junhua024-chai-16-full-_38907

developer_uid: junhua024

submission_id: junhua024-chai-16-full-_38907_v4

model_name: junhua024-chai-16-full-_38907_v4

model_group: junhua024/chai_16_full_1

status: torndown

timestamp: 2025-07-19T19:28:21+00:00

num_battles: 7601

num_wins: 3719

celo_rating: 1279.06

family_friendly_score: 0.548

family_friendly_standard_error: 0.0070384089111105224

submission_type: basic

model_repo: junhua024/chai_16_full_102_qkv_o_ffn_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': 0.5920529814626861, 'latency_mean': 1.6888902378082276, 'latency_p50': 1.698778510093689, 'latency_p90': 1.8644162893295289}, {'batch_size': 3, 'throughput': 1.081963235031131, 'latency_mean': 2.7698749005794525, 'latency_p50': 2.7643784284591675, 'latency_p90': 3.0649115562438967}, {'batch_size': 5, 'throughput': 1.2996434072911107, 'latency_mean': 3.8273926723003386, 'latency_p50': 3.847103714942932, 'latency_p90': 4.244737648963928}, {'batch_size': 6, 'throughput': 1.3542147453662527, 'latency_mean': 4.3997307395935055, 'latency_p50': 4.370047211647034, 'latency_p90': 4.910424375534058}, {'batch_size': 8, 'throughput': 1.422055917404055, 'latency_mean': 5.583563287258148, 'latency_p50': 5.606176853179932, 'latency_p90': 6.285148882865905}, {'batch_size': 10, 'throughput': 1.4599942058373565, 'latency_mean': 6.790635266304016, 'latency_p50': 6.782060503959656, 'latency_p90': 7.733716917037964}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-16-full-_38907_v4

is_internal_developer: False

language_model: junhua024/chai_16_full_102_qkv_o_ffn_1925

model_size: 13B

ranking_group: single

throughput_3p7s: 1.29

us_pacific_date: 2025-07-19

win_ratio: 0.4892777266149191

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-38907-v4-mkmlizer
Waiting for job on junhua024-chai-16-full-38907-v4-mkmlizer to finish
junhua024-chai-16-full-38907-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-16-full-38907-v4-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-38907-v4-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-16-full-38907-v4-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-16-full-38907-v4-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-16-full-38907-v4-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-16-full-38907-v4-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-16-full-38907-v4-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-16-full-38907-v4-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-16-full-38907-v4-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-16-full-38907-v4-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-38907-v4-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-16-full-38907-v4-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-16-full-38907-v4-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-16-full-38907-v4-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-16-full-38907-v4-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-38907-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-16-full-38907-v4-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-16-full-38907-v4-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-38907-v4-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-16-full-38907-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-16-full-38907-v4-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-16-full-38907-v4-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-38907-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-16-full-38907-v4-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-38907-v4-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-38907-v4-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-38907-v4-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-38907-v4-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-38907-v4-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-38907-v4-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-38907-v4-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-38907-v4-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-38907-v4-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-38907-v4-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-38907-v4-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-38907-v4-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-38907-v4-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-38907-v4-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-38907-v4-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-38907-v4-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-38907-v4-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-38907-v4-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-38907-v4-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-38907-v4-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-38907-v4-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-38907-v4-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-38907-v4-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-38907-v4-mkmlizer: Downloaded to shared memory in 125.390s
junhua024-chai-16-full-38907-v4-mkmlizer: Checking if junhua024/chai_16_full_102_qkv_o_ffn_1925 already exists in ChaiML
junhua024-chai-16-full-38907-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnru2wyp8, device:0
junhua024-chai-16-full-38907-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-16-full-38907-v4-mkmlizer: quantized model in 30.876s
junhua024-chai-16-full-38907-v4-mkmlizer: Processed model junhua024/chai_16_full_102_qkv_o_ffn_1925 in 156.342s
junhua024-chai-16-full-38907-v4-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-16-full-38907-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-16-full-38907-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-16-full-38907-v4/nvidia
junhua024-chai-16-full-38907-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-16-full-38907-v4/nvidia/config.json
junhua024-chai-16-full-38907-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-16-full-38907-v4/nvidia/special_tokens_map.json
junhua024-chai-16-full-38907-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-16-full-38907-v4/nvidia/tokenizer_config.json
junhua024-chai-16-full-38907-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-16-full-38907-v4/nvidia/tokenizer.json
junhua024-chai-16-full-38907-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-16-full-38907-v4/nvidia/flywheel_model.0.safetensors
junhua024-chai-16-full-38907-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:22, 16.11it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:19, 18.45it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 30.93it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 33.01it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:09, 35.24it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:06, 49.23it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:08, 38.07it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:08, 36.40it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:08, 38.98it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:09, 33.76it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:09, 33.57it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 34.95it/s]
Loading 0:  19%|█▉        | 69/363 [00:01<00:08, 33.62it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:08, 34.24it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:08, 32.95it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 37.89it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 37.68it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:06, 38.83it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 37.97it/s]
Loading 0:  29%|██▉       | 105/363 [00:02<00:07, 35.00it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:05, 41.82it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:07, 33.90it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:07, 33.08it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:06, 34.99it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:06, 33.68it/s]
Loading 0:  38%|███▊      | 138/363 [00:03<00:06, 34.62it/s]
Loading 0:  39%|███▉      | 143/363 [00:04<00:06, 34.43it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:06, 34.97it/s]
Loading 0:  43%|████▎     | 157/363 [00:04<00:04, 44.40it/s]
Loading 0:  45%|████▍     | 162/363 [00:04<00:05, 34.45it/s]
Loading 0:  46%|████▌     | 167/363 [00:04<00:05, 35.06it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:04, 42.21it/s]
Loading 0:  50%|████▉     | 181/363 [00:05<00:04, 36.42it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 34.61it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:04, 36.63it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:04, 35.51it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 36.19it/s]
Loading 0:  57%|█████▋    | 206/363 [00:05<00:04, 36.00it/s]
Loading 0:  58%|█████▊    | 212/363 [00:05<00:04, 36.54it/s]
Loading 0:  61%|██████    | 221/363 [00:06<00:02, 47.78it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:03, 36.32it/s]
Loading 0:  64%|██████▍   | 232/363 [00:06<00:03, 36.20it/s]
Loading 0:  66%|██████▌   | 239/363 [00:06<00:03, 40.57it/s]
Loading 0:  67%|██████▋   | 244/363 [00:06<00:03, 34.96it/s]
Loading 0:  68%|██████▊   | 248/363 [00:06<00:03, 34.62it/s]
Loading 0:  70%|██████▉   | 254/363 [00:07<00:02, 36.58it/s]
Loading 0:  71%|███████   | 258/363 [00:07<00:02, 35.47it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 35.57it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 35.54it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 36.70it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:01, 45.92it/s]
Loading 0:  79%|███████▉  | 288/363 [00:07<00:02, 34.65it/s]
Loading 0:  81%|████████  | 293/363 [00:08<00:01, 35.47it/s]
Loading 0:  83%|████████▎ | 302/363 [00:08<00:01, 43.08it/s]
Loading 0:  85%|████████▍ | 307/363 [00:08<00:01, 37.08it/s]
Loading 0:  86%|████████▌ | 312/363 [00:08<00:01, 37.82it/s]
Loading 0:  87%|████████▋ | 317/363 [00:08<00:01, 36.80it/s]
Loading 0:  88%|████████▊ | 321/363 [00:08<00:01, 35.73it/s]
Loading 0:  90%|█████████ | 327/363 [00:08<00:00, 36.40it/s]
Loading 0:  91%|█████████▏| 332/363 [00:09<00:00, 36.13it/s]
Loading 0:  93%|█████████▎| 338/363 [00:09<00:00, 36.94it/s]
Loading 0:  95%|█████████▌| 345/363 [00:09<00:00, 44.16it/s]
Loading 0:  96%|█████████▋| 350/363 [00:09<00:00, 25.48it/s]
Loading 0:  98%|█████████▊| 354/363 [00:09<00:00, 27.72it/s]
Loading 0:  99%|█████████▊| 358/363 [00:10<00:00, 29.24it/s]
                                                            
Job junhua024-chai-16-full-38907-v4-mkmlizer completed after 182.52s with status: succeeded
Stopping job with name junhua024-chai-16-full-38907-v4-mkmlizer
Pipeline stage MKMLizer completed in 183.68s
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-16-full-38907-v4
Waiting for inference service junhua024-chai-16-full-38907-v4 to be ready
Failed to get response for submission chaiml-nis-qwen32b-sim_98336_v34: HTTPConnectionPool(host='chaiml-nis-qwen32b-sim-98336-v34-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-16-full-38907-v4 ready after 331.23437666893005s
Pipeline stage MKMLDeployer completed in 331.79s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0226595401763916s
Received healthy response to inference request in 1.6898036003112793s
Received healthy response to inference request in 1.567850112915039s
Received healthy response to inference request in 1.8114466667175293s
Received healthy response to inference request in 1.6239757537841797s
5 requests
0 failed requests
5th percentile: 1.579075241088867
10th percentile: 1.5903003692626954
20th percentile: 1.6127506256103517
30th percentile: 1.6371413230895997
40th percentile: 1.6634724617004395
50th percentile: 1.6898036003112793
60th percentile: 1.7384608268737793
70th percentile: 1.7871180534362794
80th percentile: 2.0536892414093018
90th percentile: 2.5381743907928467
95th percentile: 2.780416965484619
99th percentile: 2.974211025238037
mean time: 1.9431471347808837
Pipeline stage StressChecker completed in 11.05s
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 1.10s
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 0.99s
Shutdown handler de-registered
junhua024-chai-16-full-_38907_v4 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 4362.15s
Shutdown handler de-registered
junhua024-chai-16-full-_38907_v4 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-16-full-_38907_v4 status is now torndown due to DeploymentManager action