junhua024-chai-02-full_54657

developer_uid: junhua024

submission_id: junhua024-chai-02-full_54657_v28

model_name: junhua024-chai-02-full_54657_v28

model_group: junhua024/chai_02_full_0

status: torndown

timestamp: 2025-07-25T02:22:50+00:00

num_battles: 6230

num_wins: 3179

celo_rating: 1290.36

family_friendly_score: 0.4264

family_friendly_standard_error: 0.006994040892073766

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': 0.5342756174959429, 'latency_mean': 1.8715567660331727, 'latency_p50': 1.8715510368347168, 'latency_p90': 2.038968062400818}, {'batch_size': 2, 'throughput': 0.702143693307811, 'latency_mean': 2.8439721274375915, 'latency_p50': 2.8513832092285156, 'latency_p90': 3.1000732421875}, {'batch_size': 3, 'throughput': 0.7949610077190795, 'latency_mean': 3.7681844282150267, 'latency_p50': 3.7630902528762817, 'latency_p90': 4.111651229858398}, {'batch_size': 4, 'throughput': 0.8512920198663598, 'latency_mean': 4.67875665307045, 'latency_p50': 4.698365688323975, 'latency_p90': 5.218701243400574}, {'batch_size': 5, 'throughput': 0.8825708847246624, 'latency_mean': 5.6484383046627045, 'latency_p50': 5.638750672340393, 'latency_p90': 6.467606806755065}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-02-full_54657_v28

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: 2025-07-24

win_ratio: 0.5102728731942215

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 and positive conversational AI. 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-v28-mkmlizer
Waiting for job on junhua024-chai-02-full-54657-v28-mkmlizer to finish
junhua024-chai-02-full-54657-v28-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-02-full-54657-v28-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-54657-v28-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-02-full-54657-v28-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-02-full-54657-v28-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-02-full-54657-v28-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-02-full-54657-v28-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-02-full-54657-v28-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-02-full-54657-v28-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-02-full-54657-v28-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-02-full-54657-v28-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-54657-v28-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-02-full-54657-v28-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-02-full-54657-v28-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-02-full-54657-v28-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-02-full-54657-v28-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-54657-v28-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-02-full-54657-v28-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-02-full-54657-v28-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-54657-v28-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-02-full-54657-v28-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-02-full-54657-v28-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-02-full-54657-v28-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-54657-v28-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-02-full-54657-v28-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-v28-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-v28-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-v28-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-v28-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-v28-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-v28-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-v28-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-v28-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-v28-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-v28-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-v28-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-v28-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-v28-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-v28-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-v28-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-v28-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-v28-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-v28-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-v28-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-v28-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-v28-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-v28-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-v28-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-v28-mkmlizer: Downloaded to shared memory in 88.901s
junhua024-chai-02-full-54657-v28-mkmlizer: Checking if junhua024/chai_02_full_02_019 already exists in ChaiML
junhua024-chai-02-full-54657-v28-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmp8b8cn71u, device:0
junhua024-chai-02-full-54657-v28-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-02-full-54657-v28-mkmlizer: quantized model in 166.638s
junhua024-chai-02-full-54657-v28-mkmlizer: Processed model junhua024/chai_02_full_02_019 in 255.633s
junhua024-chai-02-full-54657-v28-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-02-full-54657-v28-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-02-full-54657-v28-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-02-full-54657-v28/nvidia
junhua024-chai-02-full-54657-v28-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-02-full-54657-v28/nvidia/config.json
junhua024-chai-02-full-54657-v28-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-02-full-54657-v28/nvidia/special_tokens_map.json
junhua024-chai-02-full-54657-v28-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-02-full-54657-v28/nvidia/tokenizer_config.json
junhua024-chai-02-full-54657-v28-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-02-full-54657-v28/nvidia/tokenizer.json
junhua024-chai-02-full-54657-v28-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-02-full-54657-v28/nvidia/flywheel_model.0.safetensors
Job junhua024-chai-02-full-54657-v28-mkmlizer completed after 284.52s with status: succeeded
Stopping job with name junhua024-chai-02-full-54657-v28-mkmlizer
Pipeline stage MKMLizer completed in 285.01s
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-02-full-54657-v28
Waiting for inference service junhua024-chai-02-full-54657-v28 to be ready
Inference service junhua024-chai-02-full-54657-v28 ready after 191.40864157676697s
Pipeline stage MKMLDeployer completed in 191.85s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1941733360290527s
Received healthy response to inference request in 1.1838746070861816s
Received healthy response to inference request in 1.2344379425048828s
Received healthy response to inference request in 1.778543472290039s
Received healthy response to inference request in 1.7087740898132324s
5 requests
0 failed requests
5th percentile: 1.1939872741699218
10th percentile: 1.2040999412536622
20th percentile: 1.2243252754211427
30th percentile: 1.3293051719665527
40th percentile: 1.5190396308898926
50th percentile: 1.7087740898132324
60th percentile: 1.736681842803955
70th percentile: 1.7645895957946778
80th percentile: 1.861669445037842
90th percentile: 2.0279213905334474
95th percentile: 2.11104736328125
99th percentile: 2.1775481414794924
mean time: 1.6199606895446776
Pipeline stage StressChecker completed in 9.34s
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 0.70s
Shutdown handler de-registered
junhua024-chai-02-full_54657_v28 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 0.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service junhua024-chai-02-full-54657-v28-profiler
Waiting for inference service junhua024-chai-02-full-54657-v28-profiler to be ready
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 5873.81s
Shutdown handler de-registered
junhua024-chai-02-full_54657_v28 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-02-full_54657_v28 status is now torndown due to DeploymentManager action