junhua024-chai-16-full-_94000

developer_uid: junhua024

submission_id: junhua024-chai-16-full-_94000_v1

model_name: junhua024-chai-16-full-_94000_v1

model_group: junhua024/chai_16_full_q

status: torndown

timestamp: 2025-07-20T08:55:39+00:00

num_battles: 6668

num_wins: 3233

celo_rating: 1275.64

family_friendly_score: 0.5606

family_friendly_standard_error: 0.007018940660812

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': 0.590501725796772, 'latency_mean': 1.693293603658676, 'latency_p50': 1.6979390382766724, 'latency_p90': 1.868882131576538}, {'batch_size': 3, 'throughput': 1.0624616755306338, 'latency_mean': 2.8163255786895753, 'latency_p50': 2.81562876701355, 'latency_p90': 3.1248238325119018}, {'batch_size': 5, 'throughput': 1.2812274963310033, 'latency_mean': 3.877696440219879, 'latency_p50': 3.8903130292892456, 'latency_p90': 4.399235105514526}, {'batch_size': 6, 'throughput': 1.341684222854922, 'latency_mean': 4.439389932155609, 'latency_p50': 4.412624955177307, 'latency_p90': 4.968346285820007}, {'batch_size': 8, 'throughput': 1.4031066473690483, 'latency_mean': 5.66816069483757, 'latency_p50': 5.662405014038086, 'latency_p90': 6.383306193351745}, {'batch_size': 10, 'throughput': 1.427478175159015, 'latency_mean': 6.958022943735123, 'latency_p50': 6.965697169303894, 'latency_p90': 7.853946280479431}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-16-full-_94000_v1

is_internal_developer: False

language_model: junhua024/chai_16_full_qkv100_o106_ffn106_1925

model_size: 13B

ranking_group: single

throughput_3p7s: 1.26

us_pacific_date: 2025-07-20

win_ratio: 0.48485302939412117

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-v1-mkmlizer
Waiting for job on junhua024-chai-16-full-94000-v1-mkmlizer to finish
junhua024-chai-16-full-94000-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-16-full-94000-v1-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-94000-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-16-full-94000-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-16-full-94000-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-16-full-94000-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-16-full-94000-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-16-full-94000-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-16-full-94000-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-16-full-94000-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-16-full-94000-v1-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-94000-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-16-full-94000-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-16-full-94000-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-16-full-94000-v1-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-16-full-94000-v1-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-94000-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-16-full-94000-v1-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-16-full-94000-v1-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-94000-v1-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-16-full-94000-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-16-full-94000-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-16-full-94000-v1-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-94000-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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)
junhua024-chai-16-full-94000-v1-mkmlizer: Downloaded to shared memory in 76.839s
junhua024-chai-16-full-94000-v1-mkmlizer: Checking if junhua024/chai_16_full_qkv100_o106_ffn106_1925 already exists in ChaiML
junhua024-chai-16-full-94000-v1-mkmlizer: Creating repo ChaiML/chai_16_full_qkv100_o106_ffn106_1925 and uploading /tmp/tmphk6u150j to it
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)
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)
junhua024-chai-16-full-94000-v1-mkmlizer: 
  0%|          | 0/26 [00:00<?, ?it/s]
  4%|▍         | 1/26 [00:01<00:37,  1.50s/it]
  8%|▊         | 2/26 [00:03<00:38,  1.62s/it]
 12%|█▏        | 3/26 [00:04<00:34,  1.51s/it]
 15%|█▌        | 4/26 [00:05<00:31,  1.42s/it]
 19%|█▉        | 5/26 [00:07<00:28,  1.36s/it]
 23%|██▎       | 6/26 [00:08<00:26,  1.34s/it]
 27%|██▋       | 7/26 [00:09<00:25,  1.33s/it]
 31%|███       | 8/26 [00:11<00:25,  1.41s/it]
 35%|███▍      | 9/26 [00:13<00:25,  1.52s/it]
 38%|███▊      | 10/26 [00:14<00:23,  1.49s/it]
 42%|████▏     | 11/26 [00:16<00:23,  1.56s/it]
 46%|████▌     | 12/26 [00:17<00:20,  1.46s/it]
 50%|█████     | 13/26 [00:18<00:18,  1.44s/it]
 54%|█████▍    | 14/26 [00:20<00:16,  1.41s/it]
 58%|█████▊    | 15/26 [00:21<00:14,  1.36s/it]
 62%|██████▏   | 16/26 [00:25<00:20,  2.10s/it]
 65%|██████▌   | 17/26 [00:27<00:18,  2.05s/it]
 69%|██████▉   | 18/26 [00:28<00:14,  1.81s/it]
 73%|███████▎  | 19/26 [00:29<00:11,  1.64s/it]
 77%|███████▋  | 20/26 [00:30<00:09,  1.52s/it]
 81%|████████  | 21/26 [00:32<00:07,  1.49s/it]
 85%|████████▍ | 22/26 [00:33<00:05,  1.45s/it]
 88%|████████▊ | 23/26 [00:34<00:04,  1.37s/it]
 92%|█████████▏| 24/26 [00:38<00:04,  2.09s/it]
 96%|█████████▌| 25/26 [00:39<00:01,  1.85s/it]
100%|██████████| 26/26 [00:40<00:00,  1.62s/it]
100%|██████████| 26/26 [00:40<00:00,  1.58s/it]
junhua024-chai-16-full-94000-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphk6u150j, device:0
junhua024-chai-16-full-94000-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-16-full-94000-v1-mkmlizer: quantized model in 32.873s
junhua024-chai-16-full-94000-v1-mkmlizer: Processed model junhua024/chai_16_full_qkv100_o106_ffn106_1925 in 176.507s
junhua024-chai-16-full-94000-v1-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-16-full-94000-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-16-full-94000-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-16-full-94000-v1/nvidia
junhua024-chai-16-full-94000-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-16-full-94000-v1/nvidia/config.json
junhua024-chai-16-full-94000-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-16-full-94000-v1/nvidia/special_tokens_map.json
junhua024-chai-16-full-94000-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-16-full-94000-v1/nvidia/tokenizer_config.json
junhua024-chai-16-full-94000-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-16-full-94000-v1/nvidia/tokenizer.json
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)
junhua024-chai-16-full-94000-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-16-full-94000-v1/nvidia/flywheel_model.0.safetensors
junhua024-chai-16-full-94000-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:24, 14.54it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:21, 16.69it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:11, 31.83it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:10, 34.21it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:11, 29.12it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:11, 28.38it/s]
Loading 0:   8%|▊         | 29/363 [00:00<00:09, 36.36it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:09, 34.07it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:09, 34.57it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:10, 31.59it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:08, 37.94it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:10, 29.66it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:09, 31.16it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:09, 32.05it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:09, 30.57it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:08, 33.61it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:08, 33.54it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:09, 28.79it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:09, 30.32it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 31.61it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:07, 33.76it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:07, 33.27it/s]
Loading 0:  29%|██▉       | 105/363 [00:03<00:08, 31.12it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:06, 36.56it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:08, 29.26it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:07, 30.33it/s]
Loading 0:  35%|███▌      | 128/363 [00:04<00:07, 31.47it/s]
Loading 0:  36%|███▋      | 132/363 [00:04<00:07, 30.45it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:06, 33.85it/s]
Loading 0:  39%|███▉      | 141/363 [00:04<00:06, 34.00it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:07, 29.32it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:07, 28.99it/s]
Loading 0:  43%|████▎     | 155/363 [00:04<00:05, 34.83it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:05, 34.03it/s]
Loading 0:  45%|████▌     | 164/363 [00:05<00:05, 34.14it/s]
Loading 0:  46%|████▋     | 168/363 [00:05<00:06, 32.17it/s]
Loading 0:  48%|████▊     | 176/363 [00:05<00:04, 38.64it/s]
Loading 0:  50%|████▉     | 180/363 [00:05<00:05, 30.54it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 31.79it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:05, 33.13it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:05, 32.11it/s]
Loading 0:  55%|█████▌    | 200/363 [00:06<00:04, 35.98it/s]
Loading 0:  56%|█████▌    | 204/363 [00:06<00:04, 36.54it/s]
Loading 0:  57%|█████▋    | 208/363 [00:06<00:04, 31.28it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:05, 30.02it/s]
Loading 0:  60%|██████    | 218/363 [00:06<00:03, 36.50it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:04, 34.88it/s]
Loading 0:  63%|██████▎   | 227/363 [00:07<00:03, 34.49it/s]
Loading 0:  64%|██████▎   | 231/363 [00:07<00:04, 32.73it/s]
Loading 0:  66%|██████▌   | 239/363 [00:07<00:03, 39.36it/s]
Loading 0:  67%|██████▋   | 243/363 [00:07<00:03, 30.58it/s]
Loading 0:  68%|██████▊   | 248/363 [00:07<00:03, 29.50it/s]
Loading 0:  70%|██████▉   | 254/363 [00:07<00:03, 31.18it/s]
Loading 0:  71%|███████   | 258/363 [00:08<00:03, 30.17it/s]
Loading 0:  73%|███████▎  | 264/363 [00:08<00:03, 31.57it/s]
Loading 0:  74%|███████▍  | 269/363 [00:08<00:02, 32.15it/s]
Loading 0:  76%|███████▌  | 275/363 [00:08<00:02, 32.70it/s]
Loading 0:  77%|███████▋  | 281/363 [00:08<00:02, 37.75it/s]
Loading 0:  79%|███████▉  | 286/363 [00:08<00:02, 36.54it/s]
Loading 0:  80%|███████▉  | 290/363 [00:08<00:02, 34.98it/s]
Loading 0:  81%|████████  | 294/363 [00:09<00:02, 32.89it/s]
Loading 0:  83%|████████▎ | 302/363 [00:09<00:01, 39.33it/s]
Loading 0:  84%|████████▍ | 306/363 [00:09<00:01, 31.16it/s]
Loading 0:  86%|████████▌ | 311/363 [00:09<00:01, 31.94it/s]
Loading 0:  87%|████████▋ | 317/363 [00:09<00:01, 33.29it/s]
Loading 0:  88%|████████▊ | 321/363 [00:09<00:01, 32.25it/s]
Loading 0:  90%|████████▉ | 326/363 [00:09<00:01, 35.86it/s]
Loading 0:  91%|█████████ | 330/363 [00:10<00:00, 35.94it/s]
Loading 0:  92%|█████████▏| 334/363 [00:10<00:00, 30.01it/s]
Loading 0:  93%|█████████▎| 338/363 [00:10<00:00, 29.38it/s]
Loading 0:  95%|█████████▌| 346/363 [00:10<00:00, 40.35it/s]
Loading 0:  97%|█████████▋| 351/363 [00:10<00:00, 22.92it/s]
Loading 0:  98%|█████████▊| 355/363 [00:11<00:00, 25.50it/s]
Loading 0:  99%|█████████▉| 359/363 [00:11<00:00, 27.87it/s]
                                                            
Job junhua024-chai-16-full-94000-v1-mkmlizer completed after 201.06s with status: succeeded
Stopping job with name junhua024-chai-16-full-94000-v1-mkmlizer
Pipeline stage MKMLizer completed in 201.90s
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-16-full-94000-v1
Waiting for inference service junhua024-chai-16-full-94000-v1 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 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)
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)
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_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-v1 ready after 331.46395802497864s
Pipeline stage MKMLDeployer completed in 332.04s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.516814947128296s
Received healthy response to inference request in 1.6453351974487305s
Received healthy response to inference request in 1.9756889343261719s
Received healthy response to inference request in 1.733454942703247s
Received healthy response to inference request in 2.0294010639190674s
5 requests
0 failed requests
5th percentile: 1.6629591464996338
10th percentile: 1.6805830955505372
20th percentile: 1.7158309936523437
30th percentile: 1.781901741027832
40th percentile: 1.878795337677002
50th percentile: 1.9756889343261719
60th percentile: 1.99717378616333
70th percentile: 2.0186586380004883
80th percentile: 2.126883840560913
90th percentile: 2.3218493938446043
95th percentile: 2.41933217048645
99th percentile: 2.4973183917999267
mean time: 1.9801390171051025
Pipeline stage StressChecker completed in 11.21s
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 1.01s
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 0.70s
Shutdown handler de-registered
junhua024-chai-16-full-_94000_v1 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 4887.08s
Shutdown handler de-registered
junhua024-chai-16-full-_94000_v1 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-16-full-_94000_v1 status is now torndown due to DeploymentManager action