chaiml-goodconvo-v1-dpo_90455

developer_uid: zonemercy

submission_id: chaiml-goodconvo-v1-dpo_90455_v2

model_name: chaiml-goodconvo-v1-dpo_90455_v2

model_group: ChaiML/goodconvo-v1-dpo-

status: torndown

timestamp: 2026-01-14T16:59:07+00:00

num_battles: 10799

num_wins: 5855

celo_rating: 1325.04

family_friendly_score: 0.487

family_friendly_standard_error: 0.007068677386894949

submission_type: basic

model_repo: ChaiML/goodconvo-v1-dpo-lr5e6ep2r64g8b01-int4-mixed

model_architecture: Qwen3MoeForCausalLM

model_num_parameters: 18790207488.0

best_of: 4

max_input_tokens: 2048

max_output_tokens: 80

reward_model: default

display_name: chaiml-goodconvo-v1-dpo_90455_v2

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: ChaiML/goodconvo-v1-dpo-lr5e6ep2r64g8b01-int4-mixed

model_size: 19B

ranking_group: single

us_pacific_date: 2026-01-09

win_ratio: 0.5421798314658764

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': 2048, 'best_of': 4, 'max_output_tokens': 80}

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 0.14s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-goodconvo-v1-dpo-90455-v2
Waiting for inference service chaiml-goodconvo-v1-dpo-90455-v2 to be ready
Inference service chaiml-goodconvo-v1-dpo-90455-v2 ready after 210.83543229103088s
Pipeline stage VLLMDeployer completed in 211.31s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5061814785003662s
Received healthy response to inference request in 1.6857261657714844s
Received healthy response to inference request in 1.9621386528015137s
Received healthy response to inference request in 1.6581602096557617s
Received healthy response to inference request in 2.021014451980591s
Received healthy response to inference request in 1.6537997722625732s
Received healthy response to inference request in 1.860323429107666s
Received healthy response to inference request in 1.7730824947357178s
Received healthy response to inference request in 1.6258435249328613s
Received healthy response to inference request in 1.6717424392700195s
Received healthy response to inference request in 1.6790845394134521s
Received healthy response to inference request in 1.735337257385254s
Received healthy response to inference request in 1.6977345943450928s
Received healthy response to inference request in 1.493626356124878s
Received healthy response to inference request in 1.9439496994018555s
Received healthy response to inference request in 1.755624771118164s
Received healthy response to inference request in 1.711259126663208s
Received healthy response to inference request in 1.995650053024292s
Received healthy response to inference request in 1.6514708995819092s
Received healthy response to inference request in 1.773745059967041s
Received healthy response to inference request in 1.691136121749878s
Received healthy response to inference request in 1.9620835781097412s
Received healthy response to inference request in 1.997270107269287s
Received healthy response to inference request in 1.5578298568725586s
Received healthy response to inference request in 1.6878833770751953s
Received healthy response to inference request in 1.9253840446472168s
Received healthy response to inference request in 1.651052474975586s
Received healthy response to inference request in 1.49322509765625s
Received healthy response to inference request in 2.0599205493927s
Received healthy response to inference request in 1.9706714153289795s
30 requests
0 failed requests
5th percentile: 1.4992761611938477
10th percentile: 1.5526650190353393
20th percentile: 1.6513872146606445
30th percentile: 1.667667770385742
40th percentile: 1.687020492553711
50th percentile: 1.7044968605041504
60th percentile: 1.7626078605651856
70th percentile: 1.879841613769531
80th percentile: 1.9620945930480957
90th percentile: 1.9958120584487915
95th percentile: 2.010329496860504
99th percentile: 2.0486377811431886
mean time: 1.7617317199707032
Pipeline stage StressChecker completed in 55.64s
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 0.61s
Shutdown handler de-registered
chaiml-goodconvo-v1-dpo_90455_v2 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 2374.12s
Shutdown handler de-registered
chaiml-goodconvo-v1-dpo_90455_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-goodconvo-v1-dpo_90455_v2 status is now torndown due to DeploymentManager action