developer_uid: leosheng
submission_id: alexxi19-f1-v1-nemo-ba_19525_v12
model_name: alexxi19-f1-v1-nemo-ba_19525_v12
model_group: alexxi19/f1-v1-nemo-base
status: torndown
timestamp: 2025-02-20T07:19:30+00:00
num_battles: 5455
num_wins: 2885
celo_rating: 1263.09
family_friendly_score: 0.5622
family_friendly_standard_error: 0.007016140819567407
submission_type: basic
model_repo: alexxi19/f1-v1-nemo-base-merge
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.602579496078662, 'latency_mean': 1.6594405364990235, 'latency_p50': 1.6699391603469849, 'latency_p90': 1.817995262145996}, {'batch_size': 3, 'throughput': 1.0907862822028251, 'latency_mean': 2.745932011604309, 'latency_p50': 2.758325219154358, 'latency_p90': 3.0649070024490355}, {'batch_size': 5, 'throughput': 1.3225486123455785, 'latency_mean': 3.7649928641319277, 'latency_p50': 3.747253894805908, 'latency_p90': 4.244749069213867}, {'batch_size': 6, 'throughput': 1.3743918642108555, 'latency_mean': 4.352577022314072, 'latency_p50': 4.379375219345093, 'latency_p90': 4.864219450950622}, {'batch_size': 8, 'throughput': 1.4442534363926876, 'latency_mean': 5.4965560734272, 'latency_p50': 5.507628083229065, 'latency_p90': 6.1807044506072994}, {'batch_size': 10, 'throughput': 1.4593651389141413, 'latency_mean': 6.796042540073395, 'latency_p50': 6.7825093269348145, 'latency_p90': 7.7132244348526005}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: alexxi19-f1-v1-nemo-ba_19525_v12
is_internal_developer: False
language_model: alexxi19/f1-v1-nemo-base-merge
model_size: 13B
ranking_group: single
throughput_3p7s: 1.32
us_pacific_date: 2025-02-19
win_ratio: 0.5288725939505041
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': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{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 alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer
Waiting for job on alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer to finish
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: ║ _____ __ __ ║
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: ║ /___/ ║
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: ║ ║
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: ║ Version: 0.12.8 ║
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: ║ https://mk1.ai ║
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: ║ ║
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: ║ The license key for the current software has been verified as ║
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: ║ belonging to: ║
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: ║ ║
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: ║ Chai Research Corp. ║
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: ║ ║
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: Downloaded to shared memory in 155.734s
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpx4sccggt, device:0
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: quantized model in 40.640s
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: Processed model alexxi19/f1-v1-nemo-base-merge in 196.375s
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: creating bucket guanaco-mkml-models
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexxi19-f1-v1-nemo-ba-19525-v12
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexxi19-f1-v1-nemo-ba-19525-v12/config.json
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexxi19-f1-v1-nemo-ba-19525-v12/special_tokens_map.json
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexxi19-f1-v1-nemo-ba-19525-v12/tokenizer_config.json
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexxi19-f1-v1-nemo-ba-19525-v12/tokenizer.json
alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexxi19-f1-v1-nemo-ba-19525-v12/flywheel_model.0.safetensors
Job alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer completed after 227.49s with status: succeeded
Stopping job with name alexxi19-f1-v1-nemo-ba-19525-v12-mkmlizer
Pipeline stage MKMLizer completed in 227.97s
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 alexxi19-f1-v1-nemo-ba-19525-v12
Waiting for inference service alexxi19-f1-v1-nemo-ba-19525-v12 to be ready
Inference service alexxi19-f1-v1-nemo-ba-19525-v12 ready after 200.70776867866516s
Pipeline stage MKMLDeployer completed in 201.21s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.1024417877197266s
Received healthy response to inference request in 1.5532433986663818s
Received healthy response to inference request in 1.6515085697174072s
Received healthy response to inference request in 1.8563148975372314s
Received healthy response to inference request in 2.845308780670166s
5 requests
0 failed requests
5th percentile: 1.5728964328765869
10th percentile: 1.592549467086792
20th percentile: 1.6318555355072022
30th percentile: 1.692469835281372
40th percentile: 1.7743923664093018
50th percentile: 1.8563148975372314
60th percentile: 2.2519124507904054
70th percentile: 2.647510004043579
80th percentile: 2.8967353820800783
90th percentile: 2.9995885848999024
95th percentile: 3.0510151863098143
99th percentile: 3.092156467437744
mean time: 2.2017634868621827
Pipeline stage StressChecker completed in 12.22s
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 0.63s
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 1.05s
Shutdown handler de-registered
alexxi19-f1-v1-nemo-ba_19525_v12 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 2538.07s
Shutdown handler de-registered
alexxi19-f1-v1-nemo-ba_19525_v12 status is now inactive due to auto deactivation removed underperforming models
alexxi19-f1-v1-nemo-ba_19525_v12 status is now torndown due to DeploymentManager action