white-bird-4-dpo

developer_uid: zhenzhe

submission_id: white-bird-4-dpo_v1

model_name: white-bird-4-dpo_v1

model_group: white-bird/4_dpo

status: torndown

timestamp: 2025-03-02T11:21:11+00:00

num_battles: 8056

num_wins: 3903

celo_rating: 1267.08

family_friendly_score: 0.41080000000000005

family_friendly_standard_error: 0.006957634080634019

submission_type: basic

model_repo: white-bird/4_dpo

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6030223109236241, 'latency_mean': 1.658240830898285, 'latency_p50': 1.6632901430130005, 'latency_p90': 1.8222815990447998}, {'batch_size': 3, 'throughput': 1.135256254887081, 'latency_mean': 2.6372865056991577, 'latency_p50': 2.6321412324905396, 'latency_p90': 2.909116339683533}, {'batch_size': 5, 'throughput': 1.3798692451849368, 'latency_mean': 3.6023930168151854, 'latency_p50': 3.607885479927063, 'latency_p90': 4.074520492553711}, {'batch_size': 6, 'throughput': 1.4284896800054705, 'latency_mean': 4.171252665519714, 'latency_p50': 4.167851209640503, 'latency_p90': 4.646003222465515}, {'batch_size': 8, 'throughput': 1.5094520595461878, 'latency_mean': 5.261337753534317, 'latency_p50': 5.261431097984314, 'latency_p90': 5.9612061977386475}, {'batch_size': 10, 'throughput': 1.550334754334791, 'latency_mean': 6.403746691942215, 'latency_p50': 6.432737588882446, 'latency_p90': 7.206870412826538}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: white-bird-4-dpo_v1

is_internal_developer: False

language_model: white-bird/4_dpo

model_size: 13B

ranking_group: single

throughput_3p7s: 1.4

us_pacific_date: 2025-03-02

win_ratio: 0.48448361469712015

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', '</s>', 'You:', 'Me:', 'User:', 'Bot:', '####', '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-4-dpo-v1-mkmlizer
Waiting for job on white-bird-4-dpo-v1-mkmlizer to finish
white-bird-4-dpo-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
white-bird-4-dpo-v1-mkmlizer: ║     _____            __           __                                ║
white-bird-4-dpo-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
white-bird-4-dpo-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
white-bird-4-dpo-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
white-bird-4-dpo-v1-mkmlizer: ║       /___/                                                         ║
white-bird-4-dpo-v1-mkmlizer: ║                                                                     ║
white-bird-4-dpo-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
white-bird-4-dpo-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
white-bird-4-dpo-v1-mkmlizer: ║  https://mk1.ai                                                     ║
white-bird-4-dpo-v1-mkmlizer: ║                                                                     ║
white-bird-4-dpo-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
white-bird-4-dpo-v1-mkmlizer: ║  belonging to:                                                      ║
white-bird-4-dpo-v1-mkmlizer: ║                                                                     ║
white-bird-4-dpo-v1-mkmlizer: ║  Chai Research Corp.                                                ║
white-bird-4-dpo-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
white-bird-4-dpo-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
white-bird-4-dpo-v1-mkmlizer: ║                                                                     ║
white-bird-4-dpo-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
white-bird-4-dpo-v1-mkmlizer: Downloaded to shared memory in 42.652s
white-bird-4-dpo-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4yr9u8co, device:0
white-bird-4-dpo-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
white-bird-4-dpo-v1-mkmlizer: quantized model in 38.145s
white-bird-4-dpo-v1-mkmlizer: Processed model white-bird/4_dpo in 80.798s
white-bird-4-dpo-v1-mkmlizer: creating bucket guanaco-mkml-models
white-bird-4-dpo-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
white-bird-4-dpo-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/white-bird-4-dpo-v1
white-bird-4-dpo-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/white-bird-4-dpo-v1/special_tokens_map.json
white-bird-4-dpo-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/white-bird-4-dpo-v1/config.json
white-bird-4-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/white-bird-4-dpo-v1/tokenizer_config.json
white-bird-4-dpo-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/white-bird-4-dpo-v1/flywheel_model.0.safetensors
white-bird-4-dpo-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 27.41it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 44.31it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:08, 42.09it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:08, 40.98it/s]
Loading 0:   7%|▋         | 27/363 [00:00<00:08, 41.60it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:10, 32.24it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:08, 39.34it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:08, 39.65it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:07, 40.49it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:07, 39.61it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 31.75it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 31.59it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:07, 36.90it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:07, 38.16it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 39.08it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 40.89it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 32.99it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 39.92it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 39.73it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:06, 40.96it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:07, 32.88it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:07, 32.61it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:06, 38.47it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:06, 37.75it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:06, 36.84it/s]
Loading 0:  38%|███▊      | 138/363 [00:03<00:06, 34.41it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:09, 24.13it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:09, 22.91it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:08, 23.79it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 28.97it/s]
Loading 0:  44%|████▎     | 158/363 [00:04<00:07, 27.73it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 35.10it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 34.34it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:05, 36.05it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 34.84it/s]
Loading 0:  50%|█████     | 183/363 [00:05<00:04, 36.48it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 35.04it/s]
Loading 0:  53%|█████▎    | 192/363 [00:05<00:04, 36.34it/s]
Loading 0:  54%|█████▍    | 196/363 [00:05<00:04, 35.07it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 36.79it/s]
Loading 0:  56%|█████▋    | 205/363 [00:05<00:04, 34.82it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:04, 36.25it/s]
Loading 0:  59%|█████▉    | 214/363 [00:06<00:04, 34.58it/s]
Loading 0:  60%|██████    | 218/363 [00:06<00:04, 33.91it/s]
Loading 0:  61%|██████    | 222/363 [00:06<00:04, 34.87it/s]
Loading 0:  62%|██████▏   | 226/363 [00:06<00:05, 23.38it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:05, 24.29it/s]
Loading 0:  65%|██████▍   | 235/363 [00:06<00:04, 29.49it/s]
Loading 0:  66%|██████▌   | 239/363 [00:07<00:04, 29.24it/s]
Loading 0:  68%|██████▊   | 246/363 [00:07<00:03, 37.59it/s]
Loading 0:  69%|██████▉   | 251/363 [00:07<00:02, 38.52it/s]
Loading 0:  71%|███████   | 256/363 [00:07<00:02, 37.98it/s]
Loading 0:  72%|███████▏  | 261/363 [00:07<00:02, 39.36it/s]
Loading 0:  73%|███████▎  | 266/363 [00:07<00:02, 34.01it/s]
Loading 0:  75%|███████▌  | 273/363 [00:07<00:02, 41.06it/s]
Loading 0:  77%|███████▋  | 278/363 [00:07<00:02, 40.87it/s]
Loading 0:  78%|███████▊  | 283/363 [00:08<00:01, 41.35it/s]
Loading 0:  79%|███████▉  | 288/363 [00:08<00:01, 43.11it/s]
Loading 0:  81%|████████  | 293/363 [00:08<00:01, 35.49it/s]
Loading 0:  82%|████████▏ | 298/363 [00:08<00:01, 38.39it/s]
Loading 0:  83%|████████▎ | 303/363 [00:08<00:01, 38.11it/s]
Loading 0:  85%|████████▍ | 308/363 [00:15<00:23,  2.34it/s]
Loading 0:  86%|████████▌ | 312/363 [00:15<00:16,  3.05it/s]
Loading 0:  88%|████████▊ | 319/363 [00:15<00:09,  4.83it/s]
Loading 0:  89%|████████▉ | 323/363 [00:15<00:06,  6.08it/s]
Loading 0:  90%|█████████ | 328/363 [00:15<00:04,  8.22it/s]
Loading 0:  91%|█████████▏| 332/363 [00:16<00:03, 10.19it/s]
Loading 0:  93%|█████████▎| 337/363 [00:16<00:01, 13.50it/s]
Loading 0:  94%|█████████▍| 342/363 [00:16<00:01, 16.93it/s]
Loading 0:  96%|█████████▌| 347/363 [00:16<00:00, 20.51it/s]
Loading 0:  97%|█████████▋| 351/363 [00:16<00:00, 23.28it/s]
Loading 0:  98%|█████████▊| 355/363 [00:16<00:00, 26.08it/s]
Loading 0:  99%|█████████▉| 359/363 [00:16<00:00, 27.73it/s]
                                                            
Job white-bird-4-dpo-v1-mkmlizer completed after 103.94s with status: succeeded
Stopping job with name white-bird-4-dpo-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.41s
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 white-bird-4-dpo-v1
Waiting for inference service white-bird-4-dpo-v1 to be ready
Inference service white-bird-4-dpo-v1 ready after 130.44386863708496s
Pipeline stage MKMLDeployer completed in 130.89s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3709287643432617s
Received healthy response to inference request in 1.6945648193359375s
Received healthy response to inference request in 1.829646348953247s
Received healthy response to inference request in 1.648585319519043s
Received healthy response to inference request in 1.649876356124878s
5 requests
0 failed requests
5th percentile: 1.64884352684021
10th percentile: 1.649101734161377
20th percentile: 1.649618148803711
30th percentile: 1.65881404876709
40th percentile: 1.6766894340515137
50th percentile: 1.6945648193359375
60th percentile: 1.7485974311828614
70th percentile: 1.802630043029785
80th percentile: 1.9379028320312501
90th percentile: 2.154415798187256
95th percentile: 2.262672281265259
99th percentile: 2.3492774677276613
mean time: 1.8387203216552734
Pipeline stage StressChecker completed in 10.74s
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 0.67s
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 0.71s
Shutdown handler de-registered
white-bird-4-dpo_v1 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 3336.22s
Shutdown handler de-registered
white-bird-4-dpo_v1 status is now inactive due to auto deactivation removed underperforming models
white-bird-4-dpo_v1 status is now torndown due to DeploymentManager action