junhua024-chai-06-full-_56660

developer_uid: junhua024

submission_id: junhua024-chai-06-full-_56660_v3

model_name: junhua024-chai-06-full-_56660_v3

model_group: junhua024/chai_06_full_0

status: torndown

timestamp: 2025-07-17T13:53:56+00:00

num_battles: 8847

num_wins: 4334

celo_rating: 1278.23

family_friendly_score: 0.5522

family_friendly_standard_error: 0.007032427177013638

submission_type: basic

model_repo: junhua024/chai_06_full_02104_20241

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': 0.6003746548698029, 'latency_mean': 1.6654458475112914, 'latency_p50': 1.6666979789733887, 'latency_p90': 1.8257345676422119}, {'batch_size': 3, 'throughput': 1.0819255559909156, 'latency_mean': 2.764583798646927, 'latency_p50': 2.774477005004883, 'latency_p90': 3.0256233930587766}, {'batch_size': 5, 'throughput': 1.2996349625931654, 'latency_mean': 3.824491859674454, 'latency_p50': 3.7832270860671997, 'latency_p90': 4.362010908126831}, {'batch_size': 6, 'throughput': 1.3706127489307307, 'latency_mean': 4.3605853927135465, 'latency_p50': 4.361961007118225, 'latency_p90': 4.870956873893737}, {'batch_size': 8, 'throughput': 1.41499319427989, 'latency_mean': 5.607513383626938, 'latency_p50': 5.611316204071045, 'latency_p90': 6.303764009475708}, {'batch_size': 10, 'throughput': 1.4347588529040194, 'latency_mean': 6.911942276954651, 'latency_p50': 6.968255281448364, 'latency_p90': 7.746651005744934}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-06-full-_56660_v3

is_internal_developer: False

language_model: junhua024/chai_06_full_02104_20241

model_size: 13B

ranking_group: single

throughput_3p7s: 1.29

us_pacific_date: 2025-07-17

win_ratio: 0.48988357635356616

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-56660-v3-mkmlizer
Waiting for job on junhua024-chai-06-full-56660-v3-mkmlizer to finish
junhua024-chai-06-full-56660-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-06-full-56660-v3-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-56660-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-06-full-56660-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-06-full-56660-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-06-full-56660-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-06-full-56660-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-06-full-56660-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-06-full-56660-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-06-full-56660-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-06-full-56660-v3-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-56660-v3-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-06-full-56660-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-06-full-56660-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-06-full-56660-v3-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-06-full-56660-v3-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-56660-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-06-full-56660-v3-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-06-full-56660-v3-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-56660-v3-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-06-full-56660-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-06-full-56660-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-06-full-56660-v3-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-56660-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-06-full-56660-v3-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-56660-v3-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-56660-v3-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-56660-v3-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-56660-v3-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-56660-v3-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-56660-v3-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-56660-v3-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-56660-v3-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-56660-v3-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-56660-v3-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-56660-v3-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-56660-v3-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-56660-v3-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-56660-v3-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-56660-v3-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-56660-v3-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-56660-v3-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-56660-v3-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-56660-v3-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-56660-v3-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-56660-v3-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-56660-v3-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-56660-v3-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-56660-v3-mkmlizer: Downloaded to shared memory in 92.733s
junhua024-chai-06-full-56660-v3-mkmlizer: Checking if junhua024/chai_06_full_02104_20241 already exists in ChaiML
junhua024-chai-06-full-56660-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkv3vbk4h, device:0
junhua024-chai-06-full-56660-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-06-full-56660-v3-mkmlizer: quantized model in 31.233s
junhua024-chai-06-full-56660-v3-mkmlizer: Processed model junhua024/chai_06_full_02104_20241 in 124.029s
junhua024-chai-06-full-56660-v3-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-06-full-56660-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-06-full-56660-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-06-full-56660-v3/nvidia
junhua024-chai-06-full-56660-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-06-full-56660-v3/nvidia/config.json
junhua024-chai-06-full-56660-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-06-full-56660-v3/nvidia/special_tokens_map.json
junhua024-chai-06-full-56660-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-06-full-56660-v3/nvidia/tokenizer_config.json
junhua024-chai-06-full-56660-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-06-full-56660-v3/nvidia/tokenizer.json
junhua024-chai-06-full-56660-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-06-full-56660-v3/nvidia/flywheel_model.0.safetensors
Job junhua024-chai-06-full-56660-v3-mkmlizer completed after 149.54s with status: succeeded
Stopping job with name junhua024-chai-06-full-56660-v3-mkmlizer
Pipeline stage MKMLizer completed in 150.29s
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-56660-v3
Waiting for inference service junhua024-chai-06-full-56660-v3 to be ready
Failed to get response for submission junhua024-chai-1-full_94469_v115: HTTPConnectionPool(host='junhua024-chai-1-full-94469-v115-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission junhua024-chai-06-full-_75415_v1: HTTPConnectionPool(host='junhua024-chai-06-full-75415-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-06-full-_75415_v4: HTTPConnectionPool(host='junhua024-chai-06-full-75415-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-06-full-56660-v3 ready after 291.20163583755493s
Pipeline stage MKMLDeployer completed in 291.91s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3558340072631836s
Received healthy response to inference request in 1.597264051437378s
Received healthy response to inference request in 1.6430277824401855s
Received healthy response to inference request in 1.5435106754302979s
Received healthy response to inference request in 1.5287888050079346s
5 requests
0 failed requests
5th percentile: 1.5317331790924071
10th percentile: 1.53467755317688
20th percentile: 1.5405663013458253
30th percentile: 1.5542613506317138
40th percentile: 1.5757627010345459
50th percentile: 1.597264051437378
60th percentile: 1.615569543838501
70th percentile: 1.633875036239624
80th percentile: 1.7855890274047852
90th percentile: 2.0707115173339843
95th percentile: 2.2132727622985837
99th percentile: 2.3273217582702634
mean time: 1.733685064315796
Pipeline stage StressChecker completed in 10.46s
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 0.69s
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 0.74s
Shutdown handler de-registered
junhua024-chai-06-full-_56660_v3 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 4769.77s
Shutdown handler de-registered
junhua024-chai-06-full-_56660_v3 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-06-full-_56660_v3 status is now torndown due to DeploymentManager action
junhua024-chai-06-full-_56660_v3 status is now torndown due to DeploymentManager action