alexcuadron-chai-sft-ap_20353

developer_uid: AlexCuadron

submission_id: alexcuadron-chai-sft-ap_20353_v2

model_name: alexcuadron-chai-sft-ap_20353_v2

model_group: AlexCuadron/chai-sft-app

status: torndown

timestamp: 2025-03-13T06:36:28+00:00

num_battles: 7237

num_wins: 3390

celo_rating: 1249.12

family_friendly_score: 0.5982000000000001

family_friendly_standard_error: 0.0069333507051064424

submission_type: basic

model_repo: AlexCuadron/chai-sft-approved-models-12b-500-creative

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6046166013499825, 'latency_mean': 1.653844757080078, 'latency_p50': 1.6592516899108887, 'latency_p90': 1.8242313146591187}, {'batch_size': 3, 'throughput': 1.1125131987643766, 'latency_mean': 2.687215259075165, 'latency_p50': 2.6958385705947876, 'latency_p90': 3.00740168094635}, {'batch_size': 5, 'throughput': 1.335950647024014, 'latency_mean': 3.7157413399219514, 'latency_p50': 3.6883556842803955, 'latency_p90': 4.244934296607971}, {'batch_size': 6, 'throughput': 1.4041415077952937, 'latency_mean': 4.246396807432174, 'latency_p50': 4.238470792770386, 'latency_p90': 4.740922045707703}, {'batch_size': 8, 'throughput': 1.4781542035440114, 'latency_mean': 5.363769555091858, 'latency_p50': 5.405001759529114, 'latency_p90': 6.003136610984802}, {'batch_size': 10, 'throughput': 1.5272198755379434, 'latency_mean': 6.493742898702622, 'latency_p50': 6.555599808692932, 'latency_p90': 7.2844193220138544}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: alexcuadron-chai-sft-ap_20353_v2

is_internal_developer: False

language_model: AlexCuadron/chai-sft-approved-models-12b-500-creative

model_size: 13B

ranking_group: single

throughput_3p7s: 1.34

us_pacific_date: 2025-03-12

win_ratio: 0.4684261434295979

generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.1, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

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}

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 alexcuadron-chai-sft-ap-20353-v2-mkmlizer
Waiting for job on alexcuadron-chai-sft-ap-20353-v2-mkmlizer to finish
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: ║     _____            __           __                                ║
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: ║       /___/                                                         ║
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: ║                                                                     ║
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: ║  https://mk1.ai                                                     ║
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: ║                                                                     ║
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: ║  belonging to:                                                      ║
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: ║                                                                     ║
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: ║  Chai Research Corp.                                                ║
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: ║                                                                     ║
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: Downloaded to shared memory in 29.096s
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpf12o8q_w, device:0
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: quantized model in 34.994s
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: Processed model AlexCuadron/chai-sft-approved-models-12b-500-creative in 64.091s
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: creating bucket guanaco-mkml-models
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexcuadron-chai-sft-ap-20353-v2
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexcuadron-chai-sft-ap-20353-v2/config.json
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexcuadron-chai-sft-ap-20353-v2/special_tokens_map.json
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexcuadron-chai-sft-ap-20353-v2/tokenizer_config.json
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexcuadron-chai-sft-ap-20353-v2/tokenizer.json
alexcuadron-chai-sft-ap-20353-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexcuadron-chai-sft-ap-20353-v2/flywheel_model.0.safetensors
Job alexcuadron-chai-sft-ap-20353-v2-mkmlizer completed after 93.84s with status: succeeded
Stopping job with name alexcuadron-chai-sft-ap-20353-v2-mkmlizer
Pipeline stage MKMLizer completed in 94.46s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service alexcuadron-chai-sft-ap-20353-v2
Waiting for inference service alexcuadron-chai-sft-ap-20353-v2 to be ready
Failed to get response for submission jellywibble-enzo-mafia-enemy_v12: HTTPConnectionPool(host='jellywibble-enzo-mafia-enemy-v12-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service alexcuadron-chai-sft-ap-20353-v2 ready after 100.410569190979s
Pipeline stage MKMLDeployer completed in 100.92s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1472890377044678s
Received healthy response to inference request in 1.5056047439575195s
Received healthy response to inference request in 1.4615838527679443s
Received healthy response to inference request in 1.4237937927246094s
Received healthy response to inference request in 1.6610453128814697s
5 requests
0 failed requests
5th percentile: 1.4313518047332763
10th percentile: 1.4389098167419434
20th percentile: 1.4540258407592774
30th percentile: 1.4703880310058595
40th percentile: 1.4879963874816895
50th percentile: 1.5056047439575195
60th percentile: 1.5677809715270996
70th percentile: 1.6299571990966797
80th percentile: 1.7582940578460695
90th percentile: 1.9527915477752686
95th percentile: 2.050040292739868
99th percentile: 2.127839288711548
mean time: 1.6398633480072022
Pipeline stage StressChecker completed in 9.45s
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 0.68s
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 0.67s
Shutdown handler de-registered
alexcuadron-chai-sft-ap_20353_v2 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service alexcuadron-chai-sft-ap-20353-v2-profiler
Waiting for inference service alexcuadron-chai-sft-ap-20353-v2-profiler to be ready
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 2521.17s
Shutdown handler de-registered
alexcuadron-chai-sft-ap_20353_v2 status is now inactive due to auto deactivation removed underperforming models
alexcuadron-chai-sft-ap_20353_v2 status is now torndown due to DeploymentManager action

ChatRequest

Bot Name

Generation Params

Prompt Formatter

ChatMessage 1

Sender

Message

User Message