junhua024-chai-06-full-_88520

developer_uid: junhua024

submission_id: junhua024-chai-06-full-_88520_v1

model_name: junhua024-chai-06-full-_88520_v1

model_group: junhua024/chai_06_full_0

status: torndown

timestamp: 2025-07-17T11:36:05+00:00

num_battles: 6714

num_wins: 3395

celo_rating: 1282.98

family_friendly_score: 0.5542

family_friendly_standard_error: 0.007029400543431851

submission_type: basic

model_repo: junhua024/chai_06_full_02102_2529

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': 0.5946251738184107, 'latency_mean': 1.681541303396225, 'latency_p50': 1.6731290817260742, 'latency_p90': 1.8529172897338868}, {'batch_size': 3, 'throughput': 1.0746526356106187, 'latency_mean': 2.7775205147266386, 'latency_p50': 2.7876577377319336, 'latency_p90': 3.071105146408081}, {'batch_size': 5, 'throughput': 1.2898439284184569, 'latency_mean': 3.8568438732624055, 'latency_p50': 3.8427995443344116, 'latency_p90': 4.3026498556137085}, {'batch_size': 6, 'throughput': 1.363106610828065, 'latency_mean': 4.3749150061607365, 'latency_p50': 4.389236569404602, 'latency_p90': 4.881145548820496}, {'batch_size': 8, 'throughput': 1.422867347378833, 'latency_mean': 5.580955830812454, 'latency_p50': 5.591542482376099, 'latency_p90': 6.187651848793029}, {'batch_size': 10, 'throughput': 1.4512912972502274, 'latency_mean': 6.837654279470444, 'latency_p50': 6.821688890457153, 'latency_p90': 7.789538407325744}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-06-full-_88520_v1

is_internal_developer: False

language_model: junhua024/chai_06_full_02102_2529

model_size: 13B

ranking_group: single

throughput_3p7s: 1.27

us_pacific_date: 2025-07-17

win_ratio: 0.5056598153112899

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': "{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-06-full-88520-v1-mkmlizer
Waiting for job on junhua024-chai-06-full-88520-v1-mkmlizer to finish
junhua024-chai-06-full-88520-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-06-full-88520-v1-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-88520-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-06-full-88520-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-06-full-88520-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-06-full-88520-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-06-full-88520-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-06-full-88520-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-06-full-88520-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-06-full-88520-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-06-full-88520-v1-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-88520-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-06-full-88520-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-06-full-88520-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-06-full-88520-v1-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-06-full-88520-v1-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-88520-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-06-full-88520-v1-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-06-full-88520-v1-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-88520-v1-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-06-full-88520-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-06-full-88520-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-06-full-88520-v1-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-88520-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-06-full-88520-v1-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-06-full-88520-v1-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-06-full-88520-v1-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-06-full-88520-v1-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-06-full-88520-v1-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-06-full-88520-v1-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-06-full-88520-v1-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-06-full-88520-v1-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-06-full-88520-v1-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-06-full-88520-v1-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-06-full-88520-v1-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`
Unable to record family friendly update due to error: HTTPConnectionPool(host='chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by ConnectTimeoutError(<urllib3.connection.HTTPConnection object at 0x7dd02cd85650>, 'Connection to chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com timed out. (connect timeout=12.0)'))
junhua024-chai-06-full-88520-v1-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-06-full-88520-v1-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-06-full-88520-v1-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-06-full-88520-v1-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-06-full-88520-v1-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-06-full-88520-v1-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-06-full-88520-v1-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-06-full-88520-v1-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-06-full-88520-v1-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-06-full-88520-v1-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-06-full-88520-v1-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-06-full-88520-v1-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-06-full-88520-v1-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-06-full-88520-v1-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-06-full-88520-v1-mkmlizer: Downloaded to shared memory in 118.467s
junhua024-chai-06-full-88520-v1-mkmlizer: Checking if junhua024/chai_06_full_02102_2529 already exists in ChaiML
junhua024-chai-06-full-88520-v1-mkmlizer: Creating repo ChaiML/chai_06_full_02102_2529 and uploading /tmp/tmpy7gax9oc to it
junhua024-chai-06-full-88520-v1-mkmlizer: 
  0%|          | 0/26 [00:00<?, ?it/s]
  4%|▍         | 1/26 [00:02<01:03,  2.54s/it]
  8%|▊         | 2/26 [00:04<00:47,  1.99s/it]
 12%|█▏        | 3/26 [00:06<00:50,  2.18s/it]
 15%|█▌        | 4/26 [00:07<00:40,  1.86s/it]
 19%|█▉        | 5/26 [00:11<00:48,  2.31s/it]
 23%|██▎       | 6/26 [00:13<00:48,  2.42s/it]
 27%|██▋       | 7/26 [00:16<00:47,  2.50s/it]
 31%|███       | 8/26 [00:17<00:38,  2.16s/it]
 35%|███▍      | 9/26 [00:19<00:33,  1.98s/it]
 38%|███▊      | 10/26 [00:20<00:29,  1.84s/it]
 42%|████▏     | 11/26 [00:22<00:25,  1.69s/it]
 46%|████▌     | 12/26 [00:23<00:21,  1.55s/it]
 50%|█████     | 13/26 [00:25<00:20,  1.57s/it]
 54%|█████▍    | 14/26 [00:27<00:21,  1.76s/it]
 58%|█████▊    | 15/26 [00:29<00:20,  1.83s/it]
 62%|██████▏   | 16/26 [00:31<00:19,  1.95s/it]
 65%|██████▌   | 17/26 [00:34<00:19,  2.18s/it]
 69%|██████▉   | 18/26 [00:35<00:15,  1.94s/it]
 73%|███████▎  | 19/26 [00:40<00:20,  2.90s/it]
 77%|███████▋  | 20/26 [00:43<00:17,  2.86s/it]
 81%|████████  | 21/26 [00:44<00:12,  2.43s/it]
 85%|████████▍ | 22/26 [00:50<00:13,  3.41s/it]
 88%|████████▊ | 23/26 [00:52<00:08,  2.83s/it]
 92%|█████████▏| 24/26 [00:53<00:04,  2.43s/it]
 96%|█████████▌| 25/26 [00:59<00:03,  3.62s/it]
100%|██████████| 26/26 [01:01<00:00,  2.89s/it]
100%|██████████| 26/26 [01:01<00:00,  2.35s/it]
junhua024-chai-06-full-88520-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpy7gax9oc, device:0
junhua024-chai-06-full-88520-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-06-full-88520-v1-mkmlizer: quantized model in 32.073s
junhua024-chai-06-full-88520-v1-mkmlizer: Processed model junhua024/chai_06_full_02102_2529 in 244.199s
junhua024-chai-06-full-88520-v1-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-06-full-88520-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-06-full-88520-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-06-full-88520-v1/nvidia
junhua024-chai-06-full-88520-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-06-full-88520-v1/nvidia/config.json
junhua024-chai-06-full-88520-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-06-full-88520-v1/nvidia/special_tokens_map.json
junhua024-chai-06-full-88520-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-06-full-88520-v1/nvidia/tokenizer_config.json
junhua024-chai-06-full-88520-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-06-full-88520-v1/nvidia/tokenizer.json
junhua024-chai-06-full-88520-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-06-full-88520-v1/nvidia/flywheel_model.0.safetensors
Job junhua024-chai-06-full-88520-v1-mkmlizer completed after 272.91s with status: succeeded
Stopping job with name junhua024-chai-06-full-88520-v1-mkmlizer
Pipeline stage MKMLizer completed in 273.52s
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-06-full-88520-v1
Waiting for inference service junhua024-chai-06-full-88520-v1 to be ready
Inference service junhua024-chai-06-full-88520-v1 ready after 290.96812295913696s
Pipeline stage MKMLDeployer completed in 291.50s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.547794818878174s
Received healthy response to inference request in 1.7902131080627441s
Received healthy response to inference request in 2.0206611156463623s
Received healthy response to inference request in 1.682701826095581s
Received healthy response to inference request in 1.6487047672271729s
5 requests
0 failed requests
5th percentile: 1.6555041790008544
10th percentile: 1.662303590774536
20th percentile: 1.6759024143218995
30th percentile: 1.7042040824890137
40th percentile: 1.747208595275879
50th percentile: 1.7902131080627441
60th percentile: 1.8823923110961913
70th percentile: 1.9745715141296387
80th percentile: 2.126087856292725
90th percentile: 2.3369413375854493
95th percentile: 2.4423680782318113
99th percentile: 2.5267094707489015
mean time: 1.9380151271820067
Pipeline stage StressChecker completed in 11.24s
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 0.76s
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-06-full-_88520_v1 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 2888.27s
Shutdown handler de-registered
junhua024-chai-06-full-_88520_v1 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-06-full-_88520_v1 status is now torndown due to DeploymentManager action
junhua024-chai-06-full-_88520_v1 status is now torndown due to DeploymentManager action