developer_uid: AlexCuadron
submission_id: alexcuadron-chai-v2-sft_14944_v1
model_name: alexcuadron-chai-v2-sft_14944_v1
model_group: AlexCuadron/chai-v2-sft-
status: torndown
timestamp: 2025-03-23T14:17:00+00:00
num_battles: 10538
num_wins: 5009
celo_rating: 1261.78
family_friendly_score: 0.601
family_friendly_standard_error: 0.006925301437482704
submission_type: basic
model_repo: AlexCuadron/chai-v2-sft-12k-12b
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6016911746393828, 'latency_mean': 1.661910456418991, 'latency_p50': 1.6636395454406738, 'latency_p90': 1.8258058547973632}, {'batch_size': 3, 'throughput': 1.1034037502987988, 'latency_mean': 2.703212089538574, 'latency_p50': 2.691869616508484, 'latency_p90': 3.0676012516021727}, {'batch_size': 5, 'throughput': 1.3237062908886599, 'latency_mean': 3.7612803387641907, 'latency_p50': 3.78629469871521, 'latency_p90': 4.217229843139648}, {'batch_size': 6, 'throughput': 1.3889598132994472, 'latency_mean': 4.293344926834107, 'latency_p50': 4.269915461540222, 'latency_p90': 4.793557572364807}, {'batch_size': 8, 'throughput': 1.4431010035486083, 'latency_mean': 5.508947097063064, 'latency_p50': 5.538899779319763, 'latency_p90': 6.143120574951172}, {'batch_size': 10, 'throughput': 1.4961039571781733, 'latency_mean': 6.6381033062934875, 'latency_p50': 6.645042896270752, 'latency_p90': 7.5462065696716305}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: alexcuadron-chai-v2-sft_14944_v1
is_internal_developer: False
language_model: AlexCuadron/chai-v2-sft-12k-12b
model_size: 13B
ranking_group: single
throughput_3p7s: 1.32
us_pacific_date: 2025-03-23
win_ratio: 0.47532738660087304
generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '####', 'Me:', 'You:', 'User:', 'Bot:', '</s>'], '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-v2-sft-14944-v1-mkmlizer
Waiting for job on alexcuadron-chai-v2-sft-14944-v1-mkmlizer to finish
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: ║     _____            __           __                                ║
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: ║       /___/                                                         ║
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: ║                                                                     ║
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: ║  https://mk1.ai                                                     ║
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: ║                                                                     ║
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: ║  belonging to:                                                      ║
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: ║                                                                     ║
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: ║  Chai Research Corp.                                                ║
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: ║                                                                     ║
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: Downloaded to shared memory in 46.233s
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpgvps9gir, device:0
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: quantized model in 37.888s
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: Processed model AlexCuadron/chai-v2-sft-12k-12b in 84.122s
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: creating bucket guanaco-mkml-models
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexcuadron-chai-v2-sft-14944-v1
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexcuadron-chai-v2-sft-14944-v1/config.json
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexcuadron-chai-v2-sft-14944-v1/special_tokens_map.json
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexcuadron-chai-v2-sft-14944-v1/tokenizer_config.json
alexcuadron-chai-v2-sft-14944-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexcuadron-chai-v2-sft-14944-v1/tokenizer.json
Job alexcuadron-chai-v2-sft-14944-v1-mkmlizer completed after 114.78s with status: succeeded
Stopping job with name alexcuadron-chai-v2-sft-14944-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.32s
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 alexcuadron-chai-v2-sft-14944-v1
Waiting for inference service alexcuadron-chai-v2-sft-14944-v1 to be ready
Inference service alexcuadron-chai-v2-sft-14944-v1 ready after 90.52790594100952s
Pipeline stage MKMLDeployer completed in 91.13s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3412303924560547s
Received healthy response to inference request in 1.6237971782684326s
Received healthy response to inference request in 1.5544629096984863s
Received healthy response to inference request in 1.7605853080749512s
Received healthy response to inference request in 1.6301476955413818s
5 requests
0 failed requests
5th percentile: 1.5683297634124755
10th percentile: 1.5821966171264648
20th percentile: 1.6099303245544434
30th percentile: 1.6250672817230225
40th percentile: 1.627607488632202
50th percentile: 1.6301476955413818
60th percentile: 1.6823227405548096
70th percentile: 1.7344977855682373
80th percentile: 1.876714324951172
90th percentile: 2.108972358703613
95th percentile: 2.225101375579834
99th percentile: 2.3180045890808105
mean time: 1.7820446968078614
Pipeline stage StressChecker completed in 10.18s
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 0.69s
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 0.82s
Shutdown handler de-registered
alexcuadron-chai-v2-sft_14944_v1 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 0.09s
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-v2-sft-14944-v1-profiler
Waiting for inference service alexcuadron-chai-v2-sft-14944-v1-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4524.14s
Shutdown handler de-registered
alexcuadron-chai-v2-sft_14944_v1 status is now inactive due to auto deactivation removed underperforming models
alexcuadron-chai-v2-sft_14944_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1