chaiml-qwen3-235b-a22b-d_4549

developer_uid: chai_backend_admin

submission_id: chaiml-qwen3-235b-a22b-d_4549_v2

model_name: chaiml-qwen3-235b-a22b-d_4549_v2

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

status: torndown

timestamp: 2025-12-20T01:25:58+00:00

num_battles: 5574

num_wins: 2825

celo_rating: 1308.32

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

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

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-d_4549_v2

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

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

model_size: 19B

ranking_group: single

us_pacific_date: 2025-12-19

win_ratio: 0.5068173663437388

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': ['####', '<|im_end|>', '</s>', '</think>', '<|user|>', '<|assistant|>'], '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 0.26s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-qwen3-235b-a22b-d-4549-v2
Waiting for inference service chaiml-qwen3-235b-a22b-d-4549-v2 to be ready
Inference service chaiml-qwen3-235b-a22b-d-4549-v2 ready after 264.4856071472168s
Pipeline stage VLLMDeployer completed in 265.42s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9624686241149902s
Received healthy response to inference request in 1.7594566345214844s
Received healthy response to inference request in 2.0514023303985596s
Received healthy response to inference request in 1.8070557117462158s
Received healthy response to inference request in 2.1189475059509277s
Received healthy response to inference request in 1.8618113994598389s
Received healthy response to inference request in 2.080735206604004s
Received healthy response to inference request in 2.1455655097961426s
Received healthy response to inference request in 1.7553269863128662s
Received healthy response to inference request in 1.8810584545135498s
Received healthy response to inference request in 2.3555941581726074s
Received healthy response to inference request in 2.659661293029785s
Received healthy response to inference request in 1.8845751285552979s
Received healthy response to inference request in 1.9693822860717773s
Received healthy response to inference request in 1.8937201499938965s
Received healthy response to inference request in 1.846686601638794s
Received healthy response to inference request in 1.770409345626831s
Received healthy response to inference request in 1.9263315200805664s
Received healthy response to inference request in 1.8104705810546875s
Received healthy response to inference request in 1.8094017505645752s
Received healthy response to inference request in 1.9598870277404785s
Received healthy response to inference request in 1.8956530094146729s
Received healthy response to inference request in 2.481923818588257s
Received healthy response to inference request in 2.0567617416381836s
Received healthy response to inference request in 1.838482141494751s
Received healthy response to inference request in 1.8272826671600342s
Received healthy response to inference request in 1.827164888381958s
Received healthy response to inference request in 1.8931970596313477s
Received healthy response to inference request in 2.036783456802368s
Received healthy response to inference request in 2.05688738822937s
30 requests
0 failed requests
5th percentile: 1.7643853545188903
10th percentile: 1.8033910751342774
20th percentile: 1.8238260269165039
30th percentile: 1.8442252635955811
40th percentile: 1.8831684589385986
50th percentile: 1.8946865797042847
60th percentile: 1.9609196662902832
70th percentile: 2.0411691188812258
80th percentile: 2.061656951904297
90th percentile: 2.166568374633789
95th percentile: 2.425075471401214
99th percentile: 2.6081174254417423
mean time: 1.9741361459096274
Pipeline stage StressChecker completed in 63.24s
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 1.12s
Shutdown handler de-registered
chaiml-qwen3-235b-a22b-d_4549_v2 status is now deployed due to DeploymentManager action
chaiml-qwen3-235b-a22b-d_4549_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen3-235b-a22b-d_4549_v2 status is now torndown due to DeploymentManager action