developer_uid: NischayDnk
submission_id: chaiml-0sw-95p-5ff-rin_63828_v18
model_name: chaiml-0sw-95p-5ff-rin_63828_v18
model_group: ChaiML/0sw_95p_5ff_rinen
status: torndown
timestamp: 2025-07-18T21:44:28+00:00
num_battles: 7613
num_wins: 3869
celo_rating: 1289.93
family_friendly_score: 0.5464
family_friendly_standard_error: 0.007040554523615309
submission_type: basic
model_repo: ChaiML/0sw_95p_5ff_rinen0721_dpo_0130_cp3000_v8_merged
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': 0.5866213598427921, 'latency_mean': 1.7045061945915223, 'latency_p50': 1.7024705410003662, 'latency_p90': 1.8911731958389282}, {'batch_size': 3, 'throughput': 1.0551230795949058, 'latency_mean': 2.836842893362045, 'latency_p50': 2.8384475708007812, 'latency_p90': 3.142644429206848}, {'batch_size': 5, 'throughput': 1.2551330931023912, 'latency_mean': 3.9578440368175505, 'latency_p50': 3.9790104627609253, 'latency_p90': 4.455078363418579}, {'batch_size': 6, 'throughput': 1.310278247877967, 'latency_mean': 4.549170701503754, 'latency_p50': 4.56718385219574, 'latency_p90': 5.099657773971558}, {'batch_size': 8, 'throughput': 1.3680552935438088, 'latency_mean': 5.805097628831863, 'latency_p50': 5.769646644592285, 'latency_p90': 6.579710674285889}, {'batch_size': 10, 'throughput': 1.4042898279616862, 'latency_mean': 7.075136919021606, 'latency_p50': 7.092549443244934, 'latency_p90': 8.097576808929443}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-0sw-95p-5ff-rin_63828_v18
is_internal_developer: False
language_model: ChaiML/0sw_95p_5ff_rinen0721_dpo_0130_cp3000_v8_merged
model_size: 13B
ranking_group: single
throughput_3p7s: 1.23
us_pacific_date: 2025-07-18
win_ratio: 0.5082096414028635
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|eot_id|>', '</s>', '####', '<|im_end|>', 'Bot:', 'User:', 'You:', '\n'], 'max_input_tokens': 1024, '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': '{user_name}: {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-0sw-95p-5ff-rin-63828-v18-mkmlizer
Waiting for job on chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer to finish
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: ║                                                                     ║
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: ║                                                                     ║
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: ║                                                                     ║
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: ║  belonging to:                                                      ║
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: ║                                                                     ║
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: ║                                                                     ║
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: Downloaded to shared memory in 78.878s
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: Checking if ChaiML/0sw_95p_5ff_rinen0721_dpo_0130_cp3000_v8_merged already exists in ChaiML
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpiduuhyt0, device:0
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: quantized model in 35.811s
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: Processed model ChaiML/0sw_95p_5ff_rinen0721_dpo_0130_cp3000_v8_merged in 114.689s
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: creating bucket guanaco-mkml-models
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-0sw-95p-5ff-rin-63828-v18/nvidia
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-0sw-95p-5ff-rin-63828-v18/nvidia/config.json
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-0sw-95p-5ff-rin-63828-v18/nvidia/special_tokens_map.json
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-0sw-95p-5ff-rin-63828-v18/nvidia/tokenizer_config.json
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-0sw-95p-5ff-rin-63828-v18/nvidia/tokenizer.json
chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-0sw-95p-5ff-rin-63828-v18/nvidia/flywheel_model.0.safetensors
Job chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer completed after 161.55s with status: succeeded
Stopping job with name chaiml-0sw-95p-5ff-rin-63828-v18-mkmlizer
Pipeline stage MKMLizer completed in 162.02s
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-0sw-95p-5ff-rin-63828-v18
Waiting for inference service chaiml-0sw-95p-5ff-rin-63828-v18 to be ready
Inference service chaiml-0sw-95p-5ff-rin-63828-v18 ready after 331.5665876865387s
Pipeline stage MKMLDeployer completed in 332.07s
run pipeline stage %s
Running pipeline stage StressChecker
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 2.3478662967681885s
Received healthy response to inference request in 2.0236728191375732s
Received healthy response to inference request in 1.8086864948272705s
Received healthy response to inference request in 1.785071611404419s
5 requests
1 failed requests
5th percentile: 1.7897945880889892
10th percentile: 1.7945175647735596
20th percentile: 1.8039635181427003
30th percentile: 1.851683759689331
40th percentile: 1.937678289413452
50th percentile: 2.0236728191375732
60th percentile: 2.1533502101898194
70th percentile: 2.283027601242065
80th percentile: 5.907574605941775
90th percentile: 13.026991224288942
95th percentile: 16.58669953346252
99th percentile: 19.43446618080139
mean time: 5.622341012954712
%s, retrying in %s seconds...
Received healthy response to inference request in 1.5794765949249268s
Received healthy response to inference request in 1.708479881286621s
Received healthy response to inference request in 1.5168695449829102s
Received healthy response to inference request in 1.976977825164795s
Received healthy response to inference request in 1.6699161529541016s
5 requests
0 failed requests
5th percentile: 1.5293909549713134
10th percentile: 1.5419123649597168
20th percentile: 1.5669551849365235
30th percentile: 1.5975645065307618
40th percentile: 1.6337403297424316
50th percentile: 1.6699161529541016
60th percentile: 1.6853416442871094
70th percentile: 1.7007671356201173
80th percentile: 1.762179470062256
90th percentile: 1.8695786476135254
95th percentile: 1.92327823638916
99th percentile: 1.9662379074096679
mean time: 1.6903439998626708
Pipeline stage StressChecker completed in 39.54s
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 0.71s
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 0.67s
Shutdown handler de-registered
chaiml-0sw-95p-5ff-rin_63828_v18 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
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-0sw-95p-5ff-rin-63828-v18-profiler
Waiting for inference service chaiml-0sw-95p-5ff-rin-63828-v18-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4651.87s
Shutdown handler de-registered
chaiml-0sw-95p-5ff-rin_63828_v18 status is now inactive due to auto deactivation removed underperforming models
chaiml-0sw-95p-5ff-rin_63828_v18 status is now torndown due to DeploymentManager action
chaiml-0sw-95p-5ff-rin_63828_v18 status is now torndown due to DeploymentManager action