junhua024-chai-16-full-_94000

developer_uid: junhua024

submission_id: junhua024-chai-16-full-_94000_v3

model_name: junhua024-chai-16-full-_94000_v3

model_group: junhua024/chai_16_full_q

status: torndown

timestamp: 2025-07-20T08:59:12+00:00

num_battles: 8674

num_wins: 4245

celo_rating: 1276.55

family_friendly_score: 0.5584

family_friendly_standard_error: 0.007022669577874214

submission_type: basic

model_repo: junhua024/chai_16_full_qkv100_o106_ffn106_1925

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': 0.5906689333584731, 'latency_mean': 1.6928159320354461, 'latency_p50': 1.689914345741272, 'latency_p90': 1.873168420791626}, {'batch_size': 3, 'throughput': 1.0615442370754358, 'latency_mean': 2.8216548347473145, 'latency_p50': 2.809443235397339, 'latency_p90': 3.095344591140747}, {'batch_size': 5, 'throughput': 1.2625512587932286, 'latency_mean': 3.9372803282737734, 'latency_p50': 3.946556806564331, 'latency_p90': 4.456180000305175}, {'batch_size': 6, 'throughput': 1.3211082040857776, 'latency_mean': 4.510453196763993, 'latency_p50': 4.538641333580017, 'latency_p90': 5.056738924980164}, {'batch_size': 8, 'throughput': 1.3945154831924298, 'latency_mean': 5.69489956498146, 'latency_p50': 5.6725205183029175, 'latency_p90': 6.443347072601318}, {'batch_size': 10, 'throughput': 1.4020581236257612, 'latency_mean': 7.058830009698868, 'latency_p50': 7.056032061576843, 'latency_p90': 7.962148141860962}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-16-full-_94000_v3

is_internal_developer: False

language_model: junhua024/chai_16_full_qkv100_o106_ffn106_1925

model_size: 13B

ranking_group: single

throughput_3p7s: 1.24

us_pacific_date: 2025-07-20

win_ratio: 0.4893935900391976

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-16-full-94000-v3-mkmlizer
Waiting for job on junhua024-chai-16-full-94000-v3-mkmlizer to finish
junhua024-chai-16-full-94000-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-16-full-94000-v3-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-94000-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-16-full-94000-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-16-full-94000-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-16-full-94000-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-16-full-94000-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-16-full-94000-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-16-full-94000-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-16-full-94000-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-16-full-94000-v3-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-94000-v3-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-16-full-94000-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-16-full-94000-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-16-full-94000-v3-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-16-full-94000-v3-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-94000-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-16-full-94000-v3-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-16-full-94000-v3-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-94000-v3-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-16-full-94000-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-16-full-94000-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-16-full-94000-v3-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-94000-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-16-full-94000-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-16-full-94000-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-16-full-94000-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-16-full-94000-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-16-full-94000-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-16-full-94000-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-16-full-94000-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-16-full-94000-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-16-full-94000-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-16-full-94000-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-16-full-94000-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-16-full-94000-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-16-full-94000-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-16-full-94000-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-16-full-94000-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-16-full-94000-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-16-full-94000-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-16-full-94000-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-16-full-94000-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-16-full-94000-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-16-full-94000-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-16-full-94000-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-16-full-94000-v3-mkmlizer: Downloaded to shared memory in 119.123s
junhua024-chai-16-full-94000-v3-mkmlizer: Checking if junhua024/chai_16_full_qkv100_o106_ffn106_1925 already exists in ChaiML
junhua024-chai-16-full-94000-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpv1_qbn0u, device:0
junhua024-chai-16-full-94000-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-16-full-94000-v3-mkmlizer: quantized model in 32.398s
junhua024-chai-16-full-94000-v3-mkmlizer: Processed model junhua024/chai_16_full_qkv100_o106_ffn106_1925 in 151.604s
junhua024-chai-16-full-94000-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-16-full-94000-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-16-full-94000-v3/nvidia
junhua024-chai-16-full-94000-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-16-full-94000-v3/nvidia/config.json
junhua024-chai-16-full-94000-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-16-full-94000-v3/nvidia/special_tokens_map.json
junhua024-chai-16-full-94000-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-16-full-94000-v3/nvidia/tokenizer_config.json
junhua024-chai-16-full-94000-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-16-full-94000-v3/nvidia/tokenizer.json
junhua024-chai-16-full-94000-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-16-full-94000-v3/nvidia/flywheel_model.0.safetensors
junhua024-chai-16-full-94000-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:24, 14.69it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:22, 15.63it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:13, 26.74it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:11, 29.39it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 32.18it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 43.59it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:10, 31.06it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:10, 32.15it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:07, 39.65it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:09, 33.93it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:09, 33.44it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 34.32it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:08, 32.68it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:08, 35.75it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:07, 35.93it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:09, 31.19it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:08, 32.26it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 33.18it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:07, 35.49it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:07, 36.06it/s]
Loading 0:  29%|██▉       | 105/363 [00:03<00:07, 33.42it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:06, 38.60it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:07, 31.35it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:07, 32.48it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:06, 34.50it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:06, 33.48it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 33.65it/s]
Loading 0:  39%|███▉      | 143/363 [00:04<00:06, 33.53it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:06, 34.46it/s]
Loading 0:  43%|████▎     | 157/363 [00:04<00:04, 43.76it/s]
Loading 0:  45%|████▍     | 162/363 [00:04<00:06, 31.59it/s]
Loading 0:  46%|████▌     | 167/363 [00:04<00:06, 32.29it/s]
Loading 0:  48%|████▊     | 176/363 [00:05<00:04, 40.31it/s]
Loading 0:  50%|████▉     | 181/363 [00:05<00:05, 34.04it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 33.20it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:04, 35.27it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:04, 34.07it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 34.60it/s]
Loading 0:  57%|█████▋    | 206/363 [00:06<00:04, 32.11it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:04, 33.33it/s]
Loading 0:  60%|██████    | 218/363 [00:06<00:03, 38.31it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:04, 34.48it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:04, 33.54it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 31.37it/s]
Loading 0:  66%|██████▌   | 239/363 [00:07<00:03, 37.51it/s]
Loading 0:  67%|██████▋   | 243/363 [00:07<00:04, 29.97it/s]
Loading 0:  68%|██████▊   | 248/363 [00:07<00:03, 31.80it/s]
Loading 0:  70%|██████▉   | 254/363 [00:07<00:03, 33.43it/s]
Loading 0:  71%|███████   | 258/363 [00:07<00:03, 30.20it/s]
Loading 0:  72%|███████▏  | 262/363 [00:07<00:03, 32.07it/s]
Loading 0:  73%|███████▎  | 266/363 [00:07<00:03, 31.63it/s]
Loading 0:  74%|███████▍  | 270/363 [00:08<00:03, 28.87it/s]
Loading 0:  76%|███████▌  | 275/363 [00:08<00:02, 30.71it/s]
Loading 0:  77%|███████▋  | 281/363 [00:08<00:02, 36.38it/s]
Loading 0:  79%|███████▉  | 286/363 [00:08<00:02, 33.52it/s]
Loading 0:  80%|███████▉  | 290/363 [00:08<00:02, 32.90it/s]
Loading 0:  81%|████████  | 294/363 [00:08<00:02, 30.61it/s]
Loading 0:  83%|████████▎ | 300/363 [00:08<00:01, 37.22it/s]
Loading 0:  84%|████████▎ | 304/363 [00:09<00:01, 31.51it/s]
Loading 0:  85%|████████▍ | 308/363 [00:09<00:01, 32.19it/s]
Loading 0:  86%|████████▌ | 312/363 [00:09<00:01, 31.72it/s]
Loading 0:  87%|████████▋ | 317/363 [00:09<00:01, 31.70it/s]
Loading 0:  88%|████████▊ | 321/363 [00:09<00:01, 30.95it/s]
Loading 0:  90%|█████████ | 327/363 [00:09<00:01, 32.65it/s]
Loading 0:  91%|█████████▏| 332/363 [00:09<00:00, 32.66it/s]
Loading 0:  93%|█████████▎| 338/363 [00:10<00:00, 33.87it/s]
Loading 0:  95%|█████████▍| 344/363 [00:10<00:00, 39.43it/s]
Loading 0:  96%|█████████▌| 349/363 [00:10<00:00, 26.57it/s]
Loading 0:  97%|█████████▋| 353/363 [00:10<00:00, 24.23it/s]
Loading 0:  98%|█████████▊| 357/363 [00:10<00:00, 25.92it/s]
                                                            
Job junhua024-chai-16-full-94000-v3-mkmlizer completed after 180.21s with status: succeeded
Stopping job with name junhua024-chai-16-full-94000-v3-mkmlizer
Pipeline stage MKMLizer completed in 180.80s
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-16-full-94000-v3
Waiting for inference service junhua024-chai-16-full-94000-v3 to be ready
Failed to get response for submission junhua024-chai-16-full-_96988_v1: HTTPConnectionPool(host='junhua024-chai-16-full-96988-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-16-full-_96988_v4: HTTPConnectionPool(host='junhua024-chai-16-full-96988-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-16-full-94000-v3 ready after 342.32709670066833s
Pipeline stage MKMLDeployer completed in 343.07s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.567565441131592s
Received healthy response to inference request in 2.0958378314971924s
Received healthy response to inference request in 1.86513352394104s
Received healthy response to inference request in 1.7699532508850098s
Received healthy response to inference request in 1.680527925491333s
5 requests
0 failed requests
5th percentile: 1.6984129905700684
10th percentile: 1.7162980556488037
20th percentile: 1.7520681858062743
30th percentile: 1.7889893054962158
40th percentile: 1.827061414718628
50th percentile: 1.86513352394104
60th percentile: 1.9574152469635009
70th percentile: 2.0496969699859617
80th percentile: 2.1901833534240724
90th percentile: 2.378874397277832
95th percentile: 2.4732199192047117
99th percentile: 2.548696336746216
mean time: 1.9958035945892334
Pipeline stage StressChecker completed in 11.79s
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 0.80s
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-16-full-_94000_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 5202.02s
Shutdown handler de-registered
junhua024-chai-16-full-_94000_v3 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-16-full-_94000_v3 status is now torndown due to DeploymentManager action