cloudyu-nemo-dpo-v11

developer_uid: cloudyu

submission_id: cloudyu-nemo-dpo-v11_v2

model_name: cloudyu-nemo-dpo-v11_v1

model_group: cloudyu/Nemo-DPO-v11

status: inactive

timestamp: 2024-12-03T13:47:58+00:00

num_battles: 17234

num_wins: 8577

celo_rating: 1260.01

family_friendly_score: 0.571

family_friendly_standard_error: 0.006999414261207862

submission_type: basic

model_repo: cloudyu/Nemo-DPO-v11

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6138363046501374, 'latency_mean': 1.6290052092075349, 'latency_p50': 1.6203229427337646, 'latency_p90': 1.8016016721725463}, {'batch_size': 3, 'throughput': 1.122259045502829, 'latency_mean': 2.667121593952179, 'latency_p50': 2.6680963039398193, 'latency_p90': 2.938206362724304}, {'batch_size': 5, 'throughput': 1.34961375327148, 'latency_mean': 3.691288696527481, 'latency_p50': 3.677502989768982, 'latency_p90': 4.128106307983399}, {'batch_size': 6, 'throughput': 1.4190014653562133, 'latency_mean': 4.207305076122284, 'latency_p50': 4.2241352796554565, 'latency_p90': 4.651191234588623}, {'batch_size': 8, 'throughput': 1.4833796029168507, 'latency_mean': 5.354390274286271, 'latency_p50': 5.383673310279846, 'latency_p90': 6.045820498466492}, {'batch_size': 10, 'throughput': 1.5237951578469608, 'latency_mean': 6.494120161533356, 'latency_p50': 6.467539310455322, 'latency_p90': 7.3484608888626095}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cloudyu-nemo-dpo-v11_v1

is_internal_developer: False

language_model: cloudyu/Nemo-DPO-v11

model_size: 13B

ranking_group: single

throughput_3p7s: 1.36

us_pacific_date: 2024-12-03

win_ratio: 0.49767900661483117

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-v11-v2-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v11-v2-mkmlizer to finish
cloudyu-nemo-dpo-v11-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v11-v2-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v11-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v11-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v11-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v11-v2-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v11-v2-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v11-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v11-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v11-v2-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v11-v2-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v11-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v11-v2-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v11-v2-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v11-v2-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v11-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v11-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-nemo-dpo-v11-v2-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v11-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v11-v2-mkmlizer: Downloaded to shared memory in 38.409s
cloudyu-nemo-dpo-v11-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpm7akl_02, device:0
cloudyu-nemo-dpo-v11-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
cloudyu-nemo-dpo-v11-v2-mkmlizer: quantized model in 36.179s
cloudyu-nemo-dpo-v11-v2-mkmlizer: Processed model cloudyu/Nemo-DPO-v11 in 74.588s
cloudyu-nemo-dpo-v11-v2-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v11-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v11-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v11-v2
cloudyu-nemo-dpo-v11-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v11-v2/config.json
cloudyu-nemo-dpo-v11-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v11-v2/special_tokens_map.json
cloudyu-nemo-dpo-v11-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v11-v2/tokenizer_config.json
cloudyu-nemo-dpo-v11-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v11-v2/tokenizer.json
cloudyu-nemo-dpo-v11-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v11-v2/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v11-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:18,  3.04s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:53,  1.22it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:08,  2.74it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:21,  4.28it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:39,  8.52it/s]
Loading 0:   8%|▊         | 29/363 [00:06<00:28, 11.91it/s]
Loading 0:   9%|▉         | 34/363 [00:06<00:21, 14.97it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:18, 17.02it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:16, 19.43it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:12, 24.75it/s]
Loading 0:  15%|█▌        | 55/363 [00:07<00:10, 28.95it/s]
Loading 0:  17%|█▋        | 60/363 [00:07<00:10, 28.34it/s]
Loading 0:  18%|█▊        | 67/363 [00:07<00:08, 35.95it/s]
Loading 0:  20%|█▉        | 72/363 [00:07<00:07, 37.52it/s]
Loading 0:  21%|██        | 77/363 [00:08<00:07, 39.51it/s]
Loading 0:  23%|██▎       | 83/363 [00:08<00:07, 38.74it/s]
Loading 0:  24%|██▍       | 88/363 [00:08<00:07, 38.66it/s]
Loading 0:  26%|██▌       | 95/363 [00:08<00:06, 44.07it/s]
Loading 0:  28%|██▊       | 100/363 [00:08<00:05, 44.74it/s]
Loading 0:  29%|██▉       | 105/363 [00:08<00:06, 39.14it/s]
Loading 0:  31%|███       | 113/363 [00:08<00:05, 47.12it/s]
Loading 0:  33%|███▎      | 119/363 [00:08<00:05, 45.76it/s]
Loading 0:  34%|███▍      | 124/363 [00:09<00:07, 32.37it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:06, 38.11it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:05, 40.46it/s]
Loading 0:  39%|███▉      | 141/363 [00:09<00:06, 36.59it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:04, 44.50it/s]
Loading 0:  43%|████▎     | 155/363 [00:09<00:04, 44.19it/s]
Loading 0:  44%|████▍     | 160/363 [00:09<00:04, 44.30it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:04, 48.41it/s]
Loading 0:  48%|████▊     | 173/363 [00:10<00:04, 46.78it/s]
Loading 0:  49%|████▉     | 178/363 [00:10<00:04, 43.36it/s]
Loading 0:  51%|█████     | 184/363 [00:10<00:03, 47.20it/s]
Loading 0:  52%|█████▏    | 189/363 [00:10<00:03, 44.87it/s]
Loading 0:  53%|█████▎    | 194/363 [00:10<00:03, 45.52it/s]
Loading 0:  55%|█████▌    | 200/363 [00:10<00:03, 44.64it/s]
Loading 0:  56%|█████▋    | 205/363 [00:11<00:05, 31.15it/s]
Loading 0:  58%|█████▊    | 211/363 [00:11<00:04, 36.63it/s]
Loading 0:  60%|█████▉    | 216/363 [00:11<00:03, 37.15it/s]
Loading 0:  61%|██████    | 221/363 [00:11<00:03, 39.76it/s]
Loading 0:  63%|██████▎   | 227/363 [00:11<00:03, 40.02it/s]
Loading 0:  64%|██████▍   | 232/363 [00:11<00:03, 39.62it/s]
Loading 0:  66%|██████▌   | 239/363 [00:11<00:02, 44.91it/s]
Loading 0:  67%|██████▋   | 245/363 [00:12<00:02, 43.33it/s]
Loading 0:  69%|██████▉   | 250/363 [00:12<00:02, 42.21it/s]
Loading 0:  71%|███████   | 257/363 [00:12<00:02, 46.96it/s]
Loading 0:  72%|███████▏  | 262/363 [00:12<00:02, 46.83it/s]
Loading 0:  74%|███████▎  | 267/363 [00:12<00:02, 40.52it/s]
Loading 0:  76%|███████▌  | 275/363 [00:12<00:01, 47.58it/s]
Loading 0:  77%|███████▋  | 281/363 [00:12<00:01, 45.37it/s]
Loading 0:  79%|███████▉  | 286/363 [00:13<00:02, 31.90it/s]
Loading 0:  81%|████████  | 293/363 [00:13<00:01, 37.75it/s]
Loading 0:  82%|████████▏ | 299/363 [00:13<00:01, 39.05it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:01, 39.76it/s]
Loading 0:  86%|████████▌ | 311/363 [00:13<00:01, 44.88it/s]
Loading 0:  87%|████████▋ | 317/363 [00:13<00:01, 44.40it/s]
Loading 0:  89%|████████▊ | 322/363 [00:13<00:00, 44.01it/s]
Loading 0:  91%|█████████ | 329/363 [00:13<00:00, 48.53it/s]
Loading 0:  92%|█████████▏| 335/363 [00:14<00:00, 45.68it/s]
Loading 0:  94%|█████████▎| 340/363 [00:14<00:00, 41.65it/s]
Loading 0:  96%|█████████▌| 347/363 [00:14<00:00, 46.39it/s]
Loading 0:  97%|█████████▋| 353/363 [00:14<00:00, 45.14it/s]
Loading 0:  99%|█████████▊| 358/363 [00:14<00:00, 44.04it/s]
                                                            
Job cloudyu-nemo-dpo-v11-v2-mkmlizer completed after 104.65s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v11-v2-mkmlizer
Pipeline stage MKMLizer completed in 105.18s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.21s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-nemo-dpo-v11-v2
Waiting for inference service cloudyu-nemo-dpo-v11-v2 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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
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-v11-v2 ready after 150.55691647529602s
Pipeline stage MKMLDeployer completed in 151.16s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.037234306335449s
Received healthy response to inference request in 1.7866930961608887s
Received healthy response to inference request in 1.8214175701141357s
Received healthy response to inference request in 1.9435420036315918s
Received healthy response to inference request in 1.6306147575378418s
5 requests
0 failed requests
5th percentile: 1.6618304252624512
10th percentile: 1.6930460929870605
20th percentile: 1.7554774284362793
30th percentile: 1.793637990951538
40th percentile: 1.807527780532837
50th percentile: 1.8214175701141357
60th percentile: 1.8702673435211181
70th percentile: 1.9191171169281005
80th percentile: 1.9622804641723632
90th percentile: 1.9997573852539063
95th percentile: 2.0184958457946776
99th percentile: 2.0334866142272947
mean time: 1.8439003467559814
Pipeline stage StressChecker completed in 10.73s
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 2.50s
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 2.37s
Shutdown handler de-registered
cloudyu-nemo-dpo-v11_v2 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 0.10s
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 cloudyu-nemo-dpo-v11-v2-profiler
Waiting for inference service cloudyu-nemo-dpo-v11-v2-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 3107.51s
Shutdown handler de-registered
cloudyu-nemo-dpo-v11_v2 status is now inactive due to auto deactivation removed underperforming models