cloudyu-nemo-dpo-v22

developer_uid: cloudyu

submission_id: cloudyu-nemo-dpo-v22_v4

model_name: cloudyu-nemo-dpo-v22_v1

model_group: cloudyu/Nemo-DPO-V22

status: inactive

timestamp: 2024-12-18T13:05:17+00:00

num_battles: 13848

num_wins: 7364

celo_rating: 1281.47

family_friendly_score: 0.5622

family_friendly_standard_error: 0.007016140819567407

submission_type: basic

model_repo: cloudyu/Nemo-DPO-V22

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6204550743913431, 'latency_mean': 1.6116264235973359, 'latency_p50': 1.614892601966858, 'latency_p90': 1.7854604482650758}, {'batch_size': 3, 'throughput': 1.1417842965203286, 'latency_mean': 2.6250209832191467, 'latency_p50': 2.627056121826172, 'latency_p90': 2.9071162939071655}, {'batch_size': 5, 'throughput': 1.375053396454463, 'latency_mean': 3.618551114797592, 'latency_p50': 3.627276301383972, 'latency_p90': 4.083545827865601}, {'batch_size': 6, 'throughput': 1.4490038859180772, 'latency_mean': 4.125902940034866, 'latency_p50': 4.143754243850708, 'latency_p90': 4.6150398492813105}, {'batch_size': 8, 'throughput': 1.5121167100048318, 'latency_mean': 5.2711762523651124, 'latency_p50': 5.259524822235107, 'latency_p90': 5.934590911865234}, {'batch_size': 10, 'throughput': 1.5440656214783561, 'latency_mean': 6.413101764917374, 'latency_p50': 6.4228222370147705, 'latency_p90': 7.205242800712585}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cloudyu-nemo-dpo-v22_v1

is_internal_developer: False

language_model: cloudyu/Nemo-DPO-V22

model_size: 13B

ranking_group: single

throughput_3p7s: 1.39

us_pacific_date: 2024-12-18

win_ratio: 0.5317735413056037

generation_params: {'temperature': 1.25, '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-v22-v4-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v22-v4-mkmlizer to finish
cloudyu-nemo-dpo-v22-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v22-v4-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v22-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v22-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v22-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v22-v4-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v22-v4-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v4-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v22-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v22-v4-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v22-v4-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v22-v4-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v22-v4-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v4-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v22-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v22-v4-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-nemo-dpo-v22-v4-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v22-v4-mkmlizer: Downloaded to shared memory in 49.106s
cloudyu-nemo-dpo-v22-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpphfx4kgv, device:0
cloudyu-nemo-dpo-v22-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v22-v4-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v22-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v22-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v4
cloudyu-nemo-dpo-v22-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v4/config.json
cloudyu-nemo-dpo-v22-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v4/special_tokens_map.json
cloudyu-nemo-dpo-v22-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v4/tokenizer_config.json
cloudyu-nemo-dpo-v22-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v4/tokenizer.json
cloudyu-nemo-dpo-v22-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v4/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v22-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.08it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 48.45it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 45.06it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 42.47it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 47.97it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 45.42it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 43.35it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 48.30it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 46.05it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 34.95it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 33.51it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 39.66it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 40.24it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 41.32it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:05, 46.84it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 46.28it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 43.26it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 49.80it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:05, 43.93it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:05, 42.35it/s]
Loading 0:  34%|███▍      | 125/363 [00:02<00:05, 46.57it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 45.20it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:04, 46.20it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:04, 45.91it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 31.96it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 32.36it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 39.82it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 41.40it/s]
Loading 0:  46%|████▋     | 168/363 [00:03<00:04, 42.25it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:03, 48.11it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:03, 47.17it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:03, 45.99it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 51.17it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 47.29it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 45.23it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 49.98it/s]
Loading 0:  60%|█████▉    | 217/363 [00:04<00:03, 47.10it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:03, 35.69it/s]
Loading 0:  63%|██████▎   | 228/363 [00:05<00:03, 35.40it/s]
Loading 0:  64%|██████▍   | 233/363 [00:05<00:03, 37.99it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 39.79it/s]
Loading 0:  67%|██████▋   | 244/363 [00:05<00:02, 40.50it/s]
Loading 0:  69%|██████▊   | 249/363 [00:05<00:02, 40.93it/s]
Loading 0:  70%|███████   | 255/363 [00:05<00:02, 45.33it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 44.95it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 46.01it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 44.73it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:02, 41.93it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 47.24it/s]
Loading 0:  80%|███████▉  | 289/363 [00:06<00:01, 45.69it/s]
Loading 0:  81%|████████  | 294/363 [00:06<00:01, 44.67it/s]
Loading 0:  83%|████████▎ | 301/363 [00:06<00:01, 51.02it/s]
Loading 0:  85%|████████▍ | 307/363 [00:13<00:19,  2.80it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:13,  3.72it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.78it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  7.73it/s]
Loading 0:  91%|█████████▏| 332/363 [00:14<00:03, 10.31it/s]
Loading 0:  93%|█████████▎| 339/363 [00:14<00:01, 13.64it/s]
Loading 0:  96%|█████████▌| 347/363 [00:14<00:00, 19.05it/s]
Loading 0:  97%|█████████▋| 353/363 [00:14<00:00, 22.56it/s]
Loading 0:  99%|█████████▉| 359/363 [00:14<00:00, 26.57it/s]
                                                            
Job cloudyu-nemo-dpo-v22-v4-mkmlizer completed after 115.16s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v22-v4-mkmlizer
Pipeline stage MKMLizer completed in 115.65s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-nemo-dpo-v22-v4
Waiting for inference service cloudyu-nemo-dpo-v22-v4 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cloudyu-nemo-dpo-v22-v4 ready after 241.0585265159607s
Pipeline stage MKMLDeployer completed in 241.58s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1199402809143066s
Received healthy response to inference request in 1.7342402935028076s
Received healthy response to inference request in 2.3339462280273438s
Received healthy response to inference request in 1.7116436958312988s
Received healthy response to inference request in 1.7697198390960693s
5 requests
0 failed requests
5th percentile: 1.7161630153656007
10th percentile: 1.7206823348999023
20th percentile: 1.7297209739685058
30th percentile: 1.74133620262146
40th percentile: 1.7555280208587647
50th percentile: 1.7697198390960693
60th percentile: 1.9098080158233643
70th percentile: 2.049896192550659
80th percentile: 2.162741470336914
90th percentile: 2.248343849182129
95th percentile: 2.2911450386047365
99th percentile: 2.325385990142822
mean time: 1.9338980674743653
Pipeline stage StressChecker completed in 10.88s
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 2.64s
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 2.24s
Shutdown handler de-registered
cloudyu-nemo-dpo-v22_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 0.09s
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-v22-v4-profiler
Waiting for inference service cloudyu-nemo-dpo-v22-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 3295.33s
Shutdown handler de-registered
cloudyu-nemo-dpo-v22_v4 status is now inactive due to auto deactivation removed underperforming models