junhua024-chai-02-full_54657

developer_uid: junhua024

submission_id: junhua024-chai-02-full_54657_v44

model_name: junhua024-chai-02-full_54657_v44

model_group: junhua024/chai_02_full_0

status: torndown

timestamp: 2025-07-25T12:15:05+00:00

num_battles: 7034

num_wins: 3618

celo_rating: 1291.32

family_friendly_score: 0.42100000000000004

family_friendly_standard_error: 0.006982248921371967

submission_type: basic

model_repo: junhua024/chai_02_full_02_019

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 2048

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5362580505594342, 'latency_mean': 1.8646712172031403, 'latency_p50': 1.8739805221557617, 'latency_p90': 2.024386429786682}, {'batch_size': 2, 'throughput': 0.7082356700161484, 'latency_mean': 2.8199262118339536, 'latency_p50': 2.8259851932525635, 'latency_p90': 3.000922417640686}, {'batch_size': 3, 'throughput': 0.8010165947570522, 'latency_mean': 3.7373355531692507, 'latency_p50': 3.7512853145599365, 'latency_p90': 4.042904305458069}, {'batch_size': 4, 'throughput': 0.8592768413881253, 'latency_mean': 4.636149808168411, 'latency_p50': 4.612691402435303, 'latency_p90': 5.261078810691833}, {'batch_size': 5, 'throughput': 0.8902318137618059, 'latency_mean': 5.59699808716774, 'latency_p50': 5.60847008228302, 'latency_p90': 6.3126812934875485}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-02-full_54657_v44

is_internal_developer: False

language_model: junhua024/chai_02_full_02_019

model_size: 13B

ranking_group: single

throughput_3p7s: 0.8

us_pacific_date: 2025-07-25

win_ratio: 0.5143588285470572

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "{memory} You are an empathetic conversational AI. You understand the user's feelings and respond with warmth, compassion, and sincerity. Each of your responses should be more than 64 tokens long.", '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-02-full-54657-v44-mkmlizer
Waiting for job on junhua024-chai-02-full-54657-v44-mkmlizer to finish
junhua024-chai-02-full-54657-v44-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-02-full-54657-v44-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-54657-v44-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-02-full-54657-v44-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-02-full-54657-v44-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-02-full-54657-v44-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-02-full-54657-v44-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-02-full-54657-v44-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-02-full-54657-v44-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-02-full-54657-v44-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-02-full-54657-v44-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-54657-v44-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-02-full-54657-v44-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-02-full-54657-v44-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-02-full-54657-v44-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-02-full-54657-v44-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-54657-v44-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-02-full-54657-v44-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-02-full-54657-v44-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-54657-v44-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-02-full-54657-v44-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-02-full-54657-v44-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-02-full-54657-v44-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-54657-v44-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-next-door-annoyi_15417_v1: ('http://chaiml-next-door-annoyi-15417-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
junhua024-chai-02-full-54657-v44-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-02-full-54657-v44-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-02-full-54657-v44-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-02-full-54657-v44-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-02-full-54657-v44-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-02-full-54657-v44-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-02-full-54657-v44-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-02-full-54657-v44-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-02-full-54657-v44-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-02-full-54657-v44-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-02-full-54657-v44-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-02-full-54657-v44-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-02-full-54657-v44-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-02-full-54657-v44-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-02-full-54657-v44-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-02-full-54657-v44-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-next-door-annoyi_15417_v1: ('http://chaiml-next-door-annoyi-15417-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
junhua024-chai-02-full-54657-v44-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-02-full-54657-v44-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-02-full-54657-v44-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-02-full-54657-v44-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-02-full-54657-v44-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-02-full-54657-v44-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-02-full-54657-v44-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-02-full-54657-v44-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-02-full-54657-v44-mkmlizer: Downloaded to shared memory in 95.725s
junhua024-chai-02-full-54657-v44-mkmlizer: Checking if junhua024/chai_02_full_02_019 already exists in ChaiML
junhua024-chai-02-full-54657-v44-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmp3qc5pok9, device:0
junhua024-chai-02-full-54657-v44-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-02-full-54657-v44-mkmlizer: quantized model in 159.089s
junhua024-chai-02-full-54657-v44-mkmlizer: Processed model junhua024/chai_02_full_02_019 in 254.905s
junhua024-chai-02-full-54657-v44-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-02-full-54657-v44-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-02-full-54657-v44-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-02-full-54657-v44/nvidia
junhua024-chai-02-full-54657-v44-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-02-full-54657-v44/nvidia/config.json
junhua024-chai-02-full-54657-v44-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-02-full-54657-v44/nvidia/special_tokens_map.json
junhua024-chai-02-full-54657-v44-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-02-full-54657-v44/nvidia/tokenizer_config.json
junhua024-chai-02-full-54657-v44-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-02-full-54657-v44/nvidia/tokenizer.json
junhua024-chai-02-full-54657-v44-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-02-full-54657-v44/nvidia/flywheel_model.0.safetensors
Job junhua024-chai-02-full-54657-v44-mkmlizer completed after 286.45s with status: succeeded
Stopping job with name junhua024-chai-02-full-54657-v44-mkmlizer
Pipeline stage MKMLizer completed in 286.93s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-02-full-54657-v44
Waiting for inference service junhua024-chai-02-full-54657-v44 to be ready
Inference service junhua024-chai-02-full-54657-v44 ready after 181.94384956359863s
Pipeline stage MKMLDeployer completed in 182.91s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.3918938636779785s
Received healthy response to inference request in 1.6175744533538818s
Received healthy response to inference request in 1.7417047023773193s
Received healthy response to inference request in 1.6324858665466309s
5 requests
1 failed requests
5th percentile: 1.6205567359924316
10th percentile: 1.6235390186309815
20th percentile: 1.6295035839080811
30th percentile: 1.6543296337127686
40th percentile: 1.698017168045044
50th percentile: 1.7417047023773193
60th percentile: 2.001780366897583
70th percentile: 2.2618560314178464
80th percentile: 5.942841434478763
90th percentile: 13.044736576080325
95th percentile: 16.5956841468811
99th percentile: 19.43644220352173
mean time: 5.506058120727539
%s, retrying in %s seconds...
Received healthy response to inference request in 1.934236764907837s
Received healthy response to inference request in 1.1007251739501953s
Received healthy response to inference request in 1.3504858016967773s
Received healthy response to inference request in 1.684288501739502s
Received healthy response to inference request in 1.6965012550354004s
5 requests
0 failed requests
5th percentile: 1.1506772994995118
10th percentile: 1.200629425048828
20th percentile: 1.3005336761474608
30th percentile: 1.4172463417053223
40th percentile: 1.550767421722412
50th percentile: 1.684288501739502
60th percentile: 1.6891736030578612
70th percentile: 1.6940587043762207
80th percentile: 1.7440483570098877
90th percentile: 1.8391425609588623
95th percentile: 1.8866896629333496
99th percentile: 1.9247273445129394
mean time: 1.5532474994659424
Pipeline stage StressChecker completed in 39.05s
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 0.69s
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 0.99s
Shutdown handler de-registered
junhua024-chai-02-full_54657_v44 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4884.88s
Shutdown handler de-registered
junhua024-chai-02-full_54657_v44 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-02-full_54657_v44 status is now torndown due to DeploymentManager action