developer_uid: RandomForest1024
submission_id: albertwang8192-2025-07-11-7_v16
model_name: 2025-07-11_7_v16
model_group: AlbertWang8192/2025-07-1
status: torndown
timestamp: 2025-07-13T17:46:01+00:00
num_battles: 9078
num_wins: 4291
celo_rating: 1267.64
family_friendly_score: 0.544
family_friendly_standard_error: 0.007043635424977645
submission_type: basic
model_repo: AlbertWang8192/2025-07-11_7
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': 0.5914169097834058, 'latency_mean': 1.6906619775295257, 'latency_p50': 1.702996850013733, 'latency_p90': 1.8567771911621094}, {'batch_size': 3, 'throughput': 1.0622394116098337, 'latency_mean': 2.812143722772598, 'latency_p50': 2.818315029144287, 'latency_p90': 3.113208484649658}, {'batch_size': 5, 'throughput': 1.285650768231082, 'latency_mean': 3.867674297094345, 'latency_p50': 3.8507388830184937, 'latency_p90': 4.272259902954102}, {'batch_size': 6, 'throughput': 1.3542114158279766, 'latency_mean': 4.412843089103699, 'latency_p50': 4.45798659324646, 'latency_p90': 4.8838539838790895}, {'batch_size': 8, 'throughput': 1.3972586000963285, 'latency_mean': 5.676299101114273, 'latency_p50': 5.6706702709198, 'latency_p90': 6.32758150100708}, {'batch_size': 10, 'throughput': 1.4359380988124781, 'latency_mean': 6.9112693011760715, 'latency_p50': 6.95881986618042, 'latency_p90': 7.799303007125855}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: 2025-07-11_7_v16
is_internal_developer: False
language_model: AlbertWang8192/2025-07-11_7
model_size: 13B
ranking_group: single
throughput_3p7s: 1.27
us_pacific_date: 2025-07-13
win_ratio: 0.47268120731438645
generation_params: {'temperature': 0.6, 'top_p': 0.98, 'min_p': 0.03, 'top_k': 40, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n', '<|im_end|>', '<|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 albertwang8192-2025-07-11-7-v16-mkmlizer
Waiting for job on albertwang8192-2025-07-11-7-v16-mkmlizer to finish
albertwang8192-2025-07-11-7-v16-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
albertwang8192-2025-07-11-7-v16-mkmlizer: ║                                                                     ║
albertwang8192-2025-07-11-7-v16-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
albertwang8192-2025-07-11-7-v16-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
albertwang8192-2025-07-11-7-v16-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
albertwang8192-2025-07-11-7-v16-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
albertwang8192-2025-07-11-7-v16-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
albertwang8192-2025-07-11-7-v16-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
albertwang8192-2025-07-11-7-v16-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
albertwang8192-2025-07-11-7-v16-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
albertwang8192-2025-07-11-7-v16-mkmlizer: ║                                                                     ║
albertwang8192-2025-07-11-7-v16-mkmlizer: ║  Version: 0.29.15                                                   ║
albertwang8192-2025-07-11-7-v16-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
albertwang8192-2025-07-11-7-v16-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
albertwang8192-2025-07-11-7-v16-mkmlizer: ║  https://mk1.ai                                                     ║
albertwang8192-2025-07-11-7-v16-mkmlizer: ║                                                                     ║
albertwang8192-2025-07-11-7-v16-mkmlizer: ║  The license key for the current software has been verified as      ║
albertwang8192-2025-07-11-7-v16-mkmlizer: ║  belonging to:                                                      ║
albertwang8192-2025-07-11-7-v16-mkmlizer: ║                                                                     ║
albertwang8192-2025-07-11-7-v16-mkmlizer: ║  Chai Research Corp.                                                ║
albertwang8192-2025-07-11-7-v16-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
albertwang8192-2025-07-11-7-v16-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
albertwang8192-2025-07-11-7-v16-mkmlizer: ║                                                                     ║
albertwang8192-2025-07-11-7-v16-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
albertwang8192-2025-07-11-7-v16-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`
albertwang8192-2025-07-11-7-v16-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`
albertwang8192-2025-07-11-7-v16-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`
albertwang8192-2025-07-11-7-v16-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`
albertwang8192-2025-07-11-7-v16-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`
albertwang8192-2025-07-11-7-v16-mkmlizer: Downloaded to shared memory in 36.238s
albertwang8192-2025-07-11-7-v16-mkmlizer: Checking if AlbertWang8192/2025-07-11_7 already exists in ChaiML
albertwang8192-2025-07-11-7-v16-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2j742iv1, device:0
albertwang8192-2025-07-11-7-v16-mkmlizer: Saving flywheel model at /dev/shm/model_cache
albertwang8192-2025-07-11-7-v16-mkmlizer: quantized model in 38.046s
albertwang8192-2025-07-11-7-v16-mkmlizer: Processed model AlbertWang8192/2025-07-11_7 in 74.398s
albertwang8192-2025-07-11-7-v16-mkmlizer: creating bucket guanaco-mkml-models
albertwang8192-2025-07-11-7-v16-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
albertwang8192-2025-07-11-7-v16-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/albertwang8192-2025-07-11-7-v16/nvidia
albertwang8192-2025-07-11-7-v16-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/albertwang8192-2025-07-11-7-v16/nvidia/config.json
albertwang8192-2025-07-11-7-v16-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/albertwang8192-2025-07-11-7-v16/nvidia/special_tokens_map.json
albertwang8192-2025-07-11-7-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/albertwang8192-2025-07-11-7-v16/nvidia/tokenizer_config.json
albertwang8192-2025-07-11-7-v16-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/albertwang8192-2025-07-11-7-v16/nvidia/flywheel_model.0.safetensors
Job albertwang8192-2025-07-11-7-v16-mkmlizer completed after 105.74s with status: succeeded
Stopping job with name albertwang8192-2025-07-11-7-v16-mkmlizer
Pipeline stage MKMLizer completed in 106.27s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service albertwang8192-2025-07-11-7-v16
Waiting for inference service albertwang8192-2025-07-11-7-v16 to be ready
Failed to get response for submission albertwang8192-2025-07-11-7_v13: HTTPConnectionPool(host='albertwang8192-2025-07-11-7-v13-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission albertwang8192-2025-07-13-1_v1: HTTPConnectionPool(host='albertwang8192-2025-07-13-1-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission albertwang8192-2025-07-11-7_v11: HTTPConnectionPool(host='albertwang8192-2025-07-11-7-v11-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service albertwang8192-2025-07-11-7-v16 ready after 220.96621751785278s
Pipeline stage MKMLDeployer completed in 221.68s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3548853397369385s
Received healthy response to inference request in 1.5270681381225586s
Received healthy response to inference request in 1.7926254272460938s
Received healthy response to inference request in 1.8626878261566162s
Received healthy response to inference request in 2.1051137447357178s
5 requests
0 failed requests
5th percentile: 1.5801795959472655
10th percentile: 1.6332910537719727
20th percentile: 1.7395139694213868
30th percentile: 1.8066379070281982
40th percentile: 1.8346628665924072
50th percentile: 1.8626878261566162
60th percentile: 1.9596581935882569
70th percentile: 2.0566285610198975
80th percentile: 2.155068063735962
90th percentile: 2.2549767017364504
95th percentile: 2.3049310207366944
99th percentile: 2.3448944759368895
mean time: 1.928476095199585
Pipeline stage StressChecker completed in 11.10s
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 0.63s
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
albertwang8192-2025-07-11-7_v16 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 3295.25s
Shutdown handler de-registered
albertwang8192-2025-07-11-7_v16 status is now inactive due to auto deactivation removed underperforming models
albertwang8192-2025-07-11-7_v16 status is now torndown due to DeploymentManager action