developer_uid: azuruce
submission_id: chaiml-mistral-nemo-simp_9350_v3
model_name: chaiml-mistral-nemo-simp_9350_v3
model_group: ChaiML/mistral_nemo_simp
status: inactive
timestamp: 2024-12-15T23:17:55+00:00
num_battles: 8517
num_wins: 4345
celo_rating: 1236.2
family_friendly_score: 0.5866
family_friendly_standard_error: 0.0069642004566209895
submission_type: basic
model_repo: ChaiML/mistral_nemo_simpo_baseline_albert_20241213_v1-checkpoint-312
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6439142204892616, 'latency_mean': 1.5529130232334136, 'latency_p50': 1.5478729009628296, 'latency_p90': 1.7246372699737549}, {'batch_size': 4, 'throughput': 1.4814304636248117, 'latency_mean': 2.6869688022136686, 'latency_p50': 2.697685956954956, 'latency_p90': 3.0246493577957154}, {'batch_size': 5, 'throughput': 1.6297934554772273, 'latency_mean': 3.044853503704071, 'latency_p50': 3.0477359294891357, 'latency_p90': 3.4418289422988892}, {'batch_size': 8, 'throughput': 1.9040284981447406, 'latency_mean': 4.179372547864914, 'latency_p50': 4.15598738193512, 'latency_p90': 4.732382035255432}, {'batch_size': 10, 'throughput': 1.9877710091592613, 'latency_mean': 4.985833852291107, 'latency_p50': 4.969430923461914, 'latency_p90': 5.567845487594604}, {'batch_size': 12, 'throughput': 2.0713634985509963, 'latency_mean': 5.740762362480163, 'latency_p50': 5.722488164901733, 'latency_p90': 6.508572411537171}, {'batch_size': 15, 'throughput': 2.0926790815725584, 'latency_mean': 7.102339880466461, 'latency_p50': 7.069774508476257, 'latency_p90': 8.167679643630981}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-mistral-nemo-simp_9350_v3
is_internal_developer: True
language_model: ChaiML/mistral_nemo_simpo_baseline_albert_20241213_v1-checkpoint-312
model_size: 13B
ranking_group: single
throughput_3p7s: 1.82
us_pacific_date: 2024-12-15
win_ratio: 0.5101561582716919
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], '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 chaiml-mistral-nemo-simp-9350-v3-mkmlizer
Waiting for job on chaiml-mistral-nemo-simp-9350-v3-mkmlizer to finish
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: Downloaded to shared memory in 33.178s
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzj4bt6ga, device:0
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: quantized model in 36.749s
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: Processed model ChaiML/mistral_nemo_simpo_baseline_albert_20241213_v1-checkpoint-312 in 69.928s
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-9350-v3
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-9350-v3/config.json
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-9350-v3/special_tokens_map.json
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-9350-v3/tokenizer_config.json
chaiml-mistral-nemo-simp-9350-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-9350-v3/tokenizer.json
Job chaiml-mistral-nemo-simp-9350-v3-mkmlizer completed after 109.05s with status: succeeded
Stopping job with name chaiml-mistral-nemo-simp-9350-v3-mkmlizer
Pipeline stage MKMLizer completed in 109.53s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral-nemo-simp-9350-v3
Waiting for inference service chaiml-mistral-nemo-simp-9350-v3 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
Inference service chaiml-mistral-nemo-simp-9350-v3 ready after 210.76964664459229s
Pipeline stage MKMLDeployer completed in 211.29s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5279443264007568s
Received healthy response to inference request in 0.8188776969909668s
Received healthy response to inference request in 0.8445916175842285s
Received healthy response to inference request in 0.6836168766021729s
Received healthy response to inference request in 0.8341159820556641s
5 requests
0 failed requests
5th percentile: 0.7106690406799316
10th percentile: 0.7377212047576904
20th percentile: 0.791825532913208
30th percentile: 0.8219253540039062
40th percentile: 0.8280206680297851
50th percentile: 0.8341159820556641
60th percentile: 0.8383062362670899
70th percentile: 0.8424964904785156
80th percentile: 0.9812621593475344
90th percentile: 1.2546032428741456
95th percentile: 1.391273784637451
99th percentile: 1.5006102180480956
mean time: 0.9418292999267578
Pipeline stage StressChecker completed in 6.83s
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 2.47s
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 2.28s
Shutdown handler de-registered
chaiml-mistral-nemo-simp_9350_v3 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 2447.67s
Shutdown handler de-registered
chaiml-mistral-nemo-simp_9350_v3 status is now inactive due to auto deactivation removed underperforming models