rirv938-mistral-12b-ant_39972

developer_uid: rirv938

submission_id: rirv938-mistral-12b-ant_39972_v1

model_name: rirv938-mistral-12b-ant_39972_v1

model_group: rirv938/mistral_12b_anth

status: torndown

timestamp: 2025-02-20T17:53:33+00:00

num_battles: 6854

num_wins: 3383

celo_rating: 1268.94

family_friendly_score: 0.5676

family_friendly_standard_error: 0.007006143589736082

submission_type: basic

model_repo: rirv938/mistral_12b_anthropic_1120_450_seed_10_v2

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.5958259050670751, 'latency_mean': 1.6782722902297973, 'latency_p50': 1.672582745552063, 'latency_p90': 1.8511436462402344}, {'batch_size': 3, 'throughput': 1.063742096845747, 'latency_mean': 2.819913923740387, 'latency_p50': 2.8423677682876587, 'latency_p90': 3.09980046749115}, {'batch_size': 5, 'throughput': 1.2658239652525178, 'latency_mean': 3.9407765448093413, 'latency_p50': 3.9234461784362793, 'latency_p90': 4.387320351600647}, {'batch_size': 6, 'throughput': 1.3341015195133996, 'latency_mean': 4.473002979755401, 'latency_p50': 4.4909679889678955, 'latency_p90': 5.098147630691528}, {'batch_size': 8, 'throughput': 1.3821596741184115, 'latency_mean': 5.748948202133179, 'latency_p50': 5.725979924201965, 'latency_p90': 6.3771528720855715}, {'batch_size': 10, 'throughput': 1.4283479923296256, 'latency_mean': 6.949384558200836, 'latency_p50': 6.89711058139801, 'latency_p90': 7.890466904640197}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-mistral-12b-ant_39972_v1

is_internal_developer: True

language_model: rirv938/mistral_12b_anthropic_1120_450_seed_10_v2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.24

us_pacific_date: 2025-02-20

win_ratio: 0.4935803910125474

generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.6, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n', '</s>', '###', 'You:'], 'max_input_tokens': 1024, 'best_of': 8, '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 rirv938-mistral-12b-ant-39972-v1-mkmlizer
Waiting for job on rirv938-mistral-12b-ant-39972-v1-mkmlizer to finish
rirv938-mistral-12b-ant-39972-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-12b-ant-39972-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-mistral-12b-ant-39972-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-mistral-12b-ant-39972-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-mistral-12b-ant-39972-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-mistral-12b-ant-39972-v1-mkmlizer: ║       /___/                                                         ║
rirv938-mistral-12b-ant-39972-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-12b-ant-39972-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-mistral-12b-ant-39972-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-mistral-12b-ant-39972-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-mistral-12b-ant-39972-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-12b-ant-39972-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-mistral-12b-ant-39972-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-mistral-12b-ant-39972-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-12b-ant-39972-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-mistral-12b-ant-39972-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-mistral-12b-ant-39972-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rirv938-mistral-12b-ant-39972-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-12b-ant-39972-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission rirv938-mistral-12b-ant_23560_v1: HTTPConnectionPool(host='rirv938-mistral-12b-ant-23560-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rirv938-mistral-12b-ant-39972-v1-mkmlizer: Downloaded to shared memory in 84.675s
rirv938-mistral-12b-ant-39972-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppr59ya_e, device:0
rirv938-mistral-12b-ant-39972-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-12b-ant-39972-v1-mkmlizer: quantized model in 41.804s
rirv938-mistral-12b-ant-39972-v1-mkmlizer: Processed model rirv938/mistral_12b_anthropic_1120_450_seed_10_v2 in 126.479s
rirv938-mistral-12b-ant-39972-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-12b-ant-39972-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-12b-ant-39972-v1
rirv938-mistral-12b-ant-39972-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-12b-ant-39972-v1/config.json
rirv938-mistral-12b-ant-39972-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-12b-ant-39972-v1/special_tokens_map.json
rirv938-mistral-12b-ant-39972-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-12b-ant-39972-v1/tokenizer_config.json
rirv938-mistral-12b-ant-39972-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-12b-ant-39972-v1/tokenizer.json
Job rirv938-mistral-12b-ant-39972-v1-mkmlizer completed after 155.78s with status: succeeded
Stopping job with name rirv938-mistral-12b-ant-39972-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.28s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-mistral-12b-ant-39972-v1
Waiting for inference service rirv938-mistral-12b-ant-39972-v1 to be ready
Inference service rirv938-mistral-12b-ant-39972-v1 ready after 210.7236201763153s
Pipeline stage MKMLDeployer completed in 211.31s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.828690767288208s
Received healthy response to inference request in 1.7299139499664307s
Received healthy response to inference request in 1.7696523666381836s
Received healthy response to inference request in 1.5566558837890625s
Received healthy response to inference request in 1.6379408836364746s
5 requests
0 failed requests
5th percentile: 1.5729128837585449
10th percentile: 1.5891698837280273
20th percentile: 1.6216838836669922
30th percentile: 1.6563354969024657
40th percentile: 1.6931247234344482
50th percentile: 1.7299139499664307
60th percentile: 1.7458093166351318
70th percentile: 1.761704683303833
80th percentile: 1.9814600467681887
90th percentile: 2.4050754070281983
95th percentile: 2.616883087158203
99th percentile: 2.786329231262207
mean time: 1.9045707702636718
Pipeline stage StressChecker completed in 10.82s
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 0.70s
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 0.68s
Shutdown handler de-registered
rirv938-mistral-12b-ant_39972_v1 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4562.15s
Shutdown handler de-registered
rirv938-mistral-12b-ant_39972_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-12b-ant_39972_v1 status is now torndown due to DeploymentManager action

ChatRequest

Bot Name

Generation Params

Prompt Formatter

ChatMessage 1

Sender

Message

User Message