developer_uid: Tiun
submission_id: cloudyu-nemo-dpo-v20_v15
model_name: cloudyu-nemo-dpo-v20_v1
model_group: cloudyu/Nemo-DPO-V20
status: torndown
timestamp: 2024-12-30T15:44:29+00:00
num_battles: 14853
num_wins: 7655
celo_rating: 1272.37
family_friendly_score: 0.5754
family_friendly_standard_error: 0.0069902051472041935
submission_type: basic
model_repo: cloudyu/Nemo-DPO-V20
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6244335103038067, 'latency_mean': 1.60139573097229, 'latency_p50': 1.6011130809783936, 'latency_p90': 1.766115164756775}, {'batch_size': 3, 'throughput': 1.1501790725617786, 'latency_mean': 2.5968393754959105, 'latency_p50': 2.5959560871124268, 'latency_p90': 2.8401968002319338}, {'batch_size': 5, 'throughput': 1.399813632028485, 'latency_mean': 3.5624458277225495, 'latency_p50': 3.561483144760132, 'latency_p90': 3.972175669670105}, {'batch_size': 6, 'throughput': 1.480380292650536, 'latency_mean': 4.026623957157135, 'latency_p50': 4.012596845626831, 'latency_p90': 4.557190012931824}, {'batch_size': 8, 'throughput': 1.5451423310389227, 'latency_mean': 5.141025590896606, 'latency_p50': 5.1309274435043335, 'latency_p90': 5.76177237033844}, {'batch_size': 10, 'throughput': 1.6014929261430373, 'latency_mean': 6.204969203472137, 'latency_p50': 6.1803706884384155, 'latency_p90': 7.059561610221863}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-nemo-dpo-v20_v1
is_internal_developer: False
language_model: cloudyu/Nemo-DPO-V20
model_size: 13B
ranking_group: single
throughput_3p7s: 1.43
us_pacific_date: 2024-12-30
win_ratio: 0.5153840974887228
generation_params: {'temperature': 0.95, 'top_p': 0.99, 'min_p': 0.01, 'top_k': 80, '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': "{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 cloudyu-nemo-dpo-v20-v15-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v20-v15-mkmlizer to finish
cloudyu-nemo-dpo-v20-v15-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v20-v15-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v20-v15-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v20-v15-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v20-v15-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v20-v15-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v20-v15-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v20-v15-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v20-v15-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v20-v15-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v20-v15-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v20-v15-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v20-v15-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v20-v15-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v20-v15-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v20-v15-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v20-v15-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-nemo-dpo-v20-v15-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v20-v15-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v20-v15-mkmlizer: Downloaded to shared memory in 49.281s
cloudyu-nemo-dpo-v20-v15-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpqnuh3jkv, device:0
cloudyu-nemo-dpo-v20-v15-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v20-v15-mkmlizer: quantized model in 35.842s
cloudyu-nemo-dpo-v20-v15-mkmlizer: Processed model cloudyu/Nemo-DPO-V20 in 85.124s
cloudyu-nemo-dpo-v20-v15-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v20-v15-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v20-v15-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v15
cloudyu-nemo-dpo-v20-v15-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v15/config.json
cloudyu-nemo-dpo-v20-v15-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v15/special_tokens_map.json
cloudyu-nemo-dpo-v20-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v15/tokenizer_config.json
cloudyu-nemo-dpo-v20-v15-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v15/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v20-v15-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 26.98it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 46.25it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:08, 42.80it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 40.81it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 45.12it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 43.98it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 43.14it/s]
Loading 0:  12%|█▏        | 45/363 [00:01<00:07, 43.07it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:08, 35.25it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:07, 40.24it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 31.94it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 31.36it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:07, 37.58it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 39.38it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:07, 37.47it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:05, 45.88it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 44.38it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 43.13it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 49.43it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:05, 43.98it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:05, 42.01it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 46.09it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 46.27it/s]
Loading 0:  37%|███▋      | 136/363 [00:03<00:05, 41.73it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 35.92it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 36.07it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 34.51it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:04, 41.32it/s]
Loading 0:  45%|████▍     | 163/363 [00:04<00:04, 41.22it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:04, 39.88it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 45.88it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 44.57it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 43.90it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 48.68it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 46.48it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 44.87it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 49.49it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 45.30it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:03, 35.87it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:03, 35.07it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:03, 34.24it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 41.21it/s]
Loading 0:  67%|██████▋   | 244/363 [00:05<00:02, 41.53it/s]
Loading 0:  69%|██████▊   | 249/363 [00:06<00:02, 41.37it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 46.08it/s]
Loading 0:  72%|███████▏  | 261/363 [00:06<00:02, 46.72it/s]
Loading 0:  73%|███████▎  | 266/363 [00:06<00:02, 38.21it/s]
Loading 0:  75%|███████▌  | 273/363 [00:06<00:01, 45.07it/s]
Loading 0:  77%|███████▋  | 278/363 [00:06<00:01, 44.67it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 45.40it/s]
Loading 0:  80%|███████▉  | 289/363 [00:06<00:01, 43.88it/s]
Loading 0:  81%|████████  | 294/363 [00:07<00:01, 42.75it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 49.34it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:20,  2.77it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:13,  3.69it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.75it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  7.68it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:03,  9.76it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.75it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:01, 17.11it/s]
Loading 0:  96%|█████████▋| 350/363 [00:14<00:00, 21.21it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 26.08it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 29.42it/s]
                                                            

Job cloudyu-nemo-dpo-v20-v15-mkmlizer completed after 104.64s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v20-v15-mkmlizer
Pipeline stage MKMLizer completed in 105.11s
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 cloudyu-nemo-dpo-v20-v15
Waiting for inference service cloudyu-nemo-dpo-v20-v15 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cloudyu-nemo-dpo-v20-v15 ready after 311.13665318489075s
Pipeline stage MKMLDeployer completed in 311.69s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.485893726348877s
Received healthy response to inference request in 2.1911685466766357s
Received healthy response to inference request in 2.123544692993164s
Received healthy response to inference request in 1.6501545906066895s
Received healthy response to inference request in 1.6725876331329346s
5 requests
0 failed requests
5th percentile: 1.6546411991119385
10th percentile: 1.6591278076171876
20th percentile: 1.6681010246276855
30th percentile: 1.7627790451049805
40th percentile: 1.9431618690490724
50th percentile: 2.123544692993164
60th percentile: 2.1505942344665527
70th percentile: 2.1776437759399414
80th percentile: 2.250113582611084
90th percentile: 2.3680036544799803
95th percentile: 2.4269486904144286
99th percentile: 2.4741047191619874
mean time: 2.0246698379516603
Pipeline stage StressChecker completed in 11.22s
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 0.63s
Shutdown handler de-registered
cloudyu-nemo-dpo-v20_v15 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 0.11s
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 cloudyu-nemo-dpo-v20-v15-profiler
Waiting for inference service cloudyu-nemo-dpo-v20-v15-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 2832.63s
Shutdown handler de-registered
cloudyu-nemo-dpo-v20_v15 status is now inactive due to auto deactivation removed underperforming models
cloudyu-nemo-dpo-v20_v15 status is now torndown due to DeploymentManager action
cloudyu-nemo-dpo-v20_v15 status is now torndown due to DeploymentManager action
cloudyu-nemo-dpo-v20_v15 status is now torndown due to DeploymentManager action