developer_uid: azuruce
submission_id: chaiml-mistral-nemo-simp_9893_v2
model_name: chaiml-mistral-nemo-simp_9893_v2
model_group: ChaiML/mistral_nemo_simp
status: inactive
timestamp: 2024-12-13T20:22:59+00:00
num_battles: 14911
num_wins: 7288
celo_rating: 1253.97
family_friendly_score: 0.5840000000000001
family_friendly_standard_error: 0.006970566691453429
submission_type: basic
model_repo: ChaiML/mistral_nemo_simpo_baseline_albert_241212_v1
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6413136194319196, 'latency_mean': 1.5592355418205261, 'latency_p50': 1.559199333190918, 'latency_p90': 1.720878791809082}, {'batch_size': 4, 'throughput': 1.4833290942396007, 'latency_mean': 2.6877514016628266, 'latency_p50': 2.6944327354431152, 'latency_p90': 3.0084350824356076}, {'batch_size': 5, 'throughput': 1.6061739486259226, 'latency_mean': 3.100946443080902, 'latency_p50': 3.1292471885681152, 'latency_p90': 3.475701022148132}, {'batch_size': 8, 'throughput': 1.8929872615501149, 'latency_mean': 4.1893826162815095, 'latency_p50': 4.179901480674744, 'latency_p90': 4.6499789476394655}, {'batch_size': 10, 'throughput': 1.9835227363305405, 'latency_mean': 4.9999804472923275, 'latency_p50': 4.950161337852478, 'latency_p90': 5.714750361442566}, {'batch_size': 12, 'throughput': 2.0283698417512506, 'latency_mean': 5.854955861568451, 'latency_p50': 5.866036653518677, 'latency_p90': 6.6259665250778195}, {'batch_size': 15, 'throughput': 2.093766181177249, 'latency_mean': 7.10055682182312, 'latency_p50': 7.121860384941101, 'latency_p90': 7.985225653648376}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-mistral-nemo-simp_9893_v2
is_internal_developer: True
language_model: ChaiML/mistral_nemo_simpo_baseline_albert_241212_v1
model_size: 13B
ranking_group: single
throughput_3p7s: 1.8
us_pacific_date: 2024-12-13
win_ratio: 0.4887666823150694
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-9893-v2-mkmlizer
Waiting for job on chaiml-mistral-nemo-simp-9893-v2-mkmlizer to finish
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: Downloaded to shared memory in 48.470s
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8s_ozcbt, device:0
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: quantized model in 36.307s
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: Processed model ChaiML/mistral_nemo_simpo_baseline_albert_241212_v1 in 84.777s
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-9893-v2
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-9893-v2/config.json
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-9893-v2/special_tokens_map.json
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-9893-v2/tokenizer_config.json
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-9893-v2/tokenizer.json
chaiml-mistral-nemo-simp-9893-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-9893-v2/flywheel_model.0.safetensors
Job chaiml-mistral-nemo-simp-9893-v2-mkmlizer completed after 114.71s with status: succeeded
Stopping job with name chaiml-mistral-nemo-simp-9893-v2-mkmlizer
Pipeline stage MKMLizer completed in 115.21s
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-9893-v2
Waiting for inference service chaiml-mistral-nemo-simp-9893-v2 to be ready
Inference service chaiml-mistral-nemo-simp-9893-v2 ready after 200.83089518547058s
Pipeline stage MKMLDeployer completed in 201.35s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6567752361297607s
Received healthy response to inference request in 1.8918695449829102s
Received healthy response to inference request in 1.2172753810882568s
Received healthy response to inference request in 1.6199166774749756s
Received healthy response to inference request in 1.2867441177368164s
5 requests
0 failed requests
5th percentile: 1.2311691284179687
10th percentile: 1.2450628757476807
20th percentile: 1.2728503704071046
30th percentile: 1.3533786296844483
40th percentile: 1.486647653579712
50th percentile: 1.6199166774749756
60th percentile: 1.6346601009368897
70th percentile: 1.6494035243988037
80th percentile: 1.7037940979003907
90th percentile: 1.7978318214416504
95th percentile: 1.8448506832122802
99th percentile: 1.8824657726287841
mean time: 1.534516191482544
Pipeline stage StressChecker completed in 9.17s
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 2.87s
Shutdown handler de-registered
chaiml-mistral-nemo-simp_9893_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral-nemo-simp-9893-v2-profiler
Waiting for inference service chaiml-mistral-nemo-simp-9893-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 2630.51s
Shutdown handler de-registered
chaiml-mistral-nemo-simp_9893_v2 status is now inactive due to auto deactivation removed underperforming models