cloudyu-nemo-dpo-v19

developer_uid: cloudyu

submission_id: cloudyu-nemo-dpo-v19_v2

model_name: cloudyu-nemo-dpo-v19_v1

model_group: cloudyu/Nemo-DPO-V19

status: inactive

timestamp: 2024-12-16T07:37:43+00:00

num_battles: 12636

num_wins: 6477

celo_rating: 1273.52

family_friendly_score: 0.5638000000000001

family_friendly_standard_error: 0.00701326685646568

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': 0.6121777902869916, 'latency_mean': 1.633454267978668, 'latency_p50': 1.6352262496948242, 'latency_p90': 1.8142359495162963}, {'batch_size': 3, 'throughput': 1.1236151233457887, 'latency_mean': 2.6661113345623018, 'latency_p50': 2.6427597999572754, 'latency_p90': 2.9483602762222287}, {'batch_size': 5, 'throughput': 1.3423770493307765, 'latency_mean': 3.709735895395279, 'latency_p50': 3.6982980966567993, 'latency_p90': 4.0416419267654415}, {'batch_size': 6, 'throughput': 1.4216001468270263, 'latency_mean': 4.195665947198868, 'latency_p50': 4.235424280166626, 'latency_p90': 4.713482999801636}, {'batch_size': 8, 'throughput': 1.4815654723761935, 'latency_mean': 5.372647485733032, 'latency_p50': 5.356199502944946, 'latency_p90': 6.04805314540863}, {'batch_size': 10, 'throughput': 1.52358788356149, 'latency_mean': 6.50420740365982, 'latency_p50': 6.5045177936553955, 'latency_p90': 7.385931038856507}]

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: 1.35

us_pacific_date: 2024-12-15

win_ratio: 0.5125830959164293

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-v19-v2-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v19-v2-mkmlizer to finish
cloudyu-nemo-dpo-v19-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v19-v2-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v19-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v19-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v19-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v19-v2-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v19-v2-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v19-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v19-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v19-v2-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v19-v2-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v19-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v19-v2-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v19-v2-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v19-v2-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v19-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v19-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-nemo-dpo-v19-v2-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v19-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v19-v2-mkmlizer: Downloaded to shared memory in 31.484s
cloudyu-nemo-dpo-v19-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6hdw9zri, device:0
cloudyu-nemo-dpo-v19-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v19-v2-mkmlizer: quantized model in 36.135s
cloudyu-nemo-dpo-v19-v2-mkmlizer: Processed model cloudyu/Nemo-DPO-V19 in 67.620s
cloudyu-nemo-dpo-v19-v2-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v19-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v19-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v2
cloudyu-nemo-dpo-v19-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v2/special_tokens_map.json
cloudyu-nemo-dpo-v19-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v2/config.json
cloudyu-nemo-dpo-v19-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v2/tokenizer_config.json
cloudyu-nemo-dpo-v19-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v2/tokenizer.json
cloudyu-nemo-dpo-v19-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v2/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v19-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 27.14it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 45.01it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 46.89it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 39.77it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 46.70it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 44.47it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 42.65it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 47.73it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 45.31it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 35.31it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 33.88it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:07, 39.24it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:06, 41.08it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:07, 38.52it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:05, 45.99it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 44.05it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 41.59it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:05, 43.29it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 46.40it/s]
Loading 0:  32%|███▏      | 117/363 [00:02<00:05, 43.90it/s]
Loading 0:  34%|███▍      | 123/363 [00:02<00:05, 42.10it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:05, 40.91it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:04, 46.18it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:05, 44.34it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 32.79it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 31.82it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 37.25it/s]
Loading 0:  44%|████▍     | 161/363 [00:03<00:05, 37.99it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:04, 40.24it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:04, 40.49it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 40.33it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:03, 45.12it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:03, 44.75it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 45.72it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 43.45it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 42.59it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 48.25it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 44.44it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:04, 34.57it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:03, 34.16it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 32.83it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 39.98it/s]
Loading 0:  67%|██████▋   | 244/363 [00:05<00:02, 40.13it/s]
Loading 0:  69%|██████▊   | 249/363 [00:06<00:02, 40.03it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 44.57it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 43.77it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 42.73it/s]
Loading 0:  74%|███████▍  | 270/363 [00:06<00:02, 42.73it/s]
Loading 0:  76%|███████▌  | 275/363 [00:06<00:02, 34.05it/s]
Loading 0:  77%|███████▋  | 280/363 [00:06<00:02, 37.54it/s]
Loading 0:  79%|███████▊  | 285/363 [00:07<00:02, 36.46it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 40.67it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 40.79it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 41.59it/s]
Loading 0:  84%|████████▍ | 306/363 [00:14<00:23,  2.40it/s]
Loading 0:  85%|████████▌ | 310/363 [00:14<00:16,  3.14it/s]
Loading 0:  87%|████████▋ | 315/363 [00:14<00:10,  4.42it/s]
Loading 0:  88%|████████▊ | 321/363 [00:14<00:06,  6.35it/s]
Loading 0:  91%|█████████ | 329/363 [00:14<00:03, 10.01it/s]
Loading 0:  92%|█████████▏| 334/363 [00:14<00:02, 12.63it/s]
Loading 0:  93%|█████████▎| 339/363 [00:14<00:01, 14.96it/s]
Loading 0:  96%|█████████▌| 347/363 [00:15<00:00, 21.44it/s]
Loading 0:  97%|█████████▋| 353/363 [00:15<00:00, 25.05it/s]
Loading 0:  99%|█████████▊| 358/363 [00:15<00:00, 27.93it/s]
                                                            
Job cloudyu-nemo-dpo-v19-v2-mkmlizer completed after 95.32s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v19-v2-mkmlizer
Pipeline stage MKMLizer completed in 95.87s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.21s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-nemo-dpo-v19-v2
Waiting for inference service cloudyu-nemo-dpo-v19-v2 to be ready
Inference service cloudyu-nemo-dpo-v19-v2 ready after 220.74516367912292s
Pipeline stage MKMLDeployer completed in 221.34s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1166183948516846s
Received healthy response to inference request in 1.6107380390167236s
Received healthy response to inference request in 2.157299041748047s
Received healthy response to inference request in 1.8630354404449463s
Received healthy response to inference request in 1.8666470050811768s
5 requests
0 failed requests
5th percentile: 1.6611975193023683
10th percentile: 1.7116569995880127
20th percentile: 1.8125759601593017
30th percentile: 1.8637577533721923
40th percentile: 1.8652023792266845
50th percentile: 1.8666470050811768
60th percentile: 1.96663556098938
70th percentile: 2.066624116897583
80th percentile: 2.124754524230957
90th percentile: 2.1410267829895018
95th percentile: 2.1491629123687743
99th percentile: 2.1556718158721924
mean time: 1.9228675842285157
Pipeline stage StressChecker completed in 11.37s
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 2.51s
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 2.38s
Shutdown handler de-registered
cloudyu-nemo-dpo-v19_v2 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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cloudyu-nemo-dpo-v19-v2-profiler
Waiting for inference service cloudyu-nemo-dpo-v19-v2-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 2753.39s
Shutdown handler de-registered
cloudyu-nemo-dpo-v19_v2 status is now inactive due to auto deactivation removed underperforming models