albertwang8192-2025-07-12-3

developer_uid: RandomForest1024

submission_id: albertwang8192-2025-07-12-3_v1

model_name: 2025-07-12_3

model_group: AlbertWang8192/2025-07-1

status: torndown

timestamp: 2025-07-13T03:10:00+00:00

num_battles: 7684

num_wins: 3496

celo_rating: 1260.77

family_friendly_score: 0.5347999999999999

family_friendly_standard_error: 0.007053920328441483

submission_type: basic

model_repo: AlbertWang8192/2025-07-12_3

model_architecture: MistralForCausalLM

model_num_parameters: 12772090880.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5776749437567842, 'latency_mean': 1.7309346985816956, 'latency_p50': 1.732014775276184, 'latency_p90': 1.8993725776672363}, {'batch_size': 3, 'throughput': 1.0404056592442639, 'latency_mean': 2.872649915218353, 'latency_p50': 2.8869746923446655, 'latency_p90': 3.1599928855896}, {'batch_size': 5, 'throughput': 1.2325034731364073, 'latency_mean': 4.029272233247757, 'latency_p50': 3.9924298524856567, 'latency_p90': 4.526055097579956}, {'batch_size': 6, 'throughput': 1.2912840524622815, 'latency_mean': 4.6162349581718445, 'latency_p50': 4.628524541854858, 'latency_p90': 5.1243394851684565}, {'batch_size': 8, 'throughput': 1.3406332544482398, 'latency_mean': 5.935001339912414, 'latency_p50': 5.957117676734924, 'latency_p90': 6.59633629322052}, {'batch_size': 10, 'throughput': 1.38202128078775, 'latency_mean': 7.17566442489624, 'latency_p50': 7.1620436906814575, 'latency_p90': 8.100702166557312}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: 2025-07-12_3

is_internal_developer: False

language_model: AlbertWang8192/2025-07-12_3

model_size: 13B

ranking_group: single

throughput_3p7s: 1.2

us_pacific_date: 2025-07-12

win_ratio: 0.4549713690786049

generation_params: {'temperature': 0.6, 'top_p': 0.98, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|im_end|>', '\n', '<|im_start|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': True}

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 albertwang8192-2025-07-12-3-v1-mkmlizer
Waiting for job on albertwang8192-2025-07-12-3-v1-mkmlizer to finish
albertwang8192-2025-07-12-3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
albertwang8192-2025-07-12-3-v1-mkmlizer: ║                                                                     ║
albertwang8192-2025-07-12-3-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
albertwang8192-2025-07-12-3-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
albertwang8192-2025-07-12-3-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
albertwang8192-2025-07-12-3-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
albertwang8192-2025-07-12-3-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
albertwang8192-2025-07-12-3-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
albertwang8192-2025-07-12-3-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
albertwang8192-2025-07-12-3-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
albertwang8192-2025-07-12-3-v1-mkmlizer: ║                                                                     ║
albertwang8192-2025-07-12-3-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
albertwang8192-2025-07-12-3-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
albertwang8192-2025-07-12-3-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
albertwang8192-2025-07-12-3-v1-mkmlizer: ║  https://mk1.ai                                                     ║
albertwang8192-2025-07-12-3-v1-mkmlizer: ║                                                                     ║
albertwang8192-2025-07-12-3-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
albertwang8192-2025-07-12-3-v1-mkmlizer: ║  belonging to:                                                      ║
albertwang8192-2025-07-12-3-v1-mkmlizer: ║                                                                     ║
albertwang8192-2025-07-12-3-v1-mkmlizer: ║  Chai Research Corp.                                                ║
albertwang8192-2025-07-12-3-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
albertwang8192-2025-07-12-3-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
albertwang8192-2025-07-12-3-v1-mkmlizer: ║                                                                     ║
albertwang8192-2025-07-12-3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
albertwang8192-2025-07-12-3-v1-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`
albertwang8192-2025-07-12-3-v1-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`
albertwang8192-2025-07-12-3-v1-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`
albertwang8192-2025-07-12-3-v1-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`
albertwang8192-2025-07-12-3-v1-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`
albertwang8192-2025-07-12-3-v1-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`
albertwang8192-2025-07-12-3-v1-mkmlizer: 
  0%|          | 0/6 [00:00<?, ?it/s]
 17%|█▋        | 1/6 [00:03<00:17,  3.49s/it]
 33%|███▎      | 2/6 [00:11<00:23,  5.87s/it]
 50%|█████     | 3/6 [00:14<00:14,  4.74s/it]
 67%|██████▋   | 4/6 [00:20<00:10,  5.24s/it]
 83%|████████▎ | 5/6 [00:24<00:04,  4.96s/it]
100%|██████████| 6/6 [00:26<00:00,  3.66s/it]
100%|██████████| 6/6 [00:26<00:00,  4.34s/it]
albertwang8192-2025-07-12-3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp41qewrxd, device:0
albertwang8192-2025-07-12-3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
albertwang8192-2025-07-12-3-v1-mkmlizer: quantized model in 29.738s
albertwang8192-2025-07-12-3-v1-mkmlizer: Processed model AlbertWang8192/2025-07-12_3 in 137.923s
albertwang8192-2025-07-12-3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
albertwang8192-2025-07-12-3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/albertwang8192-2025-07-12-3-v1/nvidia
albertwang8192-2025-07-12-3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/albertwang8192-2025-07-12-3-v1/nvidia/config.json
albertwang8192-2025-07-12-3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/albertwang8192-2025-07-12-3-v1/nvidia/special_tokens_map.json
albertwang8192-2025-07-12-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/albertwang8192-2025-07-12-3-v1/nvidia/tokenizer_config.json
albertwang8192-2025-07-12-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/albertwang8192-2025-07-12-3-v1/nvidia/tokenizer.json
albertwang8192-2025-07-12-3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/albertwang8192-2025-07-12-3-v1/nvidia/flywheel_model.0.safetensors
albertwang8192-2025-07-12-3-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 33.01it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 52.66it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 45.36it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 43.77it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 49.41it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 44.32it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 43.58it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 48.73it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 45.20it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 35.38it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 34.57it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 40.71it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:06, 42.80it/s]
Loading 0:  23%|██▎       | 82/363 [00:01<00:07, 36.86it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 43.56it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 43.59it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:06, 43.39it/s]
Loading 0:  29%|██▊       | 104/363 [00:02<00:05, 45.06it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:05, 46.12it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:06, 37.66it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:06, 37.65it/s]
Loading 0:  34%|███▍      | 125/363 [00:02<00:05, 41.62it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 41.37it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 41.65it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:05, 39.99it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:07, 29.93it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:07, 29.98it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 35.05it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 35.51it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 38.09it/s]
Loading 0:  47%|████▋     | 170/363 [00:04<00:04, 39.35it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 39.82it/s]
Loading 0:  50%|████▉     | 180/363 [00:04<00:04, 41.94it/s]
Loading 0:  51%|█████     | 185/363 [00:04<00:05, 35.34it/s]
Loading 0:  53%|█████▎    | 192/363 [00:04<00:03, 42.83it/s]
Loading 0:  54%|█████▍    | 197/363 [00:04<00:03, 42.54it/s]
Loading 0:  56%|█████▌    | 202/363 [00:04<00:03, 43.82it/s]
Loading 0:  57%|█████▋    | 207/363 [00:05<00:03, 45.00it/s]
Loading 0:  58%|█████▊    | 212/363 [00:05<00:04, 37.57it/s]
Loading 0:  60%|██████    | 218/363 [00:05<00:03, 42.62it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:04, 33.31it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 33.47it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 32.81it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 38.60it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 39.80it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 40.73it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 42.72it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:02, 36.30it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 43.95it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 43.98it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:01, 44.53it/s]
Loading 0:  77%|███████▋  | 280/363 [00:06<00:01, 42.23it/s]
Loading 0:  79%|███████▊  | 285/363 [00:07<00:01, 41.85it/s]
Loading 0:  80%|████████  | 292/363 [00:07<00:01, 46.61it/s]
Loading 0:  82%|████████▏ | 297/363 [00:07<00:01, 47.37it/s]
Loading 0:  83%|████████▎ | 302/363 [00:07<00:01, 47.80it/s]
Loading 0:  85%|████████▍ | 307/363 [00:07<00:02, 22.33it/s]
Loading 0:  86%|████████▌ | 312/363 [00:08<00:02, 23.51it/s]
Loading 0:  88%|████████▊ | 320/363 [00:08<00:01, 31.80it/s]
Loading 0:  90%|████████▉ | 325/363 [00:08<00:01, 35.06it/s]
Loading 0:  91%|█████████ | 330/363 [00:08<00:01, 32.52it/s]
Loading 0:  93%|█████████▎| 337/363 [00:08<00:00, 39.66it/s]
Loading 0:  94%|█████████▍| 342/363 [00:08<00:00, 40.86it/s]
Loading 0:  96%|█████████▌| 347/363 [00:08<00:00, 42.11it/s]
Loading 0:  97%|█████████▋| 353/363 [00:09<00:00, 40.62it/s]
Loading 0:  99%|█████████▊| 358/363 [00:09<00:00, 40.43it/s]
                                                            
Job albertwang8192-2025-07-12-3-v1-mkmlizer completed after 167.48s with status: succeeded
Stopping job with name albertwang8192-2025-07-12-3-v1-mkmlizer
Pipeline stage MKMLizer completed in 168.02s
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 albertwang8192-2025-07-12-3-v1
Waiting for inference service albertwang8192-2025-07-12-3-v1 to be ready
Inference service albertwang8192-2025-07-12-3-v1 ready after 221.4172842502594s
Pipeline stage MKMLDeployer completed in 222.01s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.410186767578125s
Received healthy response to inference request in 1.992168664932251s
Received healthy response to inference request in 1.5093791484832764s
Received healthy response to inference request in 1.7529053688049316s
Received healthy response to inference request in 1.8078279495239258s
5 requests
0 failed requests
5th percentile: 1.5580843925476073
10th percentile: 1.6067896366119385
20th percentile: 1.7042001247406007
30th percentile: 1.7638898849487306
40th percentile: 1.7858589172363282
50th percentile: 1.8078279495239258
60th percentile: 1.881564235687256
70th percentile: 1.955300521850586
80th percentile: 2.075772285461426
90th percentile: 2.2429795265197754
95th percentile: 2.32658314704895
99th percentile: 2.39346604347229
mean time: 1.894493579864502
Pipeline stage StressChecker completed in 11.23s
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 1.02s
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 0.81s
Shutdown handler de-registered
albertwang8192-2025-07-12-3_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 3778.72s
Shutdown handler de-registered
albertwang8192-2025-07-12-3_v1 status is now inactive due to auto deactivation removed underperforming models
albertwang8192-2025-07-12-3_v1 status is now torndown due to DeploymentManager action