developer_uid: junhua024
submission_id: junhua024-chai-1-full-066126_v37
model_name: junhua024-chai-1-full-066126_v37
model_group: junhua024/chai-1-full-06
status: torndown
timestamp: 2025-07-14T15:53:13+00:00
num_battles: 7441
num_wins: 3612
celo_rating: 1284.45
family_friendly_score: 0.5498000000000001
family_friendly_standard_error: 0.007035907333102107
submission_type: basic
model_repo: junhua024/chai-1-full-066126
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': 0.5878127060620162, 'latency_mean': 1.7010484731197357, 'latency_p50': 1.6958507299423218, 'latency_p90': 1.8760185480117797}, {'batch_size': 3, 'throughput': 1.0733786586103111, 'latency_mean': 2.77656103849411, 'latency_p50': 2.762786030769348, 'latency_p90': 3.122843933105469}, {'batch_size': 5, 'throughput': 1.2750160657783636, 'latency_mean': 3.9102362000942232, 'latency_p50': 3.9119778871536255, 'latency_p90': 4.3901226043701165}, {'batch_size': 6, 'throughput': 1.3502536417643267, 'latency_mean': 4.422375127077102, 'latency_p50': 4.414757966995239, 'latency_p90': 4.973336219787598}, {'batch_size': 8, 'throughput': 1.409380914155182, 'latency_mean': 5.63116664648056, 'latency_p50': 5.634979963302612, 'latency_p90': 6.338162183761597}, {'batch_size': 10, 'throughput': 1.4329628573446864, 'latency_mean': 6.932853447198868, 'latency_p50': 6.931684374809265, 'latency_p90': 7.692582321166992}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: junhua024-chai-1-full-066126_v37
is_internal_developer: False
language_model: junhua024/chai-1-full-066126
model_size: 13B
ranking_group: single
throughput_3p7s: 1.25
us_pacific_date: 2025-07-14
win_ratio: 0.4854186265286924
generation_params: {'temperature': 1.0, 'top_p': 0.94, '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-1-full-066126-v37-mkmlizer
Waiting for job on junhua024-chai-1-full-066126-v37-mkmlizer to finish
junhua024-chai-1-full-066126-v37-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-1-full-066126-v37-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v37-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-1-full-066126-v37-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-1-full-066126-v37-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-1-full-066126-v37-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-1-full-066126-v37-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-1-full-066126-v37-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-1-full-066126-v37-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-1-full-066126-v37-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-1-full-066126-v37-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v37-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-1-full-066126-v37-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-1-full-066126-v37-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-1-full-066126-v37-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-1-full-066126-v37-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v37-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-1-full-066126-v37-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-1-full-066126-v37-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v37-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-1-full-066126-v37-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-1-full-066126-v37-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-1-full-066126-v37-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v37-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-1-full-066126-v37-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-1-full-066126-v37-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-1-full-066126-v37-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-1-full-066126-v37-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-1-full-066126-v37-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-1-full-066126-v37-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-1-full-066126-v37-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-1-full-066126-v37-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-1-full-066126-v37-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-1-full-066126-v37-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-1-full-066126-v37-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-1-full-066126-v37-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-1-full-066126-v37-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-1-full-066126-v37-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-1-full-066126-v37-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-1-full-066126-v37-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-1-full-066126-v37-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-1-full-066126-v37-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-1-full-066126-v37-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-1-full-066126-v37-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-1-full-066126-v37-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-1-full-066126-v37-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-1-full-066126-v37-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-1-full-066126-v37-mkmlizer: Downloaded to shared memory in 76.752s
junhua024-chai-1-full-066126-v37-mkmlizer: Checking if junhua024/chai-1-full-066126 already exists in ChaiML
junhua024-chai-1-full-066126-v37-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2fbflg2o, device:0
junhua024-chai-1-full-066126-v37-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-1-full-066126-v37-mkmlizer: quantized model in 31.110s
junhua024-chai-1-full-066126-v37-mkmlizer: Processed model junhua024/chai-1-full-066126 in 107.947s
junhua024-chai-1-full-066126-v37-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-1-full-066126-v37-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-1-full-066126-v37-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v37/nvidia
junhua024-chai-1-full-066126-v37-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v37/nvidia/special_tokens_map.json
junhua024-chai-1-full-066126-v37-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v37/nvidia/config.json
junhua024-chai-1-full-066126-v37-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v37/nvidia/tokenizer_config.json
junhua024-chai-1-full-066126-v37-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v37/nvidia/tokenizer.json
Job junhua024-chai-1-full-066126-v37-mkmlizer completed after 136.65s with status: succeeded
Stopping job with name junhua024-chai-1-full-066126-v37-mkmlizer
Pipeline stage MKMLizer completed in 137.64s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.51s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-1-full-066126-v37
Waiting for inference service junhua024-chai-1-full-066126-v37 to be ready
Failed to get response for submission chaiml-gy-exp162-lipo-g_57472_v2: HTTPConnectionPool(host='chaiml-gy-exp162-lipo-g-57472-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-gy-exp162-lipo-g_57472_v2: HTTPConnectionPool(host='chaiml-gy-exp162-lipo-g-57472-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-1-full-066126-v37 ready after 232.9186282157898s
Pipeline stage MKMLDeployer completed in 233.86s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 5.746430397033691s
Received healthy response to inference request in 1.9780349731445312s
Received healthy response to inference request in 1.7526335716247559s
Received healthy response to inference request in 1.9654943943023682s
Received healthy response to inference request in 1.9825210571289062s
5 requests
0 failed requests
5th percentile: 1.7952057361602782
10th percentile: 1.8377779006958008
20th percentile: 1.9229222297668458
30th percentile: 1.9680025100708007
40th percentile: 1.973018741607666
50th percentile: 1.9780349731445312
60th percentile: 1.9798294067382813
70th percentile: 1.9816238403320312
80th percentile: 2.735302925109864
90th percentile: 4.240866661071777
95th percentile: 4.9936485290527335
99th percentile: 5.5958740234375
mean time: 2.6850228786468504
Pipeline stage StressChecker completed in 16.80s
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 2.25s
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 1.26s
Shutdown handler de-registered
junhua024-chai-1-full-066126_v37 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 4699.00s
Shutdown handler de-registered
junhua024-chai-1-full-066126_v37 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-1-full-066126_v37 status is now torndown due to DeploymentManager action