cloudyu-nemo-dpo-v19

developer_uid: cloudyu

submission_id: cloudyu-nemo-dpo-v19_v1

model_name: cloudyu-nemo-dpo-v19_v1

model_group: cloudyu/Nemo-DPO-V19

status: inactive

timestamp: 2024-12-16T07:36:49+00:00

num_battles: 13078

num_wins: 6764

celo_rating: 1275.9

family_friendly_score: 0.5636

family_friendly_standard_error: 0.007013630158484265

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': 0.6203117938657617, 'latency_mean': 1.6120355212688446, 'latency_p50': 1.6059931516647339, 'latency_p90': 1.783756637573242}, {'batch_size': 3, 'throughput': 1.1445460769598401, 'latency_mean': 2.6089108860492707, 'latency_p50': 2.6249115467071533, 'latency_p90': 2.9118409156799316}, {'batch_size': 5, 'throughput': 1.4129086132452964, 'latency_mean': 3.5213436913490295, 'latency_p50': 3.50623881816864, 'latency_p90': 3.913575768470764}, {'batch_size': 6, 'throughput': 1.4523004980789014, 'latency_mean': 4.105907953977585, 'latency_p50': 4.116466641426086, 'latency_p90': 4.523166942596435}, {'batch_size': 8, 'throughput': 1.5338515013231508, 'latency_mean': 5.182324050664902, 'latency_p50': 5.152202248573303, 'latency_p90': 5.815317583084107}, {'batch_size': 10, 'throughput': 1.5865025576338783, 'latency_mean': 6.2560406124591825, 'latency_p50': 6.185589075088501, 'latency_p90': 7.188461446762085}]

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: 1.43

us_pacific_date: 2024-12-15

win_ratio: 0.5172044655146046

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, '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-v1-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v19-v1-mkmlizer to finish
cloudyu-nemo-dpo-v19-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v19-v1-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v19-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v19-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v19-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v19-v1-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v19-v1-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v19-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v19-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v19-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v19-v1-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v19-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v19-v1-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v19-v1-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v19-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v19-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v19-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-nemo-dpo-v19-v1-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v19-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v19-v1-mkmlizer: Downloaded to shared memory in 45.460s
cloudyu-nemo-dpo-v19-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfjzdojct, device:0
cloudyu-nemo-dpo-v19-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v19-v1-mkmlizer: quantized model in 38.705s
cloudyu-nemo-dpo-v19-v1-mkmlizer: Processed model cloudyu/Nemo-DPO-V19 in 84.166s
cloudyu-nemo-dpo-v19-v1-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v19-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v19-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v1
cloudyu-nemo-dpo-v19-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v1/config.json
cloudyu-nemo-dpo-v19-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v1/special_tokens_map.json
cloudyu-nemo-dpo-v19-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v1/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v19-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 27.97it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 48.98it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 46.55it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 43.35it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 48.79it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 44.01it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 41.78it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 46.91it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 44.60it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 33.92it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:11, 25.74it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:09, 31.41it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:08, 32.97it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:07, 36.63it/s]
Loading 0:  23%|██▎       | 85/363 [00:02<00:07, 38.93it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 41.49it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 40.91it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 39.37it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:06, 41.62it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:06, 40.92it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:06, 40.37it/s]
Loading 0:  35%|███▍      | 126/363 [00:03<00:04, 48.01it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:05, 45.28it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:05, 44.27it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 33.58it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 34.03it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 32.47it/s]
Loading 0:  43%|████▎     | 157/363 [00:04<00:05, 39.08it/s]
Loading 0:  45%|████▍     | 163/363 [00:04<00:05, 39.51it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:04, 39.75it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 44.97it/s]
Loading 0:  50%|████▉     | 180/363 [00:04<00:03, 45.93it/s]
Loading 0:  51%|█████     | 185/363 [00:04<00:04, 37.16it/s]
Loading 0:  53%|█████▎    | 192/363 [00:04<00:04, 42.27it/s]
Loading 0:  54%|█████▍    | 197/363 [00:04<00:04, 39.71it/s]
Loading 0:  56%|█████▌    | 202/363 [00:05<00:03, 40.76it/s]
Loading 0:  57%|█████▋    | 207/363 [00:05<00:03, 41.55it/s]
Loading 0:  58%|█████▊    | 212/363 [00:05<00:04, 36.07it/s]
Loading 0:  60%|██████    | 218/363 [00:05<00:03, 41.25it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:04, 28.78it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 29.50it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 28.57it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 34.31it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 33.85it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:03, 36.42it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:03, 34.99it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 36.50it/s]
Loading 0:  71%|███████▏  | 259/363 [00:06<00:02, 34.98it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 38.38it/s]
Loading 0:  74%|███████▍  | 268/363 [00:07<00:02, 36.83it/s]
Loading 0:  75%|███████▌  | 273/363 [00:07<00:02, 39.30it/s]
Loading 0:  77%|███████▋  | 278/363 [00:07<00:02, 39.17it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:02, 39.07it/s]
Loading 0:  79%|███████▉  | 286/363 [00:07<00:02, 36.59it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 38.68it/s]
Loading 0:  81%|████████▏ | 295/363 [00:07<00:01, 36.69it/s]
Loading 0:  82%|████████▏ | 299/363 [00:07<00:01, 37.47it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:29,  2.02it/s]
Loading 0:  85%|████████▍ | 307/363 [00:15<00:22,  2.54it/s]
Loading 0:  86%|████████▌ | 312/363 [00:15<00:13,  3.75it/s]
Loading 0:  88%|████████▊ | 320/363 [00:15<00:06,  6.43it/s]
Loading 0:  90%|████████▉ | 326/363 [00:15<00:04,  8.78it/s]
Loading 0:  91%|█████████ | 330/363 [00:15<00:03, 10.53it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 15.89it/s]
Loading 0:  94%|█████████▍| 343/363 [00:15<00:01, 19.26it/s]
Loading 0:  96%|█████████▌| 348/363 [00:16<00:00, 20.79it/s]
Loading 0:  98%|█████████▊| 355/363 [00:16<00:00, 27.44it/s]
Loading 0:  99%|█████████▉| 360/363 [00:16<00:00, 29.89it/s]
                                                            
Job cloudyu-nemo-dpo-v19-v1-mkmlizer completed after 114.41s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v19-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.42s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-nemo-dpo-v19-v1
Waiting for inference service cloudyu-nemo-dpo-v19-v1 to be ready
Inference service cloudyu-nemo-dpo-v19-v1 ready after 220.8578495979309s
Pipeline stage MKMLDeployer completed in 221.41s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8918609619140625s
Received healthy response to inference request in 1.6730680465698242s
Received healthy response to inference request in 1.7572956085205078s
Received healthy response to inference request in 1.8086466789245605s
Received healthy response to inference request in 2.0042591094970703s
5 requests
0 failed requests
5th percentile: 1.689913558959961
10th percentile: 1.7067590713500977
20th percentile: 1.740450096130371
30th percentile: 1.7675658226013184
40th percentile: 1.7881062507629395
50th percentile: 1.8086466789245605
60th percentile: 1.8419323921203614
70th percentile: 1.875218105316162
80th percentile: 1.9143405914306642
90th percentile: 1.9592998504638672
95th percentile: 1.9817794799804687
99th percentile: 1.99976318359375
mean time: 1.827026081085205
Pipeline stage StressChecker completed in 10.58s
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 2.26s
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 1.99s
Shutdown handler de-registered
cloudyu-nemo-dpo-v19_v1 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 2784.92s
Shutdown handler de-registered
cloudyu-nemo-dpo-v19_v1 status is now inactive due to auto deactivation removed underperforming models