developer_uid: RandomForest1024
submission_id: albertwang8192-2025-07-08-2_v1
model_name: 2025-07-08_2
model_group: AlbertWang8192/2025-07-0
status: torndown
timestamp: 2025-07-08T12:35:18+00:00
num_battles: 6731
num_wins: 3064
celo_rating: 1259.03
family_friendly_score: 0.5984
family_friendly_standard_error: 0.006932783567947294
submission_type: basic
model_repo: AlbertWang8192/2025-07-08_2
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': 0.5952219514842179, 'latency_mean': 1.6799418461322784, 'latency_p50': 1.6698535680770874, 'latency_p90': 1.862132453918457}, {'batch_size': 3, 'throughput': 1.0729473389414415, 'latency_mean': 2.792121684551239, 'latency_p50': 2.783345580101013, 'latency_p90': 3.1113292932510377}, {'batch_size': 5, 'throughput': 1.2890166335877873, 'latency_mean': 3.8626247489452363, 'latency_p50': 3.9036253690719604, 'latency_p90': 4.241349506378174}, {'batch_size': 6, 'throughput': 1.33751090561196, 'latency_mean': 4.457362413406372, 'latency_p50': 4.4422523975372314, 'latency_p90': 4.950603485107422}, {'batch_size': 8, 'throughput': 1.3953010826610246, 'latency_mean': 5.689514348506927, 'latency_p50': 5.6962350606918335, 'latency_p90': 6.323093366622925}, {'batch_size': 10, 'throughput': 1.430153197415683, 'latency_mean': 6.922975970506668, 'latency_p50': 6.964832067489624, 'latency_p90': 7.817641425132751}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: 2025-07-08_2
is_internal_developer: False
language_model: AlbertWang8192/2025-07-08_2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.27
us_pacific_date: 2025-07-08
win_ratio: 0.4552072500371416
generation_params: {'temperature': 0.6, 'top_p': 0.95, 'min_p': 0.0, '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 albertwang8192-2025-07-08-2-v1-mkmlizer
Waiting for job on albertwang8192-2025-07-08-2-v1-mkmlizer to finish
albertwang8192-2025-07-08-2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
albertwang8192-2025-07-08-2-v1-mkmlizer: ║                                                                     ║
albertwang8192-2025-07-08-2-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
albertwang8192-2025-07-08-2-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
albertwang8192-2025-07-08-2-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
albertwang8192-2025-07-08-2-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
albertwang8192-2025-07-08-2-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
albertwang8192-2025-07-08-2-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
albertwang8192-2025-07-08-2-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
albertwang8192-2025-07-08-2-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
albertwang8192-2025-07-08-2-v1-mkmlizer: ║                                                                     ║
albertwang8192-2025-07-08-2-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
albertwang8192-2025-07-08-2-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
albertwang8192-2025-07-08-2-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
albertwang8192-2025-07-08-2-v1-mkmlizer: ║  https://mk1.ai                                                     ║
albertwang8192-2025-07-08-2-v1-mkmlizer: ║                                                                     ║
albertwang8192-2025-07-08-2-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
albertwang8192-2025-07-08-2-v1-mkmlizer: ║  belonging to:                                                      ║
albertwang8192-2025-07-08-2-v1-mkmlizer: ║                                                                     ║
albertwang8192-2025-07-08-2-v1-mkmlizer: ║  Chai Research Corp.                                                ║
albertwang8192-2025-07-08-2-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
albertwang8192-2025-07-08-2-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
albertwang8192-2025-07-08-2-v1-mkmlizer: ║                                                                     ║
albertwang8192-2025-07-08-2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
albertwang8192-2025-07-08-2-v1-mkmlizer: Downloaded to shared memory in 42.945s
albertwang8192-2025-07-08-2-v1-mkmlizer: Checking if AlbertWang8192/2025-07-08_2 already exists in ChaiML
albertwang8192-2025-07-08-2-v1-mkmlizer: Creating repo ChaiML/2025-07-08_2 and uploading /tmp/tmp9z87r0o8 to it
albertwang8192-2025-07-08-2-v1-mkmlizer: 
  0%|          | 0/6 [00:00<?, ?it/s]
 17%|█▋        | 1/6 [00:06<00:31,  6.32s/it]
 33%|███▎      | 2/6 [00:10<00:19,  4.78s/it]
 50%|█████     | 3/6 [00:14<00:14,  4.67s/it]
 67%|██████▋   | 4/6 [00:20<00:10,  5.27s/it]
 83%|████████▎ | 5/6 [00:24<00:04,  4.87s/it]
100%|██████████| 6/6 [00:26<00:00,  3.62s/it]
100%|██████████| 6/6 [00:26<00:00,  4.35s/it]
albertwang8192-2025-07-08-2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9z87r0o8, device:0
albertwang8192-2025-07-08-2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
albertwang8192-2025-07-08-2-v1-mkmlizer: quantized model in 32.019s
albertwang8192-2025-07-08-2-v1-mkmlizer: Processed model AlbertWang8192/2025-07-08_2 in 128.429s
albertwang8192-2025-07-08-2-v1-mkmlizer: creating bucket guanaco-mkml-models
albertwang8192-2025-07-08-2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
albertwang8192-2025-07-08-2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/albertwang8192-2025-07-08-2-v1/nvidia
albertwang8192-2025-07-08-2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/albertwang8192-2025-07-08-2-v1/nvidia/config.json
albertwang8192-2025-07-08-2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/albertwang8192-2025-07-08-2-v1/nvidia/special_tokens_map.json
albertwang8192-2025-07-08-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/albertwang8192-2025-07-08-2-v1/nvidia/tokenizer_config.json
albertwang8192-2025-07-08-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/albertwang8192-2025-07-08-2-v1/nvidia/tokenizer.json
albertwang8192-2025-07-08-2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/albertwang8192-2025-07-08-2-v1/nvidia/flywheel_model.0.safetensors
Job albertwang8192-2025-07-08-2-v1-mkmlizer completed after 167.78s with status: succeeded
Stopping job with name albertwang8192-2025-07-08-2-v1-mkmlizer
Pipeline stage MKMLizer completed in 168.30s
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 albertwang8192-2025-07-08-2-v1
Waiting for inference service albertwang8192-2025-07-08-2-v1 to be ready
Inference service albertwang8192-2025-07-08-2-v1 ready after 191.2409987449646s
Pipeline stage MKMLDeployer completed in 191.77s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.170330047607422s
Received healthy response to inference request in 1.6198058128356934s
Received healthy response to inference request in 1.650078296661377s
Received healthy response to inference request in 1.6657698154449463s
Received healthy response to inference request in 1.7677302360534668s
5 requests
0 failed requests
5th percentile: 1.6258603096008302
10th percentile: 1.6319148063659668
20th percentile: 1.6440237998962401
30th percentile: 1.6532166004180908
40th percentile: 1.6594932079315186
50th percentile: 1.6657698154449463
60th percentile: 1.7065539836883545
70th percentile: 1.7473381519317628
80th percentile: 1.8482501983642579
90th percentile: 2.0092901229858398
95th percentile: 2.0898100852966306
99th percentile: 2.1542260551452634
mean time: 1.774742841720581
Pipeline stage StressChecker completed in 10.12s
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 0.67s
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 0.66s
Shutdown handler de-registered
albertwang8192-2025-07-08-2_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3121.15s
Shutdown handler de-registered
albertwang8192-2025-07-08-2_v1 status is now inactive due to auto deactivation removed underperforming models
albertwang8192-2025-07-08-2_v1 status is now torndown due to DeploymentManager action