developer_uid: zonemercy
submission_id: chaiml-cs-feed-score-v3_26083_v2
model_name: chaiml-cs-feed-score-v3_26083_v2
model_group: ChaiML/cs-feed-score-v3-
status: torndown
timestamp: 2025-10-14T16:38:44+00:00
num_battles: 6355
num_wins: 3370
celo_rating: 1293.8
family_friendly_score: 0.5018
family_friendly_standard_error: 0.007071021991197595
submission_type: basic
model_repo: ChaiML/cs-feed-score-v3-dpo-test-2
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 2048
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.4284081431100332, 'latency_mean': 2.3341046059131623, 'latency_p50': 2.1696659326553345, 'latency_p90': 2.405545139312744}, {'batch_size': 2, 'throughput': 0.681360215012601, 'latency_mean': 2.934459229707718, 'latency_p50': 2.943821430206299, 'latency_p90': 3.154949259757996}, {'batch_size': 3, 'throughput': 0.8317928853357606, 'latency_mean': 3.5952734971046447, 'latency_p50': 3.5908403396606445, 'latency_p90': 3.9044380664825438}, {'batch_size': 4, 'throughput': 0.9310687257170225, 'latency_mean': 4.289312871694565, 'latency_p50': 4.284510016441345, 'latency_p90': 4.893813109397888}, {'batch_size': 5, 'throughput': 0.9901699714501264, 'latency_mean': 5.03146735906601, 'latency_p50': 5.033556699752808, 'latency_p90': 5.835562634468078}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-cs-feed-score-v3_26083_v2
is_internal_developer: True
language_model: ChaiML/cs-feed-score-v3-dpo-test-2
model_size: 24B
ranking_group: single
throughput_3p7s: 0.85
us_pacific_date: 2025-10-14
win_ratio: 0.5302911093627065
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>', '\n', '####', 'You:'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s persona: {memory}", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': 'You: {message}\n', 'response_template': '####\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 chaiml-cs-feed-score-v3-26083-v2-mkmlizer
Waiting for job on chaiml-cs-feed-score-v3-26083-v2-mkmlizer to finish
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: ║ ║
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: ║ ║
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: ║ Version: 0.30.2 ║
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: ║ ║
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: ║ belonging to: ║
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: ║ ║
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: ║ ║
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: Downloaded to shared memory in 58.808s
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: Checking if ChaiML/cs-feed-score-v3-dpo-test-2 already exists in ChaiML
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmp0czafkkc, device:0
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission mistralai-mistral-nem_93303_v569: ('http://mistralai-mistral-nem-93303-v569-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission mistralai-mistral-nem_93303_v569: ('http://mistralai-mistral-nem-93303-v569-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: quantized model in 284.779s
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: Processed model ChaiML/cs-feed-score-v3-dpo-test-2 in 343.587s
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-cs-feed-score-v3-26083-v2/nvidia
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-cs-feed-score-v3-26083-v2/nvidia/config.json
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-cs-feed-score-v3-26083-v2/nvidia/special_tokens_map.json
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-cs-feed-score-v3-26083-v2/nvidia/tokenizer.json
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-cs-feed-score-v3-26083-v2/nvidia/flywheel_model.1.safetensors
chaiml-cs-feed-score-v3-26083-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-cs-feed-score-v3-26083-v2/nvidia/flywheel_model.0.safetensors
Job chaiml-cs-feed-score-v3-26083-v2-mkmlizer completed after 422.27s with status: succeeded
Stopping job with name chaiml-cs-feed-score-v3-26083-v2-mkmlizer
Pipeline stage MKMLizer completed in 422.82s
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 chaiml-cs-feed-score-v3-26083-v2
Waiting for inference service chaiml-cs-feed-score-v3-26083-v2 to be ready
Retrying (%r) after connection broken by '%r': %s
Inference service chaiml-cs-feed-score-v3-26083-v2 ready after 60.83686947822571s
Pipeline stage MKMLDeployer completed in 61.68s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0408356189727783s
Received healthy response to inference request in 1.9514718055725098s
Received healthy response to inference request in 1.733379602432251s
Received healthy response to inference request in 1.707244873046875s
Received healthy response to inference request in 1.8769867420196533s
5 requests
0 failed requests
5th percentile: 1.7124718189239503
10th percentile: 1.7176987648010253
20th percentile: 1.7281526565551757
30th percentile: 1.7621010303497315
40th percentile: 1.8195438861846924
50th percentile: 1.8769867420196533
60th percentile: 1.906780767440796
70th percentile: 1.9365747928619386
80th percentile: 1.9693445682525634
90th percentile: 2.005090093612671
95th percentile: 2.0229628562927244
99th percentile: 2.0372610664367676
mean time: 1.8619837284088134
Pipeline stage StressChecker completed in 10.92s
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 0.64s
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 0.64s
Shutdown handler de-registered
chaiml-cs-feed-score-v3_26083_v2 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 2967.91s
Shutdown handler de-registered
chaiml-cs-feed-score-v3_26083_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-cs-feed-score-v3_26083_v2 status is now torndown due to DeploymentManager action