developer_uid: chai_backend_admin
submission_id: chaiml-mamrgwlncuomxtncs_1790_v1
model_name: chaiml-mamrgwlncuomxtncs_1790_v1
model_group: ChaiML/MAMRgwlNCuOMXTNCS
status: torndown
timestamp: 2025-05-17T03:21:37+00:00
num_battles: 8953
num_wins: 4417
celo_rating: 1277.08
family_friendly_score: 0.5714
family_friendly_standard_error: 0.006998600431514861
submission_type: basic
model_repo: ChaiML/MAMRgwlNCuOMXTNCSIDm0DF86Iv2250516154830_sft
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.5378565898798691, 'latency_mean': 1.8591225492954253, 'latency_p50': 1.8442821502685547, 'latency_p90': 2.0612477540969847}, {'batch_size': 3, 'throughput': 1.1086958252262797, 'latency_mean': 2.7022812008857726, 'latency_p50': 2.682475209236145, 'latency_p90': 2.9963196516036987}, {'batch_size': 5, 'throughput': 1.437490105119658, 'latency_mean': 3.465161848068237, 'latency_p50': 3.4706215858459473, 'latency_p90': 3.8280478239059446}, {'batch_size': 6, 'throughput': 1.5562218654974305, 'latency_mean': 3.8317117071151734, 'latency_p50': 3.817982792854309, 'latency_p90': 4.318192172050476}, {'batch_size': 8, 'throughput': 1.7034203533662815, 'latency_mean': 4.663061835765839, 'latency_p50': 4.715104937553406, 'latency_p90': 5.198681926727295}, {'batch_size': 10, 'throughput': 1.8115853048113437, 'latency_mean': 5.44759692311287, 'latency_p50': 5.386140584945679, 'latency_p90': 6.250557470321655}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-mamrgwlncuomxtncs_1790_v1
is_internal_developer: True
language_model: ChaiML/MAMRgwlNCuOMXTNCSIDm0DF86Iv2250516154830_sft
model_size: 24B
ranking_group: single
throughput_3p7s: 1.52
us_pacific_date: 2025-05-16
win_ratio: 0.49335418295543393
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': ['</s>', 'You:', '\n', '####', '####\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}</s>\n', 'user_template': 'You: {message}\n', 'response_template': '{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-mamrgwlncuomxtncs-1790-v1-mkmlizer
Waiting for job on chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer to finish
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: ║       /___/                                                         ║
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: ║                                                                     ║
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: ║                                                                     ║
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: ║                                                                     ║
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: ║                                                                     ║
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: Downloaded to shared memory in 81.437s
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpyzj_tsy1, device:0
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: quantized model in 53.064s
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: Processed model ChaiML/MAMRgwlNCuOMXTNCSIDm0DF86Iv2250516154830_sft in 134.501s
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mamrgwlncuomxtncs-1790-v1
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mamrgwlncuomxtncs-1790-v1/config.json
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mamrgwlncuomxtncs-1790-v1/special_tokens_map.json
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mamrgwlncuomxtncs-1790-v1/tokenizer_config.json
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mamrgwlncuomxtncs-1790-v1/flywheel_model.1.safetensors
chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mamrgwlncuomxtncs-1790-v1/flywheel_model.0.safetensors
Job chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer completed after 165.83s with status: succeeded
Stopping job with name chaiml-mamrgwlncuomxtncs-1790-v1-mkmlizer
Pipeline stage MKMLizer completed in 166.35s
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-mamrgwlncuomxtncs-1790-v1
Waiting for inference service chaiml-mamrgwlncuomxtncs-1790-v1 to be ready
Inference service chaiml-mamrgwlncuomxtncs-1790-v1 ready after 140.76808428764343s
Pipeline stage MKMLDeployer completed in 141.39s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8198037147521973s
Received healthy response to inference request in 2.3474009037017822s
Received healthy response to inference request in 2.1194703578948975s
Received healthy response to inference request in 1.8495252132415771s
Received healthy response to inference request in 2.0569396018981934s
5 requests
0 failed requests
5th percentile: 1.8910080909729003
10th percentile: 1.9324909687042235
20th percentile: 2.01545672416687
30th percentile: 2.069445753097534
40th percentile: 2.094458055496216
50th percentile: 2.1194703578948975
60th percentile: 2.2106425762176514
70th percentile: 2.3018147945404053
80th percentile: 2.4418814659118655
90th percentile: 2.630842590332031
95th percentile: 2.725323152542114
99th percentile: 2.8009076023101804
mean time: 2.2386279582977293
Pipeline stage StressChecker completed in 12.44s
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 0.64s
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 0.82s
Shutdown handler de-registered
chaiml-mamrgwlncuomxtncs_1790_v1 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 0.10s
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-mamrgwlncuomxtncs-1790-v1-profiler
Waiting for inference service chaiml-mamrgwlncuomxtncs-1790-v1-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3029.26s
Shutdown handler de-registered
chaiml-mamrgwlncuomxtncs_1790_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mamrgwlncuomxtncs_1790_v1 status is now torndown due to DeploymentManager action