chaiml-chaiwill-qwen3-2_84869

developer_uid: chai_backend_admin

submission_id: chaiml-chaiwill-qwen3-2_84869_v3

model_name: chaiml-chaiwill-qwen3-2_84869_v3

model_group: ChaiML/chaiwill-qwen3-23

status: torndown

timestamp: 2025-12-23T07:44:46+00:00

num_battles: 6911

num_wins: 4079

celo_rating: 1356.5

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/chaiwill-qwen3-235b-a22b-instruct-2507-opus-distil-500k-qwen235b-dpo-round2-20faf44c-int4-mixed

model_architecture: Qwen3MoeForCausalLM

model_num_parameters: 18790207488.0

best_of: 6

max_input_tokens: 1992

max_output_tokens: 80

reward_model: default

display_name: chaiml-chaiwill-qwen3-2_84869_v3

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: ChaiML/chaiwill-qwen3-235b-a22b-instruct-2507-opus-distil-500k-qwen235b-dpo-round2-20faf44c-int4-mixed

model_size: 19B

ranking_group: single

us_pacific_date: 2025-12-22

win_ratio: 0.590218492258718

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|>', '<|user|>', '</s>', '<|im_end|>', '</think>'], 'max_input_tokens': 1992, 'best_of': 6, 'max_output_tokens': 80}

formatter: {'memory_template': '<|im_start|>system\nYou are {bot_name} engaged in a roleplay with user.<|im_end|>\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', '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 0.15s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-chaiwill-qwen3-2-84869-v3
Waiting for inference service chaiml-chaiwill-qwen3-2-84869-v3 to be ready
Failed to get response for submission chaiml-chaiwill-qwen3-2_84869_v1: 'DeploymentStage' object has no attribute 'endpoint'
Failed to get response for submission chaiml-chaiwill-qwen3-2_84869_v1: 'DeploymentStage' object has no attribute 'endpoint'
Inference service chaiml-chaiwill-qwen3-2-84869-v3 ready after 221.1476230621338s
Pipeline stage VLLMDeployer completed in 221.86s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2184770107269287s
Received healthy response to inference request in 2.0999512672424316s
Received healthy response to inference request in 2.084487199783325s
Received healthy response to inference request in 2.069267988204956s
Received healthy response to inference request in 2.146150588989258s
Received healthy response to inference request in 2.1092629432678223s
Received healthy response to inference request in 2.0759716033935547s
Received healthy response to inference request in 2.1701292991638184s
Received healthy response to inference request in 2.320424795150757s
Received healthy response to inference request in 2.328975200653076s
Received healthy response to inference request in 2.5031442642211914s
Received healthy response to inference request in 1.977571964263916s
Received healthy response to inference request in 2.2096235752105713s
Received healthy response to inference request in 2.619753837585449s
Received healthy response to inference request in 2.132761001586914s
Received healthy response to inference request in 2.1713080406188965s
Received healthy response to inference request in 2.110060691833496s
Received healthy response to inference request in 2.4229698181152344s
Received healthy response to inference request in 2.3306400775909424s
Received healthy response to inference request in 2.4778685569763184s
Received healthy response to inference request in 2.395496368408203s
Received healthy response to inference request in 2.1874020099639893s
Received healthy response to inference request in 2.06632137298584s
Received healthy response to inference request in 2.5365140438079834s
Received healthy response to inference request in 2.133077621459961s
Received healthy response to inference request in 2.353790521621704s
Received healthy response to inference request in 2.2843222618103027s
Received healthy response to inference request in 1.9861550331115723s
Received healthy response to inference request in 2.103362798690796s
Received healthy response to inference request in 2.0884363651275635s
30 requests
0 failed requests
5th percentile: 2.0222298860549928
10th percentile: 2.0689733266830443
20th percentile: 2.0876465320587156
30th percentile: 2.1074928998947144
40th percentile: 2.1329509735107424
50th percentile: 2.1707186698913574
60th percentile: 2.213164949417114
70th percentile: 2.3229899168014527
80th percentile: 2.362131690979004
90th percentile: 2.4803961277008058
95th percentile: 2.521497642993927
99th percentile: 2.595614297389984
mean time: 2.223789270718892
Pipeline stage StressChecker completed in 69.65s
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 0.59s
Shutdown handler de-registered
chaiml-chaiwill-qwen3-2_84869_v3 status is now deployed due to DeploymentManager action
chaiml-chaiwill-qwen3-2_84869_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-chaiwill-qwen3-2_84869_v3 status is now torndown due to DeploymentManager action