submission_id: mistralai-mistral-nemo_9330_v102
developer_uid: chai_backend_admin
best_of: 4
celo_rating: 1203.66
display_name: mistralai-mistral-nemo_9330_v102
family_friendly_score: 0.0
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}
generation_params: {'temperature': 0.8, 'top_p': 0.8, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 128}
gpu_counts: {'NVIDIA RTX A5000': 1}
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: mistralai/Mistral-Nemo-Instruct-2407
latencies: [{'batch_size': 1, 'throughput': 0.3568214057235341, 'latency_mean': 2.8024604654312135, 'latency_p50': 2.805983781814575, 'latency_p90': 2.965221571922302}, {'batch_size': 3, 'throughput': 0.8006855081635463, 'latency_mean': 3.7276128220558165, 'latency_p50': 3.7387415170669556, 'latency_p90': 3.9646639585494996}, {'batch_size': 5, 'throughput': 1.0521601058036123, 'latency_mean': 4.735758106708527, 'latency_p50': 4.725398778915405, 'latency_p90': 5.0918817043304445}, {'batch_size': 6, 'throughput': 1.1324650745773968, 'latency_mean': 5.2517001497745515, 'latency_p50': 5.265230774879456, 'latency_p90': 5.746191930770874}, {'batch_size': 10, 'throughput': 1.3058660916564813, 'latency_mean': 7.600029362440109, 'latency_p50': 7.5752081871032715, 'latency_p90': 8.32679615020752}]
max_input_tokens: 1024
max_output_tokens: 128
model_architecture: MistralForCausalLM
model_group: mistralai/Mistral-Nemo-I
model_name: mistralai-mistral-nemo_9330_v102
model_num_parameters: 12772070400.0
model_repo: mistralai/Mistral-Nemo-Instruct-2407
model_size: 13B
num_battles: 28443
num_wins: 12747
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 0.79
timestamp: 2024-09-24T02:39:50+00:00
us_pacific_date: 2024-09-23
win_ratio: 0.4481594768484337
Download Preference Data
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-nemo-9330-v102-mkmlizer
Waiting for job on mistralai-mistral-nemo-9330-v102-mkmlizer to finish
mistralai-mistral-nemo-9330-v102-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-nemo-9330-v102-mkmlizer: ║     _____            __           __                                ║
mistralai-mistral-nemo-9330-v102-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-mistral-nemo-9330-v102-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-mistral-nemo-9330-v102-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-mistral-nemo-9330-v102-mkmlizer: ║       /___/                                                         ║
mistralai-mistral-nemo-9330-v102-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v102-mkmlizer: ║  Version: 0.10.1                                                    ║
mistralai-mistral-nemo-9330-v102-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-mistral-nemo-9330-v102-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-mistral-nemo-9330-v102-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v102-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-mistral-nemo-9330-v102-mkmlizer: ║  belonging to:                                                      ║
mistralai-mistral-nemo-9330-v102-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v102-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-mistral-nemo-9330-v102-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-mistral-nemo-9330-v102-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
mistralai-mistral-nemo-9330-v102-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v102-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
mistralai-mistral-nemo-9330-v102-mkmlizer: Downloaded to shared memory in 48.925s
mistralai-mistral-nemo-9330-v102-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5yebd6sy, device:0
mistralai-mistral-nemo-9330-v102-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
mistralai-mistral-nemo-9330-v102-mkmlizer: quantized model in 37.439s
mistralai-mistral-nemo-9330-v102-mkmlizer: Processed model mistralai/Mistral-Nemo-Instruct-2407 in 86.365s
mistralai-mistral-nemo-9330-v102-mkmlizer: creating bucket guanaco-mkml-models
mistralai-mistral-nemo-9330-v102-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-nemo-9330-v102-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v102
mistralai-mistral-nemo-9330-v102-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v102/special_tokens_map.json
mistralai-mistral-nemo-9330-v102-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v102/config.json
mistralai-mistral-nemo-9330-v102-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v102/tokenizer_config.json
mistralai-mistral-nemo-9330-v102-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v102/tokenizer.json
Job mistralai-mistral-nemo-9330-v102-mkmlizer completed after 136.29s with status: succeeded
Stopping job with name mistralai-mistral-nemo-9330-v102-mkmlizer
Pipeline stage MKMLizer completed in 137.75s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.07s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service mistralai-mistral-nemo-9330-v102
Waiting for inference service mistralai-mistral-nemo-9330-v102 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service mistralai-mistral-nemo-9330-v102 ready after 264.09334111213684s
Pipeline stage MKMLDeployer completed in 264.80s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.496002197265625s
Received healthy response to inference request in 3.9527394771575928s
Received healthy response to inference request in 4.292079925537109s
Received healthy response to inference request in 3.377866744995117s
Received healthy response to inference request in 3.385000467300415s
5 requests
0 failed requests
5th percentile: 3.3792934894561766
10th percentile: 3.3807202339172364
20th percentile: 3.3835737228393556
30th percentile: 3.407200813293457
40th percentile: 3.451601505279541
50th percentile: 3.496002197265625
60th percentile: 3.678697109222412
70th percentile: 3.861392021179199
80th percentile: 4.020607566833496
90th percentile: 4.156343746185303
95th percentile: 4.224211835861206
99th percentile: 4.278506307601929
mean time: 3.7007377624511717
%s, retrying in %s seconds...
Received healthy response to inference request in 2.8612148761749268s
Received healthy response to inference request in 4.837676525115967s
Received healthy response to inference request in 2.9012725353240967s
Received healthy response to inference request in 3.4340405464172363s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 3.2175369262695312s
5 requests
0 failed requests
5th percentile: 2.869226408004761
10th percentile: 2.8772379398345946
20th percentile: 2.8932610034942625
30th percentile: 2.9645254135131838
40th percentile: 3.0910311698913575
50th percentile: 3.2175369262695312
60th percentile: 3.3041383743286135
70th percentile: 3.3907398223876952
80th percentile: 3.7147677421569827
90th percentile: 4.276222133636475
95th percentile: 4.55694932937622
99th percentile: 4.781531085968018
mean time: 3.4503482818603515
Pipeline stage StressChecker completed in 37.77s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 4.72s
Shutdown handler de-registered
mistralai-mistral-nemo_9330_v102 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 0.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service mistralai-mistral-nemo-9330-v102-profiler
Waiting for inference service mistralai-mistral-nemo-9330-v102-profiler to be ready
Inference service mistralai-mistral-nemo-9330-v102-profiler ready after 200.5072214603424s
Pipeline stage MKMLProfilerDeployer completed in 200.96s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/mistralai-mistral-neb42e94afcc9ad5682bb3341c2cbbd2f5-deplo6hv9x:/code/chaiverse_profiler_1727146286 --namespace tenant-chaiml-guanaco
kubectl exec -it mistralai-mistral-neb42e94afcc9ad5682bb3341c2cbbd2f5-deplo6hv9x --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727146286 && python profiles.py profile --best_of_n 4 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1024 --output_tokens 128 --summary /code/chaiverse_profiler_1727146286/summary.json'
kubectl exec -it mistralai-mistral-neb42e94afcc9ad5682bb3341c2cbbd2f5-deplo6hv9x --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727146286/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1338.18s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service mistralai-mistral-nemo-9330-v102-profiler is running
Tearing down inference service mistralai-mistral-nemo-9330-v102-profiler
Service mistralai-mistral-nemo-9330-v102-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.09s
Shutdown handler de-registered
mistralai-mistral-nemo_9330_v102 status is now inactive due to auto deactivation removed underperforming models
run pipeline stage %s
admin requested tearing down of mistralai-mistral-nemo_9330_v102
Running pipeline stage MKMLDeleter
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLDeleter
%s, retrying in %s seconds...
%s, retrying in %s seconds...
clean up pipeline due to error=TeardownError("module 'kubernetes.config' has no attribute 'load_kube_config'")
Shutdown handler de-registered
mistralai-mistral-nemo_9330_v103 status is now torndown due to DeploymentManager action
mistralai-mistral-nemo_9330_v102 status is now torndown due to DeploymentManager action