junhua024-chai-06-full-_21065

developer_uid: junhua024

submission_id: junhua024-chai-06-full-_21065_v3

model_name: junhua024-chai-06-full-_21065_v3

model_group: junhua024/chai_06_full_0

status: torndown

timestamp: 2025-07-17T12:13:06+00:00

num_battles: 5542

num_wins: 2841

celo_rating: 1283.47

family_friendly_score: 0.5518000000000001

family_friendly_standard_error: 0.007033018697543751

submission_type: basic

model_repo: junhua024/chai_06_full_02102_811

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': 0.5980172103366096, 'latency_mean': 1.672076712846756, 'latency_p50': 1.6829009056091309, 'latency_p90': 1.8393320083618163}, {'batch_size': 3, 'throughput': 1.0735863329700328, 'latency_mean': 2.787803353071213, 'latency_p50': 2.791212558746338, 'latency_p90': 3.04992241859436}, {'batch_size': 5, 'throughput': 1.2937693573226974, 'latency_mean': 3.844344767332077, 'latency_p50': 3.8863171339035034, 'latency_p90': 4.259343004226684}, {'batch_size': 6, 'throughput': 1.3482486724349494, 'latency_mean': 4.418221586942673, 'latency_p50': 4.4044389724731445, 'latency_p90': 4.951788330078125}, {'batch_size': 8, 'throughput': 1.4026452141934231, 'latency_mean': 5.6542141723632815, 'latency_p50': 5.658980488777161, 'latency_p90': 6.341725945472717}, {'batch_size': 10, 'throughput': 1.4502701189055949, 'latency_mean': 6.839306030273438, 'latency_p50': 6.856316447257996, 'latency_p90': 7.670635104179382}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-06-full-_21065_v3

is_internal_developer: False

language_model: junhua024/chai_06_full_02102_811

model_size: 13B

ranking_group: single

throughput_3p7s: 1.28

us_pacific_date: 2025-07-17

win_ratio: 0.5126308191988452

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-21065-v3-mkmlizer
Waiting for job on junhua024-chai-06-full-21065-v3-mkmlizer to finish
junhua024-chai-06-full-21065-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-06-full-21065-v3-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-21065-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-06-full-21065-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-06-full-21065-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-06-full-21065-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-06-full-21065-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-06-full-21065-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-06-full-21065-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-06-full-21065-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-06-full-21065-v3-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-21065-v3-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-06-full-21065-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-06-full-21065-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-06-full-21065-v3-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-06-full-21065-v3-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-21065-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-06-full-21065-v3-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-06-full-21065-v3-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-21065-v3-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-06-full-21065-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-06-full-21065-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-06-full-21065-v3-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-21065-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-06-full-21065-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-21065-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-21065-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-21065-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-21065-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-21065-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-21065-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-21065-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-21065-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-21065-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-21065-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-21065-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-21065-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-21065-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-21065-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-21065-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-21065-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-21065-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-21065-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-21065-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-21065-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-21065-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-21065-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-21065-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-21065-v3-mkmlizer: Downloaded to shared memory in 109.086s
junhua024-chai-06-full-21065-v3-mkmlizer: Checking if junhua024/chai_06_full_02102_811 already exists in ChaiML
junhua024-chai-06-full-21065-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8pf10v47, device:0
junhua024-chai-06-full-21065-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-06-full-21065-v3-mkmlizer: quantized model in 31.026s
junhua024-chai-06-full-21065-v3-mkmlizer: Processed model junhua024/chai_06_full_02102_811 in 140.196s
junhua024-chai-06-full-21065-v3-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-06-full-21065-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-06-full-21065-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-06-full-21065-v3/nvidia
junhua024-chai-06-full-21065-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-06-full-21065-v3/nvidia/tokenizer.json
junhua024-chai-06-full-21065-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-06-full-21065-v3/nvidia/flywheel_model.0.safetensors
junhua024-chai-06-full-21065-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:24, 14.99it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:20, 17.46it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 30.06it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 31.52it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 33.70it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:06, 47.36it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:08, 37.34it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:08, 35.74it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:07, 40.56it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:09, 31.09it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:09, 33.53it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 35.66it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:08, 34.42it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:08, 34.32it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:08, 32.91it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 38.16it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 36.39it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:07, 37.16it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:07, 37.12it/s]
Loading 0:  29%|██▉       | 105/363 [00:03<00:07, 34.66it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:06, 40.30it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:07, 33.95it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:07, 33.25it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:06, 34.78it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:06, 33.77it/s]
Loading 0:  38%|███▊      | 138/363 [00:03<00:06, 34.69it/s]
Loading 0:  39%|███▉      | 143/363 [00:04<00:06, 35.02it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:06, 35.21it/s]
Loading 0:  43%|████▎     | 157/363 [00:04<00:04, 44.52it/s]
Loading 0:  45%|████▍     | 162/363 [00:04<00:05, 34.54it/s]
Loading 0:  46%|████▌     | 167/363 [00:04<00:05, 34.91it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:04, 41.39it/s]
Loading 0:  50%|████▉     | 181/363 [00:05<00:05, 34.69it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 34.21it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:04, 35.96it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:04, 34.60it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 35.07it/s]
Loading 0:  57%|█████▋    | 206/363 [00:05<00:04, 34.87it/s]
Loading 0:  58%|█████▊    | 212/363 [00:05<00:04, 35.93it/s]
Loading 0:  61%|██████    | 220/363 [00:06<00:03, 45.07it/s]
Loading 0:  62%|██████▏   | 225/363 [00:06<00:04, 34.07it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:03, 33.34it/s]
Loading 0:  66%|██████▌   | 238/363 [00:06<00:02, 42.50it/s]
Loading 0:  67%|██████▋   | 243/363 [00:06<00:03, 32.51it/s]
Loading 0:  68%|██████▊   | 248/363 [00:06<00:03, 34.55it/s]
Loading 0:  70%|██████▉   | 254/363 [00:07<00:02, 36.51it/s]
Loading 0:  71%|███████▏  | 259/363 [00:07<00:02, 36.35it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 34.22it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 33.70it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 33.69it/s]
Loading 0:  77%|███████▋  | 281/363 [00:07<00:02, 37.85it/s]
Loading 0:  79%|███████▉  | 286/363 [00:08<00:02, 36.35it/s]
Loading 0:  80%|███████▉  | 290/363 [00:08<00:01, 36.70it/s]
Loading 0:  81%|████████  | 294/363 [00:08<00:01, 34.55it/s]
Loading 0:  83%|████████▎ | 302/363 [00:08<00:01, 39.64it/s]
Loading 0:  84%|████████▍ | 306/363 [00:08<00:01, 31.52it/s]
Loading 0:  86%|████████▌ | 311/363 [00:08<00:01, 33.28it/s]
Loading 0:  87%|████████▋ | 317/363 [00:08<00:01, 35.12it/s]
Loading 0:  88%|████████▊ | 321/363 [00:09<00:01, 32.52it/s]
Loading 0:  90%|████████▉ | 326/363 [00:09<00:01, 35.51it/s]
Loading 0:  91%|█████████ | 331/363 [00:09<00:00, 33.82it/s]
Loading 0:  93%|█████████▎| 336/363 [00:09<00:00, 35.63it/s]
Loading 0:  94%|█████████▎| 340/363 [00:09<00:00, 34.62it/s]
Loading 0:  95%|█████████▌| 346/363 [00:09<00:00, 40.19it/s]
Loading 0:  97%|█████████▋| 351/363 [00:10<00:00, 22.32it/s]
Loading 0:  98%|█████████▊| 355/363 [00:10<00:00, 24.70it/s]
Loading 0:  99%|█████████▉| 360/363 [00:10<00:00, 29.06it/s]
                                                            
Job junhua024-chai-06-full-21065-v3-mkmlizer completed after 160.29s with status: succeeded
Stopping job with name junhua024-chai-06-full-21065-v3-mkmlizer
Pipeline stage MKMLizer completed in 160.90s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-06-full-21065-v3
Waiting for inference service junhua024-chai-06-full-21065-v3 to be ready
Inference service junhua024-chai-06-full-21065-v3 ready after 301.86408495903015s
Pipeline stage MKMLDeployer completed in 302.72s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5296146869659424s
Received healthy response to inference request in 1.6881911754608154s
Received healthy response to inference request in 1.612818956375122s
Received healthy response to inference request in 1.5483310222625732s
Received healthy response to inference request in 1.5992045402526855s
5 requests
0 failed requests
5th percentile: 1.5585057258605957
10th percentile: 1.568680429458618
20th percentile: 1.5890298366546631
30th percentile: 1.6019274234771728
40th percentile: 1.6073731899261474
50th percentile: 1.612818956375122
60th percentile: 1.6429678440093993
70th percentile: 1.6731167316436768
80th percentile: 1.856475877761841
90th percentile: 2.1930452823638915
95th percentile: 2.3613299846649167
99th percentile: 2.4959577465057374
mean time: 1.7956320762634277
Pipeline stage StressChecker completed in 10.71s
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 1.03s
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 1.02s
Shutdown handler de-registered
junhua024-chai-06-full-_21065_v3 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service junhua024-chai-06-full-21065-v3-profiler
Waiting for inference service junhua024-chai-06-full-21065-v3-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 3084.02s
Shutdown handler de-registered
junhua024-chai-06-full-_21065_v3 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-06-full-_21065_v3 status is now torndown due to DeploymentManager action
junhua024-chai-06-full-_21065_v3 status is now torndown due to DeploymentManager action