submission_id: mistralai-mistral-small_5341_v19
developer_uid: chai_backend_admin
best_of: 8
celo_rating: 1224.9
display_name: temp-0
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': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>', '###', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 8, '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': 0.3793002551168207, 'latency_mean': 2.636367589235306, 'latency_p50': 2.6242393255233765, 'latency_p90': 2.9077874660491942}, {'batch_size': 2, 'throughput': 0.5969418512961768, 'latency_mean': 3.340083043575287, 'latency_p50': 3.32170033454895, 'latency_p90': 3.6822657346725465}, {'batch_size': 3, 'throughput': 0.7634368321868025, 'latency_mean': 3.9119725584983827, 'latency_p50': 3.9309263229370117, 'latency_p90': 4.364906311035156}, {'batch_size': 4, 'throughput': 0.8793224036029714, 'latency_mean': 4.530840151309967, 'latency_p50': 4.499512672424316, 'latency_p90': 4.985005855560303}, {'batch_size': 5, 'throughput': 0.9695834889745132, 'latency_mean': 5.12017351269722, 'latency_p50': 5.1446772813797, 'latency_p90': 5.748102855682373}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: mistralai/Mistral-Small-
model_name: temp-0
model_num_parameters: 22247282688.0
model_repo: mistralai/Mistral-Small-Instruct-2409
model_size: 22B
num_battles: 638384
num_wins: 311147
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 0.71
timestamp: 2024-09-20T21:34:12+00:00
us_pacific_date: 2024-09-20
win_ratio: 0.48739786711446403
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-v19-mkmlizer
Waiting for job on mistralai-mistral-small-5341-v19-mkmlizer to finish
mistralai-mistral-small-5341-v19-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-small-5341-v19-mkmlizer: ║     _____            __           __                                ║
mistralai-mistral-small-5341-v19-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-mistral-small-5341-v19-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-mistral-small-5341-v19-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-mistral-small-5341-v19-mkmlizer: ║       /___/                                                         ║
mistralai-mistral-small-5341-v19-mkmlizer: ║                                                                     ║
mistralai-mistral-small-5341-v19-mkmlizer: ║  Version: 0.10.1                                                    ║
mistralai-mistral-small-5341-v19-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-mistral-small-5341-v19-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-mistral-small-5341-v19-mkmlizer: ║                                                                     ║
mistralai-mistral-small-5341-v19-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-mistral-small-5341-v19-mkmlizer: ║  belonging to:                                                      ║
mistralai-mistral-small-5341-v19-mkmlizer: ║                                                                     ║
mistralai-mistral-small-5341-v19-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-mistral-small-5341-v19-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-mistral-small-5341-v19-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
mistralai-mistral-small-5341-v19-mkmlizer: ║                                                                     ║
mistralai-mistral-small-5341-v19-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
mistralai-mistral-small-5341-v19-mkmlizer: Downloaded to shared memory in 90.339s
mistralai-mistral-small-5341-v19-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8dmg7pc1, device:0
mistralai-mistral-small-5341-v19-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
mistralai-mistral-small-5341-v19-mkmlizer: quantized model in 43.914s
mistralai-mistral-small-5341-v19-mkmlizer: Processed model mistralai/Mistral-Small-Instruct-2409 in 134.254s
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-v19-mkmlizer: creating bucket guanaco-mkml-models
mistralai-mistral-small-5341-v19-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-small-5341-v19-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-small-5341-v19
mistralai-mistral-small-5341-v19-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-mistral-small-5341-v19/config.json
mistralai-mistral-small-5341-v19-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mistral-small-5341-v19/special_tokens_map.json
mistralai-mistral-small-5341-v19-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mistral-small-5341-v19/tokenizer_config.json
mistralai-mistral-small-5341-v19-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/mistralai-mistral-small-5341-v19/tokenizer.model
mistralai-mistral-small-5341-v19-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-small-5341-v19/tokenizer.json
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
Job mistralai-mistral-small-5341-v19-mkmlizer completed after 178.63s with status: succeeded
Connection pool is full, discarding connection: %s. Connection pool size: %s
Stopping job with name mistralai-mistral-small-5341-v19-mkmlizer
Pipeline stage MKMLizer completed in 187.23s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service mistralai-mistral-small-5341-v19
Waiting for inference service mistralai-mistral-small-5341-v19 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
Inference service mistralai-mistral-small-5341-v19 ready after 191.0315260887146s
Pipeline stage MKMLDeployer completed in 191.57s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.199716806411743s
Received healthy response to inference request in 3.436350107192993s
Received healthy response to inference request in 2.9760797023773193s
Received healthy response to inference request in 2.787061929702759s
Received healthy response to inference request in 3.879364013671875s
5 requests
0 failed requests
5th percentile: 2.824865484237671
10th percentile: 2.862669038772583
20th percentile: 2.9382761478424073
30th percentile: 3.020807123184204
40th percentile: 3.1102619647979735
50th percentile: 3.199716806411743
60th percentile: 3.2943701267242433
70th percentile: 3.389023447036743
80th percentile: 3.5249528884887695
90th percentile: 3.7021584510803223
95th percentile: 3.7907612323760986
99th percentile: 3.8616434574127196
mean time: 3.255714511871338
Pipeline stage StressChecker completed in 29.54s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Failed to get response for submission blend_pudib_2024-09-20: ('http://mistralai-mistral-small-5341-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:55174->127.0.0.1:8080: read: connection reset by peer\n')
Pipeline stage TriggerMKMLProfilingPipeline completed in 14.80s
Shutdown handler de-registered
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_v19 status is now deployed due to DeploymentManager action
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
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 2.89s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service mistralai-mistral-small-5341-v19-profiler
Waiting for inference service mistralai-mistral-small-5341-v19-profiler to be ready
Inference service mistralai-mistral-small-5341-v19-profiler ready after 200.4422483444214s
Pipeline stage MKMLProfilerDeployer completed in 200.82s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/mistralai-mistral-sm0e5abf7aa6bebde21a78e8f65f782386-deplo2jw9c:/code/chaiverse_profiler_1726868725 --namespace tenant-chaiml-guanaco
kubectl exec -it mistralai-mistral-sm0e5abf7aa6bebde21a78e8f65f782386-deplo2jw9c --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726868725 && python profiles.py profile --best_of_n 8 --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_1726868725/summary.json'
kubectl exec -it mistralai-mistral-sm0e5abf7aa6bebde21a78e8f65f782386-deplo2jw9c --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726868725/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1566.62s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service mistralai-mistral-small-5341-v19-profiler is running
Tearing down inference service mistralai-mistral-small-5341-v19-profiler
Service mistralai-mistral-small-5341-v19-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 8.00s
Shutdown handler de-registered
mistralai-mistral-small_5341_v19 status is now inactive due to auto deactivation removed underperforming models
mistralai-mistral-small_5341_v19 status is now torndown due to DeploymentManager action