chaiml-goodconvo-v1-dpo_90455

developer_uid: zonemercy

submission_id: chaiml-goodconvo-v1-dpo_90455_v1

model_name: chaiml-goodconvo-v1-dpo_90455_v1

model_group: ChaiML/goodconvo-v1-dpo-

status: torndown

timestamp: 2026-01-14T16:59:06+00:00

num_battles: 10310

num_wins: 5646

celo_rating: 1326.39

family_friendly_score: 0.4898

family_friendly_standard_error: 0.007069596310964298

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_v1

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: 0.547623666343356

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|>', '####', '</s>', '<|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 0.13s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-goodconvo-v1-dpo-90455-v1
Waiting for inference service chaiml-goodconvo-v1-dpo-90455-v1 to be ready
Inference service chaiml-goodconvo-v1-dpo-90455-v1 ready after 1115.8255858421326s
Pipeline stage VLLMDeployer completed in 1116.31s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5930626392364502s
Received healthy response to inference request in 1.8961288928985596s
Received healthy response to inference request in 2.2306244373321533s
Received healthy response to inference request in 1.9009394645690918s
Received healthy response to inference request in 1.8464856147766113s
Received healthy response to inference request in 1.9083788394927979s
Received healthy response to inference request in 1.7320208549499512s
Received healthy response to inference request in 1.796496868133545s
Received healthy response to inference request in 1.759481430053711s
Received healthy response to inference request in 1.8733141422271729s
Received healthy response to inference request in 1.8611845970153809s
Received healthy response to inference request in 1.926344633102417s
Received healthy response to inference request in 1.7530534267425537s
Received healthy response to inference request in 1.7251968383789062s
Received healthy response to inference request in 1.5875186920166016s
Received healthy response to inference request in 1.767892599105835s
Received healthy response to inference request in 1.6364693641662598s
Received healthy response to inference request in 1.5793054103851318s
Received healthy response to inference request in 1.7404263019561768s
Received healthy response to inference request in 1.4939486980438232s
Received healthy response to inference request in 1.896172046661377s
Received healthy response to inference request in 1.4135935306549072s
Received healthy response to inference request in 1.764735460281372s
Received healthy response to inference request in 1.795041561126709s
Received healthy response to inference request in 1.7988572120666504s
Received healthy response to inference request in 1.9336395263671875s
Received healthy response to inference request in 1.7158102989196777s
Received healthy response to inference request in 1.5805492401123047s
Received healthy response to inference request in 1.7372257709503174s
Received healthy response to inference request in 1.8430249691009521s
30 requests
0 failed requests
5th percentile: 1.5323592185974122
10th percentile: 1.5804248571395874
20th percentile: 1.6277880191802978
30th percentile: 1.7299736499786378
40th percentile: 1.748002576828003
50th percentile: 1.7663140296936035
60th percentile: 1.797441005706787
70th percentile: 1.850895309448242
80th percentile: 1.896137523651123
90th percentile: 1.9101754188537599
95th percentile: 1.9303568243980407
99th percentile: 2.1444988131523135
mean time: 1.769564112027486
Pipeline stage StressChecker completed in 55.85s
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 0.70s
Shutdown handler de-registered
chaiml-goodconvo-v1-dpo_90455_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 2439.26s
Shutdown handler de-registered
chaiml-goodconvo-v1-dpo_90455_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-goodconvo-v1-dpo_90455_v1 status is now torndown due to DeploymentManager action