developer_uid: bogoconic1
submission_id: chaiml-gy-exp76-simpo-e_59586_v1
model_name: chaiml-gy-exp76-simpo-e_59586_v1
model_group: ChaiML/gy-exp76-simpo-ex
status: torndown
timestamp: 2025-07-03T20:42:30+00:00
num_battles: 10104
num_wins: 1568
celo_rating: 937.11
family_friendly_score: 0.935
family_friendly_standard_error: 0.0034864021569520637
submission_type: basic
model_repo: ChaiML/gy-exp76-simpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-rm-win-safe-ep4
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.5134404128290547, 'latency_mean': 1.9475220572948455, 'latency_p50': 1.9617055654525757, 'latency_p90': 2.1427892208099366}, {'batch_size': 3, 'throughput': 1.0287008111000044, 'latency_mean': 2.904642654657364, 'latency_p50': 2.9362435340881348, 'latency_p90': 3.1734483003616334}, {'batch_size': 5, 'throughput': 1.3150714419490643, 'latency_mean': 3.7711963903903962, 'latency_p50': 3.8032314777374268, 'latency_p90': 4.20450873374939}, {'batch_size': 6, 'throughput': 1.4346646588290022, 'latency_mean': 4.148135250806808, 'latency_p50': 4.101987719535828, 'latency_p90': 4.762511372566223}, {'batch_size': 8, 'throughput': 1.5699865071423948, 'latency_mean': 5.060400874614715, 'latency_p50': 5.0542250871658325, 'latency_p90': 5.670455741882324}, {'batch_size': 10, 'throughput': 1.6413634978242622, 'latency_mean': 6.04043356180191, 'latency_p50': 6.100969314575195, 'latency_p90': 6.788897466659546}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-gy-exp76-simpo-e_59586_v1
is_internal_developer: True
language_model: ChaiML/gy-exp76-simpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-rm-win-safe-ep4
model_size: 24B
ranking_group: single
throughput_3p7s: 1.31
us_pacific_date: 2025-07-03
win_ratio: 0.15518606492478226
generation_params: {'temperature': 0.6, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|im_start|>', '\n', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|system|>Family Friendly{memory}\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', '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-gy-exp76-simpo-e-59586-v1-mkmlizer
Waiting for job on chaiml-gy-exp76-simpo-e-59586-v1-mkmlizer to finish
chaiml-gy-exp76-simpo-e-59586-v1-mkmlizer: Downloaded to shared memory in 78.684s
chaiml-gy-exp76-simpo-e-59586-v1-mkmlizer: Checking if ChaiML/gy-exp76-simpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-rm-win-safe-ep4 already exists in ChaiML
chaiml-gy-exp76-simpo-e-59586-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp927u__ve, device:0
chaiml-gy-exp76-simpo-e-59586-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp76-simpo-e-59586-v1-mkmlizer: quantized model in 51.604s
chaiml-gy-exp76-simpo-e-59586-v1-mkmlizer: Processed model ChaiML/gy-exp76-simpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-rm-win-safe-ep4 in 130.288s
chaiml-gy-exp76-simpo-e-59586-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp76-simpo-e-59586-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp76-simpo-e-59586-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp76-simpo-e-59586-v1/nvidia
chaiml-gy-exp76-simpo-e-59586-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp76-simpo-e-59586-v1/nvidia/config.json
chaiml-gy-exp76-simpo-e-59586-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp76-simpo-e-59586-v1/nvidia/special_tokens_map.json
chaiml-gy-exp76-simpo-e-59586-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp76-simpo-e-59586-v1/nvidia/tokenizer_config.json
chaiml-gy-exp76-simpo-e-59586-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp76-simpo-e-59586-v1/nvidia/tokenizer.json
chaiml-gy-exp76-simpo-e-59586-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp76-simpo-e-59586-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp76-simpo-e-59586-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp76-simpo-e-59586-v1/nvidia/flywheel_model.0.safetensors
Job chaiml-gy-exp76-simpo-e-59586-v1-mkmlizer completed after 229.72s with status: succeeded
Stopping job with name chaiml-gy-exp76-simpo-e-59586-v1-mkmlizer
Pipeline stage MKMLizer completed in 230.21s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp76-simpo-e-59586-v1
Waiting for inference service chaiml-gy-exp76-simpo-e-59586-v1 to be ready
Inference service chaiml-gy-exp76-simpo-e-59586-v1 ready after 221.11616253852844s
Pipeline stage MKMLDeployer completed in 221.65s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.530376672744751s
Received healthy response to inference request in 2.1470248699188232s
Received healthy response to inference request in 1.799548625946045s
Received healthy response to inference request in 2.127612829208374s
Received healthy response to inference request in 2.231449842453003s
5 requests
0 failed requests
5th percentile: 1.8651614665985108
10th percentile: 1.9307743072509767
20th percentile: 2.0619999885559084
30th percentile: 2.131495237350464
40th percentile: 2.1392600536346436
50th percentile: 2.1470248699188232
60th percentile: 2.180794858932495
70th percentile: 2.214564847946167
80th percentile: 2.2912352085113525
90th percentile: 2.4108059406280518
95th percentile: 2.4705913066864014
99th percentile: 2.518419599533081
mean time: 2.1672025680541993
Pipeline stage StressChecker completed in 12.39s
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 0.72s
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 0.66s
Shutdown handler de-registered
chaiml-gy-exp76-simpo-e_59586_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4166.84s
Shutdown handler de-registered
chaiml-gy-exp76-simpo-e_59586_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp76-simpo-e_59586_v1 status is now torndown due to DeploymentManager action