developer_uid: zonemercy
submission_id: mistralai-mistral-nem_93303_v257
model_name: tempv1-0
model_group: mistralai/Mistral-Nemo-I
status: torndown
timestamp: 2025-01-08T09:18:26+00:00
num_battles: 6176
num_wins: 2808
celo_rating: 1239.26
family_friendly_score: 0.5956
family_friendly_standard_error: 0.006940614382026997
submission_type: basic
model_repo: mistralai/Mistral-Nemo-Instruct-2407
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.6393139261951408, 'latency_mean': 1.5641120409965514, 'latency_p50': 1.5612845420837402, 'latency_p90': 1.7379438638687135}, {'batch_size': 3, 'throughput': 1.2650066675255058, 'latency_mean': 2.3630563604831694, 'latency_p50': 2.3534011840820312, 'latency_p90': 2.6297190904617307}, {'batch_size': 5, 'throughput': 1.602812053357552, 'latency_mean': 3.101020061969757, 'latency_p50': 3.115904211997986, 'latency_p90': 3.4402281045913696}, {'batch_size': 6, 'throughput': 1.7145471792547535, 'latency_mean': 3.4858604741096495, 'latency_p50': 3.488789916038513, 'latency_p90': 3.918976163864136}, {'batch_size': 8, 'throughput': 1.8706899797003593, 'latency_mean': 4.256229889392853, 'latency_p50': 4.296789050102234, 'latency_p90': 4.838226413726806}, {'batch_size': 10, 'throughput': 1.954799161006388, 'latency_mean': 5.080799602270126, 'latency_p50': 5.097851514816284, 'latency_p90': 5.697330975532532}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: tempv1-0
is_internal_developer: True
language_model: mistralai/Mistral-Nemo-Instruct-2407
model_size: 13B
ranking_group: single
throughput_3p7s: 1.77
us_pacific_date: 2025-01-08
win_ratio: 0.45466321243523317
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>', 'Bot:', '\n', 'You:', '<|im_end|>', 'User:', '####', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', '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 mistralai-mistral-nem-93303-v257-mkmlizer
Waiting for job on mistralai-mistral-nem-93303-v257-mkmlizer to finish
mistralai-mistral-nem-93303-v257-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-nem-93303-v257-mkmlizer: ║     _____            __           __                                ║
mistralai-mistral-nem-93303-v257-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-mistral-nem-93303-v257-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-mistral-nem-93303-v257-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-mistral-nem-93303-v257-mkmlizer: ║       /___/                                                         ║
mistralai-mistral-nem-93303-v257-mkmlizer: ║                                                                     ║
mistralai-mistral-nem-93303-v257-mkmlizer: ║  Version: 0.11.12                                                   ║
mistralai-mistral-nem-93303-v257-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-mistral-nem-93303-v257-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-mistral-nem-93303-v257-mkmlizer: ║                                                                     ║
mistralai-mistral-nem-93303-v257-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-mistral-nem-93303-v257-mkmlizer: ║  belonging to:                                                      ║
mistralai-mistral-nem-93303-v257-mkmlizer: ║                                                                     ║
mistralai-mistral-nem-93303-v257-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-mistral-nem-93303-v257-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-mistral-nem-93303-v257-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
mistralai-mistral-nem-93303-v257-mkmlizer: ║                                                                     ║
mistralai-mistral-nem-93303-v257-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
mistralai-mistral-nem-93303-v257-mkmlizer: Downloaded to shared memory in 58.388s
mistralai-mistral-nem-93303-v257-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpooi5_q4f, device:0
mistralai-mistral-nem-93303-v257-mkmlizer: Saving flywheel model at /dev/shm/model_cache
mistralai-mistral-nem-93303-v257-mkmlizer: quantized model in 35.333s
mistralai-mistral-nem-93303-v257-mkmlizer: Processed model mistralai/Mistral-Nemo-Instruct-2407 in 93.722s
mistralai-mistral-nem-93303-v257-mkmlizer: creating bucket guanaco-mkml-models
mistralai-mistral-nem-93303-v257-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-nem-93303-v257-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-nem-93303-v257
mistralai-mistral-nem-93303-v257-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-mistral-nem-93303-v257/config.json
mistralai-mistral-nem-93303-v257-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mistral-nem-93303-v257/special_tokens_map.json
mistralai-mistral-nem-93303-v257-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mistral-nem-93303-v257/tokenizer_config.json
mistralai-mistral-nem-93303-v257-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-nem-93303-v257/tokenizer.json
mistralai-mistral-nem-93303-v257-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mistralai-mistral-nem-93303-v257/flywheel_model.0.safetensors
Job mistralai-mistral-nem-93303-v257-mkmlizer completed after 124.48s with status: succeeded
Stopping job with name mistralai-mistral-nem-93303-v257-mkmlizer
Pipeline stage MKMLizer completed in 124.95s
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 mistralai-mistral-nem-93303-v257
Waiting for inference service mistralai-mistral-nem-93303-v257 to be ready
Inference service mistralai-mistral-nem-93303-v257 ready after 352.65190529823303s
Pipeline stage MKMLDeployer completed in 353.16s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.344724416732788s
Received healthy response to inference request in 1.4249565601348877s
Received healthy response to inference request in 0.8171775341033936s
Received healthy response to inference request in 0.6988673210144043s
Received healthy response to inference request in 0.8758645057678223s
5 requests
0 failed requests
5th percentile: 0.7225293636322021
10th percentile: 0.74619140625
20th percentile: 0.7935154914855957
30th percentile: 0.8289149284362793
40th percentile: 0.8523897171020508
50th percentile: 0.8758645057678223
60th percentile: 1.0634084701538085
70th percentile: 1.2509524345397949
80th percentile: 1.360770845413208
90th percentile: 1.3928637027740478
95th percentile: 1.4089101314544679
99th percentile: 1.4217472743988038
mean time: 1.0323180675506591
Pipeline stage StressChecker completed in 6.50s
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 0.76s
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
mistralai-mistral-nem_93303_v257 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 0.11s
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 mistralai-mistral-nem-93303-v257-profiler
Waiting for inference service mistralai-mistral-nem-93303-v257-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 2285.32s
Shutdown handler de-registered
mistralai-mistral-nem_93303_v257 status is now inactive due to auto deactivation removed underperforming models
mistralai-mistral-nem_93303_v257 status is now torndown due to DeploymentManager action