chaiml-mistral-nemo-dpo_24081

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-dpo_24081_v6

model_name: chaiml-mistral-nemo-dpo_24081_v6

model_group: ChaiML/mistral_nemo_dpo_

status: torndown

timestamp: 2024-12-30T18:12:56+00:00

num_battles: 18259

num_wins: 9401

celo_rating: 1271.53

family_friendly_score: 0.5820000000000001

family_friendly_standard_error: 0.006975327949279518

submission_type: basic

model_repo: ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-6240

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6149267664454217, 'latency_mean': 1.6261481177806854, 'latency_p50': 1.6221435070037842, 'latency_p90': 1.791823124885559}, {'batch_size': 3, 'throughput': 1.1392657876448489, 'latency_mean': 2.6275600564479826, 'latency_p50': 2.6017485857009888, 'latency_p90': 2.8857574462890625}, {'batch_size': 5, 'throughput': 1.3699334534792862, 'latency_mean': 3.630331234931946, 'latency_p50': 3.6237508058547974, 'latency_p90': 4.0735455513000485}, {'batch_size': 6, 'throughput': 1.4251300893337882, 'latency_mean': 4.178188824653626, 'latency_p50': 4.152292609214783, 'latency_p90': 4.658222031593323}, {'batch_size': 8, 'throughput': 1.495892572796496, 'latency_mean': 5.313673686981201, 'latency_p50': 5.37760329246521, 'latency_p90': 5.982537341117859}, {'batch_size': 10, 'throughput': 1.5380090289877464, 'latency_mean': 6.447042869329453, 'latency_p50': 6.473756670951843, 'latency_p90': 7.1860356092453}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-dpo_24081_v6

is_internal_developer: True

language_model: ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-6240

model_size: 13B

ranking_group: single

throughput_3p7s: 1.39

us_pacific_date: 2024-12-30

win_ratio: 0.5148693794840901

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': 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 chaiml-mistral-nemo-dpo-24081-v6-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-24081-v6-mkmlizer to finish
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: Downloaded to shared memory in 47.916s
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6i_ukxog, device:0
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: quantized model in 36.737s
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-6240 in 84.654s
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-24081-v6
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-24081-v6/config.json
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-24081-v6/special_tokens_map.json
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-24081-v6/tokenizer_config.json
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-24081-v6/tokenizer.json
chaiml-mistral-nemo-dpo-24081-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-24081-v6/flywheel_model.0.safetensors
Job chaiml-mistral-nemo-dpo-24081-v6-mkmlizer completed after 114.47s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-24081-v6-mkmlizer
Pipeline stage MKMLizer completed in 114.93s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral-nemo-dpo-24081-v6
Waiting for inference service chaiml-mistral-nemo-dpo-24081-v6 to be ready
Retrying (%r) after connection broken by '%r': %s
Inference service chaiml-mistral-nemo-dpo-24081-v6 ready after 311.49539136886597s
Pipeline stage MKMLDeployer completed in 312.01s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.041105031967163s
Received healthy response to inference request in 1.4273781776428223s
Received healthy response to inference request in 1.9035446643829346s
Received healthy response to inference request in 1.5507359504699707s
Received healthy response to inference request in 1.2041127681732178s
5 requests
0 failed requests
5th percentile: 1.2487658500671386
10th percentile: 1.2934189319610596
20th percentile: 1.3827250957489015
30th percentile: 1.452049732208252
40th percentile: 1.5013928413391113
50th percentile: 1.5507359504699707
60th percentile: 1.6918594360351562
70th percentile: 1.8329829216003417
80th percentile: 1.9310567378997803
90th percentile: 1.9860808849334717
95th percentile: 2.0135929584503174
99th percentile: 2.0356026172637938
mean time: 1.6253753185272217
Pipeline stage StressChecker completed in 9.77s
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 0.70s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo_24081_v6 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 chaiml-mistral-nemo-dpo-24081-v6-profiler
Waiting for inference service chaiml-mistral-nemo-dpo-24081-v6-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 2774.95s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo_24081_v6 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral-nemo-dpo_24081_v6 status is now torndown due to DeploymentManager action
chaiml-mistral-nemo-dpo_24081_v6 status is now torndown due to DeploymentManager action
chaiml-mistral-nemo-dpo_24081_v6 status is now torndown due to DeploymentManager action

ChatRequest

Bot Name

Generation Params

Prompt Formatter

ChatMessage 1

Sender

Message

User Message