junhua024-chai-02-full-0615

developer_uid: junhua024

submission_id: junhua024-chai-02-full-0615_v3

model_name: junhua024-chai-02-full-0615_v3

model_group: junhua024/chai_02_full_0

status: torndown

timestamp: 2025-07-16T19:22:46+00:00

num_battles: 10258

num_wins: 5088

celo_rating: 1278.98

family_friendly_score: 0.5552

family_friendly_standard_error: 0.007027844050631744

submission_type: basic

model_repo: junhua024/chai_02_full_0615

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': 0.6022881289467629, 'latency_mean': 1.6602092635631562, 'latency_p50': 1.6503795385360718, 'latency_p90': 1.8442898035049438}, {'batch_size': 3, 'throughput': 1.0841640242525528, 'latency_mean': 2.7547865355014802, 'latency_p50': 2.723299503326416, 'latency_p90': 3.047541928291321}, {'batch_size': 5, 'throughput': 1.2949719892990887, 'latency_mean': 3.8458939492702484, 'latency_p50': 3.836767792701721, 'latency_p90': 4.2927748441696165}, {'batch_size': 6, 'throughput': 1.3452836410926126, 'latency_mean': 4.433275678157806, 'latency_p50': 4.454354286193848, 'latency_p90': 5.0355148077011105}, {'batch_size': 8, 'throughput': 1.4139958938532908, 'latency_mean': 5.60668184876442, 'latency_p50': 5.591014266014099, 'latency_p90': 6.337573623657226}, {'batch_size': 10, 'throughput': 1.4395020060206498, 'latency_mean': 6.898108060359955, 'latency_p50': 6.878284454345703, 'latency_p90': 7.768221592903137}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-02-full-0615_v3

is_internal_developer: False

language_model: junhua024/chai_02_full_0615

model_size: 13B

ranking_group: single

throughput_3p7s: 1.28

us_pacific_date: 2025-07-16

win_ratio: 0.49600311951647497

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-02-full-0615-v3-mkmlizer
Waiting for job on junhua024-chai-02-full-0615-v3-mkmlizer to finish
junhua024-chai-02-full-0615-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-02-full-0615-v3-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-0615-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-02-full-0615-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-02-full-0615-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-02-full-0615-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-02-full-0615-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-02-full-0615-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-02-full-0615-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-02-full-0615-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-02-full-0615-v3-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-0615-v3-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-02-full-0615-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-02-full-0615-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-02-full-0615-v3-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-02-full-0615-v3-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-0615-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-02-full-0615-v3-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-02-full-0615-v3-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-0615-v3-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-02-full-0615-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-02-full-0615-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-02-full-0615-v3-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-0615-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-v3-mkmlizer: Downloaded to shared memory in 107.474s
junhua024-chai-02-full-0615-v3-mkmlizer: Checking if junhua024/chai_02_full_0615 already exists in ChaiML
junhua024-chai-02-full-0615-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcnn69plq, device:0
junhua024-chai-02-full-0615-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-02-full-0615-v3-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-02-full-0615-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-02-full-0615-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-02-full-0615-v3/nvidia
junhua024-chai-02-full-0615-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-02-full-0615-v3/nvidia/config.json
junhua024-chai-02-full-0615-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-02-full-0615-v3/nvidia/special_tokens_map.json
junhua024-chai-02-full-0615-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-02-full-0615-v3/nvidia/tokenizer_config.json
junhua024-chai-02-full-0615-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-02-full-0615-v3/nvidia/tokenizer.json
junhua024-chai-02-full-0615-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:22, 16.25it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:19, 18.41it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 30.89it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:11, 31.13it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:09, 34.05it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:06, 48.03it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:08, 37.24it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:08, 36.74it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:08, 38.89it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:09, 32.00it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:09, 30.81it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 31.71it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:09, 31.38it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:08, 35.09it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:08, 34.58it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 34.57it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:07, 38.67it/s]
Loading 0:  26%|██▌       | 93/363 [00:02<00:07, 35.43it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:08, 31.24it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:08, 31.82it/s]
Loading 0:  29%|██▉       | 105/363 [00:03<00:08, 30.64it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:06, 39.23it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:07, 33.09it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:07, 32.56it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:06, 35.40it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:06, 34.03it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 34.91it/s]
Loading 0:  39%|███▉      | 143/363 [00:04<00:06, 35.12it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 36.49it/s]
Loading 0:  43%|████▎     | 155/363 [00:04<00:04, 41.77it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 40.12it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 38.36it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 37.48it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:04, 42.53it/s]
Loading 0:  50%|████▉     | 181/363 [00:05<00:05, 35.13it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 34.02it/s]
Loading 0:  52%|█████▏    | 190/363 [00:05<00:04, 37.61it/s]
Loading 0:  53%|█████▎    | 194/363 [00:05<00:05, 29.89it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 33.71it/s]
Loading 0:  57%|█████▋    | 206/363 [00:05<00:04, 34.07it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:04, 35.43it/s]
Loading 0:  61%|██████    | 220/363 [00:06<00:03, 44.91it/s]
Loading 0:  62%|██████▏   | 225/363 [00:06<00:04, 33.42it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:03, 34.00it/s]
Loading 0:  66%|██████▌   | 239/363 [00:06<00:02, 41.84it/s]
Loading 0:  67%|██████▋   | 244/363 [00:06<00:03, 35.39it/s]
Loading 0:  68%|██████▊   | 248/363 [00:07<00:03, 34.75it/s]
Loading 0:  70%|██████▉   | 254/363 [00:07<00:02, 36.70it/s]
Loading 0:  71%|███████   | 258/363 [00:07<00:02, 35.65it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 35.51it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 33.82it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 34.20it/s]
Loading 0:  77%|███████▋  | 281/363 [00:07<00:02, 39.31it/s]
Loading 0:  79%|███████▉  | 286/363 [00:08<00:02, 37.67it/s]
Loading 0:  80%|███████▉  | 290/363 [00:08<00:02, 35.92it/s]
Loading 0:  81%|████████  | 294/363 [00:08<00:02, 33.97it/s]
Loading 0:  83%|████████▎ | 302/363 [00:08<00:01, 41.07it/s]
Loading 0:  85%|████████▍ | 307/363 [00:08<00:01, 35.71it/s]
Loading 0:  86%|████████▌ | 311/363 [00:08<00:01, 34.22it/s]
Loading 0:  87%|████████▋ | 317/363 [00:08<00:01, 36.61it/s]
Loading 0:  88%|████████▊ | 321/363 [00:09<00:01, 35.08it/s]
Loading 0:  90%|█████████ | 327/363 [00:09<00:01, 34.57it/s]
Loading 0:  91%|█████████▏| 332/363 [00:09<00:00, 34.18it/s]
Loading 0:  93%|█████████▎| 338/363 [00:09<00:00, 34.98it/s]
Loading 0:  95%|█████████▌| 346/363 [00:09<00:00, 44.29it/s]
Loading 0:  97%|█████████▋| 351/363 [00:10<00:00, 24.81it/s]
Loading 0:  98%|█████████▊| 355/363 [00:10<00:00, 26.89it/s]
Loading 0:  99%|█████████▉| 360/363 [00:10<00:00, 30.80it/s]
                                                            
Job junhua024-chai-02-full-0615-v3-mkmlizer completed after 170.27s with status: succeeded
Stopping job with name junhua024-chai-02-full-0615-v3-mkmlizer
Pipeline stage MKMLizer completed in 171.21s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-02-full-0615-v3
Waiting for inference service junhua024-chai-02-full-0615-v3 to be ready
Inference service junhua024-chai-02-full-0615-v3 ready after 271.9481449127197s
Pipeline stage MKMLDeployer completed in 272.49s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5123729705810547s
Received healthy response to inference request in 1.809997320175171s
Received healthy response to inference request in 1.4875397682189941s
Received healthy response to inference request in 1.5489046573638916s
Received healthy response to inference request in 1.524120569229126s
5 requests
0 failed requests
5th percentile: 1.4948559284210206
10th percentile: 1.502172088623047
20th percentile: 1.5168044090270996
30th percentile: 1.5290773868560792
40th percentile: 1.5389910221099854
50th percentile: 1.5489046573638916
60th percentile: 1.6533417224884033
70th percentile: 1.757778787612915
80th percentile: 1.9504724502563477
90th percentile: 2.231422710418701
95th percentile: 2.371897840499878
99th percentile: 2.4842779445648193
mean time: 1.7765870571136475
Pipeline stage StressChecker completed in 10.30s
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 0.75s
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 0.80s
Shutdown handler de-registered
junhua024-chai-02-full-0615_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
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 9868.14s
Shutdown handler de-registered
junhua024-chai-02-full-0615_v3 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-02-full-0615_v3 status is now torndown due to DeploymentManager action
junhua024-chai-02-full-0615_v3 status is now torndown due to DeploymentManager action