white-bird-1-dpo

developer_uid: zhenzhe

submission_id: white-bird-1-dpo_v2

model_name: white-bird-1-dpo_v2

model_group: white-bird/1_dpo

status: torndown

timestamp: 2025-03-02T06:44:38+00:00

num_battles: 13082

num_wins: 6210

celo_rating: 1262.36

family_friendly_score: 0.4538

family_friendly_standard_error: 0.007040817566163747

submission_type: basic

model_repo: white-bird/1_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': 0.6148114463496208, 'latency_mean': 1.6264393651485443, 'latency_p50': 1.6140116453170776, 'latency_p90': 1.8079599380493163}, {'batch_size': 3, 'throughput': 1.129891631338449, 'latency_mean': 2.6466924750804903, 'latency_p50': 2.636184573173523, 'latency_p90': 2.901455855369568}, {'batch_size': 5, 'throughput': 1.3655203078237896, 'latency_mean': 3.638982377052307, 'latency_p50': 3.6683807373046875, 'latency_p90': 4.064074850082397}, {'batch_size': 6, 'throughput': 1.449510666722415, 'latency_mean': 4.123858344554901, 'latency_p50': 4.150706052780151, 'latency_p90': 4.567178630828858}, {'batch_size': 8, 'throughput': 1.5075075750089793, 'latency_mean': 5.26499732375145, 'latency_p50': 5.277418851852417, 'latency_p90': 5.875997686386109}, {'batch_size': 10, 'throughput': 1.5487971767820994, 'latency_mean': 6.410908886194229, 'latency_p50': 6.406793117523193, 'latency_p90': 7.196061897277832}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: white-bird-1-dpo_v2

is_internal_developer: False

language_model: white-bird/1_dpo

model_size: 13B

ranking_group: single

throughput_3p7s: 1.39

us_pacific_date: 2025-03-01

win_ratio: 0.47469805840085616

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', '####', 'Anonymous', '</s>', 'You:', 'Me:', 'Bot:', 'User:'], '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-1-dpo-v2-mkmlizer
Waiting for job on white-bird-1-dpo-v2-mkmlizer to finish
white-bird-1-dpo-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
white-bird-1-dpo-v2-mkmlizer: ║     _____            __           __                                ║
white-bird-1-dpo-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
white-bird-1-dpo-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
white-bird-1-dpo-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
white-bird-1-dpo-v2-mkmlizer: ║       /___/                                                         ║
white-bird-1-dpo-v2-mkmlizer: ║                                                                     ║
white-bird-1-dpo-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
white-bird-1-dpo-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
white-bird-1-dpo-v2-mkmlizer: ║  https://mk1.ai                                                     ║
white-bird-1-dpo-v2-mkmlizer: ║                                                                     ║
white-bird-1-dpo-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
white-bird-1-dpo-v2-mkmlizer: ║  belonging to:                                                      ║
white-bird-1-dpo-v2-mkmlizer: ║                                                                     ║
white-bird-1-dpo-v2-mkmlizer: ║  Chai Research Corp.                                                ║
white-bird-1-dpo-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
white-bird-1-dpo-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
white-bird-1-dpo-v2-mkmlizer: ║                                                                     ║
white-bird-1-dpo-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
white-bird-1-dpo-v2-mkmlizer: Downloaded to shared memory in 30.860s
white-bird-1-dpo-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpckg9094o, device:0
white-bird-1-dpo-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
white-bird-1-dpo-v2-mkmlizer: quantized model in 37.209s
white-bird-1-dpo-v2-mkmlizer: Processed model white-bird/1_dpo in 68.070s
white-bird-1-dpo-v2-mkmlizer: creating bucket guanaco-mkml-models
white-bird-1-dpo-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
white-bird-1-dpo-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/white-bird-1-dpo-v2
white-bird-1-dpo-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/white-bird-1-dpo-v2/config.json
white-bird-1-dpo-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/white-bird-1-dpo-v2/special_tokens_map.json
white-bird-1-dpo-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/white-bird-1-dpo-v2/tokenizer_config.json
white-bird-1-dpo-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/white-bird-1-dpo-v2/tokenizer.json
white-bird-1-dpo-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/white-bird-1-dpo-v2/flywheel_model.0.safetensors
white-bird-1-dpo-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 29.32it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 47.36it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 48.51it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 40.36it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 45.05it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 43.41it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 42.94it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:07, 40.74it/s]
Loading 0:  14%|█▍        | 51/363 [00:01<00:07, 40.11it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:07, 42.44it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 30.55it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 30.49it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:07, 36.51it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 37.99it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 39.81it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 42.06it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 35.06it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 42.20it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 40.85it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 42.95it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:06, 35.96it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:06, 36.73it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 43.16it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 42.42it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 42.62it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 44.38it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:08, 27.15it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 27.33it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 33.79it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:06, 33.61it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 35.99it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 35.32it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:05, 37.70it/s]
Loading 0:  49%|████▉     | 178/363 [00:04<00:05, 35.90it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 38.49it/s]
Loading 0:  52%|█████▏    | 187/363 [00:04<00:04, 37.32it/s]
Loading 0:  53%|█████▎    | 192/363 [00:05<00:04, 39.65it/s]
Loading 0:  54%|█████▍    | 197/363 [00:05<00:04, 39.52it/s]
Loading 0:  56%|█████▌    | 202/363 [00:05<00:04, 39.46it/s]
Loading 0:  57%|█████▋    | 206/363 [00:05<00:04, 39.13it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 38.83it/s]
Loading 0:  59%|█████▉    | 214/363 [00:05<00:03, 37.25it/s]
Loading 0:  60%|██████    | 218/363 [00:05<00:04, 35.53it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:05, 26.87it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:04, 28.69it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 28.31it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 33.65it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 33.98it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:03, 36.76it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:03, 35.86it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 38.09it/s]
Loading 0:  71%|███████▏  | 259/363 [00:06<00:02, 37.38it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 40.04it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 40.05it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 40.82it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:01, 42.79it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 34.66it/s]
Loading 0:  80%|███████▉  | 289/363 [00:07<00:01, 38.12it/s]
Loading 0:  81%|████████  | 294/363 [00:07<00:01, 37.47it/s]
Loading 0:  82%|████████▏ | 299/363 [00:08<00:01, 38.83it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:25,  2.32it/s]
Loading 0:  85%|████████▍ | 307/363 [00:15<00:19,  2.84it/s]
Loading 0:  86%|████████▌ | 312/363 [00:15<00:12,  4.07it/s]
Loading 0:  88%|████████▊ | 319/363 [00:15<00:06,  6.47it/s]
Loading 0:  89%|████████▉ | 323/363 [00:15<00:04,  8.06it/s]
Loading 0:  90%|█████████ | 328/363 [00:15<00:03, 10.78it/s]
Loading 0:  92%|█████████▏| 333/363 [00:15<00:02, 13.95it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 17.63it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:00, 21.66it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 25.21it/s]
Loading 0:  98%|█████████▊| 356/363 [00:16<00:00, 32.12it/s]
Loading 0: 100%|█████████▉| 362/363 [00:16<00:00, 33.80it/s]
                                                            
Job white-bird-1-dpo-v2-mkmlizer completed after 93.75s with status: succeeded
Stopping job with name white-bird-1-dpo-v2-mkmlizer
Pipeline stage MKMLizer completed in 94.22s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service white-bird-1-dpo-v2
Waiting for inference service white-bird-1-dpo-v2 to be ready
Inference service white-bird-1-dpo-v2 ready after 140.55569291114807s
Pipeline stage MKMLDeployer completed in 141.07s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6781094074249268s
Received healthy response to inference request in 1.5269124507904053s
Received healthy response to inference request in 1.6475334167480469s
Received healthy response to inference request in 1.5530624389648438s
Received healthy response to inference request in 1.6672694683074951s
5 requests
0 failed requests
5th percentile: 1.532142448425293
10th percentile: 1.5373724460601808
20th percentile: 1.547832441329956
30th percentile: 1.5719566345214844
40th percentile: 1.6097450256347656
50th percentile: 1.6475334167480469
60th percentile: 1.655427837371826
70th percentile: 1.6633222579956055
80th percentile: 1.8694374561309817
90th percentile: 2.273773431777954
95th percentile: 2.4759414196014404
99th percentile: 2.6376758098602293
mean time: 1.8145774364471436
Pipeline stage StressChecker completed in 10.52s
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 0.62s
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 0.72s
Shutdown handler de-registered
white-bird-1-dpo_v2 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 4042.57s
Shutdown handler de-registered
white-bird-1-dpo_v2 status is now inactive due to auto deactivation removed underperforming models
white-bird-1-dpo_v2 status is now torndown due to DeploymentManager action