developer_uid: zonemercy
submission_id: mistralai-mistral-small_5341_v25
model_name: mistralai-mistral-small_5341_v25
model_group: mistralai/Mistral-Small-
status: torndown
timestamp: 2024-09-23T16:14:48+00:00
num_battles: 25914
num_wins: 10579
celo_rating: 1177.25
family_friendly_score: 0.0
submission_type: basic
model_repo: mistralai/Mistral-Small-Instruct-2409
model_architecture: MistralForCausalLM
model_num_parameters: 22247282688.0
best_of: 1
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.4015414631986748, 'latency_mean': 2.490308644771576, 'latency_p50': 2.465972661972046, 'latency_p90': 2.770184588432312}, {'batch_size': 3, 'throughput': 0.8559706745538804, 'latency_mean': 3.4888463902473448, 'latency_p50': 3.5017240047454834, 'latency_p90': 3.9101952075958253}, {'batch_size': 5, 'throughput': 1.1721397800687747, 'latency_mean': 4.242213525772095, 'latency_p50': 4.261624813079834, 'latency_p90': 4.752268528938293}, {'batch_size': 6, 'throughput': 1.2909507374354765, 'latency_mean': 4.623244067430496, 'latency_p50': 4.615513563156128, 'latency_p90': 5.160506844520569}, {'batch_size': 8, 'throughput': 1.4505224959093233, 'latency_mean': 5.470817822217941, 'latency_p50': 5.490717530250549, 'latency_p90': 6.083581209182739}, {'batch_size': 10, 'throughput': 1.5959153464038673, 'latency_mean': 6.2187822830677035, 'latency_p50': 6.22546911239624, 'latency_p90': 6.937139844894409}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: mistralai-mistral-small_5341_v25
is_internal_developer: True
language_model: mistralai/Mistral-Small-Instruct-2409
model_size: 22B
ranking_group: single
throughput_3p7s: 0.96
us_pacific_date: 2024-09-23
win_ratio: 0.4082349309253685
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': ['\n', '</s>', '###', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 1, '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': True}
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-v25-mkmlizer
Waiting for job on mistralai-mistral-small-5341-v25-mkmlizer to finish
mistralai-mistral-small-5341-v25-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-small-5341-v25-mkmlizer: ║     _____            __           __                                ║
mistralai-mistral-small-5341-v25-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-mistral-small-5341-v25-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-mistral-small-5341-v25-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-mistral-small-5341-v25-mkmlizer: ║       /___/                                                         ║
mistralai-mistral-small-5341-v25-mkmlizer: ║                                                                     ║
mistralai-mistral-small-5341-v25-mkmlizer: ║  Version: 0.10.1                                                    ║
mistralai-mistral-small-5341-v25-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-mistral-small-5341-v25-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-mistral-small-5341-v25-mkmlizer: ║                                                                     ║
mistralai-mistral-small-5341-v25-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-mistral-small-5341-v25-mkmlizer: ║  belonging to:                                                      ║
mistralai-mistral-small-5341-v25-mkmlizer: ║                                                                     ║
mistralai-mistral-small-5341-v25-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-mistral-small-5341-v25-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-mistral-small-5341-v25-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
mistralai-mistral-small-5341-v25-mkmlizer: ║                                                                     ║
mistralai-mistral-small-5341-v25-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-small-5341-v25-mkmlizer: Downloaded to shared memory in 85.221s
mistralai-mistral-small-5341-v25-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpib7tp479, device:0
mistralai-mistral-small-5341-v25-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
mistralai-mistral-small-5341-v25-mkmlizer: creating bucket guanaco-mkml-models
mistralai-mistral-small-5341-v25-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-small-5341-v25-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-small-5341-v25
mistralai-mistral-small-5341-v25-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mistral-small-5341-v25/special_tokens_map.json
mistralai-mistral-small-5341-v25-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-mistral-small-5341-v25/config.json
mistralai-mistral-small-5341-v25-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mistral-small-5341-v25/tokenizer_config.json
mistralai-mistral-small-5341-v25-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/mistralai-mistral-small-5341-v25/tokenizer.model
mistralai-mistral-small-5341-v25-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-small-5341-v25/tokenizer.json
Job mistralai-mistral-small-5341-v25-mkmlizer completed after 201.67s with status: succeeded
Stopping job with name mistralai-mistral-small-5341-v25-mkmlizer
Pipeline stage MKMLizer completed in 204.33s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service mistralai-mistral-small-5341-v25
Waiting for inference service mistralai-mistral-small-5341-v25 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
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-v25 ready after 192.18976521492004s
Pipeline stage MKMLDeployer completed in 193.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.3049640655517578s
Received healthy response to inference request in 0.49774980545043945s
Received healthy response to inference request in 0.4092223644256592s
Received healthy response to inference request in 1.825850486755371s
Received healthy response to inference request in 1.3141415119171143s
5 requests
0 failed requests
5th percentile: 0.4269278526306152
10th percentile: 0.44463334083557127
20th percentile: 0.4800443172454834
30th percentile: 0.6591926574707031
40th percentile: 0.9820783615112305
50th percentile: 1.3049640655517578
60th percentile: 1.3086350440979004
70th percentile: 1.312306022644043
80th percentile: 1.4164833068847658
90th percentile: 1.6211668968200683
95th percentile: 1.7235086917877196
99th percentile: 1.8053821277618407
mean time: 1.0703856468200683
Pipeline stage StressChecker completed in 6.49s
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 7.26s
Shutdown handler de-registered
mistralai-mistral-small_5341_v25 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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service mistralai-mistral-small-5341-v25-profiler
Waiting for inference service mistralai-mistral-small-5341-v25-profiler to be ready
Inference service mistralai-mistral-small-5341-v25-profiler ready after 190.4639401435852s
Pipeline stage MKMLProfilerDeployer completed in 190.86s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/mistralai-mistral-sm6ca41bbbf3b6a1cf301f08ea97da0778-deplocxcxr:/code/chaiverse_profiler_1727108741 --namespace tenant-chaiml-guanaco
kubectl exec -it mistralai-mistral-sm6ca41bbbf3b6a1cf301f08ea97da0778-deplocxcxr --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727108741 && 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_1727108741/summary.json'
kubectl exec -it mistralai-mistral-sm6ca41bbbf3b6a1cf301f08ea97da0778-deplocxcxr --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727108741/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1326.05s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service mistralai-mistral-small-5341-v25-profiler is running
Tearing down inference service mistralai-mistral-small-5341-v25-profiler
Service mistralai-mistral-small-5341-v25-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.88s
Shutdown handler de-registered
mistralai-mistral-small_5341_v25 status is now inactive due to auto deactivation removed underperforming models
mistralai-mistral-small_5341_v25 status is now torndown due to DeploymentManager action