developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v21_v10
model_name: cloudyu-nemo-dpo-v21_v1
model_group: cloudyu/Nemo-DPO-V21
status: inactive
timestamp: 2024-12-18T06:02:26+00:00
num_battles: 13680
num_wins: 7222
celo_rating: 1282.35
family_friendly_score: 0.5656
family_friendly_standard_error: 0.007009944935589723
submission_type: basic
model_repo: cloudyu/Nemo-DPO-V21
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6145899750729369, 'latency_mean': 1.627005981206894, 'latency_p50': 1.6209243535995483, 'latency_p90': 1.7969099283218384}, {'batch_size': 3, 'throughput': 1.1327738283631175, 'latency_mean': 2.640421576499939, 'latency_p50': 2.629119873046875, 'latency_p90': 2.9077489614486693}, {'batch_size': 5, 'throughput': 1.3551925645682703, 'latency_mean': 3.6728884208202364, 'latency_p50': 3.710254430770874, 'latency_p90': 4.121783804893494}, {'batch_size': 6, 'throughput': 1.4310673409721621, 'latency_mean': 4.171165097951889, 'latency_p50': 4.16782820224762, 'latency_p90': 4.64782223701477}, {'batch_size': 8, 'throughput': 1.5030139597390342, 'latency_mean': 5.283502546548843, 'latency_p50': 5.275258302688599, 'latency_p90': 5.931966352462768}, {'batch_size': 10, 'throughput': 1.538163584239793, 'latency_mean': 6.450886508226395, 'latency_p50': 6.4027146100997925, 'latency_p90': 7.232829213142395}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-nemo-dpo-v21_v1
is_internal_developer: False
language_model: cloudyu/Nemo-DPO-V21
model_size: 13B
ranking_group: single
throughput_3p7s: 1.37
us_pacific_date: 2024-12-17
win_ratio: 0.5279239766081871
generation_params: {'temperature': 0.99, '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-v21-v10-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v21-v10-mkmlizer to finish
cloudyu-nemo-dpo-v21-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v21-v10-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v21-v10-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v21-v10-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v21-v10-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v21-v10-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v21-v10-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v21-v10-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v21-v10-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v21-v10-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v21-v10-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v21-v10-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v21-v10-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v21-v10-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v21-v10-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v21-v10-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v21-v10-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-nemo-dpo-v21-v10-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v21-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v21-v10-mkmlizer: Downloaded to shared memory in 42.255s
cloudyu-nemo-dpo-v21-v10-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpt1didwgo, device:0
cloudyu-nemo-dpo-v21-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v21-v10-mkmlizer: quantized model in 36.635s
cloudyu-nemo-dpo-v21-v10-mkmlizer: Processed model cloudyu/Nemo-DPO-V21 in 78.890s
cloudyu-nemo-dpo-v21-v10-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v21-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v21-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v10
cloudyu-nemo-dpo-v21-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v10/config.json
cloudyu-nemo-dpo-v21-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v10/special_tokens_map.json
cloudyu-nemo-dpo-v21-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v10/tokenizer_config.json
cloudyu-nemo-dpo-v21-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v10/tokenizer.json
cloudyu-nemo-dpo-v21-v10-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.32it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 49.44it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 45.28it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 45.30it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 52.39it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 50.36it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:06, 50.37it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 51.70it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 48.40it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 36.11it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 36.20it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 40.49it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 41.41it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 40.20it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:05, 45.59it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 42.84it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 40.46it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:06, 42.68it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:06, 40.34it/s]
Loading 0:  33%|███▎      | 118/363 [00:02<00:06, 38.92it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:05, 46.53it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:05, 44.35it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:05, 42.95it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 32.54it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 33.24it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 32.62it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 39.31it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:05, 39.48it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:04, 40.41it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 45.47it/s]
Loading 0:  50%|████▉     | 180/363 [00:04<00:03, 46.59it/s]
Loading 0:  51%|█████     | 185/363 [00:04<00:04, 37.98it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 45.91it/s]
Loading 0:  55%|█████▍    | 198/363 [00:04<00:03, 46.71it/s]
Loading 0:  56%|█████▌    | 203/363 [00:04<00:04, 38.97it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 46.08it/s]
Loading 0:  60%|█████▉    | 216/363 [00:05<00:03, 46.29it/s]
Loading 0:  61%|██████    | 221/363 [00:05<00:03, 46.82it/s]
Loading 0:  62%|██████▏   | 226/363 [00:05<00:04, 30.44it/s]
Loading 0:  63%|██████▎   | 230/363 [00:05<00:04, 30.45it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 38.60it/s]
Loading 0:  67%|██████▋   | 242/363 [00:05<00:03, 39.11it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:02, 40.52it/s]
Loading 0:  70%|██████▉   | 253/363 [00:06<00:02, 40.86it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 40.89it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 44.84it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 44.96it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:01, 45.10it/s]
Loading 0:  77%|███████▋  | 280/363 [00:06<00:01, 43.97it/s]
Loading 0:  79%|███████▊  | 285/363 [00:06<00:01, 43.57it/s]
Loading 0:  80%|████████  | 292/363 [00:06<00:01, 48.04it/s]
Loading 0:  82%|████████▏ | 298/363 [00:07<00:01, 45.35it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:21,  2.72it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:16,  3.43it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:11,  4.38it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  7.13it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:03,  9.53it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:02, 12.00it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 16.78it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 20.25it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 22.68it/s]
Loading 0:  98%|█████████▊| 355/363 [00:15<00:00, 27.62it/s]
Loading 0:  99%|█████████▉| 360/363 [00:15<00:00, 29.62it/s]
                                                            

Job cloudyu-nemo-dpo-v21-v10-mkmlizer completed after 104.51s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v21-v10-mkmlizer
Pipeline stage MKMLizer completed in 105.00s
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-v21-v10
Waiting for inference service cloudyu-nemo-dpo-v21-v10 to be ready
Inference service cloudyu-nemo-dpo-v21-v10 ready after 231.21306157112122s
Pipeline stage MKMLDeployer completed in 231.85s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.269566297531128s
Received healthy response to inference request in 1.8323063850402832s
Received healthy response to inference request in 1.7861666679382324s
Received healthy response to inference request in 1.7048776149749756s
Received healthy response to inference request in 1.8011417388916016s
5 requests
0 failed requests
5th percentile: 1.721135425567627
10th percentile: 1.7373932361602784
20th percentile: 1.769908857345581
30th percentile: 1.7891616821289062
40th percentile: 1.795151710510254
50th percentile: 1.8011417388916016
60th percentile: 1.8136075973510741
70th percentile: 1.826073455810547
80th percentile: 1.9197583675384522
90th percentile: 2.09466233253479
95th percentile: 2.1821143150329587
99th percentile: 2.252075901031494
mean time: 1.878811740875244
Pipeline stage StressChecker completed in 10.77s
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 2.44s
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 2.34s
Shutdown handler de-registered
cloudyu-nemo-dpo-v21_v10 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 3167.20s
Shutdown handler de-registered
cloudyu-nemo-dpo-v21_v10 status is now inactive due to auto deactivation removed underperforming models