leosheng-ft-dpo-10074

developer_uid: leosheng

submission_id: leosheng-ft-dpo-10074_v1

model_name: leosheng-ft-dpo-10074_v1

model_group: leosheng/ft-dpo-10074

status: torndown

timestamp: 2025-02-07T05:42:52+00:00

num_battles: 7034

num_wins: 3324

celo_rating: 1240.63

family_friendly_score: 0.5873999999999999

family_friendly_standard_error: 0.006962201376001702

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_v1

is_internal_developer: False

language_model: leosheng/ft-dpo-10074

model_size: 13B

ranking_group: single

us_pacific_date: 2025-02-06

win_ratio: 0.4725618424793858

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{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-v1-mkmlizer
Waiting for job on leosheng-ft-dpo-10074-v1-mkmlizer to finish
leosheng-ft-dpo-10074-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
leosheng-ft-dpo-10074-v1-mkmlizer: ║     _____            __           __                                ║
leosheng-ft-dpo-10074-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
leosheng-ft-dpo-10074-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
leosheng-ft-dpo-10074-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
leosheng-ft-dpo-10074-v1-mkmlizer: ║       /___/                                                         ║
leosheng-ft-dpo-10074-v1-mkmlizer: ║                                                                     ║
leosheng-ft-dpo-10074-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
leosheng-ft-dpo-10074-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
leosheng-ft-dpo-10074-v1-mkmlizer: ║  https://mk1.ai                                                     ║
leosheng-ft-dpo-10074-v1-mkmlizer: ║                                                                     ║
leosheng-ft-dpo-10074-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
leosheng-ft-dpo-10074-v1-mkmlizer: ║  belonging to:                                                      ║
leosheng-ft-dpo-10074-v1-mkmlizer: ║                                                                     ║
leosheng-ft-dpo-10074-v1-mkmlizer: ║  Chai Research Corp.                                                ║
leosheng-ft-dpo-10074-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
leosheng-ft-dpo-10074-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
leosheng-ft-dpo-10074-v1-mkmlizer: ║                                                                     ║
leosheng-ft-dpo-10074-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
leosheng-ft-dpo-10074-v1-mkmlizer: Downloaded to shared memory in 47.105s
leosheng-ft-dpo-10074-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4sfrrg4u, device:0
leosheng-ft-dpo-10074-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
leosheng-ft-dpo-10074-v1-mkmlizer: quantized model in 35.928s
leosheng-ft-dpo-10074-v1-mkmlizer: Processed model leosheng/ft-dpo-10074 in 83.033s
leosheng-ft-dpo-10074-v1-mkmlizer: creating bucket guanaco-mkml-models
leosheng-ft-dpo-10074-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
leosheng-ft-dpo-10074-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/leosheng-ft-dpo-10074-v1
leosheng-ft-dpo-10074-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/leosheng-ft-dpo-10074-v1/config.json
leosheng-ft-dpo-10074-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/leosheng-ft-dpo-10074-v1/special_tokens_map.json
leosheng-ft-dpo-10074-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/leosheng-ft-dpo-10074-v1/tokenizer_config.json
leosheng-ft-dpo-10074-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/leosheng-ft-dpo-10074-v1/tokenizer.json
leosheng-ft-dpo-10074-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/leosheng-ft-dpo-10074-v1/flywheel_model.0.safetensors
leosheng-ft-dpo-10074-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 32.73it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 51.54it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 45.94it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 44.70it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 50.66it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 46.59it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 45.17it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 50.27it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 45.92it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 34.73it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 34.19it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 40.61it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:06, 42.49it/s]
Loading 0:  23%|██▎       | 82/363 [00:01<00:07, 35.79it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 42.64it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 42.49it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:06, 43.13it/s]
Loading 0:  29%|██▊       | 104/363 [00:02<00:05, 44.51it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:06, 42.05it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 42.46it/s]
Loading 0:  33%|███▎      | 120/363 [00:02<00:05, 40.55it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:05, 43.28it/s]
Loading 0:  36%|███▌      | 131/363 [00:03<00:05, 44.02it/s]
Loading 0:  37%|███▋      | 136/363 [00:03<00:06, 34.72it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:07, 29.76it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:07, 30.79it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 30.85it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 36.45it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 36.51it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 38.76it/s]
Loading 0:  47%|████▋     | 170/363 [00:04<00:04, 40.15it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 41.19it/s]
Loading 0:  50%|████▉     | 180/363 [00:04<00:04, 41.12it/s]
Loading 0:  51%|█████     | 185/363 [00:04<00:05, 34.24it/s]
Loading 0:  53%|█████▎    | 192/363 [00:04<00:04, 41.54it/s]
Loading 0:  54%|█████▍    | 197/363 [00:04<00:03, 41.94it/s]
Loading 0:  56%|█████▌    | 202/363 [00:05<00:03, 41.93it/s]
Loading 0:  57%|█████▋    | 207/363 [00:05<00:03, 43.20it/s]
Loading 0:  58%|█████▊    | 212/363 [00:05<00:04, 34.94it/s]
Loading 0:  60%|██████    | 218/363 [00:05<00:03, 39.00it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:04, 30.87it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 32.27it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 30.94it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 36.62it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 36.80it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:02, 39.09it/s]
Loading 0:  69%|██████▉   | 251/363 [00:06<00:02, 39.74it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 40.03it/s]
Loading 0:  72%|███████▏  | 261/363 [00:06<00:02, 42.47it/s]
Loading 0:  73%|███████▎  | 266/363 [00:06<00:02, 34.98it/s]
Loading 0:  75%|███████▌  | 273/363 [00:06<00:02, 41.95it/s]
Loading 0:  77%|███████▋  | 278/363 [00:07<00:02, 42.19it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:01, 41.35it/s]
Loading 0:  79%|███████▉  | 288/363 [00:07<00:01, 41.69it/s]
Loading 0:  81%|████████  | 293/363 [00:07<00:02, 34.16it/s]
Loading 0:  82%|████████▏ | 298/363 [00:07<00:01, 37.24it/s]
Loading 0:  83%|████████▎ | 303/363 [00:07<00:01, 38.62it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:23,  2.36it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:16,  3.08it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:08,  5.15it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:05,  7.04it/s]
Loading 0:  91%|█████████ | 331/363 [00:15<00:03,  9.08it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 12.96it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:01, 16.16it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 19.10it/s]
Loading 0:  98%|█████████▊| 355/363 [00:15<00:00, 24.18it/s]
Loading 0:  99%|█████████▉| 360/363 [00:15<00:00, 27.65it/s]
                                                            
Job leosheng-ft-dpo-10074-v1-mkmlizer completed after 104.04s with status: succeeded
Stopping job with name leosheng-ft-dpo-10074-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.59s
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-v1
Waiting for inference service leosheng-ft-dpo-10074-v1 to be ready
Retrying (%r) after connection broken by '%r': %s
Inference service leosheng-ft-dpo-10074-v1 ready after 180.63394904136658s
Pipeline stage MKMLDeployer completed in 181.20s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1054775714874268s
Received healthy response to inference request in 1.6280043125152588s
Received healthy response to inference request in 1.8324038982391357s
Received healthy response to inference request in 1.668050765991211s
Received healthy response to inference request in 2.2065885066986084s
5 requests
0 failed requests
5th percentile: 1.6360136032104493
10th percentile: 1.6440228939056396
20th percentile: 1.6600414752960204
30th percentile: 1.700921392440796
40th percentile: 1.7666626453399659
50th percentile: 1.8324038982391357
60th percentile: 1.941633367538452
70th percentile: 2.0508628368377684
80th percentile: 2.125699758529663
90th percentile: 2.1661441326141357
95th percentile: 2.186366319656372
99th percentile: 2.202544069290161
mean time: 1.8881050109863282
Pipeline stage StressChecker completed in 10.57s
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 0.56s
Shutdown handler de-registered
leosheng-ft-dpo-10074_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 4384.68s
Shutdown handler de-registered
leosheng-ft-dpo-10074_v1 status is now inactive due to auto deactivation removed underperforming models
leosheng-ft-dpo-10074_v1 status is now torndown due to DeploymentManager action