white-bird-7-dpo

developer_uid: zhenzhe

submission_id: white-bird-7-dpo_v1

model_name: white-bird-7-dpo_v1

model_group: white-bird/7_dpo

status: torndown

timestamp: 2025-03-03T00:02:10+00:00

num_battles: 8744

num_wins: 4254

celo_rating: 1268.84

family_friendly_score: 0.43600000000000005

family_friendly_standard_error: 0.007012902394871898

submission_type: basic

model_repo: white-bird/7_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': 0.6064878909041489, 'latency_mean': 1.6487648391723633, 'latency_p50': 1.6460120677947998, 'latency_p90': 1.8122128248214722}, {'batch_size': 3, 'throughput': 1.1111476492239893, 'latency_mean': 2.690895719528198, 'latency_p50': 2.6855485439300537, 'latency_p90': 2.949471616744995}, {'batch_size': 5, 'throughput': 1.3586111117423016, 'latency_mean': 3.6681030189990995, 'latency_p50': 3.634233832359314, 'latency_p90': 4.147508215904236}, {'batch_size': 6, 'throughput': 1.419876428079014, 'latency_mean': 4.196741509437561, 'latency_p50': 4.206363677978516, 'latency_p90': 4.723691248893737}, {'batch_size': 8, 'throughput': 1.4774674860460641, 'latency_mean': 5.384539355039596, 'latency_p50': 5.395650148391724, 'latency_p90': 6.147029852867126}, {'batch_size': 10, 'throughput': 1.5128546270851617, 'latency_mean': 6.564057322740555, 'latency_p50': 6.541443228721619, 'latency_p90': 7.492340493202209}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: white-bird-7-dpo_v1

is_internal_developer: False

language_model: white-bird/7_dpo

model_size: 13B

ranking_group: single

throughput_3p7s: 1.37

us_pacific_date: 2025-03-02

win_ratio: 0.48650503202195794

generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.05, '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-7-dpo-v1-mkmlizer
Waiting for job on white-bird-7-dpo-v1-mkmlizer to finish
white-bird-7-dpo-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
white-bird-7-dpo-v1-mkmlizer: ║     _____            __           __                                ║
white-bird-7-dpo-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
white-bird-7-dpo-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
white-bird-7-dpo-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
white-bird-7-dpo-v1-mkmlizer: ║       /___/                                                         ║
white-bird-7-dpo-v1-mkmlizer: ║                                                                     ║
white-bird-7-dpo-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
white-bird-7-dpo-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
white-bird-7-dpo-v1-mkmlizer: ║  https://mk1.ai                                                     ║
white-bird-7-dpo-v1-mkmlizer: ║                                                                     ║
white-bird-7-dpo-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
white-bird-7-dpo-v1-mkmlizer: ║  belonging to:                                                      ║
white-bird-7-dpo-v1-mkmlizer: ║                                                                     ║
white-bird-7-dpo-v1-mkmlizer: ║  Chai Research Corp.                                                ║
white-bird-7-dpo-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
white-bird-7-dpo-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
white-bird-7-dpo-v1-mkmlizer: ║                                                                     ║
white-bird-7-dpo-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
white-bird-7-dpo-v1-mkmlizer: Downloaded to shared memory in 44.683s
white-bird-7-dpo-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkjusk6lj, device:0
white-bird-7-dpo-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
white-bird-7-dpo-v1-mkmlizer: quantized model in 36.094s
white-bird-7-dpo-v1-mkmlizer: Processed model white-bird/7_dpo in 80.777s
white-bird-7-dpo-v1-mkmlizer: creating bucket guanaco-mkml-models
white-bird-7-dpo-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/white-bird-7-dpo-v1/config.json
white-bird-7-dpo-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/white-bird-7-dpo-v1/special_tokens_map.json
white-bird-7-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/white-bird-7-dpo-v1/tokenizer_config.json
white-bird-7-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/white-bird-7-dpo-v1/tokenizer.json
white-bird-7-dpo-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/white-bird-7-dpo-v1/flywheel_model.0.safetensors
white-bird-7-dpo-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 29.75it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 50.32it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 45.37it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 44.55it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 50.80it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 47.47it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:06, 46.34it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 51.40it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 47.83it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:06, 48.20it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 31.51it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:07, 37.08it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 38.80it/s]
Loading 0:  22%|██▏       | 81/363 [00:01<00:07, 39.48it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:07, 39.23it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:06, 40.02it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:05, 45.57it/s]
Loading 0:  29%|██▉       | 105/363 [00:02<00:05, 43.50it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:05, 44.99it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 45.92it/s]
Loading 0:  33%|███▎      | 120/363 [00:02<00:05, 42.06it/s]
Loading 0:  34%|███▍      | 125/363 [00:02<00:05, 43.35it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 42.84it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 42.81it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 42.85it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:07, 27.81it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 28.59it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 35.81it/s]
Loading 0:  44%|████▍     | 161/363 [00:03<00:05, 37.22it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 38.77it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 41.32it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 35.21it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 41.58it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 41.31it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:04, 42.05it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:04, 40.85it/s]
Loading 0:  56%|█████▌    | 204/363 [00:05<00:03, 40.06it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 44.49it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 44.05it/s]
Loading 0:  61%|██████    | 221/363 [00:05<00:02, 47.95it/s]
Loading 0:  62%|██████▏   | 226/363 [00:05<00:04, 29.12it/s]
Loading 0:  63%|██████▎   | 230/363 [00:05<00:04, 29.70it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 36.78it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 38.33it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 39.57it/s]
Loading 0:  70%|██████▉   | 253/363 [00:06<00:02, 39.30it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 39.02it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 42.22it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 42.67it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:02, 43.22it/s]
Loading 0:  77%|███████▋  | 280/363 [00:06<00:02, 40.99it/s]
Loading 0:  79%|███████▊  | 285/363 [00:07<00:01, 40.50it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 43.70it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 43.79it/s]
Loading 0:  83%|████████▎ | 302/363 [00:07<00:01, 47.84it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:22,  2.51it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:14,  3.42it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.47it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:05,  7.36it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:03,  9.39it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.28it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:01, 16.65it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 19.86it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 25.97it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 29.13it/s]
                                                            
Job white-bird-7-dpo-v1-mkmlizer completed after 113.83s with status: succeeded
Stopping job with name white-bird-7-dpo-v1-mkmlizer
Pipeline stage MKMLizer completed in 114.29s
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-7-dpo-v1
Waiting for inference service white-bird-7-dpo-v1 to be ready
Inference service white-bird-7-dpo-v1 ready after 140.47166085243225s
Pipeline stage MKMLDeployer completed in 140.96s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.23634672164917s
Received healthy response to inference request in 1.5471630096435547s
Received healthy response to inference request in 1.7852308750152588s
Received healthy response to inference request in 1.6013708114624023s
Received healthy response to inference request in 1.6370134353637695s
5 requests
0 failed requests
5th percentile: 1.5580045700073242
10th percentile: 1.5688461303710937
20th percentile: 1.5905292510986329
30th percentile: 1.6084993362426758
40th percentile: 1.6227563858032226
50th percentile: 1.6370134353637695
60th percentile: 1.6963004112243651
70th percentile: 1.755587387084961
80th percentile: 1.875454044342041
90th percentile: 2.0559003829956053
95th percentile: 2.1461235523223876
99th percentile: 2.2183020877838135
mean time: 1.761424970626831
Pipeline stage StressChecker completed in 10.23s
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 0.64s
Shutdown handler de-registered
white-bird-7-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2492.56s
Shutdown handler de-registered
white-bird-7-dpo_v1 status is now inactive due to auto deactivation removed underperforming models
white-bird-7-dpo_v1 status is now torndown due to DeploymentManager action