chaiml-cai-v1-2-dpo-ins_98986

developer_uid: zonemercy

submission_id: chaiml-cai-v1-2-dpo-ins_98986_v3

model_name: test

model_group: ChaiML/cai-v1-2-dpo_inst

status: torndown

timestamp: 2025-11-02T17:06:41+00:00

num_battles: 8306

num_wins: 4436

celo_rating: 1306.5

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/cai-v1-2-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': 0.2810388364238072, 'latency_mean': 3.5581298196315765, 'latency_p50': 3.562572479248047, 'latency_p90': 3.738663363456726}, {'batch_size': 2, 'throughput': 0.45874557519654036, 'latency_mean': 4.347357175350189, 'latency_p50': 4.341996788978577, 'latency_p90': 4.555030250549317}, {'batch_size': 3, 'throughput': 0.6091852381278178, 'latency_mean': 4.910985440015793, 'latency_p50': 4.89929473400116, 'latency_p90': 5.16586709022522}, {'batch_size': 4, 'throughput': 0.7170413892877961, 'latency_mean': 5.565303961038589, 'latency_p50': 5.579475164413452, 'latency_p90': 6.093116497993469}, {'batch_size': 5, 'throughput': 0.8079609382706219, 'latency_mean': 6.162428807020188, 'latency_p50': 6.172033190727234, 'latency_p90': 6.724651885032654}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: test

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: ChaiML/cai-v1-2-dpo_instructv0-lr5e6b01

model_size: 24B

ranking_group: single

throughput_3p7s: 0.32

us_pacific_date: 2025-10-30

win_ratio: 0.5340717553575728

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': ['</s>', 'User:', 'You:'], '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-v1-2-dpo-ins-98986-v3-mkmlizer
Waiting for job on chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer to finish
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: ║                                                                     ║
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: ║                                                                     ║
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: ║                                                                     ║
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: ║                                                                     ║
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: ║                                                                     ║
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: Downloaded to shared memory in 49.907s
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: Checking if ChaiML/cai-v1-2-dpo_instructv0-lr5e6b01 already exists in ChaiML
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpthsv3dwm, device:0
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: quantized model in 286.328s
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: Processed model ChaiML/cai-v1-2-dpo_instructv0-lr5e6b01 in 336.235s
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-cai-v1-2-dpo-ins-98986-v3/nvidia
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-cai-v1-2-dpo-ins-98986-v3/nvidia/config.json
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-cai-v1-2-dpo-ins-98986-v3/nvidia/special_tokens_map.json
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-cai-v1-2-dpo-ins-98986-v3/nvidia/tokenizer_config.json
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-cai-v1-2-dpo-ins-98986-v3/nvidia/tokenizer.json
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-cai-v1-2-dpo-ins-98986-v3/nvidia/flywheel_model.1.safetensors
chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-cai-v1-2-dpo-ins-98986-v3/nvidia/flywheel_model.0.safetensors
Job chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer completed after 399.24s with status: succeeded
Stopping job with name chaiml-cai-v1-2-dpo-ins-98986-v3-mkmlizer
Pipeline stage MKMLizer completed in 399.93s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-cai-v1-2-dpo-ins-98986-v3
Waiting for inference service chaiml-cai-v1-2-dpo-ins-98986-v3 to be ready
Inference service chaiml-cai-v1-2-dpo-ins-98986-v3 ready after 120.84434008598328s
Pipeline stage MKMLDeployer completed in 121.38s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.3833565711975098s
Received healthy response to inference request in 2.28890061378479s
Received healthy response to inference request in 2.962618350982666s
Received healthy response to inference request in 2.9582266807556152s
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', '')
Received healthy response to inference request in 2.7495322227478027s
5 requests
0 failed requests
5th percentile: 2.3810269355773928
10th percentile: 2.473153257369995
20th percentile: 2.6574059009552
30th percentile: 2.791271114349365
40th percentile: 2.8747488975524904
50th percentile: 2.9582266807556152
60th percentile: 2.9599833488464355
70th percentile: 2.961740016937256
80th percentile: 3.046765995025635
90th percentile: 3.2150612831115724
95th percentile: 3.299208927154541
99th percentile: 3.366527042388916
mean time: 2.868526887893677
Pipeline stage StressChecker completed in 16.24s
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 0.83s
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 0.74s
Shutdown handler de-registered
chaiml-cai-v1-2-dpo-ins_98986_v3 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-cai-v1-2-dpo-ins-98986-v3-profiler
Waiting for inference service chaiml-cai-v1-2-dpo-ins-98986-v3-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 8308.06s
Shutdown handler de-registered
chaiml-cai-v1-2-dpo-ins_98986_v3 status is now torndown due to DeploymentManager action