junhua024-chai-1-full-066126

developer_uid: junhua024

submission_id: junhua024-chai-1-full-066126_v68

model_name: junhua024-chai-1-full-066126_v68

model_group: junhua024/chai-1-full-06

status: torndown

timestamp: 2025-07-15T14:10:16+00:00

num_battles: 6261

num_wins: 3192

celo_rating: 1271.46

family_friendly_score: 0.558

family_friendly_standard_error: 0.007023332542319209

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': 0.5907335377520405, 'latency_mean': 1.6926835322380065, 'latency_p50': 1.7014809846878052, 'latency_p90': 1.8432285785675049}, {'batch_size': 3, 'throughput': 1.0916636617943571, 'latency_mean': 2.741447046995163, 'latency_p50': 2.7282867431640625, 'latency_p90': 3.0263346433639526}, {'batch_size': 5, 'throughput': 1.2900947810290118, 'latency_mean': 3.852929562330246, 'latency_p50': 3.864900231361389, 'latency_p90': 4.3310514211654665}, {'batch_size': 6, 'throughput': 1.353325232727643, 'latency_mean': 4.412977759838104, 'latency_p50': 4.442780375480652, 'latency_p90': 4.938164567947387}, {'batch_size': 8, 'throughput': 1.4145762379256213, 'latency_mean': 5.615171827077866, 'latency_p50': 5.634080529212952, 'latency_p90': 6.312874031066895}, {'batch_size': 10, 'throughput': 1.4585450646596687, 'latency_mean': 6.7946459937095645, 'latency_p50': 6.8093039989471436, 'latency_p90': 7.706468105316162}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-1-full-066126_v68

is_internal_developer: False

language_model: junhua024/chai-1-full-066126

model_size: 13B

ranking_group: single

throughput_3p7s: 1.28

us_pacific_date: 2025-07-15

win_ratio: 0.5098227120268328

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': '{memory} What nuanced feelings lie behind these words?', '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-066126-v68-mkmlizer
Waiting for job on junhua024-chai-1-full-066126-v68-mkmlizer to finish
junhua024-chai-1-full-066126-v68-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-1-full-066126-v68-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v68-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-1-full-066126-v68-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-1-full-066126-v68-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-1-full-066126-v68-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-1-full-066126-v68-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-1-full-066126-v68-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-1-full-066126-v68-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-1-full-066126-v68-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-1-full-066126-v68-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v68-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-1-full-066126-v68-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-1-full-066126-v68-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-1-full-066126-v68-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-1-full-066126-v68-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v68-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-1-full-066126-v68-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-1-full-066126-v68-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v68-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-1-full-066126-v68-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-1-full-066126-v68-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-1-full-066126-v68-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v68-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-1-full-066126-v68-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-v68-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-v68-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-v68-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-v68-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-v68-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-v68-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-v68-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-v68-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-v68-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-v68-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-v68-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-v68-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-v68-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-v68-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-v68-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-v68-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-v68-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-v68-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-v68-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-v68-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-v68-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-v68-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-v68-mkmlizer: Downloaded to shared memory in 76.801s
junhua024-chai-1-full-066126-v68-mkmlizer: Checking if junhua024/chai-1-full-066126 already exists in ChaiML
junhua024-chai-1-full-066126-v68-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7calzd2a, device:0
junhua024-chai-1-full-066126-v68-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-1-full-066126-v68-mkmlizer: quantized model in 31.051s
junhua024-chai-1-full-066126-v68-mkmlizer: Processed model junhua024/chai-1-full-066126 in 107.929s
junhua024-chai-1-full-066126-v68-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-1-full-066126-v68-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-1-full-066126-v68-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v68/nvidia
junhua024-chai-1-full-066126-v68-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v68/nvidia/config.json
junhua024-chai-1-full-066126-v68-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v68/nvidia/special_tokens_map.json
junhua024-chai-1-full-066126-v68-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v68/nvidia/tokenizer_config.json
junhua024-chai-1-full-066126-v68-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v68/nvidia/flywheel_model.0.safetensors
junhua024-chai-1-full-066126-v68-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:22, 16.07it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:19, 18.59it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 29.49it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:11, 30.87it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 33.12it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 42.00it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:09, 36.27it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:09, 35.48it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:09, 35.07it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:08, 38.63it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:09, 31.03it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:09, 33.34it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 34.69it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:08, 33.78it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:08, 33.59it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:08, 31.91it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 36.18it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 36.07it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:07, 36.04it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:07, 35.86it/s]
Loading 0:  29%|██▉       | 105/363 [00:03<00:07, 33.64it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:06, 38.78it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:07, 30.87it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:07, 31.99it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:07, 33.40it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:07, 32.67it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:06, 36.09it/s]
Loading 0:  39%|███▉      | 141/363 [00:04<00:06, 36.75it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:06, 31.54it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:06, 30.68it/s]
Loading 0:  43%|████▎     | 155/363 [00:04<00:05, 37.18it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 34.62it/s]
Loading 0:  45%|████▌     | 164/363 [00:04<00:05, 34.20it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:05, 32.58it/s]
Loading 0:  48%|████▊     | 176/363 [00:05<00:04, 38.53it/s]
Loading 0:  50%|████▉     | 180/363 [00:05<00:05, 30.97it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 32.81it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:05, 33.95it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:05, 33.47it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 34.05it/s]
Loading 0:  57%|█████▋    | 206/363 [00:06<00:04, 33.68it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:04, 33.86it/s]
Loading 0:  60%|██████    | 218/363 [00:06<00:03, 39.36it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:03, 37.41it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:03, 36.65it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:03, 34.15it/s]
Loading 0:  66%|██████▌   | 238/363 [00:06<00:02, 42.41it/s]
Loading 0:  67%|██████▋   | 243/363 [00:07<00:03, 30.75it/s]
Loading 0:  68%|██████▊   | 248/363 [00:07<00:03, 33.03it/s]
Loading 0:  70%|██████▉   | 254/363 [00:07<00:03, 34.80it/s]
Loading 0:  71%|███████   | 258/363 [00:07<00:03, 33.89it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 33.62it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 33.31it/s]
Loading 0:  76%|███████▌  | 275/363 [00:08<00:02, 34.61it/s]
Loading 0:  78%|███████▊  | 282/363 [00:08<00:01, 42.08it/s]
Loading 0:  79%|███████▉  | 287/363 [00:08<00:02, 36.91it/s]
Loading 0:  80%|████████  | 292/363 [00:08<00:01, 36.67it/s]
Loading 0:  82%|████████▏ | 297/363 [00:08<00:01, 39.30it/s]
Loading 0:  83%|████████▎ | 302/363 [00:08<00:01, 38.19it/s]
Loading 0:  84%|████████▍ | 306/363 [00:08<00:01, 31.07it/s]
Loading 0:  86%|████████▌ | 311/363 [00:09<00:01, 32.55it/s]
Loading 0:  87%|████████▋ | 317/363 [00:09<00:01, 34.16it/s]
Loading 0:  88%|████████▊ | 321/363 [00:09<00:01, 33.55it/s]
Loading 0:  90%|█████████ | 327/363 [00:09<00:01, 33.75it/s]
Loading 0:  91%|█████████▏| 332/363 [00:09<00:00, 33.30it/s]
Loading 0:  93%|█████████▎| 338/363 [00:09<00:00, 34.80it/s]
Loading 0:  95%|█████████▍| 344/363 [00:09<00:00, 39.75it/s]
Loading 0:  96%|█████████▌| 349/363 [00:10<00:00, 27.49it/s]
Loading 0:  97%|█████████▋| 353/363 [00:10<00:00, 24.80it/s]
Loading 0:  98%|█████████▊| 357/363 [00:10<00:00, 26.41it/s]
                                                            
Job junhua024-chai-1-full-066126-v68-mkmlizer completed after 128.85s with status: succeeded
Stopping job with name junhua024-chai-1-full-066126-v68-mkmlizer
Pipeline stage MKMLizer completed in 129.53s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.49s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-1-full-066126-v68
Waiting for inference service junhua024-chai-1-full-066126-v68 to be ready
Inference service junhua024-chai-1-full-066126-v68 ready after 252.00153946876526s
Pipeline stage MKMLDeployer completed in 252.61s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.299630641937256s
Received healthy response to inference request in 1.8148322105407715s
Received healthy response to inference request in 1.8121109008789062s
Received healthy response to inference request in 2.208872079849243s
Received healthy response to inference request in 2.0761160850524902s
5 requests
0 failed requests
5th percentile: 1.8126551628112793
10th percentile: 1.8131994247436523
20th percentile: 1.8142879486083985
30th percentile: 1.8670889854431152
40th percentile: 1.9716025352478028
50th percentile: 2.0761160850524902
60th percentile: 2.1292184829711913
70th percentile: 2.1823208808898924
80th percentile: 2.227023792266846
90th percentile: 2.263327217102051
95th percentile: 2.281478929519653
99th percentile: 2.2960002994537354
mean time: 2.0423123836517334
Pipeline stage StressChecker completed in 12.30s
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 0.75s
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 0.84s
Shutdown handler de-registered
junhua024-chai-1-full-066126_v68 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 4403.85s
Shutdown handler de-registered
junhua024-chai-1-full-066126_v68 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-1-full-066126_v68 status is now torndown due to DeploymentManager action
junhua024-chai-1-full-066126_v68 status is now torndown due to DeploymentManager action