developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v21_v4
model_name: cloudyu-nemo-dpo-v21_v1
model_group: cloudyu/Nemo-DPO-V21
status: inactive
timestamp: 2024-12-17T13:39:25+00:00
num_battles: 13419
num_wins: 7119
celo_rating: 1280.88
family_friendly_score: 0.5618000000000001
family_friendly_standard_error: 0.007016847725296595
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': 0.6157869604539218, 'latency_mean': 1.6238729894161223, 'latency_p50': 1.6324620246887207, 'latency_p90': 1.7966768264770507}, {'batch_size': 3, 'throughput': 1.1447518376933348, 'latency_mean': 2.6170598530769347, 'latency_p50': 2.6187647581100464, 'latency_p90': 2.8561561822891233}, {'batch_size': 5, 'throughput': 1.38822982309973, 'latency_mean': 3.5773332178592683, 'latency_p50': 3.5963610410690308, 'latency_p90': 3.959816265106201}, {'batch_size': 6, 'throughput': 1.4721087910769353, 'latency_mean': 4.062101105451584, 'latency_p50': 4.065821647644043, 'latency_p90': 4.567147326469422}, {'batch_size': 8, 'throughput': 1.5399369488153174, 'latency_mean': 5.169619604349136, 'latency_p50': 5.167598128318787, 'latency_p90': 5.861062121391297}, {'batch_size': 10, 'throughput': 1.5805887620634338, 'latency_mean': 6.292244231700897, 'latency_p50': 6.29741358757019, 'latency_p90': 7.069258356094361}]
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: 1.42
us_pacific_date: 2024-12-17
win_ratio: 0.5305164319248826
generation_params: {'temperature': 0.95, 'top_p': 0.99, 'min_p': 0.05, '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-v4-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v21-v4-mkmlizer to finish
cloudyu-nemo-dpo-v21-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v21-v4-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v21-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v21-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v21-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v21-v4-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v21-v4-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v21-v4-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v21-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v21-v4-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v21-v4-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v21-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v21-v4-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v21-v4-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v21-v4-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v21-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v21-v4-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-nemo-dpo-v21-v4-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v21-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v21-v4-mkmlizer: Downloaded to shared memory in 31.586s
cloudyu-nemo-dpo-v21-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7s507f70, device:0
cloudyu-nemo-dpo-v21-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v21-v4-mkmlizer: quantized model in 35.715s
cloudyu-nemo-dpo-v21-v4-mkmlizer: Processed model cloudyu/Nemo-DPO-V21 in 67.301s
cloudyu-nemo-dpo-v21-v4-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v21-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v21-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v4
cloudyu-nemo-dpo-v21-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v4/config.json
cloudyu-nemo-dpo-v21-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v4/special_tokens_map.json
cloudyu-nemo-dpo-v21-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v4/tokenizer_config.json
cloudyu-nemo-dpo-v21-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v4/tokenizer.json
cloudyu-nemo-dpo-v21-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v4/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v21-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.63it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:08, 42.04it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:06, 52.97it/s]
Loading 0:   8%|▊         | 28/363 [00:00<00:06, 50.91it/s]
Loading 0:   9%|▉         | 34/363 [00:00<00:06, 50.43it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:06, 51.66it/s]
Loading 0:  13%|█▎        | 46/363 [00:00<00:06, 47.99it/s]
Loading 0:  14%|█▍        | 51/363 [00:01<00:06, 45.67it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:05, 51.91it/s]
Loading 0:  18%|█▊        | 64/363 [00:01<00:09, 31.26it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 39.08it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 40.00it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:07, 39.31it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 43.52it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 42.63it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:06, 43.47it/s]
Loading 0:  29%|██▉       | 105/363 [00:02<00:05, 43.02it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 46.94it/s]
Loading 0:  32%|███▏      | 117/363 [00:02<00:05, 44.31it/s]
Loading 0:  34%|███▎      | 122/363 [00:02<00:05, 44.84it/s]
Loading 0:  35%|███▍      | 127/363 [00:02<00:06, 38.97it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:04, 46.72it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:04, 44.79it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 32.50it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 32.17it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 39.00it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 40.12it/s]
Loading 0:  46%|████▋     | 168/363 [00:03<00:04, 41.99it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:03, 48.06it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:03, 45.82it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:03, 45.36it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 51.25it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 49.36it/s]
Loading 0:  56%|█████▋    | 205/363 [00:04<00:03, 49.22it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:02, 51.74it/s]
Loading 0:  60%|█████▉    | 217/363 [00:04<00:02, 48.82it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:03, 38.19it/s]
Loading 0:  63%|██████▎   | 228/363 [00:05<00:03, 38.04it/s]
Loading 0:  64%|██████▍   | 233/363 [00:05<00:03, 39.94it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:02, 41.82it/s]
Loading 0:  67%|██████▋   | 244/363 [00:05<00:02, 43.02it/s]
Loading 0:  69%|██████▊   | 249/363 [00:05<00:02, 43.25it/s]
Loading 0:  71%|███████   | 256/363 [00:05<00:02, 48.77it/s]
Loading 0:  72%|███████▏  | 262/363 [00:06<00:02, 45.50it/s]
Loading 0:  74%|███████▎  | 267/363 [00:06<00:02, 43.38it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:01, 48.68it/s]
Loading 0:  77%|███████▋  | 280/363 [00:06<00:01, 47.40it/s]
Loading 0:  79%|███████▊  | 285/363 [00:06<00:01, 44.53it/s]
Loading 0:  80%|████████  | 292/363 [00:06<00:01, 48.97it/s]
Loading 0:  82%|████████▏ | 298/363 [00:06<00:01, 46.22it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:21,  2.81it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:15,  3.51it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:11,  4.45it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:05,  7.19it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:03,  9.58it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:02, 11.95it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 16.56it/s]
Loading 0:  94%|█████████▍| 343/363 [00:14<00:01, 19.95it/s]
Loading 0:  96%|█████████▌| 348/363 [00:14<00:00, 21.08it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 28.56it/s]
Loading 0:  99%|█████████▉| 361/363 [00:14<00:00, 31.65it/s]
                                                            

Job cloudyu-nemo-dpo-v21-v4-mkmlizer completed after 105.29s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v21-v4-mkmlizer
Pipeline stage MKMLizer completed in 105.82s
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-v21-v4
Waiting for inference service cloudyu-nemo-dpo-v21-v4 to be ready
Inference service cloudyu-nemo-dpo-v21-v4 ready after 230.8566346168518s
Pipeline stage MKMLDeployer completed in 231.46s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0381057262420654s
Received healthy response to inference request in 1.8443710803985596s
Received healthy response to inference request in 1.6852688789367676s
Received healthy response to inference request in 1.7230298519134521s
Received healthy response to inference request in 1.9008474349975586s
5 requests
0 failed requests
5th percentile: 1.6928210735321045
10th percentile: 1.7003732681274415
20th percentile: 1.7154776573181152
30th percentile: 1.7472980976104737
40th percentile: 1.7958345890045166
50th percentile: 1.8443710803985596
60th percentile: 1.866961622238159
70th percentile: 1.8895521640777588
80th percentile: 1.92829909324646
90th percentile: 1.9832024097442627
95th percentile: 2.010654067993164
99th percentile: 2.0326153945922854
mean time: 1.8383245944976807
Pipeline stage StressChecker completed in 10.46s
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 2.53s
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 2.31s
Shutdown handler de-registered
cloudyu-nemo-dpo-v21_v4 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 3383.56s
Shutdown handler de-registered
cloudyu-nemo-dpo-v21_v4 status is now inactive due to auto deactivation removed underperforming models