junhua024-chai-02-full_54657

developer_uid: junhua024

submission_id: junhua024-chai-02-full_54657_v49

model_name: junhua024-chai-02-full_54657_v49

model_group: junhua024/chai_02_full_0

status: torndown

timestamp: 2025-07-25T15:10:58+00:00

num_battles: 6594

num_wins: 3368

celo_rating: 1292.59

family_friendly_score: 0.4244

family_friendly_standard_error: 0.00698977310075227

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': 0.5327791476870443, 'latency_mean': 1.8768215036392213, 'latency_p50': 1.8744622468948364, 'latency_p90': 2.0338613510131838}, {'batch_size': 2, 'throughput': 0.7060445349584569, 'latency_mean': 2.8321947336196898, 'latency_p50': 2.845362424850464, 'latency_p90': 3.050427269935608}, {'batch_size': 3, 'throughput': 0.7964106531621413, 'latency_mean': 3.7567308068275453, 'latency_p50': 3.7573636770248413, 'latency_p90': 4.083098673820496}, {'batch_size': 4, 'throughput': 0.8549741454703313, 'latency_mean': 4.6611492991447445, 'latency_p50': 4.6614826917648315, 'latency_p90': 5.2641969442367555}, {'batch_size': 5, 'throughput': 0.8798140814475482, 'latency_mean': 5.668094445466995, 'latency_p50': 5.685936808586121, 'latency_p90': 6.296355485916138}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-02-full_54657_v49

is_internal_developer: False

language_model: junhua024/chai_02_full_02_019

model_size: 13B

ranking_group: single

throughput_3p7s: 0.79

us_pacific_date: 2025-07-25

win_ratio: 0.510767364270549

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.1, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "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 fewer 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-v49-mkmlizer
Waiting for job on junhua024-chai-02-full-54657-v49-mkmlizer to finish
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-v49-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-02-full-54657-v49-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-54657-v49-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-02-full-54657-v49-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-02-full-54657-v49-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-02-full-54657-v49-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-02-full-54657-v49-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-02-full-54657-v49-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-02-full-54657-v49-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-02-full-54657-v49-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-02-full-54657-v49-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-54657-v49-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-02-full-54657-v49-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-02-full-54657-v49-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-02-full-54657-v49-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-02-full-54657-v49-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-54657-v49-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-02-full-54657-v49-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-02-full-54657-v49-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-54657-v49-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-02-full-54657-v49-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-02-full-54657-v49-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-02-full-54657-v49-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-54657-v49-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-02-full-54657-v49-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-v49-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-v49-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-v49-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-v49-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-v49-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-v49-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-v49-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-v49-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-v49-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-v49-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-v49-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-v49-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-v49-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-v49-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-v49-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-v49-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-v49-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-v49-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-v49-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-v49-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-v49-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-v49-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-v49-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-v49-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-v49-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-v49-mkmlizer: Downloaded to shared memory in 112.466s
junhua024-chai-02-full-54657-v49-mkmlizer: Checking if junhua024/chai_02_full_02_019 already exists in ChaiML
junhua024-chai-02-full-54657-v49-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpzpa9n2jb, device:0
junhua024-chai-02-full-54657-v49-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-02-full-54657-v49-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-02-full-54657-v49-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-02-full-54657-v49-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-02-full-54657-v49/nvidia
junhua024-chai-02-full-54657-v49-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-02-full-54657-v49/nvidia/config.json
junhua024-chai-02-full-54657-v49-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-02-full-54657-v49/nvidia/special_tokens_map.json
junhua024-chai-02-full-54657-v49-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-02-full-54657-v49/nvidia/tokenizer_config.json
junhua024-chai-02-full-54657-v49-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-02-full-54657-v49/nvidia/tokenizer.json
junhua024-chai-02-full-54657-v49-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-02-full-54657-v49/nvidia/flywheel_model.0.safetensors
Job junhua024-chai-02-full-54657-v49-mkmlizer completed after 469.91s with status: succeeded
Stopping job with name junhua024-chai-02-full-54657-v49-mkmlizer
Pipeline stage MKMLizer completed in 470.63s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.23s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-02-full-54657-v49
Waiting for inference service junhua024-chai-02-full-54657-v49 to be ready
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', '')
Inference service junhua024-chai-02-full-54657-v49 ready after 191.06729865074158s
Pipeline stage MKMLDeployer completed in 191.66s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2728188037872314s
Received healthy response to inference request in 6.9668591022491455s
Received healthy response to inference request in 2.60290265083313s
Received healthy response to inference request in 6.725031852722168s
Received healthy response to inference request in 2.526155471801758s
5 requests
0 failed requests
5th percentile: 2.3234861373901365
10th percentile: 2.374153470993042
20th percentile: 2.4754881381988527
30th percentile: 2.541504907608032
40th percentile: 2.572203779220581
50th percentile: 2.60290265083313
60th percentile: 4.251754331588745
70th percentile: 5.90060601234436
80th percentile: 6.773397302627563
90th percentile: 6.870128202438354
95th percentile: 6.91849365234375
99th percentile: 6.957186012268067
mean time: 4.2187535762786865
%s, retrying in %s seconds...
Received healthy response to inference request in 2.5741817951202393s
Received healthy response to inference request in 1.2056388854980469s
Received healthy response to inference request in 1.9354228973388672s
Received healthy response to inference request in 2.88671875s
Received healthy response to inference request in 3.692190647125244s
5 requests
0 failed requests
5th percentile: 1.351595687866211
10th percentile: 1.497552490234375
20th percentile: 1.789466094970703
30th percentile: 2.063174676895142
40th percentile: 2.3186782360076905
50th percentile: 2.5741817951202393
60th percentile: 2.6991965770721436
70th percentile: 2.824211359024048
80th percentile: 3.047813129425049
90th percentile: 3.3700018882751466
95th percentile: 3.531096267700195
99th percentile: 3.6599717712402344
mean time: 2.4588305950164795
Pipeline stage StressChecker completed in 36.30s
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 0.74s
Shutdown handler de-registered
junhua024-chai-02-full_54657_v49 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
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 2735.54s
Shutdown handler de-registered
junhua024-chai-02-full_54657_v49 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-02-full_54657_v49 status is now torndown due to DeploymentManager action