cloudyu-nemo-dpo-v19

developer_uid: cloudyu

submission_id: cloudyu-nemo-dpo-v19_v4

model_name: cloudyu-nemo-dpo-v19_v1

model_group: cloudyu/Nemo-DPO-V19

status: inactive

timestamp: 2024-12-16T09:08:35+00:00

num_battles: 13204

num_wins: 6878

celo_rating: 1277.35

family_friendly_score: 0.5660000000000001

family_friendly_standard_error: 0.007009193962218481

submission_type: basic

model_repo: cloudyu/Nemo-DPO-V19

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6188300977037116, 'latency_mean': 1.6158628952503205, 'latency_p50': 1.6065301895141602, 'latency_p90': 1.806154227256775}, {'batch_size': 3, 'throughput': 1.135530272462869, 'latency_mean': 2.637742247581482, 'latency_p50': 2.6371331214904785, 'latency_p90': 2.915228772163391}, {'batch_size': 5, 'throughput': 1.3711546637431915, 'latency_mean': 3.6350555431842806, 'latency_p50': 3.633030414581299, 'latency_p90': 4.018619179725647}, {'batch_size': 6, 'throughput': 1.4463360375454588, 'latency_mean': 4.123562476634979, 'latency_p50': 4.116905093193054, 'latency_p90': 4.707127475738526}, {'batch_size': 8, 'throughput': 1.5261252958807026, 'latency_mean': 5.203161814212799, 'latency_p50': 5.214614748954773, 'latency_p90': 5.928697228431702}, {'batch_size': 10, 'throughput': 1.5423447850874967, 'latency_mean': 6.430416527986527, 'latency_p50': 6.470588684082031, 'latency_p90': 7.452648782730102}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cloudyu-nemo-dpo-v19_v1

is_internal_developer: False

language_model: cloudyu/Nemo-DPO-V19

model_size: 13B

ranking_group: single

throughput_3p7s: 1.39

us_pacific_date: 2024-12-16

win_ratio: 0.5209027567403817

generation_params: {'temperature': 0.95, 'top_p': 0.95, '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-v19-v4-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v19-v4-mkmlizer to finish
cloudyu-nemo-dpo-v19-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v19-v4-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v19-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v19-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v19-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v19-v4-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v19-v4-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v19-v4-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v19-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v19-v4-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v19-v4-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v19-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v19-v4-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v19-v4-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v19-v4-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v19-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v19-v4-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-nemo-dpo-v19-v4-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v19-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v19-v4-mkmlizer: Downloaded to shared memory in 44.598s
cloudyu-nemo-dpo-v19-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxnl6v_oa, device:0
cloudyu-nemo-dpo-v19-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v19-v4-mkmlizer: quantized model in 36.283s
cloudyu-nemo-dpo-v19-v4-mkmlizer: Processed model cloudyu/Nemo-DPO-V19 in 80.882s
cloudyu-nemo-dpo-v19-v4-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v19-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v19-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v4
cloudyu-nemo-dpo-v19-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v4/config.json
cloudyu-nemo-dpo-v19-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v4/special_tokens_map.json
cloudyu-nemo-dpo-v19-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v4/tokenizer_config.json
cloudyu-nemo-dpo-v19-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v4/tokenizer.json
cloudyu-nemo-dpo-v19-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v4/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v19-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 29.23it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 51.63it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:06, 49.48it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:06, 51.10it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 53.91it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 51.35it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:06, 51.92it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:05, 53.88it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 50.99it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 36.91it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 37.07it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:06, 41.70it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 43.26it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 43.72it/s]
Loading 0:  25%|██▍       | 90/363 [00:01<00:05, 49.46it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 48.19it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:05, 46.82it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:05, 47.50it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:05, 46.69it/s]
Loading 0:  33%|███▎      | 118/363 [00:02<00:05, 43.45it/s]
Loading 0:  34%|███▍      | 125/363 [00:02<00:04, 49.67it/s]
Loading 0:  36%|███▌      | 131/363 [00:02<00:04, 50.74it/s]
Loading 0:  38%|███▊      | 137/363 [00:02<00:05, 43.48it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 33.90it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 34.72it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 33.83it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 40.34it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 40.93it/s]
Loading 0:  46%|████▋     | 168/363 [00:03<00:04, 41.53it/s]
Loading 0:  48%|████▊     | 175/363 [00:03<00:03, 47.20it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 45.19it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 43.53it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 48.68it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 46.58it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 43.65it/s]
Loading 0:  58%|█████▊    | 210/363 [00:04<00:03, 47.36it/s]
Loading 0:  59%|█████▉    | 215/363 [00:04<00:03, 47.06it/s]
Loading 0:  61%|██████    | 222/363 [00:04<00:03, 46.66it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 31.93it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 31.11it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 35.83it/s]
Loading 0:  67%|██████▋   | 242/363 [00:05<00:03, 36.52it/s]
Loading 0:  68%|██████▊   | 246/363 [00:05<00:03, 36.68it/s]
Loading 0:  69%|██████▉   | 250/363 [00:05<00:03, 35.45it/s]
Loading 0:  70%|███████   | 255/363 [00:05<00:02, 37.11it/s]
Loading 0:  71%|███████▏  | 259/363 [00:06<00:02, 36.51it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 41.20it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 40.46it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:02, 39.59it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 45.43it/s]
Loading 0:  80%|███████▉  | 289/363 [00:06<00:01, 44.03it/s]
Loading 0:  81%|████████  | 294/363 [00:06<00:01, 41.66it/s]
Loading 0:  82%|████████▏ | 299/363 [00:07<00:01, 43.42it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:24,  2.44it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:17,  3.15it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:12,  4.13it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  6.91it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:03,  9.40it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:02, 11.96it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 16.85it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 20.55it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 23.97it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 30.72it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 33.84it/s]
                                                            
Job cloudyu-nemo-dpo-v19-v4-mkmlizer completed after 104.97s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v19-v4-mkmlizer
Pipeline stage MKMLizer completed in 105.48s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-nemo-dpo-v19-v4
Waiting for inference service cloudyu-nemo-dpo-v19-v4 to be ready
Inference service cloudyu-nemo-dpo-v19-v4 ready after 220.98663759231567s
Pipeline stage MKMLDeployer completed in 221.53s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1335694789886475s
Received healthy response to inference request in 1.6616382598876953s
Received healthy response to inference request in 1.7392480373382568s
Received healthy response to inference request in 2.123750925064087s
Received healthy response to inference request in 1.8737924098968506s
5 requests
0 failed requests
5th percentile: 1.6771602153778076
10th percentile: 1.6926821708679198
20th percentile: 1.7237260818481446
30th percentile: 1.7661569118499756
40th percentile: 1.819974660873413
50th percentile: 1.8737924098968506
60th percentile: 1.973775815963745
70th percentile: 2.0737592220306396
80th percentile: 2.125714635848999
90th percentile: 2.129642057418823
95th percentile: 2.1316057682037353
99th percentile: 2.133176736831665
mean time: 1.9063998222351075
Pipeline stage StressChecker completed in 10.96s
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 2.82s
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 2.02s
Shutdown handler de-registered
cloudyu-nemo-dpo-v19_v4 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cloudyu-nemo-dpo-v19-v4-profiler
Waiting for inference service cloudyu-nemo-dpo-v19-v4-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 3219.13s
Shutdown handler de-registered
cloudyu-nemo-dpo-v19_v4 status is now inactive due to auto deactivation removed underperforming models