junhua024-chai-02-full_54657

developer_uid: junhua024

submission_id: junhua024-chai-02-full_54657_v33

model_name: junhua024-chai-02-full_54657_v33

model_group: junhua024/chai_02_full_0

status: torndown

timestamp: 2025-07-25T07:06:39+00:00

num_battles: 6591

num_wins: 3443

celo_rating: 1303.72

family_friendly_score: 0.41500000000000004

family_friendly_standard_error: 0.006968141789602161

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': 0.5234408250920607, 'latency_mean': 1.9102824330329895, 'latency_p50': 1.9198912382125854, 'latency_p90': 2.063078427314758}, {'batch_size': 2, 'throughput': 0.6974793851078956, 'latency_mean': 2.865380688905716, 'latency_p50': 2.852170705795288, 'latency_p90': 3.094796013832092}, {'batch_size': 3, 'throughput': 0.7834142008538473, 'latency_mean': 3.8175205111503603, 'latency_p50': 3.8298064470291138, 'latency_p90': 4.113762259483337}, {'batch_size': 4, 'throughput': 0.842203514169775, 'latency_mean': 4.730281199216843, 'latency_p50': 4.758936762809753, 'latency_p90': 5.214960622787475}, {'batch_size': 5, 'throughput': 0.8654745304081136, 'latency_mean': 5.754376285076141, 'latency_p50': 5.734850883483887, 'latency_p90': 6.381744170188903}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-02-full_54657_v33

is_internal_developer: False

language_model: junhua024/chai_02_full_02_019

model_size: 13B

ranking_group: single

throughput_3p7s: 0.78

us_pacific_date: 2025-07-25

win_ratio: 0.5223790016689425

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 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-v33-mkmlizer
Waiting for job on junhua024-chai-02-full-54657-v33-mkmlizer to finish
Retrying (%r) after connection broken by '%r': %s
Failed to get response for submission chaiml-grpo-nis-12bsftqw_4593_v1: HTTPConnectionPool(host='chaiml-grpo-nis-12bsftqw-4593-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-02-full-54657-v33-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-02-full-54657-v33-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-54657-v33-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-02-full-54657-v33-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-02-full-54657-v33-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-02-full-54657-v33-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-02-full-54657-v33-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-02-full-54657-v33-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-02-full-54657-v33-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-02-full-54657-v33-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-02-full-54657-v33-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-54657-v33-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-02-full-54657-v33-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-02-full-54657-v33-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-02-full-54657-v33-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-02-full-54657-v33-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-54657-v33-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-02-full-54657-v33-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-02-full-54657-v33-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-54657-v33-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-02-full-54657-v33-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-02-full-54657-v33-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-02-full-54657-v33-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-54657-v33-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-02-full-54657-v33-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-v33-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-v33-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-v33-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-v33-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-v33-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-v33-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-v33-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-v33-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-v33-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-v33-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-v33-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-v33-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-v33-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-v33-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-v33-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-v33-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-v33-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-v33-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-v33-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-v33-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-v33-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-v33-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-v33-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-v33-mkmlizer: Downloaded to shared memory in 74.410s
junhua024-chai-02-full-54657-v33-mkmlizer: Checking if junhua024/chai_02_full_02_019 already exists in ChaiML
junhua024-chai-02-full-54657-v33-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmp9f5rbbq0, device:0
junhua024-chai-02-full-54657-v33-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Retrying (%r) after connection broken by '%r': %s
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', '')
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-v33-mkmlizer: quantized model in 162.793s
junhua024-chai-02-full-54657-v33-mkmlizer: Processed model junhua024/chai_02_full_02_019 in 237.284s
junhua024-chai-02-full-54657-v33-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-02-full-54657-v33-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-02-full-54657-v33-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-02-full-54657-v33/nvidia
junhua024-chai-02-full-54657-v33-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-02-full-54657-v33/nvidia/config.json
junhua024-chai-02-full-54657-v33-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-02-full-54657-v33/nvidia/special_tokens_map.json
junhua024-chai-02-full-54657-v33-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-02-full-54657-v33/nvidia/tokenizer_config.json
junhua024-chai-02-full-54657-v33-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-02-full-54657-v33/nvidia/tokenizer.json
junhua024-chai-02-full-54657-v33-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-02-full-54657-v33/nvidia/flywheel_model.0.safetensors
Job junhua024-chai-02-full-54657-v33-mkmlizer completed after 408.78s with status: succeeded
Stopping job with name junhua024-chai-02-full-54657-v33-mkmlizer
Pipeline stage MKMLizer completed in 409.40s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.36s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-02-full-54657-v33
Waiting for inference service junhua024-chai-02-full-54657-v33 to be ready
Failed to get response for submission chaiml-grpo-nis-12bsftqw_4593_v1: HTTPConnectionPool(host='chaiml-grpo-nis-12bsftqw-4593-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
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', '')
Failed to get response for submission chaiml-grpo-nis-12bsftqw_4593_v1: HTTPConnectionPool(host='chaiml-grpo-nis-12bsftqw-4593-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-02-full-54657-v33 ready after 191.33491015434265s
Pipeline stage MKMLDeployer completed in 191.84s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8864426612854004s
Received healthy response to inference request in 1.3612346649169922s
Received healthy response to inference request in 2.2875819206237793s
Received healthy response to inference request in 1.358841896057129s
Received healthy response to inference request in 1.5663104057312012s
5 requests
0 failed requests
5th percentile: 1.3593204498291016
10th percentile: 1.3597990036010743
20th percentile: 1.3607561111450195
30th percentile: 1.402249813079834
40th percentile: 1.4842801094055176
50th percentile: 1.5663104057312012
60th percentile: 1.6943633079528808
70th percentile: 1.8224162101745605
80th percentile: 1.9666705131530762
90th percentile: 2.1271262168884277
95th percentile: 2.2073540687561035
99th percentile: 2.271536350250244
mean time: 1.6920823097229003
Pipeline stage StressChecker completed in 10.18s
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 0.67s
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 0.67s
Shutdown handler de-registered
junhua024-chai-02-full_54657_v33 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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service junhua024-chai-02-full-54657-v33-profiler
Waiting for inference service junhua024-chai-02-full-54657-v33-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 4761.89s
Shutdown handler de-registered
junhua024-chai-02-full_54657_v33 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-02-full_54657_v33 status is now torndown due to DeploymentManager action