developer_uid: zonemercy
submission_id: chaiml-cai-v1-1-dpo-ins_84951_v8
model_name: test
model_group: ChaiML/cai-v1-1-dpo_inst
status: torndown
timestamp: 2025-11-07T23:21:41+00:00
num_battles: 6989
num_wins: 3799
celo_rating: 1327.98
family_friendly_score: 0.5065999999999999
family_friendly_standard_error: 0.0070704517536010385
submission_type: basic
model_repo: ChaiML/cai-v1-1-dpo_instructv0-lr5e6b01
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 1
max_input_tokens: 2048
max_output_tokens: 128
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.27682550456393845, 'latency_mean': 3.6122596502304076, 'latency_p50': 3.564046025276184, 'latency_p90': 3.7906339883804323}, {'batch_size': 2, 'throughput': 0.4645963913944442, 'latency_mean': 4.302702012062073, 'latency_p50': 4.283095836639404, 'latency_p90': 4.5202398777008055}, {'batch_size': 3, 'throughput': 0.6085774561379658, 'latency_mean': 4.909164935350418, 'latency_p50': 4.904199242591858, 'latency_p90': 5.258505964279175}, {'batch_size': 4, 'throughput': 0.719000591536546, 'latency_mean': 5.525066413879395, 'latency_p50': 5.544661045074463, 'latency_p90': 5.762710618972778}, {'batch_size': 5, 'throughput': 0.8128196538554519, 'latency_mean': 6.1186362540721895, 'latency_p50': 6.1260093450546265, 'latency_p90': 6.6961452007293705}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: test
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/cai-v1-1-dpo_instructv0-lr5e6b01
model_size: 24B
ranking_group: single
throughput_3p7s: 0.3
us_pacific_date: 2025-11-04
win_ratio: 0.5435684647302904
generation_params: {'temperature': 0.3, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['User:', 'You:', '</s>'], 'max_input_tokens': 2048, 'best_of': 1, 'max_output_tokens': 128}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '####\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 MKMLizer
Starting job with name chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer
Waiting for job on chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer to finish
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: ║                                                                     ║
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: ║                                                                     ║
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: ║                                                                     ║
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: ║  belonging to:                                                      ║
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: ║                                                                     ║
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: ║                                                                     ║
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission mistralai-mistral-nem_93303_v569: ('http://mistralai-mistral-nem-93303-v569-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: Downloaded to shared memory in 49.945s
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: Checking if ChaiML/cai-v1-1-dpo_instructv0-lr5e6b01 already exists in ChaiML
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpxhvh_fse, device:0
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission mistralai-mistral-nem_93303_v569: ('http://mistralai-mistral-nem-93303-v569-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: quantized model in 285.493s
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: Processed model ChaiML/cai-v1-1-dpo_instructv0-lr5e6b01 in 335.439s
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: creating bucket guanaco-mkml-models
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-cai-v1-1-dpo-ins-84951-v8/nvidia
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-cai-v1-1-dpo-ins-84951-v8/nvidia/config.json
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-cai-v1-1-dpo-ins-84951-v8/nvidia/special_tokens_map.json
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-cai-v1-1-dpo-ins-84951-v8/nvidia/tokenizer_config.json
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-cai-v1-1-dpo-ins-84951-v8/nvidia/tokenizer.json
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-cai-v1-1-dpo-ins-84951-v8/nvidia/flywheel_model.1.safetensors
chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-cai-v1-1-dpo-ins-84951-v8/nvidia/flywheel_model.0.safetensors
Job chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer completed after 479.6s with status: succeeded
Stopping job with name chaiml-cai-v1-1-dpo-ins-84951-v8-mkmlizer
Pipeline stage MKMLizer completed in 480.28s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-cai-v1-1-dpo-ins-84951-v8
Waiting for inference service chaiml-cai-v1-1-dpo-ins-84951-v8 to be ready
Inference service chaiml-cai-v1-1-dpo-ins-84951-v8 ready after 140.8547966480255s
Pipeline stage MKMLDeployer completed in 141.42s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.327244281768799s
Received healthy response to inference request in 3.0409796237945557s
Received healthy response to inference request in 3.103829860687256s
Received healthy response to inference request in 3.0092546939849854s
Received healthy response to inference request in 3.2793540954589844s
5 requests
0 failed requests
5th percentile: 3.0155996799468996
10th percentile: 3.0219446659088134
20th percentile: 3.0346346378326414
30th percentile: 3.0535496711730956
40th percentile: 3.078689765930176
50th percentile: 3.103829860687256
60th percentile: 3.1740395545959474
70th percentile: 3.2442492485046386
80th percentile: 3.288932132720947
90th percentile: 3.308088207244873
95th percentile: 3.317666244506836
99th percentile: 3.325328674316406
mean time: 3.152132511138916
Pipeline stage StressChecker completed in 17.03s
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 0.69s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 1.26s
Shutdown handler de-registered
chaiml-cai-v1-1-dpo-ins_84951_v8 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2954.48s
Shutdown handler de-registered
chaiml-cai-v1-1-dpo-ins_84951_v8 status is now inactive due to auto deactivation removed underperforming models
chaiml-cai-v1-1-dpo-ins_84951_v8 status is now torndown due to DeploymentManager action