junhua024-chai-06-full-_88520

developer_uid: junhua024

submission_id: junhua024-chai-06-full-_88520_v2

model_name: junhua024-chai-06-full-_88520_v2

model_group: junhua024/chai_06_full_0

status: torndown

timestamp: 2025-07-17T11:36:32+00:00

num_battles: 5667

num_wins: 2811

celo_rating: 1279.5

family_friendly_score: 0.5544

family_friendly_standard_error: 0.0070290915486995904

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': 0.594717683663622, 'latency_mean': 1.6813482284545898, 'latency_p50': 1.665496587753296, 'latency_p90': 1.8673821210861206}, {'batch_size': 3, 'throughput': 1.0772840373340218, 'latency_mean': 2.772907853126526, 'latency_p50': 2.7559707164764404, 'latency_p90': 3.095708799362183}, {'batch_size': 5, 'throughput': 1.2959239482860563, 'latency_mean': 3.838110098838806, 'latency_p50': 3.8566548824310303, 'latency_p90': 4.275497579574584}, {'batch_size': 6, 'throughput': 1.353000718570664, 'latency_mean': 4.40162644982338, 'latency_p50': 4.413097381591797, 'latency_p90': 4.916627073287964}, {'batch_size': 8, 'throughput': 1.4195726512317899, 'latency_mean': 5.600984754562378, 'latency_p50': 5.577932238578796, 'latency_p90': 6.295034575462341}, {'batch_size': 10, 'throughput': 1.4365167135655892, 'latency_mean': 6.904178657531738, 'latency_p50': 6.8909608125686646, 'latency_p90': 7.776622605323792}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-06-full-_88520_v2

is_internal_developer: False

language_model: junhua024/chai_06_full_02102_2529

model_size: 13B

ranking_group: single

throughput_3p7s: 1.28

us_pacific_date: 2025-07-17

win_ratio: 0.49602964531498145

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-v2-mkmlizer
Waiting for job on junhua024-chai-06-full-88520-v2-mkmlizer to finish
junhua024-chai-06-full-88520-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-06-full-88520-v2-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-88520-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-06-full-88520-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-06-full-88520-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-06-full-88520-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-06-full-88520-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-06-full-88520-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-06-full-88520-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-06-full-88520-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-06-full-88520-v2-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-88520-v2-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-06-full-88520-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-06-full-88520-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-06-full-88520-v2-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-06-full-88520-v2-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-88520-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-06-full-88520-v2-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-06-full-88520-v2-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-88520-v2-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-06-full-88520-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-06-full-88520-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-06-full-88520-v2-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-88520-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-06-full-88520-v2-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-v2-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-v2-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-v2-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-v2-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-v2-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-v2-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-v2-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-v2-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-v2-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-v2-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-v2-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-v2-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-v2-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-v2-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-v2-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-v2-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-v2-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-v2-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-v2-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-v2-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-v2-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-v2-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-v2-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-v2-mkmlizer: Downloaded to shared memory in 124.997s
junhua024-chai-06-full-88520-v2-mkmlizer: Checking if junhua024/chai_06_full_02102_2529 already exists in ChaiML
junhua024-chai-06-full-88520-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp05tz3212, device:0
junhua024-chai-06-full-88520-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-06-full-88520-v2-mkmlizer: quantized model in 33.636s
junhua024-chai-06-full-88520-v2-mkmlizer: Processed model junhua024/chai_06_full_02102_2529 in 158.713s
junhua024-chai-06-full-88520-v2-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-06-full-88520-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-06-full-88520-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-06-full-88520-v2/nvidia
junhua024-chai-06-full-88520-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-06-full-88520-v2/nvidia/config.json
junhua024-chai-06-full-88520-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-06-full-88520-v2/nvidia/special_tokens_map.json
junhua024-chai-06-full-88520-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-06-full-88520-v2/nvidia/tokenizer_config.json
junhua024-chai-06-full-88520-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-06-full-88520-v2/nvidia/tokenizer.json
junhua024-chai-06-full-88520-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-06-full-88520-v2/nvidia/flywheel_model.0.safetensors
Job junhua024-chai-06-full-88520-v2-mkmlizer completed after 190.46s with status: succeeded
Stopping job with name junhua024-chai-06-full-88520-v2-mkmlizer
Pipeline stage MKMLizer completed in 190.99s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-06-full-88520-v2
Waiting for inference service junhua024-chai-06-full-88520-v2 to be ready
Inference service junhua024-chai-06-full-88520-v2 ready after 291.07084584236145s
Pipeline stage MKMLDeployer completed in 291.69s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3306145668029785s
Received healthy response to inference request in 1.8904097080230713s
Received healthy response to inference request in 2.1933696269989014s
Received healthy response to inference request in 1.506528615951538s
Received healthy response to inference request in 1.8945395946502686s
5 requests
0 failed requests
5th percentile: 1.5833048343658447
10th percentile: 1.6600810527801513
20th percentile: 1.8136334896087647
30th percentile: 1.8912356853485108
40th percentile: 1.8928876399993897
50th percentile: 1.8945395946502686
60th percentile: 2.0140716075897216
70th percentile: 2.1336036205291746
80th percentile: 2.220818614959717
90th percentile: 2.2757165908813475
95th percentile: 2.303165578842163
99th percentile: 2.3251247692108152
mean time: 1.9630924224853517
Pipeline stage StressChecker completed in 11.06s
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 0.65s
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 1.03s
Shutdown handler de-registered
junhua024-chai-06-full-_88520_v2 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 2961.48s
Shutdown handler de-registered
junhua024-chai-06-full-_88520_v2 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-06-full-_88520_v2 status is now torndown due to DeploymentManager action
junhua024-chai-06-full-_88520_v2 status is now torndown due to DeploymentManager action