leosheng-ft-dpo-10074

developer_uid: leosheng
submission_id: leosheng-ft-dpo-10074_v2
model_name: leosheng-ft-dpo-10074_v2
model_group: leosheng/ft-dpo-10074
status: torndown
timestamp: 2025-02-09T19:49:09+00:00
num_battles: 15003
num_wins: 6560
celo_rating: 1234.07
family_friendly_score: 0.5932
family_friendly_standard_error: 0.006947139843129689
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_v2
is_internal_developer: False
language_model: leosheng/ft-dpo-10074
model_size: 13B
ranking_group: single
us_pacific_date: 2025-02-09
win_ratio: 0.437245884156502
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-v2-mkmlizer
Waiting for job on leosheng-ft-dpo-10074-v2-mkmlizer to finish
leosheng-ft-dpo-10074-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
leosheng-ft-dpo-10074-v2-mkmlizer: ║     _____            __           __                                ║
leosheng-ft-dpo-10074-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
leosheng-ft-dpo-10074-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
leosheng-ft-dpo-10074-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
leosheng-ft-dpo-10074-v2-mkmlizer: ║       /___/                                                         ║
leosheng-ft-dpo-10074-v2-mkmlizer: ║                                                                     ║
leosheng-ft-dpo-10074-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
leosheng-ft-dpo-10074-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
leosheng-ft-dpo-10074-v2-mkmlizer: ║  https://mk1.ai                                                     ║
leosheng-ft-dpo-10074-v2-mkmlizer: ║                                                                     ║
leosheng-ft-dpo-10074-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
leosheng-ft-dpo-10074-v2-mkmlizer: ║  belonging to:                                                      ║
leosheng-ft-dpo-10074-v2-mkmlizer: ║                                                                     ║
leosheng-ft-dpo-10074-v2-mkmlizer: ║  Chai Research Corp.                                                ║
leosheng-ft-dpo-10074-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
leosheng-ft-dpo-10074-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
leosheng-ft-dpo-10074-v2-mkmlizer: ║                                                                     ║
leosheng-ft-dpo-10074-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
leosheng-ft-dpo-10074-v2-mkmlizer: Downloaded to shared memory in 45.460s
leosheng-ft-dpo-10074-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpn6z01miv, device:0
leosheng-ft-dpo-10074-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
leosheng-ft-dpo-10074-v2-mkmlizer: quantized model in 35.019s
leosheng-ft-dpo-10074-v2-mkmlizer: Processed model leosheng/ft-dpo-10074 in 80.479s
leosheng-ft-dpo-10074-v2-mkmlizer: creating bucket guanaco-mkml-models
leosheng-ft-dpo-10074-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
leosheng-ft-dpo-10074-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/leosheng-ft-dpo-10074-v2
leosheng-ft-dpo-10074-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/leosheng-ft-dpo-10074-v2/config.json
leosheng-ft-dpo-10074-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/leosheng-ft-dpo-10074-v2/special_tokens_map.json
leosheng-ft-dpo-10074-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/leosheng-ft-dpo-10074-v2/tokenizer_config.json
leosheng-ft-dpo-10074-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/leosheng-ft-dpo-10074-v2/tokenizer.json
leosheng-ft-dpo-10074-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/leosheng-ft-dpo-10074-v2/flywheel_model.0.safetensors
leosheng-ft-dpo-10074-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 31.71it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 48.48it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:06, 50.60it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 43.22it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 49.67it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 46.96it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:06, 46.04it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 51.30it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 48.06it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 34.82it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 36.16it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 40.63it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 40.41it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 40.54it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:05, 45.78it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 43.93it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 43.07it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:05, 44.40it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 48.05it/s]
Loading 0:  32%|███▏      | 117/363 [00:02<00:05, 45.66it/s]
Loading 0:  34%|███▎      | 122/363 [00:02<00:05, 44.70it/s]
Loading 0:  35%|███▍      | 127/363 [00:02<00:06, 37.02it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:05, 44.17it/s]
Loading 0:  38%|███▊      | 139/363 [00:03<00:05, 44.53it/s]
Loading 0:  40%|███▉      | 144/363 [00:03<00:07, 28.22it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:06, 30.60it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 37.71it/s]
Loading 0:  44%|████▍     | 161/363 [00:03<00:05, 38.96it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:04, 39.72it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:04, 38.62it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 39.37it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 44.24it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:03, 44.34it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 44.37it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 42.57it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 42.34it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 45.62it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 45.21it/s]
Loading 0:  61%|██████    | 221/363 [00:05<00:02, 49.05it/s]
Loading 0:  62%|██████▏   | 226/363 [00:05<00:05, 27.23it/s]
Loading 0:  63%|██████▎   | 230/363 [00:05<00:04, 28.43it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 36.27it/s]
Loading 0:  67%|██████▋   | 242/363 [00:05<00:03, 38.54it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 39.91it/s]
Loading 0:  70%|██████▉   | 253/363 [00:06<00:02, 39.12it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 39.41it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 44.34it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 44.46it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:02, 43.54it/s]
Loading 0:  77%|███████▋  | 279/363 [00:06<00:01, 44.87it/s]
Loading 0:  78%|███████▊  | 284/363 [00:06<00:02, 38.49it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 45.24it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 45.13it/s]
Loading 0:  83%|████████▎ | 303/363 [00:07<00:01, 45.13it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:20,  2.63it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:15,  3.36it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.43it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:05,  7.34it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:03,  9.42it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.35it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:01, 16.73it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 19.97it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 26.14it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 29.44it/s]
                                                            
Job leosheng-ft-dpo-10074-v2-mkmlizer completed after 113.71s with status: succeeded
Stopping job with name leosheng-ft-dpo-10074-v2-mkmlizer
Pipeline stage MKMLizer completed in 114.19s
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-v2
Waiting for inference service leosheng-ft-dpo-10074-v2 to be ready
Inference service leosheng-ft-dpo-10074-v2 ready after 190.77080869674683s
Pipeline stage MKMLDeployer completed in 191.29s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0730676651000977s
Received healthy response to inference request in 1.707625150680542s
Received healthy response to inference request in 1.930185079574585s
Received healthy response to inference request in 1.2971630096435547s
Received healthy response to inference request in 1.4167149066925049s
5 requests
0 failed requests
5th percentile: 1.3210733890533448
10th percentile: 1.3449837684631347
20th percentile: 1.3928045272827148
30th percentile: 1.4748969554901123
40th percentile: 1.591261053085327
50th percentile: 1.707625150680542
60th percentile: 1.796649122238159
70th percentile: 1.8856730937957764
80th percentile: 1.9587615966796876
90th percentile: 2.0159146308898928
95th percentile: 2.044491147994995
99th percentile: 2.067352361679077
mean time: 1.684951162338257
Pipeline stage StressChecker completed in 9.89s
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 0.72s
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 0.77s
Shutdown handler de-registered
leosheng-ft-dpo-10074_v2 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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service leosheng-ft-dpo-10074-v2-profiler
Waiting for inference service leosheng-ft-dpo-10074-v2-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
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 5178.00s
Shutdown handler de-registered
leosheng-ft-dpo-10074_v2 status is now inactive due to auto deactivation removed underperforming models
leosheng-ft-dpo-10074_v2 status is now torndown due to DeploymentManager action
leosheng-ft-dpo-10074_v2 status is now torndown due to DeploymentManager action
leosheng-ft-dpo-10074_v2 status is now torndown due to DeploymentManager action