cloudyu-nemo-dpo-v15

developer_uid: cloudyu

submission_id: cloudyu-nemo-dpo-v15_v1

model_name: cloudyu-nemo-dpo-v15_v1

model_group: cloudyu/Nemo-DPO-v15

status: inactive

timestamp: 2024-12-04T10:31:09+00:00

num_battles: 13787

num_wins: 6900

celo_rating: 1263.0

family_friendly_score: 0.562

family_friendly_standard_error: 0.00701649485141976

submission_type: basic

model_repo: cloudyu/Nemo-DPO-v15

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6237115296701763, 'latency_mean': 1.6032370042800903, 'latency_p50': 1.595933437347412, 'latency_p90': 1.7747247219085693}, {'batch_size': 3, 'throughput': 1.1531528297724305, 'latency_mean': 2.591946588754654, 'latency_p50': 2.5897319316864014, 'latency_p90': 2.848110318183899}, {'batch_size': 5, 'throughput': 1.3859341641785337, 'latency_mean': 3.5959172368049623, 'latency_p50': 3.5956417322158813, 'latency_p90': 4.012951326370239}, {'batch_size': 6, 'throughput': 1.4569422707609356, 'latency_mean': 4.096754664182663, 'latency_p50': 4.094006538391113, 'latency_p90': 4.618585562705993}, {'batch_size': 8, 'throughput': 1.5200587420619336, 'latency_mean': 5.231460548639298, 'latency_p50': 5.278192639350891, 'latency_p90': 5.798250913619995}, {'batch_size': 10, 'throughput': 1.5705266627126389, 'latency_mean': 6.306846059560776, 'latency_p50': 6.300707817077637, 'latency_p90': 7.114842104911804}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cloudyu-nemo-dpo-v15_v1

is_internal_developer: False

language_model: cloudyu/Nemo-DPO-v15

model_size: 13B

ranking_group: single

throughput_3p7s: 1.41

us_pacific_date: 2024-12-04

win_ratio: 0.5004714586204395

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-v15-v1-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v15-v1-mkmlizer to finish
cloudyu-nemo-dpo-v15-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v15-v1-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v15-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v15-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v15-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v15-v1-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v15-v1-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v15-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v15-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v15-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v15-v1-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v15-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v15-v1-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v15-v1-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v15-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v15-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v15-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-nemo-dpo-v15-v1-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v15-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v15-v1-mkmlizer: Downloaded to shared memory in 48.978s
cloudyu-nemo-dpo-v15-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmps8rl6n3_, device:0
cloudyu-nemo-dpo-v15-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
cloudyu-nemo-dpo-v15-v1-mkmlizer: quantized model in 35.714s
cloudyu-nemo-dpo-v15-v1-mkmlizer: Processed model cloudyu/Nemo-DPO-v15 in 84.692s
cloudyu-nemo-dpo-v15-v1-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v15-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v15-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v15-v1
cloudyu-nemo-dpo-v15-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v15-v1/config.json
cloudyu-nemo-dpo-v15-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v15-v1/special_tokens_map.json
cloudyu-nemo-dpo-v15-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v15-v1/tokenizer_config.json
cloudyu-nemo-dpo-v15-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v15-v1/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v15-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 27.70it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 47.12it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 46.64it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 42.67it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 48.87it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 48.00it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:06, 46.58it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 51.44it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 48.78it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 37.51it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:07, 37.20it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 41.14it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 42.61it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 42.95it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:05, 48.19it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 46.97it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:05, 45.53it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:04, 51.32it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:05, 46.77it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:05, 45.59it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:04, 50.37it/s]
Loading 0:  36%|███▋      | 132/363 [00:02<00:04, 47.66it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:04, 46.27it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 36.00it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 35.89it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 35.27it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 41.12it/s]
Loading 0:  44%|████▍     | 161/363 [00:03<00:04, 41.75it/s]
Loading 0:  46%|████▌     | 166/363 [00:03<00:04, 43.14it/s]
Loading 0:  47%|████▋     | 171/363 [00:03<00:04, 44.82it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:04, 37.48it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:03, 45.02it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:03, 45.35it/s]
Loading 0:  53%|█████▎    | 194/363 [00:04<00:04, 41.79it/s]
Loading 0:  56%|█████▌    | 202/363 [00:04<00:03, 48.83it/s]
Loading 0:  57%|█████▋    | 208/363 [00:04<00:03, 47.11it/s]
Loading 0:  59%|█████▊    | 213/363 [00:04<00:03, 45.86it/s]
Loading 0:  61%|██████    | 220/363 [00:04<00:02, 51.41it/s]
Loading 0:  62%|██████▏   | 226/363 [00:05<00:04, 33.76it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:03, 35.08it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 41.28it/s]
Loading 0:  67%|██████▋   | 244/363 [00:05<00:02, 40.62it/s]
Loading 0:  69%|██████▊   | 249/363 [00:05<00:02, 39.34it/s]
Loading 0:  71%|███████   | 256/363 [00:05<00:02, 44.35it/s]
Loading 0:  72%|███████▏  | 262/363 [00:06<00:02, 43.41it/s]
Loading 0:  74%|███████▎  | 267/363 [00:06<00:02, 43.21it/s]
Loading 0:  75%|███████▌  | 273/363 [00:06<00:01, 47.27it/s]
Loading 0:  77%|███████▋  | 278/363 [00:06<00:01, 46.40it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 45.70it/s]
Loading 0:  79%|███████▉  | 288/363 [00:06<00:01, 46.28it/s]
Loading 0:  81%|████████  | 293/363 [00:06<00:01, 37.77it/s]
Loading 0:  82%|████████▏ | 299/363 [00:06<00:01, 42.69it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:23,  2.51it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:16,  3.24it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:12,  4.22it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  7.03it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:03,  9.46it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:02, 11.93it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 16.68it/s]
Loading 0:  94%|█████████▍| 343/363 [00:14<00:00, 20.02it/s]
Loading 0:  96%|█████████▌| 348/363 [00:14<00:00, 21.19it/s]
Loading 0:  98%|█████████▊| 355/363 [00:14<00:00, 28.06it/s]
Loading 0:  99%|█████████▉| 360/363 [00:14<00:00, 30.93it/s]
                                                            
Job cloudyu-nemo-dpo-v15-v1-mkmlizer completed after 104.09s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v15-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.61s
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-v15-v1
Waiting for inference service cloudyu-nemo-dpo-v15-v1 to be ready
Inference service cloudyu-nemo-dpo-v15-v1 ready after 160.59484601020813s
Pipeline stage MKMLDeployer completed in 161.14s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9664268493652344s
Received healthy response to inference request in 1.6409997940063477s
Received healthy response to inference request in 1.6395456790924072s
Received healthy response to inference request in 1.4584541320800781s
Received healthy response to inference request in 1.598893404006958s
5 requests
0 failed requests
5th percentile: 1.486541986465454
10th percentile: 1.51462984085083
20th percentile: 1.570805549621582
30th percentile: 1.6070238590240478
40th percentile: 1.6232847690582275
50th percentile: 1.6395456790924072
60th percentile: 1.6401273250579833
70th percentile: 1.6407089710235596
80th percentile: 1.706085205078125
90th percentile: 1.8362560272216797
95th percentile: 1.901341438293457
99th percentile: 1.953409767150879
mean time: 1.6608639717102052
Pipeline stage StressChecker completed in 15.99s
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 2.23s
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 2.13s
Shutdown handler de-registered
cloudyu-nemo-dpo-v15_v1 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
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 2682.84s
Shutdown handler de-registered
cloudyu-nemo-dpo-v15_v1 status is now inactive due to auto deactivation removed underperforming models