junhua024-chai-1-full-002

developer_uid: junhua024

submission_id: junhua024-chai-1-full-002_v12

model_name: junhua024-chai-1-full-002_v12

model_group: junhua024/chai_1-full_00

status: torndown

timestamp: 2025-06-29T04:53:02+00:00

num_battles: 6764

num_wins: 3122

celo_rating: 1246.98

family_friendly_score: 0.593

family_friendly_standard_error: 0.00694767587039004

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': 0.5997444889011632, 'latency_mean': 1.6672599852085113, 'latency_p50': 1.6577112674713135, 'latency_p90': 1.8496923208236695}, {'batch_size': 3, 'throughput': 1.076339961941463, 'latency_mean': 2.780600872039795, 'latency_p50': 2.785654902458191, 'latency_p90': 3.0412962436676025}, {'batch_size': 5, 'throughput': 1.2887892750133374, 'latency_mean': 3.86204540014267, 'latency_p50': 3.8593335151672363, 'latency_p90': 4.339640331268311}, {'batch_size': 6, 'throughput': 1.3527426393844015, 'latency_mean': 4.418644083738327, 'latency_p50': 4.392539620399475, 'latency_p90': 5.009350848197937}, {'batch_size': 8, 'throughput': 1.4076157577982047, 'latency_mean': 5.636043821573257, 'latency_p50': 5.659310460090637, 'latency_p90': 6.30095694065094}, {'batch_size': 10, 'throughput': 1.4469293284588436, 'latency_mean': 6.859653379917145, 'latency_p50': 6.834158778190613, 'latency_p90': 7.686091136932373}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-1-full-002_v12

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: 0.4615612063867534

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.4, '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-v12-mkmlizer
Waiting for job on junhua024-chai-1-full-002-v12-mkmlizer to finish
junhua024-chai-1-full-002-v12-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-1-full-002-v12-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v12-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-1-full-002-v12-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-1-full-002-v12-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-1-full-002-v12-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-1-full-002-v12-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-1-full-002-v12-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-1-full-002-v12-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-1-full-002-v12-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-1-full-002-v12-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v12-mkmlizer: ║  Version: 0.29.3                                                    ║
junhua024-chai-1-full-002-v12-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-1-full-002-v12-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-1-full-002-v12-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-1-full-002-v12-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v12-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-1-full-002-v12-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-1-full-002-v12-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v12-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-1-full-002-v12-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-1-full-002-v12-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-1-full-002-v12-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v12-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-1-full-002-v12-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-v12-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-v12-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-v12-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-v12-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-v12-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-v12-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-v12-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-v12-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-v12-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-v12-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-v12-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-v12-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-v12-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-v12-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-v12-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-v12-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-v12-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-v12-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-v12-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-v12-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-v12-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-v12-mkmlizer: Downloaded to shared memory in 78.265s
junhua024-chai-1-full-002-v12-mkmlizer: Checking if junhua024/chai_1-full_002 already exists in ChaiML
junhua024-chai-1-full-002-v12-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp1cy8fzjb, device:0
junhua024-chai-1-full-002-v12-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-1-full-002-v12-mkmlizer: quantized model in 31.331s
junhua024-chai-1-full-002-v12-mkmlizer: Processed model junhua024/chai_1-full_002 in 109.671s
junhua024-chai-1-full-002-v12-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-1-full-002-v12-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-1-full-002-v12-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-1-full-002-v12
junhua024-chai-1-full-002-v12-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v12/config.json
junhua024-chai-1-full-002-v12-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v12/special_tokens_map.json
junhua024-chai-1-full-002-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v12/tokenizer_config.json
junhua024-chai-1-full-002-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v12/tokenizer.json
junhua024-chai-1-full-002-v12-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:23, 15.23it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:20, 17.10it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:10, 32.30it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:10, 32.11it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:10, 33.96it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:10, 32.29it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 41.97it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:10, 30.92it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:10, 31.52it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:07, 41.69it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:10, 30.17it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:09, 32.43it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 33.98it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:08, 33.47it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:07, 37.08it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:08, 34.29it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 34.58it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:07, 38.62it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:07, 38.36it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:08, 32.02it/s]
Loading 0:  28%|██▊       | 102/363 [00:03<00:08, 32.60it/s]
Loading 0:  29%|██▉       | 106/363 [00:03<00:07, 33.06it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:06, 37.08it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:08, 29.86it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:07, 32.22it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:06, 34.05it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:06, 33.33it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:06, 36.99it/s]
Loading 0:  39%|███▉      | 141/363 [00:04<00:05, 37.72it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:06, 32.93it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:06, 31.89it/s]
Loading 0:  43%|████▎     | 155/363 [00:04<00:05, 38.54it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 35.80it/s]
Loading 0:  45%|████▌     | 164/363 [00:04<00:05, 35.59it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:05, 33.39it/s]
Loading 0:  48%|████▊     | 176/363 [00:05<00:04, 39.53it/s]
Loading 0:  50%|████▉     | 180/363 [00:05<00:05, 31.85it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 33.46it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:04, 34.46it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:05, 33.46it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 33.16it/s]
Loading 0:  57%|█████▋    | 206/363 [00:06<00:04, 32.23it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:04, 33.63it/s]
Loading 0:  60%|██████    | 218/363 [00:06<00:03, 39.09it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:03, 37.10it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:03, 36.40it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:03, 33.97it/s]
Loading 0:  66%|██████▌   | 239/363 [00:06<00:03, 39.62it/s]
Loading 0:  67%|██████▋   | 243/363 [00:07<00:03, 32.36it/s]
Loading 0:  68%|██████▊   | 248/363 [00:07<00:03, 34.41it/s]
Loading 0:  70%|██████▉   | 254/363 [00:07<00:03, 35.73it/s]
Loading 0:  71%|███████   | 258/363 [00:07<00:03, 34.67it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 34.18it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 33.38it/s]
Loading 0:  76%|███████▌  | 275/363 [00:08<00:02, 34.70it/s]
Loading 0:  77%|███████▋  | 281/363 [00:08<00:02, 40.11it/s]
Loading 0:  79%|███████▉  | 286/363 [00:08<00:02, 37.67it/s]
Loading 0:  80%|███████▉  | 290/363 [00:08<00:01, 37.12it/s]
Loading 0:  81%|████████  | 294/363 [00:08<00:02, 34.46it/s]
Loading 0:  83%|████████▎ | 300/363 [00:08<00:01, 40.07it/s]
Loading 0:  84%|████████▍ | 305/363 [00:08<00:01, 33.07it/s]
Loading 0:  85%|████████▌ | 309/363 [00:08<00:01, 33.08it/s]
Loading 0:  86%|████████▌ | 313/363 [00:09<00:01, 33.57it/s]
Loading 0:  87%|████████▋ | 317/363 [00:09<00:01, 30.73it/s]
Loading 0:  88%|████████▊ | 321/363 [00:09<00:01, 30.74it/s]
Loading 0:  90%|█████████ | 327/363 [00:09<00:01, 31.44it/s]
Loading 0:  91%|█████████▏| 332/363 [00:09<00:01, 30.74it/s]
Loading 0:  93%|█████████▎| 338/363 [00:09<00:00, 32.46it/s]
Loading 0:  95%|█████████▍| 344/363 [00:10<00:00, 37.32it/s]
Loading 0:  96%|█████████▌| 349/363 [00:10<00:00, 25.90it/s]
Loading 0:  97%|█████████▋| 353/363 [00:10<00:00, 23.66it/s]
Loading 0:  98%|█████████▊| 357/363 [00:10<00:00, 25.35it/s]
                                                            
Job junhua024-chai-1-full-002-v12-mkmlizer completed after 136.82s with status: succeeded
Stopping job with name junhua024-chai-1-full-002-v12-mkmlizer
Pipeline stage MKMLizer completed in 137.37s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-1-full-002-v12
Waiting for inference service junhua024-chai-1-full-002-v12 to be ready
Inference service junhua024-chai-1-full-002-v12 ready after 181.02180910110474s
Pipeline stage MKMLDeployer completed in 181.56s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0935094356536865s
Received healthy response to inference request in 1.6273090839385986s
Received healthy response to inference request in 2.020792007446289s
Received healthy response to inference request in 1.6634013652801514s
Received healthy response to inference request in 1.7025830745697021s
5 requests
0 failed requests
5th percentile: 1.6345275402069093
10th percentile: 1.6417459964752197
20th percentile: 1.6561829090118407
30th percentile: 1.6712377071380615
40th percentile: 1.6869103908538818
50th percentile: 1.7025830745697021
60th percentile: 1.829866647720337
70th percentile: 1.9571502208709717
80th percentile: 2.0353354930877687
90th percentile: 2.0644224643707276
95th percentile: 2.078965950012207
99th percentile: 2.0906007385253904
mean time: 1.8215189933776856
Pipeline stage StressChecker completed in 10.49s
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 0.70s
Shutdown handler de-registered
junhua024-chai-1-full-002_v12 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 3165.78s
Shutdown handler de-registered
junhua024-chai-1-full-002_v12 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-1-full-002_v12 status is now torndown due to DeploymentManager action