junhua024-chai-06-full_30622

developer_uid: junhua024

submission_id: junhua024-chai-06-full_30622_v24

model_name: junhua024-chai-06-full_30622_v24

model_group: junhua024/chai_06_full_0

status: torndown

timestamp: 2025-07-18T20:32:57+00:00

num_battles: 11106

num_wins: 5391

celo_rating: 1272.23

family_friendly_score: 0.5569999999999999

family_friendly_standard_error: 0.007024969750824553

submission_type: basic

model_repo: junhua024/chai_06_full_02102_1925

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': 0.5951927468739836, 'latency_mean': 1.6799512672424317, 'latency_p50': 1.672719955444336, 'latency_p90': 1.854166865348816}, {'batch_size': 3, 'throughput': 1.0763386513277338, 'latency_mean': 2.7797099328041077, 'latency_p50': 2.7884820699691772, 'latency_p90': 3.0456632137298585}, {'batch_size': 5, 'throughput': 1.2994641350610856, 'latency_mean': 3.8259735560417174, 'latency_p50': 3.8440663814544678, 'latency_p90': 4.261372780799865}, {'batch_size': 6, 'throughput': 1.3579300903238756, 'latency_mean': 4.392435938119888, 'latency_p50': 4.383391857147217, 'latency_p90': 4.90564272403717}, {'batch_size': 8, 'throughput': 1.4295588131380035, 'latency_mean': 5.562925394773483, 'latency_p50': 5.522256255149841, 'latency_p90': 6.236213493347168}, {'batch_size': 10, 'throughput': 1.4682495674556757, 'latency_mean': 6.753468707799912, 'latency_p50': 6.748400807380676, 'latency_p90': 7.653750085830689}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-06-full_30622_v24

is_internal_developer: False

language_model: junhua024/chai_06_full_02102_1925

model_size: 13B

ranking_group: single

throughput_3p7s: 1.29

us_pacific_date: 2025-07-18

win_ratio: 0.4854132901134522

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-30622-v24-mkmlizer
Waiting for job on junhua024-chai-06-full-30622-v24-mkmlizer to finish
Failed to get response for submission chaiml-simon-ghost-rile_65921_v1: HTTPConnectionPool(host='chaiml-simon-ghost-rile-65921-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-06-full-30622-v24-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-06-full-30622-v24-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-30622-v24-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-06-full-30622-v24-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-06-full-30622-v24-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-06-full-30622-v24-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-06-full-30622-v24-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-06-full-30622-v24-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-06-full-30622-v24-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-06-full-30622-v24-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-06-full-30622-v24-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-30622-v24-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-06-full-30622-v24-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-06-full-30622-v24-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-06-full-30622-v24-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-06-full-30622-v24-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-30622-v24-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-06-full-30622-v24-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-06-full-30622-v24-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-30622-v24-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-06-full-30622-v24-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-06-full-30622-v24-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-06-full-30622-v24-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-30622-v24-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-06-full-30622-v24-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-30622-v24-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-30622-v24-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-30622-v24-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-30622-v24-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-30622-v24-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-30622-v24-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-30622-v24-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-30622-v24-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-30622-v24-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-30622-v24-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-30622-v24-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-30622-v24-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-30622-v24-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-30622-v24-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-30622-v24-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-30622-v24-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-30622-v24-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-30622-v24-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-30622-v24-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-30622-v24-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`
Failed to get response for submission chaiml-bat-boys-azeril-_87348_v1: ('http://chaiml-bat-boys-azeril-87348-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
junhua024-chai-06-full-30622-v24-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-30622-v24-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-30622-v24-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`
Failed to get response for submission junhua024-chai-12-full-_19228_v2: HTTPConnectionPool(host='junhua024-chai-12-full-19228-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 0x776a408e7e50>, 'Connection to junhua024-chai-12-full-19228-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com timed out. (connect timeout=12.0)'))
junhua024-chai-06-full-30622-v24-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-30622-v24-mkmlizer: Downloaded to shared memory in 91.892s
junhua024-chai-06-full-30622-v24-mkmlizer: Checking if junhua024/chai_06_full_02102_1925 already exists in ChaiML
junhua024-chai-06-full-30622-v24-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3guxuiz1, device:0
junhua024-chai-06-full-30622-v24-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission junhua024-chai-12-full-_19228_v2: HTTPConnectionPool(host='junhua024-chai-12-full-19228-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-06-full-30622-v24-mkmlizer: quantized model in 38.874s
junhua024-chai-06-full-30622-v24-mkmlizer: Processed model junhua024/chai_06_full_02102_1925 in 130.849s
junhua024-chai-06-full-30622-v24-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-06-full-30622-v24-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-06-full-30622-v24-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-06-full-30622-v24/nvidia
junhua024-chai-06-full-30622-v24-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-06-full-30622-v24/nvidia/config.json
junhua024-chai-06-full-30622-v24-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-06-full-30622-v24/nvidia/special_tokens_map.json
junhua024-chai-06-full-30622-v24-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-06-full-30622-v24/nvidia/tokenizer_config.json
junhua024-chai-06-full-30622-v24-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-06-full-30622-v24/nvidia/tokenizer.json
junhua024-chai-06-full-30622-v24-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-06-full-30622-v24/nvidia/flywheel_model.0.safetensors
Failed to get response for submission chaiml-bat-boys-azeril-_87348_v1: ('http://chaiml-bat-boys-azeril-87348-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Job junhua024-chai-06-full-30622-v24-mkmlizer completed after 159.53s with status: succeeded
Stopping job with name junhua024-chai-06-full-30622-v24-mkmlizer
Pipeline stage MKMLizer completed in 160.25s
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-06-full-30622-v24
Waiting for inference service junhua024-chai-06-full-30622-v24 to be ready
Failed to get response for submission chaiml-gy-exp188-sft-gy_24525_v1: HTTPConnectionPool(host='chaiml-gy-exp188-sft-gy-24525-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-gy-exp188-sft-gy_24525_v1: HTTPConnectionPool(host='chaiml-gy-exp188-sft-gy-24525-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Retrying (%r) after connection broken by '%r': %s
Failed to get response for submission junhua024-chai-06-full-_95931_v1: HTTPConnectionPool(host='junhua024-chai-06-full-95931-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-06-full-30622-v24 ready after 321.3742024898529s
Pipeline stage MKMLDeployer completed in 321.87s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3875536918640137s
Received healthy response to inference request in 1.885394811630249s
Received healthy response to inference request in 1.5431289672851562s
Received healthy response to inference request in 1.8199257850646973s
Received healthy response to inference request in 1.6720516681671143s
5 requests
0 failed requests
5th percentile: 1.568913507461548
10th percentile: 1.5946980476379395
20th percentile: 1.6462671279907226
30th percentile: 1.7016264915466308
40th percentile: 1.7607761383056642
50th percentile: 1.8199257850646973
60th percentile: 1.846113395690918
70th percentile: 1.8723010063171386
80th percentile: 1.985826587677002
90th percentile: 2.1866901397705076
95th percentile: 2.2871219158172607
99th percentile: 2.3674673366546632
mean time: 1.8616109848022462
Pipeline stage StressChecker completed in 10.80s
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 0.66s
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 0.76s
Shutdown handler de-registered
junhua024-chai-06-full_30622_v24 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service junhua024-chai-06-full-30622-v24-profiler
Waiting for inference service junhua024-chai-06-full-30622-v24-profiler to be ready
Inference service junhua024-chai-06-full-30622-v24-profiler ready after 323.4509093761444s
Pipeline stage MKMLProfilerDeployer completed in 324.43s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/junhua024-chai-06-fu87f0f4386548a6ada4f61cd52f3de632-deplovqw9p:/code/chaiverse_profiler_1752871668 --namespace tenant-chaiml-guanaco
kubectl exec -it junhua024-chai-06-fu87f0f4386548a6ada4f61cd52f3de632-deplovqw9p --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752871668 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1752871668/summary.json'
kubectl exec -it junhua024-chai-06-fu87f0f4386548a6ada4f61cd52f3de632-deplovqw9p --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1752871668/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1112.51s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service junhua024-chai-06-full-30622-v24-profiler is running
Tearing down inference service junhua024-chai-06-full-30622-v24-profiler
Service junhua024-chai-06-full-30622-v24-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 4.58s
Shutdown handler de-registered
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 2890.53s
Shutdown handler de-registered
junhua024-chai-06-full_30622_v24 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-06-full_30622_v24 status is now torndown due to DeploymentManager action
junhua024-chai-06-full_30622_v24 status is now torndown due to DeploymentManager action