submission_id: mistralai-mistral-small_5341_v26
developer_uid: zonemercy
best_of: 1
celo_rating: 1176.51
display_name: mistralai-mistral-small_5341_v26
family_friendly_score: 0.0
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '###', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 1, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A6000': 1}
is_internal_developer: True
language_model: mistralai/Mistral-Small-Instruct-2409
latencies: [{'batch_size': 1, 'throughput': 0.3979317294420417, 'latency_mean': 2.5128986501693724, 'latency_p50': 2.507619261741638, 'latency_p90': 2.75505952835083}, {'batch_size': 3, 'throughput': 0.8462710984012942, 'latency_mean': 3.525833213329315, 'latency_p50': 3.51824414730072, 'latency_p90': 3.866414451599121}, {'batch_size': 5, 'throughput': 1.1510639562871867, 'latency_mean': 4.3138629710674286, 'latency_p50': 4.318927645683289, 'latency_p90': 4.857990479469299}, {'batch_size': 6, 'throughput': 1.2620235817379997, 'latency_mean': 4.720100368261337, 'latency_p50': 4.717157959938049, 'latency_p90': 5.316433453559876}, {'batch_size': 8, 'throughput': 1.4454393765528128, 'latency_mean': 5.47956298828125, 'latency_p50': 5.475357532501221, 'latency_p90': 6.137347340583801}, {'batch_size': 10, 'throughput': 1.5623632268806917, 'latency_mean': 6.347962347269058, 'latency_p50': 6.31951117515564, 'latency_p90': 7.1717530488967896}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: mistralai/Mistral-Small-
model_name: mistralai-mistral-small_5341_v26
model_num_parameters: 22247282688.0
model_repo: mistralai/Mistral-Small-Instruct-2409
model_size: 22B
num_battles: 26160
num_wins: 10666
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 0.93
timestamp: 2024-09-23T16:16:22+00:00
us_pacific_date: 2024-09-23
win_ratio: 0.4077217125382263
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-small-5341-v26-mkmlizer
Waiting for job on mistralai-mistral-small-5341-v26-mkmlizer to finish
mistralai-mistral-small-5341-v26-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-small-5341-v26-mkmlizer: ║     _____            __           __                                ║
mistralai-mistral-small-5341-v26-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-mistral-small-5341-v26-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-mistral-small-5341-v26-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-mistral-small-5341-v26-mkmlizer: ║       /___/                                                         ║
mistralai-mistral-small-5341-v26-mkmlizer: ║                                                                     ║
mistralai-mistral-small-5341-v26-mkmlizer: ║  Version: 0.10.1                                                    ║
mistralai-mistral-small-5341-v26-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-mistral-small-5341-v26-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-mistral-small-5341-v26-mkmlizer: ║                                                                     ║
mistralai-mistral-small-5341-v26-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-mistral-small-5341-v26-mkmlizer: ║  belonging to:                                                      ║
mistralai-mistral-small-5341-v26-mkmlizer: ║                                                                     ║
mistralai-mistral-small-5341-v26-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-mistral-small-5341-v26-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-mistral-small-5341-v26-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
mistralai-mistral-small-5341-v26-mkmlizer: ║                                                                     ║
mistralai-mistral-small-5341-v26-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
mistralai-mistral-small-5341-v26-mkmlizer: Downloaded to shared memory in 89.256s
mistralai-mistral-small-5341-v26-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpc951kcmh, device:0
mistralai-mistral-small-5341-v26-mkmlizer: Saving flywheel model at /dev/shm/model_cache
mistralai-mistral-small-5341-v26-mkmlizer: quantized model in 50.104s
mistralai-mistral-small-5341-v26-mkmlizer: Processed model mistralai/Mistral-Small-Instruct-2409 in 139.360s
mistralai-mistral-small-5341-v26-mkmlizer: creating bucket guanaco-mkml-models
mistralai-mistral-small-5341-v26-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-small-5341-v26-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-small-5341-v26
mistralai-mistral-small-5341-v26-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-mistral-small-5341-v26/config.json
mistralai-mistral-small-5341-v26-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mistral-small-5341-v26/special_tokens_map.json
mistralai-mistral-small-5341-v26-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mistral-small-5341-v26/tokenizer_config.json
mistralai-mistral-small-5341-v26-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/mistralai-mistral-small-5341-v26/tokenizer.model
mistralai-mistral-small-5341-v26-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-small-5341-v26/tokenizer.json
Job mistralai-mistral-small-5341-v26-mkmlizer completed after 217.49s with status: succeeded
Stopping job with name mistralai-mistral-small-5341-v26-mkmlizer
Pipeline stage MKMLizer completed in 218.45s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service mistralai-mistral-small-5341-v26
Waiting for inference service mistralai-mistral-small-5341-v26 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
Failed to get response for submission zonemercy-vingt-deux-v0-1e5_v11: ('http://zonemercy-vingt-deux-v0-1e5-v11-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:45072->127.0.0.1:8080: read: connection reset by peer\n')
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
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-small-5341-v26 ready after 182.10310316085815s
Pipeline stage MKMLDeployer completed in 182.61s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.1969358921051025s
Received healthy response to inference request in 0.4395766258239746s
Received healthy response to inference request in 0.5834019184112549s
Received healthy response to inference request in 1.7682321071624756s
Received healthy response to inference request in 1.4419076442718506s
5 requests
0 failed requests
5th percentile: 0.46834168434143064
10th percentile: 0.49710674285888673
20th percentile: 0.5546368598937989
30th percentile: 0.7061087131500243
40th percentile: 0.9515223026275635
50th percentile: 1.1969358921051025
60th percentile: 1.2949245929718018
70th percentile: 1.392913293838501
80th percentile: 1.5071725368499755
90th percentile: 1.6377023220062257
95th percentile: 1.7029672145843506
99th percentile: 1.7551791286468506
mean time: 1.0860108375549316
Pipeline stage StressChecker completed in 7.44s
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 7.18s
Shutdown handler de-registered
mistralai-mistral-small_5341_v26 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 0.40s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service mistralai-mistral-small-5341-v26-profiler
Waiting for inference service mistralai-mistral-small-5341-v26-profiler to be ready
Inference service mistralai-mistral-small-5341-v26-profiler ready after 190.51922750473022s
Pipeline stage MKMLProfilerDeployer completed in 190.89s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/mistralai-mistral-sme1d5d48703ad9235d422a9adeb75f3d7-deplopfwth:/code/chaiverse_profiler_1727108844 --namespace tenant-chaiml-guanaco
kubectl exec -it mistralai-mistral-sme1d5d48703ad9235d422a9adeb75f3d7-deplopfwth --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727108844 && python profiles.py profile --best_of_n 1 --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 64 --summary /code/chaiverse_profiler_1727108844/summary.json'
kubectl exec -it mistralai-mistral-sme1d5d48703ad9235d422a9adeb75f3d7-deplopfwth --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727108844/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1342.84s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service mistralai-mistral-small-5341-v26-profiler is running
Tearing down inference service mistralai-mistral-small-5341-v26-profiler
Service mistralai-mistral-small-5341-v26-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.04s
Shutdown handler de-registered
mistralai-mistral-small_5341_v26 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of mistralai-mistral-small_5341_v26
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
admin requested tearing down of zonemercy-vingt-deux-v0-1e5_v15
Running pipeline stage MKMLDeleter
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of zonemercy-vingt-deux-v0-1e5_v16
Checking if service mistralai-mistral-small-5341-v26 is running
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline stage %s
admin requested tearing down of zonemercy-vingt-deux-v0-1e5_v18
run pipeline %s
Running pipeline stage MKMLDeleter
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline stage %s
Checking if service zonemercy-vingt-deux-v0-1e5-v15 is running
run pipeline %s
Running pipeline stage MKMLDeleter
run pipeline stage %s
Checking if service zonemercy-vingt-deux-v0-1e5-v16 is running
Running pipeline stage MKMLDeleter
Checking if service zonemercy-vingt-deux-v0-1e5-v18 is running
Tearing down inference service mistralai-mistral-small-5341-v26
Service mistralai-mistral-small-5341-v26 has been torndown
Pipeline stage MKMLDeleter completed in 2.12s
Tearing down inference service zonemercy-vingt-deux-v0-1e5-v15
run pipeline stage %s
Service zonemercy-vingt-deux-v0-1e5-v15 has been torndown
Running pipeline stage MKMLModelDeleter
Pipeline stage MKMLDeleter completed in 2.14s
Tearing down inference service zonemercy-vingt-deux-v0-1e5-v16
Cleaning model data from S3
run pipeline stage %s
Tearing down inference service zonemercy-vingt-deux-v0-1e5-v18
Cleaning model data from model cache
Service zonemercy-vingt-deux-v0-1e5-v16 has been torndown
Running pipeline stage MKMLModelDeleter
Service zonemercy-vingt-deux-v0-1e5-v18 has been torndown
Deleting key mistralai-mistral-small-5341-v26/config.json from bucket guanaco-mkml-models
Pipeline stage MKMLDeleter completed in 2.70s
Cleaning model data from S3
Pipeline stage MKMLDeleter completed in 2.48s
Deleting key mistralai-mistral-small-5341-v26/flywheel_model.0.safetensors from bucket guanaco-mkml-models
run pipeline stage %s
Cleaning model data from model cache
run pipeline stage %s
Running pipeline stage MKMLModelDeleter
Deleting key zonemercy-vingt-deux-v0-1e5-v15/config.json from bucket guanaco-mkml-models
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Deleting key zonemercy-vingt-deux-v0-1e5-v15/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Cleaning model data from model cache
Cleaning model data from S3
Cleaning model data from model cache
Deleting key zonemercy-vingt-deux-v0-1e5-v16/config.json from bucket guanaco-mkml-models
Deleting key mistralai-mistral-small-5341-v26/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v0-1e5-v16/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v0-1e5-v18/config.json from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v0-1e5-v15/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v0-1e5-v18/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key mistralai-mistral-small-5341-v26/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key mistralai-mistral-small-5341-v26/tokenizer.json from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v0-1e5-v15/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key mistralai-mistral-small-5341-v26/tokenizer.model from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v0-1e5-v16/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v0-1e5-v15/tokenizer.json from bucket guanaco-mkml-models
Deleting key mistralai-mistral-small-5341-v26/tokenizer_config.json from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v0-1e5-v15/tokenizer_config.json from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v0-1e5-v18/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Pipeline stage MKMLModelDeleter completed in 4.84s
Pipeline stage MKMLModelDeleter completed in 4.13s
Shutdown handler de-registered
Deleting key zonemercy-vingt-deux-v0-1e5-v16/special_tokens_map.json from bucket guanaco-mkml-models
Shutdown handler de-registered
Deleting key zonemercy-vingt-deux-v0-1e5-v16/special_tokens_map.json from bucket guanaco-mkml-models
Shutdown handler de-registered
mistralai-mistral-small_5341_v26 status is now torndown due to DeploymentManager action
Deleting key zonemercy-vingt-deux-v0-1e5-v16/tokenizer.json from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v0-1e5-v18/special_tokens_map.json from bucket guanaco-mkml-models