junhua024-chai-16-full-_18823

developer_uid: junhua024

submission_id: junhua024-chai-16-full-_18823_v4

model_name: junhua024-chai-16-full-_18823_v4

model_group: junhua024/chai_16_full_1

status: torndown

timestamp: 2025-07-20T04:43:04+00:00

num_battles: 6661

num_wins: 3395

celo_rating: 1284.74

family_friendly_score: 0.552

family_friendly_standard_error: 0.007032723512267492

submission_type: basic

model_repo: junhua024/chai_16_full_106_qkv098_o_ffn_1925

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': 0.5953641765546233, 'latency_mean': 1.6795389556884766, 'latency_p50': 1.6810698509216309, 'latency_p90': 1.836604380607605}, {'batch_size': 3, 'throughput': 1.0666059618425419, 'latency_mean': 2.803639062643051, 'latency_p50': 2.812476634979248, 'latency_p90': 3.0744253158569337}, {'batch_size': 5, 'throughput': 1.290229190834056, 'latency_mean': 3.8572405326366423, 'latency_p50': 3.8562560081481934, 'latency_p90': 4.3246677160263065}, {'batch_size': 6, 'throughput': 1.3510843174138276, 'latency_mean': 4.420112905502319, 'latency_p50': 4.450361609458923, 'latency_p90': 4.896623229980468}, {'batch_size': 8, 'throughput': 1.4062479739397618, 'latency_mean': 5.65214181303978, 'latency_p50': 5.639400243759155, 'latency_p90': 6.429475498199462}, {'batch_size': 10, 'throughput': 1.4409890757084607, 'latency_mean': 6.88814486503601, 'latency_p50': 6.917436599731445, 'latency_p90': 7.880413699150085}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-16-full-_18823_v4

is_internal_developer: False

language_model: junhua024/chai_16_full_106_qkv098_o_ffn_1925

model_size: 13B

ranking_group: single

throughput_3p7s: 1.27

us_pacific_date: 2025-07-19

win_ratio: 0.5096832307461342

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-16-full-18823-v4-mkmlizer
Waiting for job on junhua024-chai-16-full-18823-v4-mkmlizer to finish
junhua024-chai-16-full-18823-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-16-full-18823-v4-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-18823-v4-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-16-full-18823-v4-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-16-full-18823-v4-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-16-full-18823-v4-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-16-full-18823-v4-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-16-full-18823-v4-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-16-full-18823-v4-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-16-full-18823-v4-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-16-full-18823-v4-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-18823-v4-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-16-full-18823-v4-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-16-full-18823-v4-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-16-full-18823-v4-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-16-full-18823-v4-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-18823-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-16-full-18823-v4-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-16-full-18823-v4-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-18823-v4-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-16-full-18823-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-16-full-18823-v4-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-16-full-18823-v4-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-18823-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-16-full-18823-v4-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-16-full-18823-v4-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-16-full-18823-v4-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-16-full-18823-v4-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-16-full-18823-v4-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-16-full-18823-v4-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-16-full-18823-v4-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-16-full-_63690_v1: HTTPConnectionPool(host='junhua024-chai-16-full-63690-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-16-full-18823-v4-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-16-full-18823-v4-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-16-full-18823-v4-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-16-full-18823-v4-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-16-full-18823-v4-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-16-full-18823-v4-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-16-full-_63690_v1: HTTPConnectionPool(host='junhua024-chai-16-full-63690-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission junhua024-chai-16-full-_63690_v2: HTTPConnectionPool(host='junhua024-chai-16-full-63690-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-16-full-18823-v4-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-16-full-18823-v4-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-16-full-18823-v4-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-16-full-18823-v4-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-16-full-18823-v4-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-16-full-18823-v4-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-16-full-18823-v4-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-16-full-18823-v4-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-16-full-18823-v4-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-16-full-18823-v4-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 chaiml-nis-qwen32b-sim_98336_v34: HTTPConnectionPool(host='chaiml-nis-qwen32b-sim-98336-v34-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission junhua024-chai-16-full-_63690_v1: HTTPConnectionPool(host='junhua024-chai-16-full-63690-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission junhua024-chai-16-full-_63690_v4: HTTPConnectionPool(host='junhua024-chai-16-full-63690-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-16-full-18823-v4-mkmlizer: quantized model in 32.570s
junhua024-chai-16-full-18823-v4-mkmlizer: Processed model junhua024/chai_16_full_106_qkv098_o_ffn_1925 in 108.885s
junhua024-chai-16-full-18823-v4-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-16-full-18823-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-16-full-18823-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-16-full-18823-v4/nvidia
junhua024-chai-16-full-18823-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-16-full-18823-v4/nvidia/config.json
junhua024-chai-16-full-18823-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-16-full-18823-v4/nvidia/special_tokens_map.json
junhua024-chai-16-full-18823-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-16-full-18823-v4/nvidia/tokenizer_config.json
junhua024-chai-16-full-18823-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-16-full-18823-v4/nvidia/tokenizer.json
Job junhua024-chai-16-full-18823-v4-mkmlizer completed after 139.34s with status: succeeded
Stopping job with name junhua024-chai-16-full-18823-v4-mkmlizer
Pipeline stage MKMLizer completed in 139.88s
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-16-full-18823-v4
Waiting for inference service junhua024-chai-16-full-18823-v4 to be ready
Failed to get response for submission junhua024-chai-16-full-_63690_v1: HTTPConnectionPool(host='junhua024-chai-16-full-63690-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission junhua024-chai-16-full-_63690_v1: HTTPConnectionPool(host='junhua024-chai-16-full-63690-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission junhua024-chai-16-full-_63690_v3: HTTPConnectionPool(host='junhua024-chai-16-full-63690-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission junhua024-chai-16-full-_63690_v1: HTTPConnectionPool(host='junhua024-chai-16-full-63690-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-16-full-18823-v4 ready after 332.7855975627899s
Pipeline stage MKMLDeployer completed in 333.32s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3292582035064697s
Received healthy response to inference request in 1.636646032333374s
Received healthy response to inference request in 2.457764148712158s
Received healthy response to inference request in 2.5296084880828857s
Received healthy response to inference request in 1.8693935871124268s
5 requests
0 failed requests
5th percentile: 1.6831955432891845
10th percentile: 1.729745054244995
20th percentile: 1.8228440761566163
30th percentile: 1.9613665103912354
40th percentile: 2.1453123569488524
50th percentile: 2.3292582035064697
60th percentile: 2.380660581588745
70th percentile: 2.4320629596710206
80th percentile: 2.472133016586304
90th percentile: 2.5008707523345945
95th percentile: 2.51523962020874
99th percentile: 2.5267347145080565
mean time: 2.164534091949463
Pipeline stage StressChecker completed in 12.59s
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 0.71s
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
Failed to get response for submission junhua024-chai-16-full-_63690_v4: HTTPConnectionPool(host='junhua024-chai-16-full-63690-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.97s
Shutdown handler de-registered
junhua024-chai-16-full-_18823_v4 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 4989.47s
Shutdown handler de-registered
junhua024-chai-16-full-_18823_v4 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-16-full-_18823_v4 status is now torndown due to DeploymentManager action