junhua024-chai-1-full-002

developer_uid: junhua024

submission_id: junhua024-chai-1-full-002_v3

model_name: junhua024-chai-1-full-002_v3

model_group: junhua024/chai_1-full_00

status: torndown

timestamp: 2025-06-29T00:17:19+00:00

num_battles: 6595

num_wins: 2985

celo_rating: 1249.23

family_friendly_score: 0.5871999999999999

family_friendly_standard_error: 0.006962702923434261

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': 0.5941059941208521, 'latency_mean': 1.6830190896987915, 'latency_p50': 1.675912618637085, 'latency_p90': 1.8576557397842406}, {'batch_size': 3, 'throughput': 1.0807905302514, 'latency_mean': 2.7660652017593383, 'latency_p50': 2.7489254474639893, 'latency_p90': 3.116547393798828}, {'batch_size': 5, 'throughput': 1.2745233399914146, 'latency_mean': 3.9013959872722626, 'latency_p50': 3.8795281648635864, 'latency_p90': 4.379304361343384}, {'batch_size': 6, 'throughput': 1.3510742922842331, 'latency_mean': 4.416657133102417, 'latency_p50': 4.407788991928101, 'latency_p90': 4.98057541847229}, {'batch_size': 8, 'throughput': 1.4250849220590258, 'latency_mean': 5.572339828014374, 'latency_p50': 5.612869620323181, 'latency_p90': 6.265273809432983}, {'batch_size': 10, 'throughput': 1.4438804137404173, 'latency_mean': 6.855259463787079, 'latency_p50': 6.8956040143966675, 'latency_p90': 7.658715724945068}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-1-full-002_v3

is_internal_developer: False

language_model: junhua024/chai_1-full_002

model_size: 13B

ranking_group: single

throughput_3p7s: 1.26

us_pacific_date: 2025-06-28

win_ratio: 0.45261561789234267

generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, '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-1-full-002-v3-mkmlizer
Waiting for job on junhua024-chai-1-full-002-v3-mkmlizer to finish
junhua024-chai-1-full-002-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-1-full-002-v3-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-1-full-002-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-1-full-002-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-1-full-002-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-1-full-002-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-1-full-002-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-1-full-002-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-1-full-002-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-1-full-002-v3-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v3-mkmlizer: ║  Version: 0.29.3                                                    ║
junhua024-chai-1-full-002-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-1-full-002-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-1-full-002-v3-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-1-full-002-v3-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-1-full-002-v3-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-1-full-002-v3-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v3-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-1-full-002-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-1-full-002-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-1-full-002-v3-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-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-1-full-002-v3-mkmlizer: Downloaded to shared memory in 81.354s
junhua024-chai-1-full-002-v3-mkmlizer: Checking if junhua024/chai_1-full_002 already exists in ChaiML
junhua024-chai-1-full-002-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmptwx3s9n4, device:0
junhua024-chai-1-full-002-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-1-full-002-v3-mkmlizer: quantized model in 32.104s
junhua024-chai-1-full-002-v3-mkmlizer: Processed model junhua024/chai_1-full_002 in 113.551s
junhua024-chai-1-full-002-v3-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-1-full-002-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-1-full-002-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-1-full-002-v3
junhua024-chai-1-full-002-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v3/config.json
junhua024-chai-1-full-002-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v3/special_tokens_map.json
junhua024-chai-1-full-002-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v3/tokenizer_config.json
junhua024-chai-1-full-002-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v3/tokenizer.json
junhua024-chai-1-full-002-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-1-full-002-v3/flywheel_model.0.safetensors
junhua024-chai-1-full-002-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:23, 15.45it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:19, 17.92it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:12, 28.29it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:11, 29.53it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 31.90it/s]
Loading 0:   8%|▊         | 29/363 [00:00<00:08, 38.32it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:09, 35.42it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:09, 34.95it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:09, 32.34it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:08, 38.56it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:10, 30.31it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:09, 32.26it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:09, 32.81it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:09, 31.59it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:08, 34.98it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:08, 35.39it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:09, 30.90it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:08, 32.76it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 32.11it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:07, 33.43it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:07, 33.38it/s]
Loading 0:  29%|██▉       | 105/363 [00:03<00:08, 30.76it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:06, 36.90it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:08, 30.11it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:07, 31.87it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:07, 32.76it/s]
Loading 0:  36%|███▋      | 132/363 [00:04<00:07, 31.99it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:06, 35.31it/s]
Loading 0:  39%|███▉      | 141/363 [00:04<00:06, 35.83it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:07, 30.75it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:07, 30.00it/s]
Loading 0:  43%|████▎     | 155/363 [00:04<00:05, 36.43it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 34.99it/s]
Loading 0:  45%|████▌     | 164/363 [00:04<00:05, 34.19it/s]
Loading 0:  46%|████▋     | 168/363 [00:05<00:06, 31.89it/s]
Loading 0:  48%|████▊     | 176/363 [00:05<00:04, 38.08it/s]
Loading 0:  50%|████▉     | 180/363 [00:05<00:05, 30.91it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 32.30it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:05, 32.47it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:05, 31.87it/s]
Loading 0:  55%|█████▌    | 201/363 [00:06<00:05, 32.38it/s]
Loading 0:  57%|█████▋    | 206/363 [00:06<00:04, 32.08it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:04, 32.86it/s]
Loading 0:  60%|██████    | 218/363 [00:06<00:03, 37.23it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:04, 33.92it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:04, 33.62it/s]
Loading 0:  64%|██████▎   | 231/363 [00:07<00:04, 31.13it/s]
Loading 0:  66%|██████▌   | 238/363 [00:07<00:03, 39.68it/s]
Loading 0:  67%|██████▋   | 243/363 [00:07<00:04, 29.81it/s]
Loading 0:  68%|██████▊   | 248/363 [00:07<00:03, 31.62it/s]
Loading 0:  70%|██████▉   | 254/363 [00:07<00:03, 33.18it/s]
Loading 0:  71%|███████   | 258/363 [00:07<00:03, 32.15it/s]
Loading 0:  72%|███████▏  | 263/363 [00:07<00:02, 35.13it/s]
Loading 0:  74%|███████▎  | 267/363 [00:08<00:02, 35.73it/s]
Loading 0:  75%|███████▍  | 271/363 [00:08<00:02, 30.94it/s]
Loading 0:  76%|███████▌  | 275/363 [00:08<00:02, 29.84it/s]
Loading 0:  77%|███████▋  | 281/363 [00:08<00:02, 35.98it/s]
Loading 0:  79%|███████▉  | 286/363 [00:08<00:02, 34.23it/s]
Loading 0:  80%|███████▉  | 290/363 [00:08<00:02, 32.85it/s]
Loading 0:  81%|████████  | 294/363 [00:08<00:02, 30.67it/s]
Loading 0:  82%|████████▏ | 298/363 [00:09<00:01, 32.78it/s]
Loading 0:  83%|████████▎ | 303/363 [00:09<00:01, 31.68it/s]
Loading 0:  85%|████████▍ | 307/363 [00:09<00:01, 30.99it/s]
Loading 0:  86%|████████▌ | 311/363 [00:09<00:01, 30.76it/s]
Loading 0:  87%|████████▋ | 317/363 [00:09<00:01, 32.45it/s]
Loading 0:  88%|████████▊ | 321/363 [00:09<00:01, 32.19it/s]
Loading 0:  90%|█████████ | 327/363 [00:09<00:01, 33.03it/s]
Loading 0:  91%|█████████▏| 332/363 [00:10<00:00, 32.01it/s]
Loading 0:  93%|█████████▎| 338/363 [00:10<00:00, 33.33it/s]
Loading 0:  95%|█████████▍| 344/363 [00:10<00:00, 37.98it/s]
Loading 0:  96%|█████████▌| 349/363 [00:10<00:00, 26.24it/s]
Loading 0:  97%|█████████▋| 353/363 [00:10<00:00, 24.16it/s]
Loading 0:  98%|█████████▊| 357/363 [00:11<00:00, 25.93it/s]
                                                            
Job junhua024-chai-1-full-002-v3-mkmlizer completed after 137.27s with status: succeeded
Stopping job with name junhua024-chai-1-full-002-v3-mkmlizer
Pipeline stage MKMLizer completed in 137.76s
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-v3
Waiting for inference service junhua024-chai-1-full-002-v3 to be ready
Inference service junhua024-chai-1-full-002-v3 ready after 170.58591532707214s
Pipeline stage MKMLDeployer completed in 171.24s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9465551376342773s
Received healthy response to inference request in 1.6759681701660156s
Received healthy response to inference request in 1.696228265762329s
Received healthy response to inference request in 1.373896598815918s
Received healthy response to inference request in 1.7114408016204834s
5 requests
0 failed requests
5th percentile: 1.4343109130859375
10th percentile: 1.494725227355957
20th percentile: 1.615553855895996
30th percentile: 1.6800201892852784
40th percentile: 1.6881242275238038
50th percentile: 1.696228265762329
60th percentile: 1.702313280105591
70th percentile: 1.7083982944488525
80th percentile: 1.7584636688232422
90th percentile: 1.8525094032287597
95th percentile: 1.8995322704315185
99th percentile: 1.9371505641937257
mean time: 1.6808177947998046
Pipeline stage StressChecker completed in 9.72s
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 0.87s
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 0.65s
Shutdown handler de-registered
junhua024-chai-1-full-002_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 2928.33s
Shutdown handler de-registered
junhua024-chai-1-full-002_v3 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-1-full-002_v3 status is now torndown due to DeploymentManager action