developer_uid: azuruce
submission_id: mistralai-mistral-sma_53415_v103
model_name: mistralai-mistral-sma_53415_v103
model_group: mistralai/Mistral-Small-
status: torndown
timestamp: 2025-01-10T19:01:14+00:00
num_battles: 9128
num_wins: 4371
celo_rating: 1237.85
family_friendly_score: 0.5938
family_friendly_standard_error: 0.006945524602216884
submission_type: basic
model_repo: mistralai/Mistral-Small-Instruct-2409
model_architecture: MistralForCausalLM
model_num_parameters: 22247282688.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.39016481204357173, 'latency_mean': 2.5629398691654206, 'latency_p50': 2.5416314601898193, 'latency_p90': 2.8578025102615356}, {'batch_size': 3, 'throughput': 0.8276630168080601, 'latency_mean': 3.6209418034553527, 'latency_p50': 3.6055186986923218, 'latency_p90': 4.0137101173400875}, {'batch_size': 5, 'throughput': 1.0910999881145316, 'latency_mean': 4.547785096168518, 'latency_p50': 4.537272095680237, 'latency_p90': 5.034464025497437}, {'batch_size': 6, 'throughput': 1.1763143252023764, 'latency_mean': 5.081793794631958, 'latency_p50': 5.102096080780029, 'latency_p90': 5.736391973495484}, {'batch_size': 10, 'throughput': 1.4015415806562386, 'latency_mean': 7.067186374664306, 'latency_p50': 7.036144018173218, 'latency_p90': 8.020827794075013}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: mistralai-mistral-sma_53415_v103
is_internal_developer: True
language_model: mistralai/Mistral-Small-Instruct-2409
model_size: 22B
ranking_group: single
throughput_3p7s: 0.86
us_pacific_date: 2025-01-10
win_ratio: 0.47885626643295354
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.001, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>', 'Me:'], '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-sma-53415-v103-mkmlizer
Waiting for job on mistralai-mistral-sma-53415-v103-mkmlizer to finish
mistralai-mistral-sma-53415-v103-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-sma-53415-v103-mkmlizer: ║     _____            __           __                                ║
mistralai-mistral-sma-53415-v103-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-mistral-sma-53415-v103-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-mistral-sma-53415-v103-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-mistral-sma-53415-v103-mkmlizer: ║       /___/                                                         ║
mistralai-mistral-sma-53415-v103-mkmlizer: ║                                                                     ║
mistralai-mistral-sma-53415-v103-mkmlizer: ║  Version: 0.11.12                                                   ║
mistralai-mistral-sma-53415-v103-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-mistral-sma-53415-v103-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-mistral-sma-53415-v103-mkmlizer: ║                                                                     ║
mistralai-mistral-sma-53415-v103-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-mistral-sma-53415-v103-mkmlizer: ║  belonging to:                                                      ║
mistralai-mistral-sma-53415-v103-mkmlizer: ║                                                                     ║
mistralai-mistral-sma-53415-v103-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-mistral-sma-53415-v103-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-mistral-sma-53415-v103-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
mistralai-mistral-sma-53415-v103-mkmlizer: ║                                                                     ║
mistralai-mistral-sma-53415-v103-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
mistralai-mistral-sma-53415-v103-mkmlizer: Downloaded to shared memory in 89.341s
mistralai-mistral-sma-53415-v103-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpbu60fy81, device:0
mistralai-mistral-sma-53415-v103-mkmlizer: Saving flywheel model at /dev/shm/model_cache
mistralai-mistral-sma-53415-v103-mkmlizer: quantized model in 49.683s
mistralai-mistral-sma-53415-v103-mkmlizer: Processed model mistralai/Mistral-Small-Instruct-2409 in 139.024s
mistralai-mistral-sma-53415-v103-mkmlizer: creating bucket guanaco-mkml-models
mistralai-mistral-sma-53415-v103-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-sma-53415-v103-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-sma-53415-v103
mistralai-mistral-sma-53415-v103-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-mistral-sma-53415-v103/config.json
mistralai-mistral-sma-53415-v103-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mistral-sma-53415-v103/special_tokens_map.json
mistralai-mistral-sma-53415-v103-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mistral-sma-53415-v103/tokenizer_config.json
mistralai-mistral-sma-53415-v103-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/mistralai-mistral-sma-53415-v103/tokenizer.model
mistralai-mistral-sma-53415-v103-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-sma-53415-v103/tokenizer.json
mistralai-mistral-sma-53415-v103-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/mistralai-mistral-sma-53415-v103/flywheel_model.1.safetensors
Job mistralai-mistral-sma-53415-v103-mkmlizer completed after 261.93s with status: succeeded
Stopping job with name mistralai-mistral-sma-53415-v103-mkmlizer
Pipeline stage MKMLizer completed in 262.44s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service mistralai-mistral-sma-53415-v103
Waiting for inference service mistralai-mistral-sma-53415-v103 to be ready
Failed to get response for submission mistralai-mistral-nem_93303_v260: ('http://mistralai-mistral-nem-93303-v260-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:37414->127.0.0.1:8080: read: connection reset by peer\n')
Inference service mistralai-mistral-sma-53415-v103 ready after 371.61070919036865s
Pipeline stage MKMLDeployer completed in 372.14s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5485177040100098s
Received healthy response to inference request in 6.771023988723755s
Received healthy response to inference request in 1.0691750049591064s
Received healthy response to inference request in 2.2831997871398926s
Received healthy response to inference request in 1.668241024017334s
5 requests
0 failed requests
5th percentile: 1.165043544769287
10th percentile: 1.2609120845794677
20th percentile: 1.4526491641998291
30th percentile: 1.5724623680114747
40th percentile: 1.6203516960144042
50th percentile: 1.668241024017334
60th percentile: 1.9142245292663573
70th percentile: 2.1602080345153807
80th percentile: 3.180764627456666
90th percentile: 4.9758943080902105
95th percentile: 5.873459148406981
99th percentile: 6.5915110206604
mean time: 2.6680315017700194
Pipeline stage StressChecker completed in 14.60s
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 0.65s
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 0.69s
Shutdown handler de-registered
mistralai-mistral-sma_53415_v103 status is now deployed due to DeploymentManager action
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 3263.84s
Shutdown handler de-registered
mistralai-mistral-sma_53415_v103 status is now inactive due to auto deactivation removed underperforming models
mistralai-mistral-sma_53415_v103 status is now torndown due to DeploymentManager action