developer_uid: zonemercy
submission_id: chaiml-cai-v1-1-dpo-ba_42726_v14
model_name: test
model_group: ChaiML/cai-v1-1-dpo_base
status: torndown
timestamp: 2025-11-09T09:36:59+00:00
num_battles: 5522
num_wins: 3211
celo_rating: 1369.88
family_friendly_score: 0.4404
family_friendly_standard_error: 0.0070206529610856
submission_type: basic
model_repo: ChaiML/cai-v1-1-dpo_basev0-lr5e6b01
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 2048
max_output_tokens: 128
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.2665747815123495, 'latency_mean': 3.751195785999298, 'latency_p50': 3.75995934009552, 'latency_p90': 3.9630945682525636}, {'batch_size': 2, 'throughput': 0.43693469739292534, 'latency_mean': 4.573111742734909, 'latency_p50': 4.599266767501831, 'latency_p90': 4.843797731399536}, {'batch_size': 3, 'throughput': 0.5576537259384838, 'latency_mean': 5.3663409805297855, 'latency_p50': 5.344969630241394, 'latency_p90': 5.927090001106262}, {'batch_size': 5, 'throughput': 0.6969782228304271, 'latency_mean': 7.152280631065369, 'latency_p50': 7.1326223611831665, 'latency_p90': 7.792631578445435}]
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_basev0-lr5e6b01
model_size: 24B
ranking_group: single
us_pacific_date: 2025-11-06
win_ratio: 0.5814922129663166
generation_params: {'temperature': 0.5, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['You:', 'User:', '</s>'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 128}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', '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-ba-42726-v14-mkmlizer
Waiting for job on chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer to finish
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: ║ ║
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: ║ ║
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: ║ Version: 0.30.2 ║
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: ║ https://mk1.ai ║
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: ║ ║
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: ║ belonging to: ║
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: ║ ║
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: ║ Chai Research Corp. ║
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: ║ ║
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: Downloaded to shared memory in 56.021s
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: Checking if ChaiML/cai-v1-1-dpo_basev0-lr5e6b01 already exists in ChaiML
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpi5v4xm95, device:0
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: quantized model in 290.455s
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: Processed model ChaiML/cai-v1-1-dpo_basev0-lr5e6b01 in 346.477s
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: creating bucket guanaco-mkml-models
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-cai-v1-1-dpo-ba-42726-v14/nvidia
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-cai-v1-1-dpo-ba-42726-v14/nvidia/config.json
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-cai-v1-1-dpo-ba-42726-v14/nvidia/tokenizer_config.json
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-cai-v1-1-dpo-ba-42726-v14/nvidia/special_tokens_map.json
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-cai-v1-1-dpo-ba-42726-v14/nvidia/tokenizer.json
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-cai-v1-1-dpo-ba-42726-v14/nvidia/flywheel_model.1.safetensors
chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-cai-v1-1-dpo-ba-42726-v14/nvidia/flywheel_model.0.safetensors
Job chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer completed after 388.34s with status: succeeded
Stopping job with name chaiml-cai-v1-1-dpo-ba-42726-v14-mkmlizer
Pipeline stage MKMLizer completed in 389.00s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-cai-v1-1-dpo-ba-42726-v14
Waiting for inference service chaiml-cai-v1-1-dpo-ba-42726-v14 to be ready
Inference service chaiml-cai-v1-1-dpo-ba-42726-v14 ready after 160.64952182769775s
Pipeline stage MKMLDeployer completed in 161.26s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.77919602394104s
Received healthy response to inference request in 3.237729787826538s
Received healthy response to inference request in 3.6252481937408447s
Received healthy response to inference request in 3.414994955062866s
Received healthy response to inference request in 3.2965409755706787s
5 requests
0 failed requests
5th percentile: 3.2494920253753663
10th percentile: 3.2612542629241945
20th percentile: 3.2847787380218505
30th percentile: 3.3202317714691163
40th percentile: 3.367613363265991
50th percentile: 3.414994955062866
60th percentile: 3.4990962505340577
70th percentile: 3.583197546005249
80th percentile: 3.656037759780884
90th percentile: 3.717616891860962
95th percentile: 3.748406457901001
99th percentile: 3.773038110733032
mean time: 3.4707419872283936
Pipeline stage StressChecker completed in 18.72s
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 0.72s
Shutdown handler de-registered
chaiml-cai-v1-1-dpo-ba_42726_v14 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
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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-cai-v1-1-dpo-ba-42726-v14-profiler
Waiting for inference service chaiml-cai-v1-1-dpo-ba-42726-v14-profiler to be ready
Inference service chaiml-cai-v1-1-dpo-ba-42726-v14-profiler ready after 161.22206926345825s
Pipeline stage MKMLProfilerDeployer completed in 161.81s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-cai-v1-1-dpo-2a565c50e8c0e14ed5f021f242de53b1-deplotj6jp:/code/chaiverse_profiler_1762413795 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-cai-v1-1-dpo-2a565c50e8c0e14ed5f021f242de53b1-deplotj6jp --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1762413795 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 2048 --output_tokens 128 --summary /code/chaiverse_profiler_1762413795/summary.json'
%s, retrying in %s seconds...
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-cai-v1-1-dpo-2a565c50e8c0e14ed5f021f242de53b1-deplotj6jp:/code/chaiverse_profiler_1762415125 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-cai-v1-1-dpo-2a565c50e8c0e14ed5f021f242de53b1-deplotj6jp --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1762415125 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 2048 --output_tokens 128 --summary /code/chaiverse_profiler_1762415125/summary.json'
%s, retrying in %s seconds...
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-cai-v1-1-dpo-2a565c50e8c0e14ed5f021f242de53b1-deplotj6jp:/code/chaiverse_profiler_1762416682 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-cai-v1-1-dpo-2a565c50e8c0e14ed5f021f242de53b1-deplotj6jp --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1762416682 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 2048 --output_tokens 128 --summary /code/chaiverse_profiler_1762416682/summary.json'
Received signal 15, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-cai-v1-1-dpo-ba-42726-v14-profiler is running
Tearing down inference service chaiml-cai-v1-1-dpo-ba-42726-v14-profiler
Service chaiml-cai-v1-1-dpo-ba-42726-v14-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 0.80s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-cai-v1-1-dpo-ba-42726-v14-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 0.91s
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-v1-1-dpo-ba-42726-v14-profiler
Waiting for inference service chaiml-cai-v1-1-dpo-ba-42726-v14-profiler to be ready
Inference service chaiml-cai-v1-1-dpo-ba-42726-v14-profiler ready after 161.09165954589844s
Pipeline stage MKMLProfilerDeployer completed in 161.53s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-cai-v1-1-dpo-2a565c50e8c0e14ed5f021f242de53b1-deplorwj6k:/code/chaiverse_profiler_1762417453 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-cai-v1-1-dpo-2a565c50e8c0e14ed5f021f242de53b1-deplorwj6k --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1762417453 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 2048 --output_tokens 128 --summary /code/chaiverse_profiler_1762417453/summary.json'
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-cai-v1-1-dpo-2a565c50e8c0e14ed5f021f242de53b1-deplorwj6k --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1762417453/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1871.30s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-cai-v1-1-dpo-ba-42726-v14-profiler is running
Tearing down inference service chaiml-cai-v1-1-dpo-ba-42726-v14-profiler
Service chaiml-cai-v1-1-dpo-ba-42726-v14-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.62s
Shutdown handler de-registered
chaiml-cai-v1-1-dpo-ba_42726_v14 status is now inactive due to auto deactivation removed underperforming models
chaiml-cai-v1-1-dpo-ba_42726_v14 status is now torndown due to DeploymentManager action