developer_uid: junhua024
submission_id: junhua024-chai-06-full-_33146_v3
model_name: junhua024-chai-06-full-_33146_v3
model_group: junhua024/chai_06_full_0
status: torndown
timestamp: 2025-07-18T21:05:41+00:00
num_battles: 10656
num_wins: 5161
celo_rating: 1277.29
family_friendly_score: 0.5552
family_friendly_standard_error: 0.007027844050631744
submission_type: basic
model_repo: junhua024/chai_06_full_02098_0106
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': 0.5933625702559365, 'latency_mean': 1.685135692358017, 'latency_p50': 1.6902518272399902, 'latency_p90': 1.8561915159225464}, {'batch_size': 3, 'throughput': 1.0660926200269454, 'latency_mean': 2.80400283575058, 'latency_p50': 2.822006940841675, 'latency_p90': 3.0752091646194457}, {'batch_size': 5, 'throughput': 1.2830561663319844, 'latency_mean': 3.8811909902095794, 'latency_p50': 3.8766255378723145, 'latency_p90': 4.363810896873474}, {'batch_size': 6, 'throughput': 1.3402063853556772, 'latency_mean': 4.447267078161239, 'latency_p50': 4.467689633369446, 'latency_p90': 4.97579026222229}, {'batch_size': 8, 'throughput': 1.4058431852285, 'latency_mean': 5.649857138395309, 'latency_p50': 5.672780156135559, 'latency_p90': 6.4022297859191895}, {'batch_size': 10, 'throughput': 1.4349522242156505, 'latency_mean': 6.913222198486328, 'latency_p50': 6.911878705024719, 'latency_p90': 7.8557565927505495}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: junhua024-chai-06-full-_33146_v3
is_internal_developer: False
language_model: junhua024/chai_06_full_02098_0106
model_size: 13B
ranking_group: single
throughput_3p7s: 1.26
us_pacific_date: 2025-07-18
win_ratio: 0.4843280780780781
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-33146-v3-mkmlizer
Waiting for job on junhua024-chai-06-full-33146-v3-mkmlizer to finish
junhua024-chai-06-full-33146-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-06-full-33146-v3-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-33146-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-06-full-33146-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-06-full-33146-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-06-full-33146-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-06-full-33146-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-06-full-33146-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-06-full-33146-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-06-full-33146-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-06-full-33146-v3-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-33146-v3-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-06-full-33146-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-06-full-33146-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-06-full-33146-v3-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-06-full-33146-v3-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-33146-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-06-full-33146-v3-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-06-full-33146-v3-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-33146-v3-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-06-full-33146-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-06-full-33146-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-06-full-33146-v3-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-33146-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-06-full-33146-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-33146-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-33146-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-33146-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-33146-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-33146-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-33146-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-33146-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-33146-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-33146-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-33146-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`
Failed to get response for submission junhua024-chai-12-full-_19228_v2: HTTPConnectionPool(host='junhua024-chai-12-full-19228-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-06-full-33146-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-33146-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-33146-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-33146-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-33146-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-33146-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-33146-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-33146-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-33146-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-33146-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-33146-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-33146-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-33146-v3-mkmlizer: Downloaded to shared memory in 261.119s
junhua024-chai-06-full-33146-v3-mkmlizer: Checking if junhua024/chai_06_full_02098_0106 already exists in ChaiML
junhua024-chai-06-full-33146-v3-mkmlizer: Creating repo ChaiML/chai_06_full_02098_0106 and uploading /tmp/tmp8n81y3gj to it
junhua024-chai-06-full-33146-v3-mkmlizer: 
  0%|          | 0/26 [00:00<?, ?it/s]
  4%|▍         | 1/26 [00:01<00:34,  1.39s/it]
  8%|▊         | 2/26 [00:03<00:41,  1.71s/it]
 12%|█▏        | 3/26 [00:05<00:40,  1.78s/it]
 15%|█▌        | 4/26 [00:06<00:36,  1.68s/it]
 19%|█▉        | 5/26 [00:07<00:31,  1.49s/it]
 23%|██▎       | 6/26 [00:09<00:32,  1.65s/it]
 27%|██▋       | 7/26 [00:11<00:30,  1.63s/it]
 31%|███       | 8/26 [00:12<00:27,  1.51s/it]
 35%|███▍      | 9/26 [00:14<00:28,  1.69s/it]
 38%|███▊      | 10/26 [00:16<00:25,  1.59s/it]
 42%|████▏     | 11/26 [00:17<00:21,  1.43s/it]
 46%|████▌     | 12/26 [00:20<00:29,  2.13s/it]
 50%|█████     | 13/26 [00:21<00:23,  1.81s/it]
 54%|█████▍    | 14/26 [00:23<00:19,  1.61s/it]
 58%|█████▊    | 15/26 [00:24<00:15,  1.42s/it]
 62%|██████▏   | 16/26 [00:25<00:14,  1.40s/it]
 65%|██████▌   | 17/26 [00:26<00:11,  1.28s/it]
 69%|██████▉   | 18/26 [00:27<00:10,  1.28s/it]
 73%|███████▎  | 19/26 [00:29<00:09,  1.29s/it]
 77%|███████▋  | 20/26 [00:32<00:12,  2.05s/it]
 81%|████████  | 21/26 [00:35<00:10,  2.13s/it]
 85%|████████▍ | 22/26 [00:36<00:07,  1.80s/it]
 88%|████████▊ | 23/26 [00:37<00:04,  1.66s/it]
 92%|█████████▏| 24/26 [00:43<00:05,  2.94s/it]
 96%|█████████▌| 25/26 [00:45<00:02,  2.52s/it]
100%|██████████| 26/26 [00:45<00:00,  1.97s/it]
100%|██████████| 26/26 [00:45<00:00,  1.76s/it]
junhua024-chai-06-full-33146-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8n81y3gj, device:0
junhua024-chai-06-full-33146-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-06-full-33146-v3-mkmlizer: quantized model in 30.580s
junhua024-chai-06-full-33146-v3-mkmlizer: Processed model junhua024/chai_06_full_02098_0106 in 362.934s
junhua024-chai-06-full-33146-v3-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-06-full-33146-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-06-full-33146-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-06-full-33146-v3/nvidia
junhua024-chai-06-full-33146-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-06-full-33146-v3/nvidia/special_tokens_map.json
junhua024-chai-06-full-33146-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-06-full-33146-v3/nvidia/config.json
junhua024-chai-06-full-33146-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-06-full-33146-v3/nvidia/tokenizer_config.json
junhua024-chai-06-full-33146-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-06-full-33146-v3/nvidia/tokenizer.json
junhua024-chai-06-full-33146-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-06-full-33146-v3/nvidia/flywheel_model.0.safetensors
Job junhua024-chai-06-full-33146-v3-mkmlizer completed after 387.92s with status: succeeded
Stopping job with name junhua024-chai-06-full-33146-v3-mkmlizer
Pipeline stage MKMLizer completed in 388.46s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-06-full-33146-v3
Waiting for inference service junhua024-chai-06-full-33146-v3 to be ready
Inference service junhua024-chai-06-full-33146-v3 ready after 331.7788360118866s
Pipeline stage MKMLDeployer completed in 332.41s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8464205265045166s
Received healthy response to inference request in 2.0866100788116455s
Received healthy response to inference request in 2.2123422622680664s
Received healthy response to inference request in 1.9411253929138184s
Received healthy response to inference request in 1.7290723323822021s
5 requests
0 failed requests
5th percentile: 1.7714829444885254
10th percentile: 1.8138935565948486
20th percentile: 1.8987147808074951
30th percentile: 1.9702223300933839
40th percentile: 2.0284162044525145
50th percentile: 2.0866100788116455
60th percentile: 2.136902952194214
70th percentile: 2.187195825576782
80th percentile: 2.3391579151153565
90th percentile: 2.5927892208099363
95th percentile: 2.7196048736572265
99th percentile: 2.8210573959350587
mean time: 2.1631141185760496
Pipeline stage StressChecker completed in 12.36s
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 0.76s
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 1.00s
Shutdown handler de-registered
junhua024-chai-06-full-_33146_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 4870.20s
Shutdown handler de-registered
junhua024-chai-06-full-_33146_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-glen-powell-rhet_64912_v1
junhua024-chai-06-full-_33146_v3 status is now torndown due to DeploymentManager action
Shutdown handler not registered because Python interpreter is not running in the main thread
junhua024-chai-06-full-_33146_v3 status is now torndown due to DeploymentManager action