developer_uid: richhx
submission_id: chaiml-banished-pharaoh_16194_v2
model_name: chaiml-banished-pharaoh_16194_v2
model_group: ChaiML/Banished-Pharaoh-
status: torndown
timestamp: 2025-06-26T18:46:58+00:00
num_battles: 6503
num_wins: 3263
celo_rating: 1283.92
family_friendly_score: 0.534
family_friendly_standard_error: 0.00705470056061914
submission_type: basic
model_repo: ChaiML/Banished-Pharaoh-Noa250614102030_preference_dpo
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.5209398589671594, 'latency_mean': 1.9194808411598205, 'latency_p50': 1.9097135066986084, 'latency_p90': 2.1438933849334716}, {'batch_size': 3, 'throughput': 1.0450702725804935, 'latency_mean': 2.8641233825683594, 'latency_p50': 2.863272190093994, 'latency_p90': 3.1553252935409546}, {'batch_size': 5, 'throughput': 1.3260045750323073, 'latency_mean': 3.7556335401535033, 'latency_p50': 3.7686851024627686, 'latency_p90': 4.198548746109009}, {'batch_size': 6, 'throughput': 1.435273022003442, 'latency_mean': 4.148568003177643, 'latency_p50': 4.116693019866943, 'latency_p90': 4.627578067779541}, {'batch_size': 8, 'throughput': 1.5567997309373969, 'latency_mean': 5.0873288404941555, 'latency_p50': 5.086550831794739, 'latency_p90': 5.719446587562561}, {'batch_size': 10, 'throughput': 1.6316912282165583, 'latency_mean': 6.070178971290589, 'latency_p50': 6.1109747886657715, 'latency_p90': 6.837970924377442}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-banished-pharaoh_16194_v2
ineligible_reason: num_battles<10000
is_internal_developer: True
language_model: ChaiML/Banished-Pharaoh-Noa250614102030_preference_dpo
model_size: 24B
ranking_group: single
throughput_3p7s: 1.32
us_pacific_date: 2025-06-26
win_ratio: 0.5017684145778871
generation_params: {'temperature': 0.5, 'top_p': 0.95, 'min_p': 0.02, 'top_k': 60, 'presence_penalty': 0.2, 'frequency_penalty': 0.2, 'stopping_words': ['\n', '####\n', '####', 'You:', '</s>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}</s>\n', 'user_template': 'You: {message}\n', 'response_template': '{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 chaiml-banished-pharaoh-16194-v2-mkmlizer
Waiting for job on chaiml-banished-pharaoh-16194-v2-mkmlizer to finish
chaiml-banished-pharaoh-16194-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-banished-pharaoh-16194-v2-mkmlizer: ║                                                                     ║
chaiml-banished-pharaoh-16194-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-banished-pharaoh-16194-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-banished-pharaoh-16194-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-banished-pharaoh-16194-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-banished-pharaoh-16194-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-banished-pharaoh-16194-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-banished-pharaoh-16194-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-banished-pharaoh-16194-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-banished-pharaoh-16194-v2-mkmlizer: ║                                                                     ║
chaiml-banished-pharaoh-16194-v2-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-banished-pharaoh-16194-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-banished-pharaoh-16194-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-banished-pharaoh-16194-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-banished-pharaoh-16194-v2-mkmlizer: ║                                                                     ║
chaiml-banished-pharaoh-16194-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-banished-pharaoh-16194-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-banished-pharaoh-16194-v2-mkmlizer: ║                                                                     ║
chaiml-banished-pharaoh-16194-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-banished-pharaoh-16194-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-banished-pharaoh-16194-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-banished-pharaoh-16194-v2-mkmlizer: ║                                                                     ║
chaiml-banished-pharaoh-16194-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-banished-pharaoh-16194-v2-mkmlizer: Downloaded to shared memory in 119.065s
chaiml-banished-pharaoh-16194-v2-mkmlizer: Checking if ChaiML/Banished-Pharaoh-Noa250614102030_preference_dpo already exists in ChaiML
chaiml-banished-pharaoh-16194-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcl2f2jon, device:0
chaiml-banished-pharaoh-16194-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-banished-pharaoh-16194-v2-mkmlizer: quantized model in 49.111s
chaiml-banished-pharaoh-16194-v2-mkmlizer: Processed model ChaiML/Banished-Pharaoh-Noa250614102030_preference_dpo in 168.177s
chaiml-banished-pharaoh-16194-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-banished-pharaoh-16194-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-banished-pharaoh-16194-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-banished-pharaoh-16194-v2
chaiml-banished-pharaoh-16194-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-banished-pharaoh-16194-v2/config.json
chaiml-banished-pharaoh-16194-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-banished-pharaoh-16194-v2/special_tokens_map.json
chaiml-banished-pharaoh-16194-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-banished-pharaoh-16194-v2/tokenizer_config.json
chaiml-banished-pharaoh-16194-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-banished-pharaoh-16194-v2/tokenizer.json
chaiml-banished-pharaoh-16194-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-banished-pharaoh-16194-v2/flywheel_model.1.safetensors
chaiml-banished-pharaoh-16194-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-banished-pharaoh-16194-v2/flywheel_model.0.safetensors
Job chaiml-banished-pharaoh-16194-v2-mkmlizer completed after 199.06s with status: succeeded
Stopping job with name chaiml-banished-pharaoh-16194-v2-mkmlizer
Pipeline stage MKMLizer completed in 199.93s
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 chaiml-banished-pharaoh-16194-v2
Waiting for inference service chaiml-banished-pharaoh-16194-v2 to be ready
Inference service chaiml-banished-pharaoh-16194-v2 ready after 150.55060505867004s
Pipeline stage MKMLDeployer completed in 151.06s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5380170345306396s
Received healthy response to inference request in 2.0395002365112305s
Received healthy response to inference request in 1.92439866065979s
Received healthy response to inference request in 2.0529956817626953s
Received healthy response to inference request in 2.280225992202759s
5 requests
0 failed requests
5th percentile: 1.9474189758300782
10th percentile: 1.9704392910003663
20th percentile: 2.0164799213409426
30th percentile: 2.0421993255615236
40th percentile: 2.0475975036621095
50th percentile: 2.0529956817626953
60th percentile: 2.1438878059387205
70th percentile: 2.234779930114746
80th percentile: 2.331784200668335
90th percentile: 2.4349006175994874
95th percentile: 2.4864588260650633
99th percentile: 2.5277053928375244
mean time: 2.1670275211334227
Pipeline stage StressChecker completed in 12.31s
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 0.96s
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 0.84s
Shutdown handler de-registered
chaiml-banished-pharaoh_16194_v2 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-banished-pharaoh-16194-v2-profiler
Waiting for inference service chaiml-banished-pharaoh-16194-v2-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 3351.13s
Shutdown handler de-registered
chaiml-banished-pharaoh_16194_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-banished-pharaoh_16194_v2 status is now torndown due to DeploymentManager action