developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v23_v2
model_name: cloudyu-nemo-dpo-v23_v2
model_group: cloudyu/Nemo-DPO-V23
status: torndown
timestamp: 2025-01-10T07:42:16+00:00
num_battles: 8686
num_wins: 4475
celo_rating: 1272.32
family_friendly_score: 0.5796
family_friendly_standard_error: 0.006980885903665809
submission_type: basic
model_repo: cloudyu/Nemo-DPO-V23
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6204587906946774, 'latency_mean': 1.6116210579872132, 'latency_p50': 1.6098767518997192, 'latency_p90': 1.7811184406280518}, {'batch_size': 3, 'throughput': 1.161762793580298, 'latency_mean': 2.574692738056183, 'latency_p50': 2.573379397392273, 'latency_p90': 2.8678925752639772}, {'batch_size': 5, 'throughput': 1.404465328557236, 'latency_mean': 3.542192132472992, 'latency_p50': 3.5185075998306274, 'latency_p90': 3.997306203842163}, {'batch_size': 6, 'throughput': 1.496074747936498, 'latency_mean': 3.988540655374527, 'latency_p50': 4.000120162963867, 'latency_p90': 4.517788243293762}, {'batch_size': 8, 'throughput': 1.550841408401514, 'latency_mean': 5.115497207641601, 'latency_p50': 5.141681790351868, 'latency_p90': 5.723745036125183}, {'batch_size': 10, 'throughput': 1.5995307803449892, 'latency_mean': 6.216129552125931, 'latency_p50': 6.206895232200623, 'latency_p90': 6.948957824707031}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-nemo-dpo-v23_v2
is_internal_developer: False
language_model: cloudyu/Nemo-DPO-V23
model_size: 13B
ranking_group: single
throughput_3p7s: 1.45
us_pacific_date: 2025-01-09
win_ratio: 0.5151968685240617
generation_params: {'temperature': 0.95, '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-v23-v2-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v23-v2-mkmlizer to finish
cloudyu-nemo-dpo-v23-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v23-v2-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v23-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v23-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v23-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v23-v2-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v23-v2-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v23-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v23-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v23-v2-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v23-v2-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v23-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v23-v2-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v23-v2-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v23-v2-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v23-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v23-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
cloudyu-nemo-dpo-v23-v2-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v23-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v23-v2-mkmlizer: Downloaded to shared memory in 50.781s
cloudyu-nemo-dpo-v23-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9kohnhaf, device:0
cloudyu-nemo-dpo-v23-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v23-v2-mkmlizer: quantized model in 35.259s
cloudyu-nemo-dpo-v23-v2-mkmlizer: Processed model cloudyu/Nemo-DPO-V23 in 86.041s
cloudyu-nemo-dpo-v23-v2-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v23-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v23-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v2
cloudyu-nemo-dpo-v23-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v2/config.json
cloudyu-nemo-dpo-v23-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v2/special_tokens_map.json
cloudyu-nemo-dpo-v23-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v2/tokenizer_config.json
cloudyu-nemo-dpo-v23-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v2/tokenizer.json
cloudyu-nemo-dpo-v23-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v2/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v23-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<18:00,  2.99s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:47,  1.24it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:42,  3.42it/s]
Loading 0:   5%|▌         | 19/363 [00:06<00:58,  5.87it/s]
Loading 0:   7%|▋         | 24/363 [00:06<00:41,  8.18it/s]
Loading 0:   9%|▉         | 32/363 [00:06<00:24, 13.52it/s]
Loading 0:  10%|█         | 38/363 [00:06<00:18, 17.41it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:16, 18.83it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:13, 23.74it/s]
Loading 0:  15%|█▌        | 56/363 [00:07<00:11, 27.52it/s]
Loading 0:  17%|█▋        | 61/363 [00:07<00:10, 30.12it/s]
Loading 0:  19%|█▊        | 68/363 [00:07<00:07, 37.09it/s]
Loading 0:  20%|██        | 74/363 [00:07<00:07, 38.69it/s]
Loading 0:  22%|██▏       | 79/363 [00:07<00:07, 39.59it/s]
Loading 0:  24%|██▎       | 86/363 [00:07<00:06, 44.87it/s]
Loading 0:  25%|██▌       | 92/363 [00:08<00:06, 43.32it/s]
Loading 0:  27%|██▋       | 97/363 [00:08<00:06, 43.22it/s]
Loading 0:  29%|██▊       | 104/363 [00:08<00:05, 47.70it/s]
Loading 0:  30%|███       | 110/363 [00:08<00:05, 45.25it/s]
Loading 0:  32%|███▏      | 115/363 [00:08<00:05, 44.64it/s]
Loading 0:  33%|███▎      | 121/363 [00:08<00:06, 36.28it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:06, 35.24it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:05, 39.21it/s]
Loading 0:  38%|███▊      | 137/363 [00:09<00:05, 38.96it/s]
Loading 0:  39%|███▉      | 142/363 [00:09<00:05, 39.31it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:04, 44.47it/s]
Loading 0:  43%|████▎     | 155/363 [00:09<00:04, 42.54it/s]
Loading 0:  44%|████▍     | 160/363 [00:09<00:04, 41.73it/s]
Loading 0:  46%|████▌     | 167/363 [00:09<00:04, 46.60it/s]
Loading 0:  48%|████▊     | 173/363 [00:09<00:04, 44.77it/s]
Loading 0:  49%|████▉     | 178/363 [00:10<00:04, 42.81it/s]
Loading 0:  51%|█████     | 184/363 [00:10<00:03, 46.98it/s]
Loading 0:  52%|█████▏    | 189/363 [00:10<00:03, 47.02it/s]
Loading 0:  53%|█████▎    | 194/363 [00:10<00:03, 47.27it/s]
Loading 0:  55%|█████▌    | 200/363 [00:10<00:03, 44.18it/s]
Loading 0:  56%|█████▋    | 205/363 [00:10<00:04, 32.20it/s]
Loading 0:  58%|█████▊    | 212/363 [00:10<00:03, 38.52it/s]
Loading 0:  60%|██████    | 218/363 [00:11<00:03, 38.50it/s]
Loading 0:  61%|██████▏   | 223/363 [00:11<00:03, 39.74it/s]
Loading 0:  63%|██████▎   | 230/363 [00:11<00:02, 45.30it/s]
Loading 0:  65%|██████▍   | 235/363 [00:11<00:02, 45.19it/s]
Loading 0:  66%|██████▌   | 240/363 [00:11<00:03, 37.85it/s]
Loading 0:  68%|██████▊   | 248/363 [00:11<00:02, 45.17it/s]
Loading 0:  70%|██████▉   | 254/363 [00:11<00:02, 43.89it/s]
Loading 0:  71%|███████▏  | 259/363 [00:11<00:02, 42.37it/s]
Loading 0:  73%|███████▎  | 265/363 [00:12<00:02, 46.51it/s]
Loading 0:  74%|███████▍  | 270/363 [00:12<00:02, 46.08it/s]
Loading 0:  76%|███████▌  | 275/363 [00:12<00:01, 46.43it/s]
Loading 0:  77%|███████▋  | 280/363 [00:12<00:01, 47.38it/s]
Loading 0:  79%|███████▊  | 285/363 [00:12<00:02, 29.91it/s]
Loading 0:  81%|████████  | 293/363 [00:12<00:01, 38.35it/s]
Loading 0:  82%|████████▏ | 299/363 [00:12<00:01, 38.58it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:01, 38.89it/s]
Loading 0:  86%|████████▌ | 311/363 [00:13<00:01, 44.72it/s]
Loading 0:  87%|████████▋ | 317/363 [00:13<00:01, 43.40it/s]
Loading 0:  89%|████████▊ | 322/363 [00:13<00:00, 42.53it/s]
Loading 0:  90%|█████████ | 328/363 [00:13<00:00, 46.59it/s]
Loading 0:  92%|█████████▏| 333/363 [00:13<00:00, 47.36it/s]
Loading 0:  93%|█████████▎| 338/363 [00:13<00:00, 47.79it/s]
Loading 0:  95%|█████████▍| 344/363 [00:13<00:00, 45.82it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 43.94it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 48.74it/s]
Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 46.87it/s]
                                                            

Job cloudyu-nemo-dpo-v23-v2-mkmlizer completed after 114.7s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v23-v2-mkmlizer
Pipeline stage MKMLizer completed in 115.54s
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-v23-v2
Waiting for inference service cloudyu-nemo-dpo-v23-v2 to be ready
Inference service cloudyu-nemo-dpo-v23-v2 ready after 371.77298521995544s
Pipeline stage MKMLDeployer completed in 372.31s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0952508449554443s
Received healthy response to inference request in 1.7806658744812012s
Received healthy response to inference request in 1.7600162029266357s
Received healthy response to inference request in 1.707329511642456s
Received healthy response to inference request in 2.1941680908203125s
5 requests
0 failed requests
5th percentile: 1.717866849899292
10th percentile: 1.7284041881561278
20th percentile: 1.7494788646697998
30th percentile: 1.7641461372375489
40th percentile: 1.772406005859375
50th percentile: 1.7806658744812012
60th percentile: 1.9064998626708984
70th percentile: 2.0323338508605957
80th percentile: 2.115034294128418
90th percentile: 2.1546011924743653
95th percentile: 2.1743846416473387
99th percentile: 2.1902114009857176
mean time: 1.9074861049652099
Pipeline stage StressChecker completed in 10.96s
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 0.74s
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 0.65s
Shutdown handler de-registered
cloudyu-nemo-dpo-v23_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
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 2657.35s
Shutdown handler de-registered
cloudyu-nemo-dpo-v23_v2 status is now inactive due to auto deactivation removed underperforming models
cloudyu-nemo-dpo-v23_v2 status is now torndown due to DeploymentManager action