leosheng-ft-dpo-219

developer_uid: huohuo12
submission_id: leosheng-ft-dpo-219_v9
model_name: alexxi19-ft-v1-violet_v8
model_group: leosheng/ft-dpo-219
status: torndown
timestamp: 2025-02-11T08:54:26+00:00
num_battles: 8488
num_wins: 4011
celo_rating: 1237.13
family_friendly_score: 0.5818
family_friendly_standard_error: 0.006975797588806602
submission_type: basic
model_repo: leosheng/ft-dpo-219
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
display_name: alexxi19-ft-v1-violet_v8
is_internal_developer: False
language_model: leosheng/ft-dpo-219
model_size: 13B
ranking_group: single
us_pacific_date: 2025-02-11
win_ratio: 0.47254948162111216
generation_params: {'temperature': 0.8, 'top_p': 0.8, 'min_p': 0.04, 'top_k': 49, 'presence_penalty': 0.8, 'frequency_penalty': 0.4, '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-219-v9-mkmlizer
Waiting for job on leosheng-ft-dpo-219-v9-mkmlizer to finish
leosheng-ft-dpo-219-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
leosheng-ft-dpo-219-v9-mkmlizer: ║     _____            __           __                                ║
leosheng-ft-dpo-219-v9-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
leosheng-ft-dpo-219-v9-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
leosheng-ft-dpo-219-v9-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
leosheng-ft-dpo-219-v9-mkmlizer: ║       /___/                                                         ║
leosheng-ft-dpo-219-v9-mkmlizer: ║                                                                     ║
leosheng-ft-dpo-219-v9-mkmlizer: ║  Version: 0.11.12                                                   ║
leosheng-ft-dpo-219-v9-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
leosheng-ft-dpo-219-v9-mkmlizer: ║  https://mk1.ai                                                     ║
leosheng-ft-dpo-219-v9-mkmlizer: ║                                                                     ║
leosheng-ft-dpo-219-v9-mkmlizer: ║  The license key for the current software has been verified as      ║
leosheng-ft-dpo-219-v9-mkmlizer: ║  belonging to:                                                      ║
leosheng-ft-dpo-219-v9-mkmlizer: ║                                                                     ║
leosheng-ft-dpo-219-v9-mkmlizer: ║  Chai Research Corp.                                                ║
leosheng-ft-dpo-219-v9-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
leosheng-ft-dpo-219-v9-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
leosheng-ft-dpo-219-v9-mkmlizer: ║                                                                     ║
leosheng-ft-dpo-219-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
leosheng-ft-dpo-219-v9-mkmlizer: Downloaded to shared memory in 34.875s
leosheng-ft-dpo-219-v9-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplpiifb57, device:0
leosheng-ft-dpo-219-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
leosheng-ft-dpo-219-v9-mkmlizer: quantized model in 35.748s
leosheng-ft-dpo-219-v9-mkmlizer: Processed model leosheng/ft-dpo-219 in 70.623s
leosheng-ft-dpo-219-v9-mkmlizer: creating bucket guanaco-mkml-models
leosheng-ft-dpo-219-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
leosheng-ft-dpo-219-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/leosheng-ft-dpo-219-v9
leosheng-ft-dpo-219-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/leosheng-ft-dpo-219-v9/special_tokens_map.json
leosheng-ft-dpo-219-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/leosheng-ft-dpo-219-v9/tokenizer_config.json
leosheng-ft-dpo-219-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/leosheng-ft-dpo-219-v9/tokenizer.json
leosheng-ft-dpo-219-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/leosheng-ft-dpo-219-v9/flywheel_model.0.safetensors
leosheng-ft-dpo-219-v9-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 29.68it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 46.42it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 47.64it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:08, 40.06it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 50.98it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 48.62it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:06, 49.11it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 50.48it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 47.72it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:07, 38.06it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:07, 37.51it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 41.57it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 41.82it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 41.71it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:05, 45.93it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 45.03it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:05, 44.34it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:04, 52.44it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 44.76it/s]
Loading 0:  33%|███▎      | 120/363 [00:02<00:05, 42.39it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:05, 45.36it/s]
Loading 0:  36%|███▋      | 132/363 [00:02<00:05, 44.47it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:05, 43.36it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 32.87it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 33.96it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 33.06it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 38.77it/s]
Loading 0:  44%|████▍     | 161/363 [00:03<00:04, 41.09it/s]
Loading 0:  46%|████▌     | 166/363 [00:03<00:04, 43.04it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:04, 42.30it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 41.61it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:03, 46.24it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:03, 46.68it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 47.42it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 45.62it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 44.80it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 49.26it/s]
Loading 0:  60%|█████▉    | 217/363 [00:04<00:03, 45.87it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:03, 36.26it/s]
Loading 0:  63%|██████▎   | 228/363 [00:05<00:03, 36.62it/s]
Loading 0:  64%|██████▍   | 232/363 [00:05<00:03, 35.80it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 38.78it/s]
Loading 0:  67%|██████▋   | 242/363 [00:05<00:02, 40.61it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:02, 42.41it/s]
Loading 0:  70%|██████▉   | 253/363 [00:05<00:02, 41.57it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 40.77it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 45.80it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 45.00it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:02, 43.13it/s]
Loading 0:  78%|███████▊  | 282/363 [00:06<00:01, 46.60it/s]
Loading 0:  79%|███████▉  | 287/363 [00:06<00:01, 46.59it/s]
Loading 0:  80%|████████  | 292/363 [00:06<00:01, 46.66it/s]
Loading 0:  82%|████████▏ | 298/363 [00:06<00:01, 45.94it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:22,  2.60it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:16,  3.32it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:11,  4.29it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  7.06it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:03,  9.49it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:02, 11.96it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 16.72it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 20.68it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 23.63it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 30.30it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 33.77it/s]
                                                            
Job leosheng-ft-dpo-219-v9-mkmlizer completed after 93.51s with status: succeeded
Stopping job with name leosheng-ft-dpo-219-v9-mkmlizer
Pipeline stage MKMLizer completed in 93.94s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service leosheng-ft-dpo-219-v9
Waiting for inference service leosheng-ft-dpo-219-v9 to be ready
Inference service leosheng-ft-dpo-219-v9 ready after 210.93805289268494s
Pipeline stage MKMLDeployer completed in 211.46s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8808670043945312s
Received healthy response to inference request in 1.2842762470245361s
Received healthy response to inference request in 1.1477713584899902s
Received healthy response to inference request in 1.5981321334838867s
Received healthy response to inference request in 1.1557862758636475s
5 requests
0 failed requests
5th percentile: 1.1493743419647218
10th percentile: 1.150977325439453
20th percentile: 1.154183292388916
30th percentile: 1.1814842700958252
40th percentile: 1.2328802585601806
50th percentile: 1.2842762470245361
60th percentile: 1.4098186016082763
70th percentile: 1.5353609561920165
80th percentile: 1.6546791076660157
90th percentile: 1.7677730560302733
95th percentile: 1.8243200302124023
99th percentile: 1.8695576095581055
mean time: 1.4133666038513184
Pipeline stage StressChecker completed in 8.36s
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 0.62s
Shutdown handler de-registered
leosheng-ft-dpo-219_v9 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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service leosheng-ft-dpo-219-v9-profiler
Waiting for inference service leosheng-ft-dpo-219-v9-profiler to be ready
Inference service leosheng-ft-dpo-219-v9-profiler ready after 210.7881875038147s
Pipeline stage MKMLProfilerDeployer completed in 211.18s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/leosheng-ft-dpo-219-v9-profiler-predictor-00001-deployment6gmkv:/code/chaiverse_profiler_1739264635 --namespace tenant-chaiml-guanaco
kubectl exec -it leosheng-ft-dpo-219-v9-profiler-predictor-00001-deployment6gmkv --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1739264635 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1739264635/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/leosheng-ft-dpo-219-v9-profiler-predictor-00001-deployment6gmkv:/code/chaiverse_profiler_1739264639 --namespace tenant-chaiml-guanaco
kubectl exec -it leosheng-ft-dpo-219-v9-profiler-predictor-00001-deployment6gmkv --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1739264639 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1739264639/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/leosheng-ft-dpo-219-v9-profiler-predictor-00001-deployment6gmkv:/code/chaiverse_profiler_1739264642 --namespace tenant-chaiml-guanaco
kubectl exec -it leosheng-ft-dpo-219-v9-profiler-predictor-00001-deployment6gmkv --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1739264642 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1739264642/summary.json'
clean up pipeline due to error=ISVCScriptError('Command failed with error: Defaulted container "kserve-container" out of: kserve-container, queue-proxy\nUnable to use a TTY - input is not a terminal or the right kind of file\nTraceback (most recent call last):\n  File "/code/chaiverse_profiler_1739264642/profiles.py", line 602, in <module>\n    cli()\n  File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1157, in __call__\n    return self.main(*args, **kwargs)\n  File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1078, in main\n    rv = self.invoke(ctx)\n  File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1688, in invoke\n    return _process_result(sub_ctx.command.invoke(sub_ctx))\n  File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1434, in invoke\n    return ctx.invoke(self.callback, **ctx.params)\n  File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 783, in invoke\n    return __callback(*args, **kwargs)\n  File "/code/chaiverse_profiler_1739264642/profiles.py", line 104, in profile_batches\n    profiles = run_batch_profile_with_auto_batch(target, batches, settings, output, auto_batch)\n  File "/code/chaiverse_profiler_1739264642/profiles.py", line 154, in run_batch_profile_with_auto_batch\n    profiles = run_batch_profile(target, batches, settings, output)\n  File "/code/chaiverse_profiler_1739264642/profiles.py", line 261, in run_batch_profile\n    batch_profile = profile_throughput(\n  File "/code/chaiverse_profiler_1739264642/profiles.py", line 279, in profile_throughput\n    raw = analysis_data.load_raw_data(\nTypeError: load_raw_data() got an unexpected keyword argument \'num_unique_prompts\'\ncommand terminated with exit code 1\n, output: waiting for startup of TargetModel(endpoint=\'localhost\', route=\'GPT-J-6B-lit-v2\', namespace=\'tenant-chaiml-guanaco\', max_characters=9999, reward=False, url_format=\'{endpoint}-predictor-default.{namespace}.knative.ord1.coreweave.cloud\')\n')
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service leosheng-ft-dpo-219-v9-profiler is running
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 4201.76s
Shutdown handler de-registered
leosheng-ft-dpo-219_v9 status is now inactive due to auto deactivation removed underperforming models
leosheng-ft-dpo-219_v9 status is now torndown due to DeploymentManager action
leosheng-ft-dpo-219_v9 status is now torndown due to DeploymentManager action
leosheng-ft-dpo-219_v9 status is now torndown due to DeploymentManager action