junhua024-chai-1-full-06612

developer_uid: junhua024

submission_id: junhua024-chai-1-full-06612_v2

model_name: junhua024-chai-1-full-06612_v2

model_group: junhua024/chai_1-full_06

status: torndown

timestamp: 2025-06-29T17:49:43+00:00

num_battles: 7408

num_wins: 3610

celo_rating: 1264.99

family_friendly_score: 0.5604

family_friendly_standard_error: 0.007019285433717595

submission_type: basic

model_repo: junhua024/chai_1-full_06612

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': 0.5965561756376762, 'latency_mean': 1.676103311777115, 'latency_p50': 1.6729899644851685, 'latency_p90': 1.838883399963379}, {'batch_size': 3, 'throughput': 1.083916238067959, 'latency_mean': 2.7570726084709167, 'latency_p50': 2.760830521583557, 'latency_p90': 3.0226759195327757}, {'batch_size': 5, 'throughput': 1.3031184134802745, 'latency_mean': 3.8191508758068085, 'latency_p50': 3.7908992767333984, 'latency_p90': 4.29655351638794}, {'batch_size': 6, 'throughput': 1.3509734334402093, 'latency_mean': 4.419151155948639, 'latency_p50': 4.418692231178284, 'latency_p90': 4.98936173915863}, {'batch_size': 8, 'throughput': 1.4187876306015805, 'latency_mean': 5.592625243663788, 'latency_p50': 5.508734107017517, 'latency_p90': 6.3110647916793825}, {'batch_size': 10, 'throughput': 1.4555166952937733, 'latency_mean': 6.816648355722427, 'latency_p50': 6.8417969942092896, 'latency_p90': 7.703518652915955}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-1-full-06612_v2

is_internal_developer: False

language_model: junhua024/chai_1-full_06612

model_size: 13B

ranking_group: single

throughput_3p7s: 1.29

us_pacific_date: 2025-06-29

win_ratio: 0.4873110151187905

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.2, 'top_k': 40, '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': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{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-06612-v2-mkmlizer
Waiting for job on junhua024-chai-1-full-06612-v2-mkmlizer to finish
junhua024-chai-1-full-06612-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-1-full-06612-v2-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-06612-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-1-full-06612-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-1-full-06612-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-1-full-06612-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-1-full-06612-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-1-full-06612-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-1-full-06612-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-1-full-06612-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-1-full-06612-v2-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-06612-v2-mkmlizer: ║  Version: 0.29.3                                                    ║
junhua024-chai-1-full-06612-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-1-full-06612-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-1-full-06612-v2-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-1-full-06612-v2-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-06612-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-1-full-06612-v2-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-1-full-06612-v2-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-06612-v2-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-1-full-06612-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-1-full-06612-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-1-full-06612-v2-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-06612-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-1-full-06612-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-1-full-06612-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-1-full-06612-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-1-full-06612-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-1-full-06612-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-1-full-06612-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-1-full-06612-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-1-full-06612-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-1-full-06612-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-1-full-06612-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-1-full-06612-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-1-full-06612-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-1-full-06612-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-1-full-06612-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-1-full-06612-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-1-full-06612-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-1-full-06612-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-1-full-06612-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-1-full-06612-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-1-full-06612-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-1-full-06612-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-1-full-06612-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`
Failed to get response for submission junhua024-chai-1-full-06611_v3: HTTPConnectionPool(host='junhua024-chai-1-full-06611-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-1-full-06612-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-1-full-06612-v2-mkmlizer: Downloaded to shared memory in 155.006s
junhua024-chai-1-full-06612-v2-mkmlizer: Checking if junhua024/chai_1-full_06612 already exists in ChaiML
junhua024-chai-1-full-06612-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5ac928nu, device:0
junhua024-chai-1-full-06612-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-1-full-06612-v2-mkmlizer: quantized model in 56.518s
junhua024-chai-1-full-06612-v2-mkmlizer: Processed model junhua024/chai_1-full_06612 in 211.626s
junhua024-chai-1-full-06612-v2-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-1-full-06612-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-1-full-06612-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-1-full-06612-v2
junhua024-chai-1-full-06612-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-1-full-06612-v2/special_tokens_map.json
junhua024-chai-1-full-06612-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-1-full-06612-v2/config.json
junhua024-chai-1-full-06612-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-1-full-06612-v2/tokenizer_config.json
junhua024-chai-1-full-06612-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-1-full-06612-v2/tokenizer.json
junhua024-chai-1-full-06612-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-1-full-06612-v2/flywheel_model.0.safetensors
Job junhua024-chai-1-full-06612-v2-mkmlizer completed after 252.77s with status: succeeded
Stopping job with name junhua024-chai-1-full-06612-v2-mkmlizer
Pipeline stage MKMLizer completed in 253.41s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-1-full-06612-v2
Waiting for inference service junhua024-chai-1-full-06612-v2 to be ready
Inference service junhua024-chai-1-full-06612-v2 ready after 190.67073225975037s
Pipeline stage MKMLDeployer completed in 191.45s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2617857456207275s
Received healthy response to inference request in 1.820688247680664s
Received healthy response to inference request in 1.6438653469085693s
Received healthy response to inference request in 1.757826328277588s
Received healthy response to inference request in 1.948991060256958s
5 requests
0 failed requests
5th percentile: 1.6666575431823731
10th percentile: 1.6894497394561767
20th percentile: 1.735034132003784
30th percentile: 1.7703987121582032
40th percentile: 1.7955434799194336
50th percentile: 1.820688247680664
60th percentile: 1.8720093727111817
70th percentile: 1.9233304977416992
80th percentile: 2.011549997329712
90th percentile: 2.1366678714752196
95th percentile: 2.1992268085479734
99th percentile: 2.2492739582061767
mean time: 1.8866313457489015
Pipeline stage StressChecker completed in 11.29s
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 0.77s
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 0.82s
Shutdown handler de-registered
junhua024-chai-1-full-06612_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5396.44s
Shutdown handler de-registered
junhua024-chai-1-full-06612_v2 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-1-full-06612_v2 status is now torndown due to DeploymentManager action