6334900856018066
40th percentile: 1.639246940612793
50th percentile: 1.6450037956237793
60th percentile: 1.6510187149047852
70th percentile: 1.657033634185791
80th percentile: 1.840142822265625
90th percentile: 2.2003462791442874
95th percentile: 2.380448007583618
99th percentile: 2.524529390335083
mean time: 1.8077298164367677
Pipeline stage StressChecker completed in 10.63s
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 0.80s
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 0.73s
Shutdown handler de-registered
junhua024-chai-1-full-002_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3135.90s
Shutdown handler de-registered
junhua024-chai-1-full-002_v2 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-1-full-002_v2 status is now torndown due to DeploymentManager action