developer_uid: rica40325
submission_id: rica40325-3112000_v1
model_name: google-gemma-2-9b-it_v3
model_group: rica40325/3112000
status: torndown
timestamp: 2025-03-11T05:37:20+00:00
num_battles: 10197
num_wins: 4274
celo_rating: 1225.26
family_friendly_score: 0.5992
family_friendly_standard_error: 0.0069305030120475385
submission_type: basic
model_repo: rica40325/3112000
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.848352749991837, 'latency_mean': 1.1786694645881652, 'latency_p50': 1.1786845922470093, 'latency_p90': 1.2922958135604858}, {'batch_size': 4, 'throughput': 1.7800220934639384, 'latency_mean': 2.2404695343971253, 'latency_p50': 2.2443134784698486, 'latency_p90': 2.507736563682556}, {'batch_size': 5, 'throughput': 1.9197765538393219, 'latency_mean': 2.5940037298202516, 'latency_p50': 2.5868818759918213, 'latency_p90': 2.8981915712356567}, {'batch_size': 8, 'throughput': 2.11181226940813, 'latency_mean': 3.7598020434379578, 'latency_p50': 3.778576612472534, 'latency_p90': 4.220047926902771}, {'batch_size': 10, 'throughput': 2.171739345382268, 'latency_mean': 4.563093110322952, 'latency_p50': 4.5427069664001465, 'latency_p90': 5.1851722478866575}, {'batch_size': 12, 'throughput': 2.22080538330802, 'latency_mean': 5.347900002002716, 'latency_p50': 5.353259086608887, 'latency_p90': 6.046160626411438}, {'batch_size': 15, 'throughput': 2.2156300530905244, 'latency_mean': 6.680027894973755, 'latency_p50': 6.655113697052002, 'latency_p90': 7.4303950548171995}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: google-gemma-2-9b-it_v3
is_internal_developer: False
language_model: rica40325/3112000
model_size: 8B
ranking_group: single
throughput_3p7s: 2.12
us_pacific_date: 2025-03-10
win_ratio: 0.41914288516230264
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': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
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': '{bot_name}:', 'truncate_by_message': False}
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 rica40325-3112000-v1-mkmlizer
Waiting for job on rica40325-3112000-v1-mkmlizer to finish
rica40325-3112000-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-3112000-v1-mkmlizer: ║     _____            __           __                                ║
rica40325-3112000-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-3112000-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-3112000-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-3112000-v1-mkmlizer: ║       /___/                                                         ║
rica40325-3112000-v1-mkmlizer: ║                                                                     ║
rica40325-3112000-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rica40325-3112000-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-3112000-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-3112000-v1-mkmlizer: ║                                                                     ║
rica40325-3112000-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-3112000-v1-mkmlizer: ║  belonging to:                                                      ║
rica40325-3112000-v1-mkmlizer: ║                                                                     ║
rica40325-3112000-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-3112000-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-3112000-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rica40325-3112000-v1-mkmlizer: ║                                                                     ║
rica40325-3112000-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-3112000-v1-mkmlizer: Downloaded to shared memory in 32.251s
rica40325-3112000-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpf7ngeq_o, device:0
rica40325-3112000-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-3112000-v1-mkmlizer: quantized model in 26.894s
rica40325-3112000-v1-mkmlizer: Processed model rica40325/3112000 in 59.146s
rica40325-3112000-v1-mkmlizer: creating bucket guanaco-mkml-models
rica40325-3112000-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-3112000-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-3112000-v1
rica40325-3112000-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-3112000-v1/config.json
rica40325-3112000-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-3112000-v1/special_tokens_map.json
rica40325-3112000-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-3112000-v1/tokenizer_config.json
rica40325-3112000-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-3112000-v1/tokenizer.json
rica40325-3112000-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-3112000-v1/flywheel_model.0.safetensors
Job rica40325-3112000-v1-mkmlizer completed after 83.46s with status: succeeded
Stopping job with name rica40325-3112000-v1-mkmlizer
Pipeline stage MKMLizer completed in 83.98s
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 rica40325-3112000-v1
Waiting for inference service rica40325-3112000-v1 to be ready
Inference service rica40325-3112000-v1 ready after 90.32628512382507s
Pipeline stage MKMLDeployer completed in 90.85s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.002346038818359s
Received healthy response to inference request in 1.9842197895050049s
Received healthy response to inference request in 1.1981449127197266s
Received healthy response to inference request in 1.152277946472168s
Received healthy response to inference request in 1.3154008388519287s
5 requests
0 failed requests
5th percentile: 1.1614513397216797
10th percentile: 1.1706247329711914
20th percentile: 1.1889715194702148
30th percentile: 1.221596097946167
40th percentile: 1.268498468399048
50th percentile: 1.3154008388519287
60th percentile: 1.5829284191131592
70th percentile: 1.8504559993743896
80th percentile: 2.3878450393676762
90th percentile: 3.1950955390930176
95th percentile: 3.598720788955688
99th percentile: 3.921620988845825
mean time: 1.9304779052734375
Pipeline stage StressChecker completed in 11.12s
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 0.67s
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 0.70s
Shutdown handler de-registered
rica40325-3112000_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2248.62s
Shutdown handler de-registered
rica40325-3112000_v1 status is now inactive due to auto deactivation removed underperforming models
rica40325-3112000_v1 status is now torndown due to DeploymentManager action