junhua024-chai-1-full-066126

developer_uid: junhua024

submission_id: junhua024-chai-1-full-066126_v8

model_name: junhua024-chai-1-full-066126_v8

model_group: junhua024/chai-1-full-06

status: torndown

timestamp: 2025-06-29T20:33:19+00:00

num_battles: 6511

num_wins: 3342

celo_rating: 1277.86

family_friendly_score: 0.552

family_friendly_standard_error: 0.007032723512267492

submission_type: basic

model_repo: junhua024/chai-1-full-066126

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': 0.5992386090894936, 'latency_mean': 1.6686189293861389, 'latency_p50': 1.6754040718078613, 'latency_p90': 1.8378095149993896}, {'batch_size': 3, 'throughput': 1.084918642664115, 'latency_mean': 2.7544520032405853, 'latency_p50': 2.745209813117981, 'latency_p90': 3.0401453018188476}, {'batch_size': 5, 'throughput': 1.3014024485278997, 'latency_mean': 3.825962928533554, 'latency_p50': 3.8172340393066406, 'latency_p90': 4.252863550186158}, {'batch_size': 6, 'throughput': 1.3749739078354555, 'latency_mean': 4.345441293716431, 'latency_p50': 4.325270414352417, 'latency_p90': 4.901747131347657}, {'batch_size': 8, 'throughput': 1.4274727096588844, 'latency_mean': 5.565694313049317, 'latency_p50': 5.577868461608887, 'latency_p90': 6.270992469787598}, {'batch_size': 10, 'throughput': 1.4642188837821468, 'latency_mean': 6.764441163539886, 'latency_p50': 6.811468124389648, 'latency_p90': 7.580266618728637}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-1-full-066126_v8

is_internal_developer: False

language_model: junhua024/chai-1-full-066126

model_size: 13B

ranking_group: single

throughput_3p7s: 1.29

us_pacific_date: 2025-06-29

win_ratio: 0.5132852096452157

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.2, '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': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{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-066126-v8-mkmlizer
Waiting for job on junhua024-chai-1-full-066126-v8-mkmlizer to finish
junhua024-chai-1-full-066126-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-1-full-066126-v8-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v8-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-1-full-066126-v8-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-1-full-066126-v8-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-1-full-066126-v8-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-1-full-066126-v8-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-1-full-066126-v8-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-1-full-066126-v8-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-1-full-066126-v8-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-1-full-066126-v8-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v8-mkmlizer: ║  Version: 0.29.3                                                    ║
junhua024-chai-1-full-066126-v8-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-1-full-066126-v8-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-1-full-066126-v8-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-1-full-066126-v8-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v8-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-1-full-066126-v8-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-1-full-066126-v8-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v8-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-1-full-066126-v8-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-1-full-066126-v8-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-1-full-066126-v8-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-1-full-066126-v8-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-066126-v8-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-066126-v8-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-066126-v8-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-066126-v8-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-066126-v8-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-066126-v8-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-066126-v8-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-066126-v8-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-066126-v8-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-066126-v8-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-066126-v8-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-066126-v8-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-066126-v8-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-066126-v8-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-066126-v8-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`
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
junhua024-chai-1-full-066126-v8-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-066126-v8-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-066126-v8-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-066126-v8-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-066126-v8-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-066126-v8-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-066126-v8-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-066126-v8-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-066126-v8-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-066126-v8-mkmlizer: Downloaded to shared memory in 80.369s
junhua024-chai-1-full-066126-v8-mkmlizer: Checking if junhua024/chai-1-full-066126 already exists in ChaiML
junhua024-chai-1-full-066126-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjc085a5w, device:0
junhua024-chai-1-full-066126-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-1-full-066126-v8-mkmlizer: quantized model in 32.911s
junhua024-chai-1-full-066126-v8-mkmlizer: Processed model junhua024/chai-1-full-066126 in 113.408s
junhua024-chai-1-full-066126-v8-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-1-full-066126-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v8/config.json
junhua024-chai-1-full-066126-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v8/special_tokens_map.json
junhua024-chai-1-full-066126-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v8/tokenizer_config.json
junhua024-chai-1-full-066126-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v8/tokenizer.json
junhua024-chai-1-full-066126-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v8/flywheel_model.0.safetensors
junhua024-chai-1-full-066126-v8-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:24, 14.86it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:20, 17.26it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:12, 27.83it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:11, 29.11it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 31.43it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:08, 40.36it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:09, 35.32it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:09, 34.50it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:09, 34.02it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:08, 38.01it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:10, 30.13it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:09, 32.15it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:08, 33.38it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:09, 32.37it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:08, 35.98it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:07, 36.46it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:08, 31.49it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:08, 33.11it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 33.27it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:07, 34.43it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:07, 34.48it/s]
Loading 0:  29%|██▉       | 105/363 [00:03<00:08, 31.91it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:06, 37.33it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:08, 29.72it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:07, 31.03it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:07, 32.72it/s]
Loading 0:  36%|███▋      | 132/363 [00:04<00:07, 32.03it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:06, 35.04it/s]
Loading 0:  39%|███▉      | 141/363 [00:04<00:06, 35.97it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:06, 31.54it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:07, 27.40it/s]
Loading 0:  43%|████▎     | 155/363 [00:04<00:06, 33.17it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:06, 31.92it/s]
Loading 0:  45%|████▌     | 164/363 [00:05<00:06, 32.07it/s]
Loading 0:  46%|████▋     | 168/363 [00:05<00:06, 30.14it/s]
Loading 0:  48%|████▊     | 175/363 [00:05<00:04, 39.00it/s]
Loading 0:  50%|████▉     | 180/363 [00:05<00:06, 28.28it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 30.68it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:05, 32.37it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:05, 31.56it/s]
Loading 0:  55%|█████▌    | 200/363 [00:06<00:04, 35.22it/s]
Loading 0:  56%|█████▌    | 204/363 [00:06<00:04, 36.16it/s]
Loading 0:  57%|█████▋    | 208/363 [00:06<00:04, 31.04it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:05, 29.96it/s]
Loading 0:  60%|██████    | 218/363 [00:06<00:03, 36.48it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:04, 34.72it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:03, 34.35it/s]
Loading 0:  64%|██████▎   | 231/363 [00:07<00:04, 31.81it/s]
Loading 0:  65%|██████▌   | 237/363 [00:07<00:03, 38.28it/s]
Loading 0:  67%|██████▋   | 242/363 [00:07<00:03, 31.47it/s]
Loading 0:  68%|██████▊   | 246/363 [00:07<00:03, 30.79it/s]
Loading 0:  69%|██████▉   | 250/363 [00:07<00:03, 31.68it/s]
Loading 0:  70%|██████▉   | 254/363 [00:07<00:03, 29.73it/s]
Loading 0:  71%|███████   | 258/363 [00:07<00:03, 29.50it/s]
Loading 0:  73%|███████▎  | 264/363 [00:08<00:03, 30.69it/s]
Loading 0:  74%|███████▍  | 269/363 [00:08<00:03, 30.72it/s]
Loading 0:  76%|███████▌  | 275/363 [00:08<00:02, 32.34it/s]
Loading 0:  77%|███████▋  | 281/363 [00:08<00:02, 36.72it/s]
Loading 0:  79%|███████▉  | 286/363 [00:08<00:02, 32.84it/s]
Loading 0:  80%|███████▉  | 290/363 [00:08<00:02, 32.27it/s]
Loading 0:  81%|████████  | 294/363 [00:09<00:02, 30.61it/s]
Loading 0:  82%|████████▏ | 299/363 [00:09<00:01, 34.76it/s]
Loading 0:  83%|████████▎ | 303/363 [00:09<00:01, 31.70it/s]
Loading 0:  85%|████████▍ | 307/363 [00:09<00:01, 31.23it/s]
Loading 0:  86%|████████▌ | 311/363 [00:09<00:01, 30.44it/s]
Loading 0:  87%|████████▋ | 317/363 [00:09<00:01, 32.52it/s]
Loading 0:  88%|████████▊ | 321/363 [00:09<00:01, 31.71it/s]
Loading 0:  90%|████████▉ | 326/363 [00:09<00:01, 35.36it/s]
Loading 0:  91%|█████████ | 330/363 [00:10<00:00, 35.82it/s]
Loading 0:  92%|█████████▏| 334/363 [00:10<00:00, 29.36it/s]
Loading 0:  93%|█████████▎| 338/363 [00:10<00:00, 28.87it/s]
Loading 0:  95%|█████████▍| 344/363 [00:10<00:00, 35.34it/s]
Loading 0:  96%|█████████▌| 349/363 [00:10<00:00, 24.02it/s]
Loading 0:  97%|█████████▋| 353/363 [00:11<00:00, 22.55it/s]
Loading 0:  98%|█████████▊| 357/363 [00:11<00:00, 24.41it/s]
                                                            
Job junhua024-chai-1-full-066126-v8-mkmlizer completed after 146.71s with status: succeeded
Stopping job with name junhua024-chai-1-full-066126-v8-mkmlizer
Pipeline stage MKMLizer completed in 147.24s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-1-full-066126-v8
Waiting for inference service junhua024-chai-1-full-066126-v8 to be ready
Inference service junhua024-chai-1-full-066126-v8 ready after 382.68219447135925s
Pipeline stage MKMLDeployer completed in 383.32s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6392605304718018s
Received healthy response to inference request in 1.7370731830596924s
Received healthy response to inference request in 1.5291907787322998s
Received healthy response to inference request in 1.9995431900024414s
Received healthy response to inference request in 1.9451711177825928s
5 requests
0 failed requests
5th percentile: 1.5707672595977784
10th percentile: 1.6123437404632568
20th percentile: 1.6954967021942138
30th percentile: 1.7786927700042725
40th percentile: 1.8619319438934325
50th percentile: 1.9451711177825928
60th percentile: 1.9669199466705323
70th percentile: 1.9886687755584718
80th percentile: 2.1274866580963137
90th percentile: 2.3833735942840577
95th percentile: 2.5113170623779295
99th percentile: 2.6136718368530274
mean time: 1.9700477600097657
Pipeline stage StressChecker completed in 11.48s
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 0.72s
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-1-full-066126_v8 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 6270.13s
Shutdown handler de-registered
junhua024-chai-1-full-066126_v8 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-1-full-066126_v8 status is now torndown due to DeploymentManager action