junhua024-chai-1-full-066126

developer_uid: junhua024

submission_id: junhua024-chai-1-full-066126_v25

model_name: junhua024-chai-1-full-066126_v25

model_group: junhua024/chai-1-full-06

status: torndown

timestamp: 2025-07-14T10:06:16+00:00

num_battles: 7645

num_wins: 3676

celo_rating: 1276.11

family_friendly_score: 0.5502

family_friendly_standard_error: 0.007035338797812086

submission_type: basic

model_repo: junhua024/chai-1-full-066126

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': 0.5899375303897693, 'latency_mean': 1.6949868738651275, 'latency_p50': 1.6934633255004883, 'latency_p90': 1.8694533109664917}, {'batch_size': 3, 'throughput': 1.0693514481562745, 'latency_mean': 2.7953589940071106, 'latency_p50': 2.789060354232788, 'latency_p90': 3.0605014085769655}, {'batch_size': 5, 'throughput': 1.2630645413063593, 'latency_mean': 3.9428026282787325, 'latency_p50': 3.934675931930542, 'latency_p90': 4.372485208511352}, {'batch_size': 6, 'throughput': 1.3245468911873877, 'latency_mean': 4.507144070863724, 'latency_p50': 4.54148268699646, 'latency_p90': 5.025425624847412}, {'batch_size': 8, 'throughput': 1.383886231561467, 'latency_mean': 5.732383924722671, 'latency_p50': 5.728574156761169, 'latency_p90': 6.449605488777161}, {'batch_size': 10, 'throughput': 1.4205853905289172, 'latency_mean': 6.978925124406815, 'latency_p50': 6.987974405288696, 'latency_p90': 7.907361245155334}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-1-full-066126_v25

is_internal_developer: False

language_model: junhua024/chai-1-full-066126

model_size: 13B

ranking_group: single

throughput_3p7s: 1.24

us_pacific_date: 2025-07-14

win_ratio: 0.48083714846304776

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.05, '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-1-full-066126-v25-mkmlizer
Waiting for job on junhua024-chai-1-full-066126-v25-mkmlizer to finish
junhua024-chai-1-full-066126-v25-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-1-full-066126-v25-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v25-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-1-full-066126-v25-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-1-full-066126-v25-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-1-full-066126-v25-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-1-full-066126-v25-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-1-full-066126-v25-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-1-full-066126-v25-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-1-full-066126-v25-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-1-full-066126-v25-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v25-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-1-full-066126-v25-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-1-full-066126-v25-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-1-full-066126-v25-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-1-full-066126-v25-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v25-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-1-full-066126-v25-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-1-full-066126-v25-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v25-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-1-full-066126-v25-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-1-full-066126-v25-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-1-full-066126-v25-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v25-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-1-full-066126-v25-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-1-full-066126-v25-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-1-full-066126-v25-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-1-full-066126-v25-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-1-full-066126-v25-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-1-full-066126-v25-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-1-full-066126-v25-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-1-full-066126-v25-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-1-full-066126-v25-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-1-full-066126-v25-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-1-full-066126-v25-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-1-full-066126-v25-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-1-full-066126-v25-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-1-full-066126-v25-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-1-full-066126-v25-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-1-full-066126-v25-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-1-full-066126-v25-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-1-full-066126-v25-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-1-full-066126-v25-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-1-full-066126-v25-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-1-full-066126-v25-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-1-full-066126-v25-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-1-full-066126-v25-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-1-full-066126-v25-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-1-full-066126-v25-mkmlizer: Downloaded to shared memory in 76.918s
junhua024-chai-1-full-066126-v25-mkmlizer: Checking if junhua024/chai-1-full-066126 already exists in ChaiML
junhua024-chai-1-full-066126-v25-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp60saxet0, device:0
junhua024-chai-1-full-066126-v25-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-1-full-066126-v25-mkmlizer: quantized model in 37.942s
junhua024-chai-1-full-066126-v25-mkmlizer: Processed model junhua024/chai-1-full-066126 in 114.945s
junhua024-chai-1-full-066126-v25-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-1-full-066126-v25-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v25/nvidia/config.json
junhua024-chai-1-full-066126-v25-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v25/nvidia/special_tokens_map.json
junhua024-chai-1-full-066126-v25-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v25/nvidia/tokenizer_config.json
junhua024-chai-1-full-066126-v25-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v25/nvidia/tokenizer.json
junhua024-chai-1-full-066126-v25-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:25, 14.30it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:22, 16.15it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:11, 30.66it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:10, 32.51it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:12, 27.21it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:12, 26.80it/s]
Loading 0:   8%|▊         | 29/363 [00:00<00:09, 34.11it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:10, 29.96it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 29.82it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:11, 28.45it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:08, 37.35it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:11, 27.21it/s]
Loading 0:  16%|█▋        | 59/363 [00:02<00:10, 28.58it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:09, 29.97it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:10, 28.84it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:08, 32.31it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:08, 32.50it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:10, 27.44it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:09, 29.44it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:08, 30.41it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 31.55it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:08, 31.59it/s]
Loading 0:  29%|██▉       | 105/363 [00:03<00:08, 30.05it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:06, 38.78it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:09, 26.82it/s]
Loading 0:  34%|███▎      | 122/363 [00:04<00:08, 28.86it/s]
Loading 0:  35%|███▌      | 128/363 [00:04<00:07, 30.14it/s]
Loading 0:  36%|███▋      | 132/363 [00:04<00:08, 28.62it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 31.35it/s]
Loading 0:  39%|███▉      | 141/363 [00:04<00:07, 31.46it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:07, 27.52it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:07, 26.78it/s]
Loading 0:  43%|████▎     | 155/363 [00:05<00:06, 32.26it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:06, 30.63it/s]
Loading 0:  45%|████▌     | 164/363 [00:05<00:06, 30.97it/s]
Loading 0:  46%|████▋     | 168/363 [00:05<00:06, 29.10it/s]
Loading 0:  48%|████▊     | 175/363 [00:05<00:04, 38.04it/s]
Loading 0:  50%|████▉     | 180/363 [00:06<00:06, 27.73it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:06, 28.65it/s]
Loading 0:  52%|█████▏    | 190/363 [00:06<00:05, 32.64it/s]
Loading 0:  53%|█████▎    | 194/363 [00:06<00:06, 25.89it/s]
Loading 0:  55%|█████▍    | 199/363 [00:06<00:05, 30.36it/s]
Loading 0:  56%|█████▌    | 203/363 [00:06<00:05, 28.73it/s]
Loading 0:  57%|█████▋    | 207/363 [00:07<00:06, 23.82it/s]
Loading 0:  58%|█████▊    | 212/363 [00:07<00:05, 25.39it/s]
Loading 0:  60%|█████▉    | 217/363 [00:07<00:04, 29.60it/s]
Loading 0:  61%|██████    | 222/363 [00:07<00:04, 31.87it/s]
Loading 0:  62%|██████▏   | 226/363 [00:07<00:05, 24.72it/s]
Loading 0:  63%|██████▎   | 230/363 [00:07<00:05, 24.43it/s]
Loading 0:  65%|██████▌   | 236/363 [00:08<00:04, 31.27it/s]
Loading 0:  66%|██████▌   | 240/363 [00:08<00:04, 27.74it/s]
Loading 0:  67%|██████▋   | 244/363 [00:08<00:04, 27.97it/s]
Loading 0:  68%|██████▊   | 248/363 [00:08<00:04, 28.09it/s]
Loading 0:  70%|██████▉   | 254/363 [00:08<00:03, 29.94it/s]
Loading 0:  71%|███████   | 258/363 [00:08<00:03, 29.50it/s]
Loading 0:  72%|███████▏  | 263/363 [00:08<00:03, 33.24it/s]
Loading 0:  74%|███████▎  | 267/363 [00:09<00:02, 33.98it/s]
Loading 0:  75%|███████▍  | 271/363 [00:09<00:03, 29.73it/s]
Loading 0:  76%|███████▌  | 275/363 [00:09<00:03, 28.96it/s]
Loading 0:  77%|███████▋  | 281/363 [00:09<00:02, 35.20it/s]
Loading 0:  79%|███████▉  | 286/363 [00:09<00:02, 32.97it/s]
Loading 0:  80%|███████▉  | 290/363 [00:09<00:02, 32.78it/s]
Loading 0:  81%|████████  | 294/363 [00:09<00:02, 30.17it/s]
Loading 0:  83%|████████▎ | 300/363 [00:10<00:01, 36.83it/s]
Loading 0:  84%|████████▎ | 304/363 [00:10<00:01, 30.96it/s]
Loading 0:  85%|████████▍ | 308/363 [00:10<00:01, 31.03it/s]
Loading 0:  86%|████████▌ | 312/363 [00:10<00:01, 29.14it/s]
Loading 0:  87%|████████▋ | 317/363 [00:10<00:01, 28.54it/s]
Loading 0:  88%|████████▊ | 320/363 [00:10<00:01, 25.94it/s]
Loading 0:  90%|████████▉ | 326/363 [00:10<00:01, 32.12it/s]
Loading 0:  91%|█████████ | 330/363 [00:11<00:01, 32.75it/s]
Loading 0:  92%|█████████▏| 334/363 [00:11<00:01, 27.83it/s]
Loading 0:  93%|█████████▎| 338/363 [00:11<00:00, 26.22it/s]
Loading 0:  95%|█████████▍| 344/363 [00:11<00:00, 31.98it/s]
Loading 0:  96%|█████████▌| 349/363 [00:11<00:00, 20.98it/s]
Loading 0:  97%|█████████▋| 352/363 [00:12<00:00, 17.92it/s]
Loading 0:  98%|█████████▊| 357/363 [00:12<00:00, 21.03it/s]
                                                            
Job junhua024-chai-1-full-066126-v25-mkmlizer completed after 148.62s with status: succeeded
Stopping job with name junhua024-chai-1-full-066126-v25-mkmlizer
Pipeline stage MKMLizer completed in 149.17s
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-1-full-066126-v25
Waiting for inference service junhua024-chai-1-full-066126-v25 to be ready
Inference service junhua024-chai-1-full-066126-v25 ready after 231.17612099647522s
Pipeline stage MKMLDeployer completed in 231.85s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4461076259613037s
Received healthy response to inference request in 1.6429455280303955s
Received healthy response to inference request in 1.693406581878662s
Received healthy response to inference request in 1.7074675559997559s
Received healthy response to inference request in 1.9661264419555664s
5 requests
0 failed requests
5th percentile: 1.6530377388000488
10th percentile: 1.663129949569702
20th percentile: 1.6833143711090088
30th percentile: 1.696218776702881
40th percentile: 1.7018431663513183
50th percentile: 1.7074675559997559
60th percentile: 1.81093111038208
70th percentile: 1.9143946647644043
80th percentile: 2.062122678756714
90th percentile: 2.2541151523590086
95th percentile: 2.350111389160156
99th percentile: 2.426908378601074
mean time: 1.8912107467651367
Pipeline stage StressChecker completed in 10.85s
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 0.92s
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 0.68s
Shutdown handler de-registered
junhua024-chai-1-full-066126_v25 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 5334.66s
Shutdown handler de-registered
junhua024-chai-1-full-066126_v25 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-1-full-066126_v25 status is now torndown due to DeploymentManager action