cloudyu-nemo-dpo-v20

developer_uid: azuruce

submission_id: cloudyu-nemo-dpo-v20_v16

model_name: cloudyu-nemo-dpo-v20_v16

model_group: cloudyu/Nemo-DPO-V20

status: torndown

timestamp: 2025-01-09T23:08:43+00:00

num_battles: 8366

num_wins: 4262

celo_rating: 1259.43

family_friendly_score: 0.5740000000000001

family_friendly_standard_error: 0.006993196693930466

submission_type: basic

model_repo: cloudyu/Nemo-DPO-V20

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6427642787106376, 'latency_mean': 1.5557183980941773, 'latency_p50': 1.5505467653274536, 'latency_p90': 1.7207279205322266}, {'batch_size': 3, 'throughput': 1.262861242897227, 'latency_mean': 2.3663092505931855, 'latency_p50': 2.364701986312866, 'latency_p90': 2.597945785522461}, {'batch_size': 5, 'throughput': 1.5985537041699853, 'latency_mean': 3.116564830541611, 'latency_p50': 3.1089333295822144, 'latency_p90': 3.560240459442139}, {'batch_size': 6, 'throughput': 1.7037155147214844, 'latency_mean': 3.5048390579223634, 'latency_p50': 3.543212890625, 'latency_p90': 3.8839370250701903}, {'batch_size': 8, 'throughput': 1.8728604181988884, 'latency_mean': 4.236288142204285, 'latency_p50': 4.203723430633545, 'latency_p90': 4.828843784332276}, {'batch_size': 10, 'throughput': 1.9415879585295113, 'latency_mean': 5.114409328699112, 'latency_p50': 5.112010359764099, 'latency_p90': 5.783692026138305}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cloudyu-nemo-dpo-v20_v16

is_internal_developer: False

language_model: cloudyu/Nemo-DPO-V20

model_size: 13B

ranking_group: single

throughput_3p7s: 1.77

us_pacific_date: 2025-01-09

win_ratio: 0.5094429835046618

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.001, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>', 'Me:', '<|im_end|>', '<|eot_id|>', '\n', 'User:', 'Bot:', '####', 'You:'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', '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-v16-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v20-v16-mkmlizer to finish
cloudyu-nemo-dpo-v20-v16-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v20-v16-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v20-v16-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v20-v16-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v20-v16-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v20-v16-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v20-v16-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v20-v16-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v20-v16-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v20-v16-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v20-v16-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v20-v16-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v20-v16-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v20-v16-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v20-v16-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v20-v16-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v20-v16-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
cloudyu-nemo-dpo-v20-v16-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v20-v16-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v20-v16-mkmlizer: Downloaded to shared memory in 53.910s
cloudyu-nemo-dpo-v20-v16-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp576l_7r1, device:0
cloudyu-nemo-dpo-v20-v16-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v20-v16-mkmlizer: quantized model in 35.554s
cloudyu-nemo-dpo-v20-v16-mkmlizer: Processed model cloudyu/Nemo-DPO-V20 in 89.464s
cloudyu-nemo-dpo-v20-v16-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v20-v16-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v20-v16-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v16
cloudyu-nemo-dpo-v20-v16-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v16/config.json
cloudyu-nemo-dpo-v20-v16-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v16/special_tokens_map.json
cloudyu-nemo-dpo-v20-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v16/tokenizer_config.json
cloudyu-nemo-dpo-v20-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v16/tokenizer.json
cloudyu-nemo-dpo-v20-v16-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v16/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v20-v16-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.35it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 48.98it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 46.43it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 45.21it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 51.52it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 49.19it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:06, 49.85it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 52.21it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 48.07it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 36.89it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 37.06it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:06, 41.57it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 41.25it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 41.47it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:05, 46.89it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:05, 46.63it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:06, 38.15it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 47.42it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:05, 43.93it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:05, 43.20it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:04, 48.21it/s]
Loading 0:  36%|███▋      | 132/363 [00:02<00:04, 46.51it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:04, 45.65it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 36.21it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:05, 36.28it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:05, 35.55it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:04, 42.99it/s]
Loading 0:  45%|████▍     | 162/363 [00:03<00:04, 44.67it/s]
Loading 0:  46%|████▌     | 167/363 [00:03<00:05, 37.69it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 46.09it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 44.81it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 44.23it/s]
Loading 0:  53%|█████▎    | 192/363 [00:04<00:03, 47.77it/s]
Loading 0:  54%|█████▍    | 197/363 [00:04<00:03, 46.83it/s]
Loading 0:  56%|█████▌    | 202/363 [00:04<00:03, 46.13it/s]
Loading 0:  57%|█████▋    | 208/363 [00:04<00:03, 45.79it/s]
Loading 0:  59%|█████▊    | 213/363 [00:04<00:03, 45.54it/s]
Loading 0:  61%|██████    | 220/363 [00:04<00:02, 51.46it/s]
Loading 0:  62%|██████▏   | 226/363 [00:05<00:03, 34.47it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:03, 36.19it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:02, 42.69it/s]
Loading 0:  67%|██████▋   | 244/363 [00:05<00:02, 43.44it/s]
Loading 0:  69%|██████▊   | 249/363 [00:05<00:02, 43.52it/s]
Loading 0:  71%|███████   | 256/363 [00:05<00:02, 47.67it/s]
Loading 0:  72%|███████▏  | 262/363 [00:06<00:02, 45.63it/s]
Loading 0:  74%|███████▎  | 267/363 [00:06<00:02, 44.18it/s]
Loading 0:  75%|███████▌  | 273/363 [00:06<00:01, 47.62it/s]
Loading 0:  77%|███████▋  | 278/363 [00:06<00:01, 44.34it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 44.02it/s]
Loading 0:  80%|███████▉  | 289/363 [00:06<00:01, 42.67it/s]
Loading 0:  81%|████████  | 294/363 [00:06<00:01, 39.87it/s]
Loading 0:  82%|████████▏ | 299/363 [00:06<00:01, 40.61it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:24,  2.44it/s]
Loading 0:  85%|████████▍ | 307/363 [00:13<00:18,  2.97it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:12,  4.21it/s]
Loading 0:  88%|████████▊ | 319/363 [00:14<00:06,  6.66it/s]
Loading 0:  89%|████████▉ | 324/363 [00:14<00:04,  8.80it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:02, 11.64it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 17.23it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 20.68it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 23.76it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 30.02it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 31.52it/s]
                                                            
Job cloudyu-nemo-dpo-v20-v16-mkmlizer completed after 114.98s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v20-v16-mkmlizer
Pipeline stage MKMLizer completed in 115.52s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-nemo-dpo-v20-v16
Waiting for inference service cloudyu-nemo-dpo-v20-v16 to be ready
Inference service cloudyu-nemo-dpo-v20-v16 ready after 351.71446228027344s
Pipeline stage MKMLDeployer completed in 352.22s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.66078519821167s
Received healthy response to inference request in 1.1372528076171875s
Received healthy response to inference request in 1.264753818511963s
Received healthy response to inference request in 1.5318140983581543s
Received healthy response to inference request in 1.0103464126586914s
5 requests
0 failed requests
5th percentile: 1.0357276916503906
10th percentile: 1.0611089706420898
20th percentile: 1.1118715286254883
30th percentile: 1.1627530097961425
40th percentile: 1.2137534141540527
50th percentile: 1.264753818511963
60th percentile: 1.3715779304504394
70th percentile: 1.478402042388916
80th percentile: 1.5576083183288574
90th percentile: 1.6091967582702638
95th percentile: 1.6349909782409668
99th percentile: 1.6556263542175294
mean time: 1.3209904670715331
Pipeline stage StressChecker completed in 7.90s
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 0.59s
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
cloudyu-nemo-dpo-v20_v16 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2432.59s
Shutdown handler de-registered
cloudyu-nemo-dpo-v20_v16 status is now inactive due to auto deactivation removed underperforming models
cloudyu-nemo-dpo-v20_v16 status is now torndown due to DeploymentManager action