developer_uid: zonemercy
submission_id: chaiml-cs-feed-score-v2_14306_v4
model_name: chaiml-cs-feed-score-v2_14306_v4
model_group: ChaiML/cs-feed-score-v2-
status: torndown
timestamp: 2025-10-13T18:15:01+00:00
num_battles: 9556
num_wins: 5260
celo_rating: 1273.29
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/cs-feed-score-v2-1-full-lr2e6
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': 0.46010003555572854, 'latency_mean': 2.173339385986328, 'latency_p50': 2.189503788948059, 'latency_p90': 2.37452392578125}, {'batch_size': 2, 'throughput': 0.6900315563075298, 'latency_mean': 2.89442564368248, 'latency_p50': 2.893833875656128, 'latency_p90': 3.1367398262023927}, {'batch_size': 3, 'throughput': 0.8255002712764541, 'latency_mean': 3.6181843554973603, 'latency_p50': 3.6101882457733154, 'latency_p90': 3.910370349884033}, {'batch_size': 4, 'throughput': 0.9271652312065662, 'latency_mean': 4.293996175527573, 'latency_p50': 4.289554715156555, 'latency_p90': 4.944114375114441}, {'batch_size': 5, 'throughput': 0.9927986096117625, 'latency_mean': 5.013240867853165, 'latency_p50': 5.05257260799408, 'latency_p90': 5.725513029098511}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-cs-feed-score-v2_14306_v4
is_internal_developer: True
language_model: ChaiML/cs-feed-score-v2-1-full-lr2e6
model_size: 24B
ranking_group: single
throughput_3p7s: 0.84
us_pacific_date: 2025-10-13
win_ratio: 0.5504395144411888
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['You:', '####', '####\n', '\n', '</s>'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", '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-v2-14306-v4-mkmlizer
Waiting for job on chaiml-cs-feed-score-v2-14306-v4-mkmlizer to finish
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: ║ ║
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: ║ ║
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: ║ Version: 0.30.2 ║
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: ║ https://mk1.ai ║
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: ║ ║
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: ║ belonging to: ║
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: ║ ║
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: ║ Chai Research Corp. ║
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: ║ ║
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: Downloaded to shared memory in 48.470s
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: Checking if ChaiML/cs-feed-score-v2-1-full-lr2e6 already exists in ChaiML
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpgaaw9fmr, device:0
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: quantized model in 284.715s
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: Processed model ChaiML/cs-feed-score-v2-1-full-lr2e6 in 333.185s
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-cs-feed-score-v2-14306-v4/nvidia
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-cs-feed-score-v2-14306-v4/nvidia/tokenizer_config.json
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-cs-feed-score-v2-14306-v4/nvidia/tokenizer.json
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-cs-feed-score-v2-14306-v4/nvidia/flywheel_model.1.safetensors
chaiml-cs-feed-score-v2-14306-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-cs-feed-score-v2-14306-v4/nvidia/flywheel_model.0.safetensors
Job chaiml-cs-feed-score-v2-14306-v4-mkmlizer completed after 409.52s with status: succeeded
Stopping job with name chaiml-cs-feed-score-v2-14306-v4-mkmlizer
Pipeline stage MKMLizer completed in 410.11s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.22s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-cs-feed-score-v2-14306-v4
Waiting for inference service chaiml-cs-feed-score-v2-14306-v4 to be ready
Inference service chaiml-cs-feed-score-v2-14306-v4 ready after 40.227736473083496s
Pipeline stage MKMLDeployer completed in 41.19s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.12335205078125s
Received healthy response to inference request in 2.322730302810669s
Received healthy response to inference request in 2.255892276763916s
Received healthy response to inference request in 1.948383092880249s
Received healthy response to inference request in 2.806565284729004s
5 requests
0 failed requests
5th percentile: 1.9833768844604491
10th percentile: 2.0183706760406492
20th percentile: 2.08835825920105
30th percentile: 2.1498600959777834
40th percentile: 2.2028761863708497
50th percentile: 2.255892276763916
60th percentile: 2.282627487182617
70th percentile: 2.309362697601318
80th percentile: 2.419497299194336
90th percentile: 2.61303129196167
95th percentile: 2.7097982883453366
99th percentile: 2.7872118854522703
mean time: 2.2913846015930175
Pipeline stage StressChecker completed in 13.02s
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 0.59s
Shutdown handler de-registered
chaiml-cs-feed-score-v2_14306_v4 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-cs-feed-score-v2-14306-v4-profiler
Waiting for inference service chaiml-cs-feed-score-v2-14306-v4-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 3265.27s
Shutdown handler de-registered
chaiml-cs-feed-score-v2_14306_v4 status is now torndown due to DeploymentManager action