white-bird-5-dpo-50step

developer_uid: zhenzhe

submission_id: white-bird-5-dpo-50step_v3

model_name: white-bird-5-dpo-50step_v3

model_group: white-bird/5_dpo_50step

status: torndown

timestamp: 2025-03-02T20:11:44+00:00

num_battles: 10563

num_wins: 5199

celo_rating: 1273.14

family_friendly_score: 0.4284

family_friendly_standard_error: 0.006998191766449387

submission_type: basic

model_repo: white-bird/5_dpo_50step

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6098393165224999, 'latency_mean': 1.6397087204456329, 'latency_p50': 1.6274707317352295, 'latency_p90': 1.822414231300354}, {'batch_size': 3, 'throughput': 1.1049214208996154, 'latency_mean': 2.6998613142967223, 'latency_p50': 2.7236541509628296, 'latency_p90': 2.989183044433594}, {'batch_size': 5, 'throughput': 1.3330183180213184, 'latency_mean': 3.7241654896736147, 'latency_p50': 3.7443861961364746, 'latency_p90': 4.136960816383362}, {'batch_size': 6, 'throughput': 1.4026220590361165, 'latency_mean': 4.263256731033326, 'latency_p50': 4.249553322792053, 'latency_p90': 4.760662078857422}, {'batch_size': 8, 'throughput': 1.4532983154711003, 'latency_mean': 5.474379221200943, 'latency_p50': 5.507017254829407, 'latency_p90': 6.192364811897278}, {'batch_size': 10, 'throughput': 1.495695947609276, 'latency_mean': 6.644385961294174, 'latency_p50': 6.640682697296143, 'latency_p90': 7.52087562084198}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: white-bird-5-dpo-50step_v3

is_internal_developer: False

language_model: white-bird/5_dpo_50step

model_size: 13B

ranking_group: single

throughput_3p7s: 1.34

us_pacific_date: 2025-03-02

win_ratio: 0.4921897188298779

generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.1, 'stopping_words': ['\n', '####', 'You:', 'Me:', 'Bot:', '</s>', 'User:', 'Anonymous'], '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 white-bird-5-dpo-50step-v3-mkmlizer
Waiting for job on white-bird-5-dpo-50step-v3-mkmlizer to finish
white-bird-5-dpo-50step-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
white-bird-5-dpo-50step-v3-mkmlizer: ║     _____            __           __                                ║
white-bird-5-dpo-50step-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
white-bird-5-dpo-50step-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
white-bird-5-dpo-50step-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
white-bird-5-dpo-50step-v3-mkmlizer: ║       /___/                                                         ║
white-bird-5-dpo-50step-v3-mkmlizer: ║                                                                     ║
white-bird-5-dpo-50step-v3-mkmlizer: ║  Version: 0.12.8                                                    ║
white-bird-5-dpo-50step-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
white-bird-5-dpo-50step-v3-mkmlizer: ║  https://mk1.ai                                                     ║
white-bird-5-dpo-50step-v3-mkmlizer: ║                                                                     ║
white-bird-5-dpo-50step-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
white-bird-5-dpo-50step-v3-mkmlizer: ║  belonging to:                                                      ║
white-bird-5-dpo-50step-v3-mkmlizer: ║                                                                     ║
white-bird-5-dpo-50step-v3-mkmlizer: ║  Chai Research Corp.                                                ║
white-bird-5-dpo-50step-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
white-bird-5-dpo-50step-v3-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
white-bird-5-dpo-50step-v3-mkmlizer: ║                                                                     ║
white-bird-5-dpo-50step-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
white-bird-5-dpo-50step-v3-mkmlizer: Downloaded to shared memory in 44.635s
white-bird-5-dpo-50step-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpu1wgjo4k, device:0
white-bird-5-dpo-50step-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
white-bird-5-dpo-50step-v3-mkmlizer: quantized model in 38.791s
white-bird-5-dpo-50step-v3-mkmlizer: Processed model white-bird/5_dpo_50step in 83.427s
white-bird-5-dpo-50step-v3-mkmlizer: creating bucket guanaco-mkml-models
white-bird-5-dpo-50step-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
white-bird-5-dpo-50step-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/white-bird-5-dpo-50step-v3
white-bird-5-dpo-50step-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/white-bird-5-dpo-50step-v3/config.json
white-bird-5-dpo-50step-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/white-bird-5-dpo-50step-v3/special_tokens_map.json
white-bird-5-dpo-50step-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/white-bird-5-dpo-50step-v3/tokenizer_config.json
white-bird-5-dpo-50step-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/white-bird-5-dpo-50step-v3/tokenizer.json
white-bird-5-dpo-50step-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/white-bird-5-dpo-50step-v3/flywheel_model.0.safetensors
Job white-bird-5-dpo-50step-v3-mkmlizer completed after 114.51s with status: succeeded
Stopping job with name white-bird-5-dpo-50step-v3-mkmlizer
Pipeline stage MKMLizer completed in 115.00s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.32s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service white-bird-5-dpo-50step-v3
Waiting for inference service white-bird-5-dpo-50step-v3 to be ready
Failed to get response for submission white-bird-5-dpo-50step_v2: HTTPConnectionPool(host='white-bird-5-dpo-50step-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service white-bird-5-dpo-50step-v3 ready after 140.69854259490967s
Pipeline stage MKMLDeployer completed in 141.24s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4467079639434814s
Received healthy response to inference request in 1.797734022140503s
Received healthy response to inference request in 1.8598644733428955s
Received healthy response to inference request in 1.6578431129455566s
Received healthy response to inference request in 1.686378002166748s
5 requests
0 failed requests
5th percentile: 1.6635500907897949
10th percentile: 1.6692570686340331
20th percentile: 1.6806710243225098
30th percentile: 1.708649206161499
40th percentile: 1.7531916141510009
50th percentile: 1.797734022140503
60th percentile: 1.8225862026214599
70th percentile: 1.847438383102417
80th percentile: 1.9772331714630127
90th percentile: 2.211970567703247
95th percentile: 2.3293392658233643
99th percentile: 2.423234224319458
mean time: 1.889705514907837
Pipeline stage StressChecker completed in 10.65s
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 0.65s
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 0.68s
Shutdown handler de-registered
white-bird-5-dpo-50step_v3 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
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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 3842.53s
Shutdown handler de-registered
white-bird-5-dpo-50step_v3 status is now inactive due to auto deactivation removed underperforming models
white-bird-5-dpo-50step_v3 status is now torndown due to DeploymentManager action