albertwang8192-2025-07-05-3

developer_uid: RandomForest1024

submission_id: albertwang8192-2025-07-05-3_v1

model_name: 2025-07-05_3

model_group: AlbertWang8192/2025-07-0

status: torndown

timestamp: 2025-07-05T20:06:05+00:00

num_battles: 9571

num_wins: 4244

celo_rating: 1252.14

family_friendly_score: 0.5828

family_friendly_standard_error: 0.006973437602789603

submission_type: basic

model_repo: AlbertWang8192/2025-07-05_3

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': 0.5989398980971486, 'latency_mean': 1.6695107066631316, 'latency_p50': 1.6654682159423828, 'latency_p90': 1.8389688014984131}, {'batch_size': 3, 'throughput': 1.0742301549345337, 'latency_mean': 2.7871781504154205, 'latency_p50': 2.772948741912842, 'latency_p90': 3.0578792095184326}, {'batch_size': 5, 'throughput': 1.2822063277389004, 'latency_mean': 3.8774065411090852, 'latency_p50': 3.8826024532318115, 'latency_p90': 4.324595642089844}, {'batch_size': 6, 'throughput': 1.3426766998770034, 'latency_mean': 4.444775120019913, 'latency_p50': 4.456122159957886, 'latency_p90': 4.9307819366455075}, {'batch_size': 8, 'throughput': 1.3997410880257228, 'latency_mean': 5.683705332279206, 'latency_p50': 5.673487544059753, 'latency_p90': 6.320629334449768}, {'batch_size': 10, 'throughput': 1.4357706524746585, 'latency_mean': 6.903406820297241, 'latency_p50': 6.972771883010864, 'latency_p90': 7.824224472045898}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: 2025-07-05_3

is_internal_developer: False

language_model: AlbertWang8192/2025-07-05_3

model_size: 13B

ranking_group: single

throughput_3p7s: 1.26

us_pacific_date: 2025-07-05

win_ratio: 0.44342283982864905

generation_params: {'temperature': 0.6, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|im_end|>', '<|im_start|>', '\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 albertwang8192-2025-07-05-3-v1-mkmlizer
Waiting for job on albertwang8192-2025-07-05-3-v1-mkmlizer to finish
albertwang8192-2025-07-05-3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
albertwang8192-2025-07-05-3-v1-mkmlizer: ║                                                                     ║
albertwang8192-2025-07-05-3-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
albertwang8192-2025-07-05-3-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
albertwang8192-2025-07-05-3-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
albertwang8192-2025-07-05-3-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
albertwang8192-2025-07-05-3-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
albertwang8192-2025-07-05-3-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
albertwang8192-2025-07-05-3-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
albertwang8192-2025-07-05-3-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
albertwang8192-2025-07-05-3-v1-mkmlizer: ║                                                                     ║
albertwang8192-2025-07-05-3-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
albertwang8192-2025-07-05-3-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
albertwang8192-2025-07-05-3-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
albertwang8192-2025-07-05-3-v1-mkmlizer: ║  https://mk1.ai                                                     ║
albertwang8192-2025-07-05-3-v1-mkmlizer: ║                                                                     ║
albertwang8192-2025-07-05-3-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
albertwang8192-2025-07-05-3-v1-mkmlizer: ║  belonging to:                                                      ║
albertwang8192-2025-07-05-3-v1-mkmlizer: ║                                                                     ║
albertwang8192-2025-07-05-3-v1-mkmlizer: ║  Chai Research Corp.                                                ║
albertwang8192-2025-07-05-3-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
albertwang8192-2025-07-05-3-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
albertwang8192-2025-07-05-3-v1-mkmlizer: ║                                                                     ║
albertwang8192-2025-07-05-3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-gy-exp91-dpo-exp_59578_v1: HTTPConnectionPool(host='chaiml-gy-exp91-dpo-exp-59578-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
albertwang8192-2025-07-05-3-v1-mkmlizer: Downloaded to shared memory in 83.652s
albertwang8192-2025-07-05-3-v1-mkmlizer: Checking if AlbertWang8192/2025-07-05_3 already exists in ChaiML
albertwang8192-2025-07-05-3-v1-mkmlizer: Creating repo ChaiML/2025-07-05_3 and uploading /tmp/tmpcl0alz6x to it
albertwang8192-2025-07-05-3-v1-mkmlizer: 
  0%|          | 0/11 [00:00<?, ?it/s]
  9%|▉         | 1/11 [00:08<01:22,  8.23s/it]
 18%|█▊        | 2/11 [00:11<00:50,  5.59s/it]
 27%|██▋       | 3/11 [00:20<00:56,  7.02s/it]
 36%|███▋      | 4/11 [00:24<00:41,  5.93s/it]
 45%|████▌     | 5/11 [00:31<00:37,  6.20s/it]
 55%|█████▍    | 6/11 [00:35<00:27,  5.42s/it]
 64%|██████▎   | 7/11 [00:39<00:19,  4.88s/it]
 73%|███████▎  | 8/11 [00:43<00:14,  4.76s/it]
 82%|████████▏ | 9/11 [00:48<00:09,  4.76s/it]
 91%|█████████ | 10/11 [00:52<00:04,  4.54s/it]
100%|██████████| 11/11 [00:54<00:00,  3.58s/it]
100%|██████████| 11/11 [00:54<00:00,  4.91s/it]
albertwang8192-2025-07-05-3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcl0alz6x, device:0
albertwang8192-2025-07-05-3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
albertwang8192-2025-07-05-3-v1-mkmlizer: quantized model in 39.661s
albertwang8192-2025-07-05-3-v1-mkmlizer: Processed model AlbertWang8192/2025-07-05_3 in 226.690s
albertwang8192-2025-07-05-3-v1-mkmlizer: creating bucket guanaco-mkml-models
albertwang8192-2025-07-05-3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
albertwang8192-2025-07-05-3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/albertwang8192-2025-07-05-3-v1/nvidia
albertwang8192-2025-07-05-3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/albertwang8192-2025-07-05-3-v1/nvidia/config.json
albertwang8192-2025-07-05-3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/albertwang8192-2025-07-05-3-v1/nvidia/special_tokens_map.json
albertwang8192-2025-07-05-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/albertwang8192-2025-07-05-3-v1/nvidia/tokenizer_config.json
albertwang8192-2025-07-05-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/albertwang8192-2025-07-05-3-v1/nvidia/tokenizer.json
albertwang8192-2025-07-05-3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/albertwang8192-2025-07-05-3-v1/nvidia/flywheel_model.0.safetensors
albertwang8192-2025-07-05-3-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 20.46it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:13, 25.96it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:15, 22.86it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:10, 31.73it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:16, 20.71it/s]
Loading 0:   7%|▋         | 27/363 [00:01<00:16, 19.96it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:14, 23.02it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:14, 22.88it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:12, 25.87it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:13, 23.70it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 28.98it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:11, 27.45it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 28.15it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 23.66it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:14, 20.24it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:11, 24.77it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:12, 22.50it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:12, 22.85it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 27.44it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 24.18it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:09, 29.97it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:09, 27.83it/s]
Loading 0:  28%|██▊       | 101/363 [00:04<00:12, 21.81it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:13, 19.50it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:10, 24.21it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 25.31it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:10, 24.48it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:09, 25.66it/s]
Loading 0:  33%|███▎      | 121/363 [00:04<00:09, 26.39it/s]
Loading 0:  34%|███▍      | 124/363 [00:05<00:09, 25.81it/s]
Loading 0:  35%|███▌      | 128/363 [00:05<00:07, 29.42it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:09, 24.66it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:08, 27.65it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:09, 23.18it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 21.92it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:10, 21.36it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:07, 26.52it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:08, 23.88it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 29.74it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:07, 27.59it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 29.97it/s]
Loading 0:  49%|████▉     | 178/363 [00:07<00:06, 28.49it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:07, 22.72it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:08, 20.41it/s]
Loading 0:  53%|█████▎    | 192/363 [00:07<00:06, 27.26it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 26.38it/s]
Loading 0:  55%|█████▌    | 201/363 [00:08<00:05, 29.01it/s]
Loading 0:  56%|█████▋    | 205/363 [00:08<00:05, 27.96it/s]
Loading 0:  58%|█████▊    | 210/363 [00:08<00:05, 30.24it/s]
Loading 0:  59%|█████▉    | 214/363 [00:08<00:05, 28.54it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:05, 28.38it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 23.98it/s]
Loading 0:  62%|██████▏   | 226/363 [00:09<00:06, 22.68it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 21.91it/s]
Loading 0:  65%|██████▍   | 235/363 [00:09<00:04, 27.06it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:05, 24.50it/s]
Loading 0:  67%|██████▋   | 244/363 [00:09<00:04, 29.46it/s]
Loading 0:  68%|██████▊   | 248/363 [00:09<00:04, 25.59it/s]
Loading 0:  70%|███████   | 255/363 [00:10<00:03, 31.65it/s]
Loading 0:  71%|███████▏  | 259/363 [00:10<00:03, 29.89it/s]
Loading 0:  72%|███████▏  | 263/363 [00:10<00:04, 23.25it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 20.73it/s]
Loading 0:  75%|███████▌  | 273/363 [00:10<00:03, 27.10it/s]
Loading 0:  76%|███████▋  | 277/363 [00:10<00:03, 26.48it/s]
Loading 0:  78%|███████▊  | 282/363 [00:11<00:02, 28.93it/s]
Loading 0:  79%|███████▉  | 286/363 [00:11<00:02, 27.77it/s]
Loading 0:  80%|████████  | 291/363 [00:11<00:02, 29.56it/s]
Loading 0:  81%|████████▏ | 295/363 [00:11<00:02, 27.92it/s]
Loading 0:  82%|████████▏ | 299/363 [00:11<00:02, 27.79it/s]
Loading 0:  83%|████████▎ | 303/363 [00:11<00:01, 30.08it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 21.07it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:02, 20.13it/s]
Loading 0:  87%|████████▋ | 316/363 [00:12<00:01, 25.12it/s]
Loading 0:  88%|████████▊ | 320/363 [00:12<00:01, 23.44it/s]
Loading 0:  90%|████████▉ | 325/363 [00:12<00:01, 28.42it/s]
Loading 0:  91%|█████████ | 329/363 [00:12<00:01, 25.17it/s]
Loading 0:  93%|█████████▎| 336/363 [00:13<00:00, 31.46it/s]
Loading 0:  94%|█████████▎| 340/363 [00:13<00:00, 30.08it/s]
Loading 0:  95%|█████████▍| 344/363 [00:13<00:01, 14.44it/s]
Loading 0:  96%|█████████▌| 348/363 [00:14<00:00, 15.51it/s]
Loading 0:  97%|█████████▋| 353/363 [00:14<00:00, 18.63it/s]
Loading 0:  98%|█████████▊| 357/363 [00:14<00:00, 18.99it/s]
                                                            
Job albertwang8192-2025-07-05-3-v1-mkmlizer completed after 249.21s with status: succeeded
Stopping job with name albertwang8192-2025-07-05-3-v1-mkmlizer
Pipeline stage MKMLizer completed in 249.75s
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 albertwang8192-2025-07-05-3-v1
Waiting for inference service albertwang8192-2025-07-05-3-v1 to be ready
Inference service albertwang8192-2025-07-05-3-v1 ready after 221.3373761177063s
Pipeline stage MKMLDeployer completed in 222.05s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9966979026794434s
Received healthy response to inference request in 2.0092177391052246s
Received healthy response to inference request in 1.842034101486206s
Received healthy response to inference request in 1.6130127906799316s
Received healthy response to inference request in 1.7795002460479736s
5 requests
0 failed requests
5th percentile: 1.64631028175354
10th percentile: 1.6796077728271483
20th percentile: 1.7462027549743653
30th percentile: 1.7920070171356202
40th percentile: 1.817020559310913
50th percentile: 1.842034101486206
60th percentile: 1.9089075565338134
70th percentile: 1.975781011581421
80th percentile: 2.2067137718200684
90th percentile: 2.601705837249756
95th percentile: 2.7992018699645995
99th percentile: 2.9571986961364747
mean time: 2.048092555999756
Pipeline stage StressChecker completed in 11.73s
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 0.95s
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 0.63s
Shutdown handler de-registered
albertwang8192-2025-07-05-3_v1 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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service albertwang8192-2025-07-05-3-v1-profiler
Waiting for inference service albertwang8192-2025-07-05-3-v1-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 3319.47s
Shutdown handler de-registered
albertwang8192-2025-07-05-3_v1 status is now inactive due to auto deactivation removed underperforming models
albertwang8192-2025-07-05-3_v1 status is now torndown due to DeploymentManager action