developer_uid: RandomForest1024
submission_id: albertwang8192-2025-07-11-0_v1
model_name: 2025-07-11_0
model_group: AlbertWang8192/2025-07-1
status: torndown
timestamp: 2025-07-11T14:04:06+00:00
num_battles: 11006
num_wins: 5077
celo_rating: 1265.26
family_friendly_score: 0.5828
family_friendly_standard_error: 0.006973437602789603
submission_type: basic
model_repo: AlbertWang8192/2025-07-11_0
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': 0.5812586581939173, 'latency_mean': 1.7202792930603028, 'latency_p50': 1.7244751453399658, 'latency_p90': 1.8757942199707032}, {'batch_size': 3, 'throughput': 1.05161577163004, 'latency_mean': 2.843232800960541, 'latency_p50': 2.8439903259277344, 'latency_p90': 3.109172892570496}, {'batch_size': 5, 'throughput': 1.255141097080192, 'latency_mean': 3.961765521764755, 'latency_p50': 3.958608865737915, 'latency_p90': 4.454047274589539}, {'batch_size': 6, 'throughput': 1.3325277091705563, 'latency_mean': 4.470681592226028, 'latency_p50': 4.452817678451538, 'latency_p90': 5.1644542694091795}, {'batch_size': 8, 'throughput': 1.3867208939933742, 'latency_mean': 5.7374229180812835, 'latency_p50': 5.693613171577454, 'latency_p90': 6.382141423225403}, {'batch_size': 10, 'throughput': 1.4050556986655494, 'latency_mean': 7.057054953575134, 'latency_p50': 7.073305130004883, 'latency_p90': 8.016604161262512}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: 2025-07-11_0
is_internal_developer: False
language_model: AlbertWang8192/2025-07-11_0
model_size: 13B
ranking_group: single
throughput_3p7s: 1.22
us_pacific_date: 2025-07-11
win_ratio: 0.461293839723787
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|>', '\n', '<|im_start|>'], '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 albertwang8192-2025-07-11-0-v1-mkmlizer
Waiting for job on albertwang8192-2025-07-11-0-v1-mkmlizer to finish
albertwang8192-2025-07-11-0-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
albertwang8192-2025-07-11-0-v1-mkmlizer: ║                                                                     ║
albertwang8192-2025-07-11-0-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
albertwang8192-2025-07-11-0-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
albertwang8192-2025-07-11-0-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
albertwang8192-2025-07-11-0-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
albertwang8192-2025-07-11-0-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
albertwang8192-2025-07-11-0-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
albertwang8192-2025-07-11-0-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
albertwang8192-2025-07-11-0-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
albertwang8192-2025-07-11-0-v1-mkmlizer: ║                                                                     ║
albertwang8192-2025-07-11-0-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
albertwang8192-2025-07-11-0-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
albertwang8192-2025-07-11-0-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
albertwang8192-2025-07-11-0-v1-mkmlizer: ║  https://mk1.ai                                                     ║
albertwang8192-2025-07-11-0-v1-mkmlizer: ║                                                                     ║
albertwang8192-2025-07-11-0-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
albertwang8192-2025-07-11-0-v1-mkmlizer: ║  belonging to:                                                      ║
albertwang8192-2025-07-11-0-v1-mkmlizer: ║                                                                     ║
albertwang8192-2025-07-11-0-v1-mkmlizer: ║  Chai Research Corp.                                                ║
albertwang8192-2025-07-11-0-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
albertwang8192-2025-07-11-0-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
albertwang8192-2025-07-11-0-v1-mkmlizer: ║                                                                     ║
albertwang8192-2025-07-11-0-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
albertwang8192-2025-07-11-0-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`
albertwang8192-2025-07-11-0-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`
albertwang8192-2025-07-11-0-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`
albertwang8192-2025-07-11-0-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`
albertwang8192-2025-07-11-0-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`
albertwang8192-2025-07-11-0-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`
albertwang8192-2025-07-11-0-v1-mkmlizer: Downloaded to shared memory in 53.203s
albertwang8192-2025-07-11-0-v1-mkmlizer: Checking if AlbertWang8192/2025-07-11_0 already exists in ChaiML
albertwang8192-2025-07-11-0-v1-mkmlizer: Creating repo ChaiML/2025-07-11_0 and uploading /tmp/tmp6c7_0k19 to it
albertwang8192-2025-07-11-0-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6c7_0k19, device:0
albertwang8192-2025-07-11-0-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
albertwang8192-2025-07-11-0-v1-mkmlizer: quantized model in 31.054s
albertwang8192-2025-07-11-0-v1-mkmlizer: Processed model AlbertWang8192/2025-07-11_0 in 140.059s
albertwang8192-2025-07-11-0-v1-mkmlizer: creating bucket guanaco-mkml-models
albertwang8192-2025-07-11-0-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
albertwang8192-2025-07-11-0-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/albertwang8192-2025-07-11-0-v1/nvidia
albertwang8192-2025-07-11-0-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/albertwang8192-2025-07-11-0-v1/nvidia/config.json
albertwang8192-2025-07-11-0-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/albertwang8192-2025-07-11-0-v1/nvidia/special_tokens_map.json
albertwang8192-2025-07-11-0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/albertwang8192-2025-07-11-0-v1/nvidia/tokenizer_config.json
albertwang8192-2025-07-11-0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/albertwang8192-2025-07-11-0-v1/nvidia/tokenizer.json
albertwang8192-2025-07-11-0-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/albertwang8192-2025-07-11-0-v1/nvidia/flywheel_model.0.safetensors
Retrying (%r) after connection broken by '%r': %s
Job albertwang8192-2025-07-11-0-v1-mkmlizer completed after 167.09s with status: succeeded
Stopping job with name albertwang8192-2025-07-11-0-v1-mkmlizer
Pipeline stage MKMLizer completed in 167.87s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service albertwang8192-2025-07-11-0-v1
Waiting for inference service albertwang8192-2025-07-11-0-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service albertwang8192-2025-07-11-0-v1 ready after 200.84560108184814s
Pipeline stage MKMLDeployer completed in 201.47s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.647261381149292s
Received healthy response to inference request in 1.689516544342041s
Received healthy response to inference request in 2.2163925170898438s
Received healthy response to inference request in 2.070577621459961s
Received healthy response to inference request in 1.385002613067627s
5 requests
0 failed requests
5th percentile: 1.4459053993225097
10th percentile: 1.5068081855773925
20th percentile: 1.6286137580871582
30th percentile: 1.765728759765625
40th percentile: 1.9181531906127929
50th percentile: 2.070577621459961
60th percentile: 2.1289035797119142
70th percentile: 2.187229537963867
80th percentile: 2.3025662899017334
90th percentile: 2.4749138355255127
95th percentile: 2.5610876083374023
99th percentile: 2.630026626586914
mean time: 2.001750135421753
Pipeline stage StressChecker completed in 11.85s
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 0.78s
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 0.76s
Shutdown handler de-registered
albertwang8192-2025-07-11-0_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 3074.69s
Shutdown handler de-registered
albertwang8192-2025-07-11-0_v1 status is now inactive due to auto deactivation removed underperforming models
albertwang8192-2025-07-11-0_v1 status is now torndown due to DeploymentManager action