chaiml-qwen3-235b-a22b-d_7566

developer_uid: chai_backend_admin

submission_id: chaiml-qwen3-235b-a22b-d_7566_v1

model_name: chaiml-qwen3-235b-a22b-d_7566_v1

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

status: torndown

timestamp: 2025-12-20T01:25:47+00:00

num_battles: 8400

num_wins: 4388

celo_rating: 1308.74

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/Qwen3-235B-A22B-Dummy-SFT-Verification-2EP-int4-mixed-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_7566_v1

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: ChaiML/Qwen3-235B-A22B-Dummy-SFT-Verification-2EP-int4-mixed-AutoRound

model_size: 19B

ranking_group: single

us_pacific_date: 2025-12-19

win_ratio: 0.5223809523809524

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': ['<|assistant|>', '</s>', '</think>', '<|user|>', '####', '<|im_end|>'], '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 0.25s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-qwen3-235b-a22b-d-7566-v1
Waiting for inference service chaiml-qwen3-235b-a22b-d-7566-v1 to be ready
Inference service chaiml-qwen3-235b-a22b-d-7566-v1 ready after 568.7879297733307s
Pipeline stage VLLMDeployer completed in 570.15s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.736896276473999s
Received healthy response to inference request in 1.8321034908294678s
Received healthy response to inference request in 1.8074743747711182s
Received healthy response to inference request in 1.930480718612671s
Received healthy response to inference request in 1.917795181274414s
Received healthy response to inference request in 1.9586436748504639s
Received healthy response to inference request in 2.0935726165771484s
Received healthy response to inference request in 1.9295666217803955s
Received healthy response to inference request in 1.7353341579437256s
Received healthy response to inference request in 1.7971916198730469s
Received healthy response to inference request in 1.6453938484191895s
Received healthy response to inference request in 1.767139196395874s
Received healthy response to inference request in 1.8707687854766846s
Received healthy response to inference request in 1.952620267868042s
Received healthy response to inference request in 2.1746251583099365s
Received healthy response to inference request in 2.1347880363464355s
Received healthy response to inference request in 2.356395959854126s
Received healthy response to inference request in 1.729325532913208s
Received healthy response to inference request in 1.615436315536499s
Received healthy response to inference request in 2.0872063636779785s
Received healthy response to inference request in 1.9642305374145508s
Received healthy response to inference request in 1.808565378189087s
Received healthy response to inference request in 1.9201006889343262s
Received healthy response to inference request in 1.8174946308135986s
Received healthy response to inference request in 1.6213428974151611s
Received healthy response to inference request in 2.186506986618042s
Received healthy response to inference request in 1.7718250751495361s
Received healthy response to inference request in 2.5628864765167236s
Received healthy response to inference request in 1.834993600845337s
Received healthy response to inference request in 1.9946715831756592s
30 requests
0 failed requests
5th percentile: 1.632165825366974
10th percentile: 1.7209323644638062
20th percentile: 1.7610906124114991
30th percentile: 1.8043895483016967
40th percentile: 1.8262599468231202
50th percentile: 1.8942819833755493
60th percentile: 1.9299322605133056
70th percentile: 1.96031973361969
80th percentile: 2.0884796142578126
90th percentile: 2.175813341140747
95th percentile: 2.2799459218978875
99th percentile: 2.5030042266845705
mean time: 1.9185125350952148
Pipeline stage StressChecker completed in 62.00s
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 1.45s
Shutdown handler de-registered
chaiml-qwen3-235b-a22b-d_7566_v1 status is now deployed due to DeploymentManager action
chaiml-qwen3-235b-a22b-d_7566_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen3-235b-a22b-d_7566_v1 status is now torndown due to DeploymentManager action