chaiml-qwen3-235b-a22b-_13233

developer_uid: chai_backend_admin

submission_id: chaiml-qwen3-235b-a22b-_13233_v1

model_name: chaiml-qwen3-235b-a22b-_13233_v1

model_group: ChaiML/Qwen3-235B-A22B-D

status: inactive

timestamp: 2025-12-09T18:27:18+00:00

num_battles: 6791

num_wins: 3448

celo_rating: 1300.94

family_friendly_score: 0.48760000000000003

family_friendly_standard_error: 0.007068892982638795

submission_type: basic

model_repo: ChaiML/Qwen3-235B-A22B-Dummy-SFT-Verification-2EP

model_architecture: Qwen3MoeForCausalLM

model_num_parameters: 18790207488.0

best_of: 8

max_input_tokens: 1978

max_output_tokens: 70

reward_model: default

display_name: chaiml-qwen3-235b-a22b-_13233_v1

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: ChaiML/Qwen3-235B-A22B-Dummy-SFT-Verification-2EP

model_size: 19B

ranking_group: single

us_pacific_date: 2025-12-09

win_ratio: 0.5077308202032101

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': ['</think>', '<|assistant|>', '<|user|>', '####', '<|im_end|>', '</s>'], 'max_input_tokens': 1978, 'best_of': 8, 'max_output_tokens': 70}

formatter: {'memory_template': "<|im_start|>system\n{bot_name}'s persona: {memory}<|im_end|>\n", 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\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 VLLMTemplater
Pipeline stage VLLMTemplater completed in 0.38s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-qwen3-235b-a22b-13233-v1
Waiting for inference service chaiml-qwen3-235b-a22b-13233-v1 to be ready
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 0.46s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-wb-cai-hq-ep2-rh-79474-v1
Waiting for inference service chaiml-wb-cai-hq-ep2-rh-79474-v1 to be ready
Inference service qwen-qwen3-235b-a22b-i-47730-v14 ready after 506.42819356918335s
Pipeline stage VLLMDeployer completed in 507.74s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.601287603378296s
Received healthy response to inference request in 1.7351646423339844s
Received healthy response to inference request in 2.345020055770874s
Received healthy response to inference request in 2.5507397651672363s
Received healthy response to inference request in 2.561331033706665s
Received healthy response to inference request in 2.038681745529175s
Shutdown handler not registered because Python interpreter is not running in the main thread
Received healthy response to inference request in 1.6344273090362549s
run pipeline %s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 0.68s
run pipeline stage %s
Received healthy response to inference request in 1.7584846019744873s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-kimid-v4a-q235-n-98827-v1
Waiting for inference service chaiml-kimid-v4a-q235-n-98827-v1 to be ready
Received healthy response to inference request in 2.4452264308929443s
Received healthy response to inference request in 1.64005708694458s
Received healthy response to inference request in 2.3121936321258545s
Received healthy response to inference request in 2.3297946453094482s
Received healthy response to inference request in 2.465017080307007s
Received healthy response to inference request in 2.4643428325653076s
Received healthy response to inference request in 1.7290902137756348s
Received healthy response to inference request in 2.265662908554077s
Received healthy response to inference request in 1.9082050323486328s
Received healthy response to inference request in 1.743034839630127s
Received healthy response to inference request in 1.7323687076568604s
Received healthy response to inference request in 2.4501678943634033s
Received healthy response to inference request in 1.7877094745635986s
Received healthy response to inference request in 1.8205325603485107s
Received healthy response to inference request in 2.109382390975952s
Received healthy response to inference request in 1.82071852684021s
Received healthy response to inference request in 2.5014824867248535s
Received healthy response to inference request in 1.9738624095916748s
Received healthy response to inference request in 1.9534573554992676s
Received healthy response to inference request in 1.8873779773712158s
Received healthy response to inference request in 1.782801866531372s
Received healthy response to inference request in 1.7835376262664795s
30 requests
0 failed requests
5th percentile: 1.6801219940185548
10th percentile: 1.7320408582687379
20th percentile: 1.7553946495056152
30th percentile: 1.7864579200744628
40th percentile: 1.8607141971588135
50th percentile: 1.9636598825454712
60th percentile: 2.171894598007202
70th percentile: 2.334362268447876
80th percentile: 2.4530028820037844
90th percentile: 2.506408214569092
95th percentile: 2.556564962863922
99th percentile: 2.589700198173523
mean time: 2.0710386912027996
Pipeline stage StressChecker completed in 82.89s
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 2.48s
Shutdown handler de-registered
qwen-qwen3-235b-a22b-i_47730_v14 status is now deployed due to DeploymentManager action
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 0.51s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-kimid-v4a-q235-2k-v1
Waiting for inference service chaiml-kimid-v4a-q235-2k-v1 to be ready
Inference service chaiml-qwen3-235b-a22b-13233-v1 ready after 486.43226957321167s
Pipeline stage VLLMDeployer completed in 487.80s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6321561336517334s
Received healthy response to inference request in 1.993988275527954s
Received healthy response to inference request in 2.3837087154388428s
Received healthy response to inference request in 1.4881682395935059s
Received healthy response to inference request in 1.890869140625s
Received healthy response to inference request in 1.8058178424835205s
Received healthy response to inference request in 1.8059470653533936s
Received healthy response to inference request in 2.932853937149048s
Received healthy response to inference request in 1.8793082237243652s
Received healthy response to inference request in 2.4703493118286133s
Received healthy response to inference request in 1.8774974346160889s
Received healthy response to inference request in 1.6038942337036133s
Received healthy response to inference request in 1.6912939548492432s
Received healthy response to inference request in 2.3012397289276123s
Received healthy response to inference request in 1.936863899230957s
Received healthy response to inference request in 1.524482250213623s
Received healthy response to inference request in 1.759728193283081s
Received healthy response to inference request in 1.8096106052398682s
Received healthy response to inference request in 2.377040386199951s
Received healthy response to inference request in 1.4458727836608887s
Received healthy response to inference request in 1.7264354228973389s
Received healthy response to inference request in 1.6110868453979492s
Received healthy response to inference request in 2.449134349822998s
Received healthy response to inference request in 2.212009906768799s
Received healthy response to inference request in 1.6271474361419678s
Received healthy response to inference request in 1.8121490478515625s
Received healthy response to inference request in 1.8937151432037354s
Received healthy response to inference request in 1.8491930961608887s
Received healthy response to inference request in 1.6193532943725586s
Received healthy response to inference request in 1.6004054546356201s
30 requests
0 failed requests
5th percentile: 1.5045095443725587
10th percentile: 1.5928131341934204
20th percentile: 1.6177000045776366
30th percentile: 1.7158929824829101
40th percentile: 1.8058953762054444
50th percentile: 1.8306710720062256
60th percentile: 1.8839325904846191
70th percentile: 1.954001212120056
80th percentile: 2.3163998603820803
90th percentile: 2.4512558460235594
95th percentile: 2.559343063831329
99th percentile: 2.845651574134827
mean time: 1.9337106784184774
Pipeline stage StressChecker completed in 77.38s
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 3.35s
Shutdown handler de-registered
chaiml-qwen3-235b-a22b-_13233_v1 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
Generating Leaderboard row for %s
Generated Leaderboard row for %s
Pipeline stage OfflineFamilyFriendlyScorer completed in 2240.29s
Shutdown handler de-registered
chaiml-qwen3-235b-a22b-_13233_v1 status is now inactive due to auto deactivation removed underperforming models