white-bird-7-dpo

developer_uid: zhenzhe

submission_id: white-bird-7-dpo_v3

model_name: white-bird-7-dpo_v3

model_group: white-bird/7_dpo

status: torndown

timestamp: 2025-03-03T03:23:39+00:00

num_battles: 8750

num_wins: 4260

celo_rating: 1270.96

family_friendly_score: 0.4444

family_friendly_standard_error: 0.007027213387965389

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': 0.6085598213632334, 'latency_mean': 1.6431538581848144, 'latency_p50': 1.6345614194869995, 'latency_p90': 1.8223535776138307}, {'batch_size': 3, 'throughput': 1.121459961886146, 'latency_mean': 2.6687701046466827, 'latency_p50': 2.669202446937561, 'latency_p90': 2.9284298419952393}, {'batch_size': 5, 'throughput': 1.3600743085032505, 'latency_mean': 3.660959746837616, 'latency_p50': 3.6555469036102295, 'latency_p90': 4.155364084243774}, {'batch_size': 6, 'throughput': 1.427985558222456, 'latency_mean': 4.18924922823906, 'latency_p50': 4.193381667137146, 'latency_p90': 4.677251672744751}, {'batch_size': 8, 'throughput': 1.4949645462632952, 'latency_mean': 5.317733044624329, 'latency_p50': 5.290575623512268, 'latency_p90': 6.038129448890686}, {'batch_size': 10, 'throughput': 1.521436024865043, 'latency_mean': 6.515547946691513, 'latency_p50': 6.48023247718811, 'latency_p90': 7.279646849632263}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: white-bird-7-dpo_v3

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: 0.4868571428571429

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', '</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-7-dpo-v3-mkmlizer
Waiting for job on white-bird-7-dpo-v3-mkmlizer to finish
white-bird-7-dpo-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
white-bird-7-dpo-v3-mkmlizer: ║     _____            __           __                                ║
white-bird-7-dpo-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
white-bird-7-dpo-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
white-bird-7-dpo-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
white-bird-7-dpo-v3-mkmlizer: ║       /___/                                                         ║
white-bird-7-dpo-v3-mkmlizer: ║                                                                     ║
white-bird-7-dpo-v3-mkmlizer: ║  Version: 0.12.8                                                    ║
white-bird-7-dpo-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
white-bird-7-dpo-v3-mkmlizer: ║  https://mk1.ai                                                     ║
white-bird-7-dpo-v3-mkmlizer: ║                                                                     ║
white-bird-7-dpo-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
white-bird-7-dpo-v3-mkmlizer: ║  belonging to:                                                      ║
white-bird-7-dpo-v3-mkmlizer: ║                                                                     ║
white-bird-7-dpo-v3-mkmlizer: ║  Chai Research Corp.                                                ║
white-bird-7-dpo-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
white-bird-7-dpo-v3-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
white-bird-7-dpo-v3-mkmlizer: ║                                                                     ║
white-bird-7-dpo-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
white-bird-7-dpo-v3-mkmlizer: Downloaded to shared memory in 42.123s
white-bird-7-dpo-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp27_67bl5, device:0
white-bird-7-dpo-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
white-bird-7-dpo-v3-mkmlizer: quantized model in 36.118s
white-bird-7-dpo-v3-mkmlizer: Processed model white-bird/7_dpo in 78.241s
white-bird-7-dpo-v3-mkmlizer: creating bucket guanaco-mkml-models
white-bird-7-dpo-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
white-bird-7-dpo-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/white-bird-7-dpo-v3
white-bird-7-dpo-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/white-bird-7-dpo-v3/config.json
white-bird-7-dpo-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/white-bird-7-dpo-v3/special_tokens_map.json
white-bird-7-dpo-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/white-bird-7-dpo-v3/tokenizer_config.json
white-bird-7-dpo-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/white-bird-7-dpo-v3/tokenizer.json
white-bird-7-dpo-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/white-bird-7-dpo-v3/flywheel_model.0.safetensors
white-bird-7-dpo-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 32.37it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 51.29it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 45.56it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 44.64it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 51.10it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 46.81it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 45.50it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 50.47it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 46.99it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 35.96it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 37.00it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 40.86it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:06, 42.69it/s]
Loading 0:  23%|██▎       | 82/363 [00:01<00:07, 37.53it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 45.12it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 42.86it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 41.20it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:06, 41.60it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 44.65it/s]
Loading 0:  32%|███▏      | 117/363 [00:02<00:05, 41.69it/s]
Loading 0:  34%|███▍      | 123/363 [00:02<00:05, 40.53it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:05, 40.23it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:05, 44.13it/s]
Loading 0:  38%|███▊      | 139/363 [00:03<00:05, 44.21it/s]
Loading 0:  40%|███▉      | 144/363 [00:03<00:08, 26.79it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 29.21it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 36.36it/s]
Loading 0:  44%|████▍     | 161/363 [00:03<00:05, 37.65it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 38.44it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 40.90it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 34.54it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 41.38it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 41.59it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 42.52it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:04, 40.74it/s]
Loading 0:  56%|█████▌    | 204/363 [00:05<00:03, 40.37it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 44.96it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 45.39it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 46.54it/s]
Loading 0:  62%|██████▏   | 225/363 [00:05<00:04, 29.21it/s]
Loading 0:  63%|██████▎   | 230/363 [00:05<00:04, 31.78it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 38.57it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 39.69it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 41.33it/s]
Loading 0:  70%|██████▉   | 253/363 [00:06<00:02, 40.71it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 38.72it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 42.69it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 42.75it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:02, 41.76it/s]
Loading 0:  77%|███████▋  | 280/363 [00:06<00:02, 40.20it/s]
Loading 0:  79%|███████▊  | 285/363 [00:07<00:02, 37.28it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 42.07it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 43.01it/s]
Loading 0:  83%|████████▎ | 302/363 [00:07<00:01, 46.95it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:22,  2.52it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:14,  3.43it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.49it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:05,  7.37it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:03,  9.37it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.22it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:01, 16.45it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 19.50it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 25.39it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 28.42it/s]
                                                            
Job white-bird-7-dpo-v3-mkmlizer completed after 104.08s with status: succeeded
Stopping job with name white-bird-7-dpo-v3-mkmlizer
Pipeline stage MKMLizer completed in 104.57s
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-7-dpo-v3
Waiting for inference service white-bird-7-dpo-v3 to be ready
Inference service white-bird-7-dpo-v3 ready after 141.16974592208862s
Pipeline stage MKMLDeployer completed in 141.59s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4482457637786865s
Received healthy response to inference request in 1.6391119956970215s
Received healthy response to inference request in 1.9582159519195557s
Received healthy response to inference request in 1.5122511386871338s
Received healthy response to inference request in 1.599485158920288s
5 requests
0 failed requests
5th percentile: 1.5296979427337647
10th percentile: 1.5471447467803956
20th percentile: 1.5820383548736572
30th percentile: 1.6074105262756349
40th percentile: 1.6232612609863282
50th percentile: 1.6391119956970215
60th percentile: 1.766753578186035
70th percentile: 1.8943951606750489
80th percentile: 2.056221914291382
90th percentile: 2.2522338390350343
95th percentile: 2.35023980140686
99th percentile: 2.4286445713043214
mean time: 1.8314620018005372
Pipeline stage StressChecker completed in 10.61s
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 0.63s
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 0.65s
Shutdown handler de-registered
white-bird-7-dpo_v3 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 2509.02s
Shutdown handler de-registered
white-bird-7-dpo_v3 status is now inactive due to auto deactivation removed underperforming models
white-bird-7-dpo_v3 status is now torndown due to DeploymentManager action