chaiml-attack-on-titan-_55668

developer_uid: chai_backend_admin

submission_id: chaiml-attack-on-titan-_55668_v1

model_name: chaiml-attack-on-titan-_55668_v1

model_group: ChaiML/Attack-on-Titan_A

status: torndown

timestamp: 2025-07-15T22:18:34+00:00

num_battles: 7643

num_wins: 3849

celo_rating: 1292.76

family_friendly_score: 0.49839999999999995

family_friendly_standard_error: 0.007071031607905596

submission_type: basic

model_repo: ChaiML/Attack-on-Titan_Attack-on-Titan-RPG_At250715143919_sft

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': 0.5200025694497232, 'latency_mean': 1.92294499874115, 'latency_p50': 1.912516713142395, 'latency_p90': 2.1326547622680665}, {'batch_size': 3, 'throughput': 1.0588076768100478, 'latency_mean': 2.827027586698532, 'latency_p50': 2.8485764265060425, 'latency_p90': 3.100738549232483}, {'batch_size': 5, 'throughput': 1.3617960171999643, 'latency_mean': 3.656905550956726, 'latency_p50': 3.638043165206909, 'latency_p90': 4.033278703689575}, {'batch_size': 6, 'throughput': 1.4645416236741169, 'latency_mean': 4.0696024119853975, 'latency_p50': 4.053573250770569, 'latency_p90': 4.611185908317566}, {'batch_size': 8, 'throughput': 1.586081431172515, 'latency_mean': 4.992266284227371, 'latency_p50': 4.977224588394165, 'latency_p90': 5.6727152347564695}, {'batch_size': 10, 'throughput': 1.678101800812603, 'latency_mean': 5.893572956323624, 'latency_p50': 5.867372035980225, 'latency_p90': 6.57528030872345}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: chaiml-attack-on-titan-_55668_v1

is_internal_developer: True

language_model: ChaiML/Attack-on-Titan_Attack-on-Titan-RPG_At250715143919_sft

model_size: 24B

ranking_group: single

throughput_3p7s: 1.38

us_pacific_date: 2025-07-15

win_ratio: 0.5035980635875965

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': ['####', '####\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-attack-on-titan-55668-v1-mkmlizer
Waiting for job on chaiml-attack-on-titan-55668-v1-mkmlizer to finish
chaiml-attack-on-titan-55668-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-attack-on-titan-55668-v1-mkmlizer: ║                                                                     ║
chaiml-attack-on-titan-55668-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-attack-on-titan-55668-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-attack-on-titan-55668-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-attack-on-titan-55668-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-attack-on-titan-55668-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-attack-on-titan-55668-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-attack-on-titan-55668-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-attack-on-titan-55668-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-attack-on-titan-55668-v1-mkmlizer: ║                                                                     ║
chaiml-attack-on-titan-55668-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-attack-on-titan-55668-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-attack-on-titan-55668-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-attack-on-titan-55668-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-attack-on-titan-55668-v1-mkmlizer: ║                                                                     ║
chaiml-attack-on-titan-55668-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-attack-on-titan-55668-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-attack-on-titan-55668-v1-mkmlizer: ║                                                                     ║
chaiml-attack-on-titan-55668-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-attack-on-titan-55668-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-attack-on-titan-55668-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-attack-on-titan-55668-v1-mkmlizer: ║                                                                     ║
chaiml-attack-on-titan-55668-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-attack-on-titan-55668-v1-mkmlizer: Downloaded to shared memory in 78.331s
chaiml-attack-on-titan-55668-v1-mkmlizer: Checking if ChaiML/Attack-on-Titan_Attack-on-Titan-RPG_At250715143919_sft already exists in ChaiML
chaiml-attack-on-titan-55668-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpr3cm2g_o, device:0
chaiml-attack-on-titan-55668-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Unable to record family friendly update due to error: HTTPConnectionPool(host='chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-attack-on-titan-55668-v1-mkmlizer: quantized model in 48.523s
chaiml-attack-on-titan-55668-v1-mkmlizer: Processed model ChaiML/Attack-on-Titan_Attack-on-Titan-RPG_At250715143919_sft in 126.855s
chaiml-attack-on-titan-55668-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-attack-on-titan-55668-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-attack-on-titan-55668-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-attack-on-titan-55668-v1/nvidia
chaiml-attack-on-titan-55668-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-attack-on-titan-55668-v1/nvidia/special_tokens_map.json
chaiml-attack-on-titan-55668-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-attack-on-titan-55668-v1/nvidia/config.json
chaiml-attack-on-titan-55668-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-attack-on-titan-55668-v1/nvidia/tokenizer_config.json
chaiml-attack-on-titan-55668-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-attack-on-titan-55668-v1/nvidia/flywheel_model.1.safetensors
chaiml-attack-on-titan-55668-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-attack-on-titan-55668-v1/nvidia/flywheel_model.0.safetensors
Job chaiml-attack-on-titan-55668-v1-mkmlizer completed after 158.61s with status: succeeded
Stopping job with name chaiml-attack-on-titan-55668-v1-mkmlizer
Pipeline stage MKMLizer completed in 159.60s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.48s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-attack-on-titan-55668-v1
Waiting for inference service chaiml-attack-on-titan-55668-v1 to be ready
Unable to record family friendly update due to error: HTTPConnectionPool(host='chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Unable to record family friendly update due to error: HTTPConnectionPool(host='chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Unable to record family friendly update due to error: HTTPConnectionPool(host='chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Unable to record family friendly update due to error: HTTPConnectionPool(host='chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Unable to record family friendly update due to error: HTTPConnectionPool(host='chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Unable to record family friendly update due to error: HTTPConnectionPool(host='chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Unable to record family friendly update due to error: HTTPConnectionPool(host='chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Unable to record family friendly update due to error: HTTPConnectionPool(host='chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Unable to record family friendly update due to error: HTTPConnectionPool(host='chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Unable to record family friendly update due to error: HTTPConnectionPool(host='chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Unable to record family friendly update due to error: HTTPConnectionPool(host='chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Unable to record family friendly update due to error: HTTPConnectionPool(host='chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Unable to record family friendly update due to error: HTTPConnectionPool(host='chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Unable to record family friendly update due to error: HTTPConnectionPool(host='chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-attack-on-titan-55668-v1 ready after 272.00893092155457s
Pipeline stage MKMLDeployer completed in 272.48s
run pipeline stage %s
Running pipeline stage StressChecker
Unable to record family friendly update due to error: HTTPConnectionPool(host='chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.4031574726104736s
Received healthy response to inference request in 2.1289470195770264s
Received healthy response to inference request in 1.9747700691223145s
Received healthy response to inference request in 2.0530812740325928s
5 requests
1 failed requests
5th percentile: 1.9904323101043702
10th percentile: 2.006094551086426
20th percentile: 2.0374190330505373
30th percentile: 2.0682544231414797
40th percentile: 2.098600721359253
50th percentile: 2.1289470195770264
60th percentile: 2.2386312007904055
70th percentile: 2.348315382003784
80th percentile: 5.9550709724426305
90th percentile: 13.058897972106935
95th percentile: 16.610811471939083
99th percentile: 19.45234227180481
mean time: 5.7445361614227295
%s, retrying in %s seconds...
Received healthy response to inference request in 2.451261281967163s
Unable to record family friendly update due to error: HTTPConnectionPool(host='chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Received healthy response to inference request in 2.4588279724121094s
Received healthy response to inference request in 2.386173725128174s
Received healthy response to inference request in 2.4043447971343994s
Received healthy response to inference request in 1.8124520778656006s
5 requests
0 failed requests
5th percentile: 1.9271964073181151
10th percentile: 2.0419407367706297
20th percentile: 2.2714293956756593
30th percentile: 2.389807939529419
40th percentile: 2.397076368331909
50th percentile: 2.4043447971343994
60th percentile: 2.423111391067505
70th percentile: 2.4418779850006103
80th percentile: 2.4527746200561524
90th percentile: 2.4558012962341307
95th percentile: 2.45731463432312
99th percentile: 2.4585253047943114
mean time: 2.302611970901489
Pipeline stage StressChecker completed in 42.92s
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 0.78s
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 0.71s
Shutdown handler de-registered
chaiml-attack-on-titan-_55668_v1 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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 8395.97s
Shutdown handler de-registered
chaiml-attack-on-titan-_55668_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-attack-on-titan-_55668_v1 status is now torndown due to DeploymentManager action
chaiml-attack-on-titan-_55668_v1 status is now torndown due to DeploymentManager action
chaiml-attack-on-titan-_55668_v1 status is now torndown due to DeploymentManager action