leosheng-ft-dpo-10074

developer_uid: huohuo12
submission_id: leosheng-ft-dpo-10074_v8
model_name: leosheng-ft-dpo-10074_v4
model_group: leosheng/ft-dpo-10074
status: torndown
timestamp: 2025-02-12T06:36:52+00:00
num_battles: 6051
num_wins: 2857
celo_rating: 1231.57
family_friendly_score: 0.5846
family_friendly_standard_error: 0.006969115295358515
submission_type: basic
model_repo: leosheng/ft-dpo-10074
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
display_name: leosheng-ft-dpo-10074_v4
is_internal_developer: False
language_model: leosheng/ft-dpo-10074
model_size: 13B
ranking_group: single
us_pacific_date: 2025-02-11
win_ratio: 0.47215336308048256
generation_params: {'temperature': 1.3, 'top_p': 0.88, 'min_p': 0.015, 'top_k': 45, 'presence_penalty': 0.55, 'frequency_penalty': 0.25, 'stopping_words': ['\n'], '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 leosheng-ft-dpo-10074-v8-mkmlizer
Waiting for job on leosheng-ft-dpo-10074-v8-mkmlizer to finish
leosheng-ft-dpo-10074-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
leosheng-ft-dpo-10074-v8-mkmlizer: ║     _____            __           __                                ║
leosheng-ft-dpo-10074-v8-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
leosheng-ft-dpo-10074-v8-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
leosheng-ft-dpo-10074-v8-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
leosheng-ft-dpo-10074-v8-mkmlizer: ║       /___/                                                         ║
leosheng-ft-dpo-10074-v8-mkmlizer: ║                                                                     ║
leosheng-ft-dpo-10074-v8-mkmlizer: ║  Version: 0.11.12                                                   ║
leosheng-ft-dpo-10074-v8-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
leosheng-ft-dpo-10074-v8-mkmlizer: ║  https://mk1.ai                                                     ║
leosheng-ft-dpo-10074-v8-mkmlizer: ║                                                                     ║
leosheng-ft-dpo-10074-v8-mkmlizer: ║  The license key for the current software has been verified as      ║
leosheng-ft-dpo-10074-v8-mkmlizer: ║  belonging to:                                                      ║
leosheng-ft-dpo-10074-v8-mkmlizer: ║                                                                     ║
leosheng-ft-dpo-10074-v8-mkmlizer: ║  Chai Research Corp.                                                ║
leosheng-ft-dpo-10074-v8-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
leosheng-ft-dpo-10074-v8-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
leosheng-ft-dpo-10074-v8-mkmlizer: ║                                                                     ║
leosheng-ft-dpo-10074-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
leosheng-ft-dpo-10074-v8-mkmlizer: Downloaded to shared memory in 30.636s
leosheng-ft-dpo-10074-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6yxtle_o, device:0
leosheng-ft-dpo-10074-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
leosheng-ft-dpo-10074-v8-mkmlizer: quantized model in 36.099s
leosheng-ft-dpo-10074-v8-mkmlizer: Processed model leosheng/ft-dpo-10074 in 66.735s
leosheng-ft-dpo-10074-v8-mkmlizer: creating bucket guanaco-mkml-models
leosheng-ft-dpo-10074-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
leosheng-ft-dpo-10074-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/leosheng-ft-dpo-10074-v8
leosheng-ft-dpo-10074-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/leosheng-ft-dpo-10074-v8/config.json
leosheng-ft-dpo-10074-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/leosheng-ft-dpo-10074-v8/special_tokens_map.json
leosheng-ft-dpo-10074-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/leosheng-ft-dpo-10074-v8/tokenizer_config.json
leosheng-ft-dpo-10074-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/leosheng-ft-dpo-10074-v8/tokenizer.json
leosheng-ft-dpo-10074-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/leosheng-ft-dpo-10074-v8/flywheel_model.0.safetensors
leosheng-ft-dpo-10074-v8-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 34.40it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 53.40it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 46.78it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 45.15it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 50.85it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 46.90it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 45.45it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 50.34it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 46.66it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 30.34it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 30.70it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 37.27it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:07, 39.92it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:07, 35.49it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 43.43it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 41.83it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 41.16it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 47.40it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:05, 42.88it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:05, 41.99it/s]
Loading 0:  34%|███▍      | 125/363 [00:02<00:05, 45.51it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 45.13it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 44.75it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 44.34it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:08, 25.18it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:08, 26.51it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:06, 33.70it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 36.04it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 38.37it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:04, 38.46it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 38.31it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 42.10it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 41.54it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:04, 42.05it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:04, 40.00it/s]
Loading 0:  56%|█████▌    | 204/363 [00:05<00:04, 39.68it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 44.23it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 44.06it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 44.16it/s]
Loading 0:  62%|██████▏   | 225/363 [00:05<00:05, 24.76it/s]
Loading 0:  63%|██████▎   | 230/363 [00:05<00:04, 27.39it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 34.09it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 35.79it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 37.90it/s]
Loading 0:  70%|██████▉   | 253/363 [00:06<00:02, 37.29it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 37.10it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 41.89it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 42.90it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:02, 43.18it/s]
Loading 0:  77%|███████▋  | 280/363 [00:07<00:02, 41.06it/s]
Loading 0:  79%|███████▊  | 285/363 [00:07<00:01, 40.79it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 45.17it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 45.22it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 46.00it/s]
Loading 0:  84%|████████▍ | 306/363 [00:14<00:23,  2.45it/s]
Loading 0:  85%|████████▌ | 310/363 [00:14<00:16,  3.20it/s]
Loading 0:  87%|████████▋ | 314/363 [00:14<00:11,  4.21it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  6.30it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  8.78it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:02, 11.37it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 16.23it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:00, 19.86it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 23.06it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 29.47it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 32.16it/s]
                                                            
Job leosheng-ft-dpo-10074-v8-mkmlizer completed after 93.74s with status: succeeded
Stopping job with name leosheng-ft-dpo-10074-v8-mkmlizer
Pipeline stage MKMLizer completed in 94.20s
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 leosheng-ft-dpo-10074-v8
Waiting for inference service leosheng-ft-dpo-10074-v8 to be ready
Failed to get response for submission leosheng-ft-dpo-10074_v4: HTTPConnectionPool(host='leosheng-ft-dpo-10074-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service leosheng-ft-dpo-10074-v8 ready after 221.05006384849548s
Pipeline stage MKMLDeployer completed in 221.60s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.4884445667266846s
Received healthy response to inference request in 1.0751187801361084s
Received healthy response to inference request in 1.0598878860473633s
Received healthy response to inference request in 1.214768648147583s
Received healthy response to inference request in 1.0979692935943604s
5 requests
0 failed requests
5th percentile: 1.0629340648651122
10th percentile: 1.0659802436828614
20th percentile: 1.0720726013183595
30th percentile: 1.0796888828277589
40th percentile: 1.0888290882110596
50th percentile: 1.0979692935943604
60th percentile: 1.1446890354156494
70th percentile: 1.1914087772369384
80th percentile: 1.2695038318634033
90th percentile: 1.378974199295044
95th percentile: 1.4337093830108643
99th percentile: 1.4774975299835205
mean time: 1.18723783493042
Pipeline stage StressChecker completed in 7.28s
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 0.78s
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 0.67s
Shutdown handler de-registered
leosheng-ft-dpo-10074_v8 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service leosheng-ft-dpo-10074-v8-profiler
Waiting for inference service leosheng-ft-dpo-10074-v8-profiler to be ready
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 2336.35s
Shutdown handler de-registered
leosheng-ft-dpo-10074_v8 status is now inactive due to auto deactivation removed underperforming models
leosheng-ft-dpo-10074_v8 status is now torndown due to DeploymentManager action
leosheng-ft-dpo-10074_v8 status is now torndown due to DeploymentManager action
leosheng-ft-dpo-10074_v8 status is now torndown due to DeploymentManager action