cloudyu-nemo-dpo-v16

developer_uid: cloudyu

submission_id: cloudyu-nemo-dpo-v16_v9

model_name: cloudyu-nemo-dpo-v16_v1

model_group: cloudyu/Nemo-DPO-V16

status: inactive

timestamp: 2024-12-08T12:37:37+00:00

num_battles: 20380

num_wins: 10484

celo_rating: 1272.48

family_friendly_score: 0.5522

family_friendly_standard_error: 0.007032427177013638

submission_type: basic

model_repo: cloudyu/Nemo-DPO-V16

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6178269286505963, 'latency_mean': 1.6184789311885834, 'latency_p50': 1.6265751123428345, 'latency_p90': 1.7971628665924073}, {'batch_size': 3, 'throughput': 1.1357997103622783, 'latency_mean': 2.632000722885132, 'latency_p50': 2.615994691848755, 'latency_p90': 2.9148340940475466}, {'batch_size': 5, 'throughput': 1.3757624276021416, 'latency_mean': 3.6132742309570314, 'latency_p50': 3.6187392473220825, 'latency_p90': 4.044785046577454}, {'batch_size': 6, 'throughput': 1.4496637115543929, 'latency_mean': 4.106609793901444, 'latency_p50': 4.15385365486145, 'latency_p90': 4.6262282371521}, {'batch_size': 8, 'throughput': 1.5273158317057378, 'latency_mean': 5.220588973760605, 'latency_p50': 5.228992581367493, 'latency_p90': 5.84894962310791}, {'batch_size': 10, 'throughput': 1.5621091314960653, 'latency_mean': 6.342373040914535, 'latency_p50': 6.3375643491744995, 'latency_p90': 7.126078200340271}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cloudyu-nemo-dpo-v16_v1

is_internal_developer: False

language_model: cloudyu/Nemo-DPO-V16

model_size: 13B

ranking_group: single

throughput_3p7s: 1.4

us_pacific_date: 2024-12-08

win_ratio: 0.5144259077526987

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-v16-v9-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v16-v9-mkmlizer to finish
cloudyu-nemo-dpo-v16-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v16-v9-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v16-v9-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v16-v9-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v16-v9-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v16-v9-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v16-v9-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v16-v9-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v16-v9-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v16-v9-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v16-v9-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v16-v9-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v16-v9-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v16-v9-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v16-v9-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v16-v9-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v16-v9-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-nemo-dpo-v16-v9-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v16-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v16-v9-mkmlizer: Downloaded to shared memory in 36.947s
cloudyu-nemo-dpo-v16-v9-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphcbvqz8r, device:0
cloudyu-nemo-dpo-v16-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
cloudyu-nemo-dpo-v16-v9-mkmlizer: quantized model in 35.293s
cloudyu-nemo-dpo-v16-v9-mkmlizer: Processed model cloudyu/Nemo-DPO-V16 in 72.240s
cloudyu-nemo-dpo-v16-v9-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v16-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v16-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v9
cloudyu-nemo-dpo-v16-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v9/config.json
cloudyu-nemo-dpo-v16-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v9/special_tokens_map.json
cloudyu-nemo-dpo-v16-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v9/tokenizer.json
cloudyu-nemo-dpo-v16-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v9/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v16-v9-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 27.35it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 46.95it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 43.63it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 44.96it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 52.51it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 49.37it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:06, 50.84it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:05, 52.99it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 50.30it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 36.22it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 36.35it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 40.81it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:06, 42.89it/s]
Loading 0:  23%|██▎       | 82/363 [00:01<00:07, 36.27it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 44.56it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 43.67it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 41.64it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 47.74it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:05, 43.64it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:05, 41.20it/s]
Loading 0:  34%|███▍      | 125/363 [00:02<00:05, 45.40it/s]
Loading 0:  36%|███▌      | 130/363 [00:02<00:05, 45.96it/s]
Loading 0:  37%|███▋      | 136/363 [00:03<00:05, 41.66it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 36.46it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:05, 36.80it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:05, 36.05it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:04, 42.65it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 41.70it/s]
Loading 0:  46%|████▋     | 168/363 [00:03<00:04, 39.17it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:04, 43.14it/s]
Loading 0:  49%|████▉     | 179/363 [00:04<00:04, 43.14it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:03, 44.78it/s]
Loading 0:  52%|█████▏    | 190/363 [00:04<00:03, 44.47it/s]
Loading 0:  54%|█████▎    | 195/363 [00:04<00:03, 44.46it/s]
Loading 0:  56%|█████▌    | 202/363 [00:04<00:03, 49.85it/s]
Loading 0:  57%|█████▋    | 208/363 [00:04<00:03, 47.53it/s]
Loading 0:  59%|█████▊    | 213/363 [00:04<00:03, 47.61it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:02, 53.20it/s]
Loading 0:  62%|██████▏   | 226/363 [00:05<00:03, 35.78it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:03, 37.16it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:02, 43.22it/s]
Loading 0:  67%|██████▋   | 244/363 [00:05<00:02, 43.69it/s]
Loading 0:  69%|██████▊   | 249/363 [00:05<00:02, 43.97it/s]
Loading 0:  71%|███████   | 256/363 [00:05<00:02, 49.04it/s]
Loading 0:  72%|███████▏  | 262/363 [00:06<00:02, 47.62it/s]
Loading 0:  74%|███████▎  | 267/363 [00:06<00:02, 47.26it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:01, 51.85it/s]
Loading 0:  77%|███████▋  | 280/363 [00:06<00:01, 49.29it/s]
Loading 0:  79%|███████▉  | 286/363 [00:06<00:01, 49.38it/s]
Loading 0:  80%|████████  | 292/363 [00:06<00:01, 50.84it/s]
Loading 0:  82%|████████▏ | 298/363 [00:06<00:01, 48.54it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:20,  2.84it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:15,  3.56it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:11,  4.53it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:05,  7.31it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:03,  9.79it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:02, 12.41it/s]
Loading 0:  93%|█████████▎| 339/363 [00:14<00:01, 17.28it/s]
Loading 0:  96%|█████████▌| 347/363 [00:14<00:00, 23.58it/s]
Loading 0:  97%|█████████▋| 353/363 [00:14<00:00, 26.37it/s]
Loading 0:  99%|█████████▊| 358/363 [00:14<00:00, 29.01it/s]
                                                            
Job cloudyu-nemo-dpo-v16-v9-mkmlizer completed after 94.7s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v16-v9-mkmlizer
Pipeline stage MKMLizer completed in 95.20s
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-v16-v9
Waiting for inference service cloudyu-nemo-dpo-v16-v9 to be ready
Inference service cloudyu-nemo-dpo-v16-v9 ready after 180.61004614830017s
Pipeline stage MKMLDeployer completed in 181.11s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.015312433242798s
Received healthy response to inference request in 1.5431973934173584s
Received healthy response to inference request in 1.8913393020629883s
Received healthy response to inference request in 1.6432077884674072s
Received healthy response to inference request in 1.658984661102295s
5 requests
0 failed requests
5th percentile: 1.5631994724273681
10th percentile: 1.5832015514373778
20th percentile: 1.6232057094573975
30th percentile: 1.6463631629943847
40th percentile: 1.6526739120483398
50th percentile: 1.658984661102295
60th percentile: 1.7519265174865724
70th percentile: 1.8448683738708496
80th percentile: 1.9161339282989502
90th percentile: 1.965723180770874
95th percentile: 1.990517807006836
99th percentile: 2.0103535079956054
mean time: 1.7504083156585692
Pipeline stage StressChecker completed in 10.08s
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 2.17s
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-v16_v9 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 2801.51s
Shutdown handler de-registered
cloudyu-nemo-dpo-v16_v9 status is now inactive due to auto deactivation removed underperforming models