developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v23_v4
model_name: cloudyu-nemo-dpo-v23_v2
model_group: cloudyu/Nemo-DPO-V23
status: torndown
timestamp: 2025-01-10T12:40:57+00:00
num_battles: 8882
num_wins: 4575
celo_rating: 1271.3
family_friendly_score: 0.5766
family_friendly_standard_error: 0.00698759529452014
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': 0.6149206495307544, 'latency_mean': 1.6261571431159973, 'latency_p50': 1.6311618089675903, 'latency_p90': 1.7929535627365112}, {'batch_size': 3, 'throughput': 1.1502507879174733, 'latency_mean': 2.603053287267685, 'latency_p50': 2.5999696254730225, 'latency_p90': 2.872869849205017}, {'batch_size': 5, 'throughput': 1.397315094404872, 'latency_mean': 3.571931093931198, 'latency_p50': 3.5769309997558594, 'latency_p90': 3.997035694122314}, {'batch_size': 6, 'throughput': 1.4641043481529377, 'latency_mean': 4.075284167528152, 'latency_p50': 4.082627534866333, 'latency_p90': 4.529690957069397}, {'batch_size': 8, 'throughput': 1.552260823654536, 'latency_mean': 5.129827975034714, 'latency_p50': 5.101555585861206, 'latency_p90': 5.837017345428467}, {'batch_size': 10, 'throughput': 1.5687051567369386, 'latency_mean': 6.31705405831337, 'latency_p50': 6.311972737312317, 'latency_p90': 7.101662731170654}]
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: 1.42
us_pacific_date: 2025-01-10
win_ratio: 0.5150866921864445
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-v23-v4-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v23-v4-mkmlizer to finish
cloudyu-nemo-dpo-v23-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v23-v4-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v23-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v23-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v23-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v23-v4-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v23-v4-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v23-v4-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v23-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v23-v4-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v23-v4-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v23-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v23-v4-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v23-v4-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v23-v4-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v23-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v23-v4-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
cloudyu-nemo-dpo-v23-v4-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v23-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v23-v4-mkmlizer: Downloaded to shared memory in 33.145s
cloudyu-nemo-dpo-v23-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxb17rufe, device:0
cloudyu-nemo-dpo-v23-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v23-v4-mkmlizer: quantized model in 35.857s
cloudyu-nemo-dpo-v23-v4-mkmlizer: Processed model cloudyu/Nemo-DPO-V23 in 69.001s
cloudyu-nemo-dpo-v23-v4-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v23-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v23-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v4
cloudyu-nemo-dpo-v23-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v4/special_tokens_map.json
cloudyu-nemo-dpo-v23-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v4/config.json
cloudyu-nemo-dpo-v23-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v4/tokenizer_config.json
cloudyu-nemo-dpo-v23-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v4/tokenizer.json
cloudyu-nemo-dpo-v23-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v4/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v23-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:10,  3.02s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:50,  1.23it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:43,  3.38it/s]
Loading 0:   5%|▍         | 18/363 [00:06<01:04,  5.37it/s]
Loading 0:   7%|▋         | 24/363 [00:06<00:41,  8.22it/s]
Loading 0:   9%|▉         | 32/363 [00:06<00:24, 13.41it/s]
Loading 0:  10%|█         | 38/363 [00:06<00:18, 17.13it/s]
Loading 0:  12%|█▏        | 43/363 [00:07<00:18, 17.31it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:14, 22.27it/s]
Loading 0:  15%|█▍        | 54/363 [00:07<00:12, 25.39it/s]
Loading 0:  16%|█▋        | 59/363 [00:07<00:10, 28.68it/s]
Loading 0:  18%|█▊        | 64/363 [00:07<00:09, 32.56it/s]
Loading 0:  19%|█▉        | 69/363 [00:07<00:09, 31.70it/s]
Loading 0:  21%|██        | 77/363 [00:07<00:07, 40.28it/s]
Loading 0:  23%|██▎       | 83/363 [00:08<00:06, 40.24it/s]
Loading 0:  24%|██▍       | 88/363 [00:08<00:06, 40.86it/s]
Loading 0:  26%|██▌       | 94/363 [00:08<00:05, 45.17it/s]
Loading 0:  27%|██▋       | 99/363 [00:08<00:06, 43.50it/s]
Loading 0:  29%|██▊       | 104/363 [00:08<00:05, 44.72it/s]
Loading 0:  30%|███       | 110/363 [00:08<00:05, 43.02it/s]
Loading 0:  32%|███▏      | 115/363 [00:08<00:05, 41.55it/s]
Loading 0:  33%|███▎      | 121/363 [00:08<00:06, 34.89it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:06, 34.94it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:06, 38.60it/s]
Loading 0:  38%|███▊      | 137/363 [00:09<00:05, 39.04it/s]
Loading 0:  39%|███▉      | 142/363 [00:09<00:05, 38.62it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:05, 42.65it/s]
Loading 0:  42%|████▏     | 153/363 [00:09<00:05, 41.80it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:04, 42.10it/s]
Loading 0:  45%|████▍     | 163/363 [00:09<00:04, 43.82it/s]
Loading 0:  46%|████▋     | 168/363 [00:10<00:05, 36.20it/s]
Loading 0:  48%|████▊     | 175/363 [00:10<00:04, 43.39it/s]
Loading 0:  50%|████▉     | 180/363 [00:10<00:04, 43.39it/s]
Loading 0:  51%|█████     | 185/363 [00:10<00:04, 43.99it/s]
Loading 0:  52%|█████▏    | 190/363 [00:10<00:03, 45.20it/s]
Loading 0:  54%|█████▎    | 195/363 [00:10<00:04, 36.93it/s]
Loading 0:  56%|█████▌    | 202/363 [00:11<00:04, 33.34it/s]
Loading 0:  57%|█████▋    | 206/363 [00:11<00:04, 33.48it/s]
Loading 0:  58%|█████▊    | 212/363 [00:11<00:04, 37.69it/s]
Loading 0:  60%|█████▉    | 217/363 [00:11<00:03, 39.87it/s]
Loading 0:  61%|██████    | 222/363 [00:11<00:03, 35.90it/s]
Loading 0:  63%|██████▎   | 230/363 [00:11<00:03, 44.26it/s]
Loading 0:  65%|██████▌   | 236/363 [00:11<00:02, 43.38it/s]
Loading 0:  66%|██████▋   | 241/363 [00:11<00:02, 42.17it/s]
Loading 0:  68%|██████▊   | 247/363 [00:12<00:02, 45.39it/s]
Loading 0:  69%|██████▉   | 252/363 [00:12<00:02, 45.35it/s]
Loading 0:  71%|███████   | 257/363 [00:12<00:02, 45.58it/s]
Loading 0:  72%|███████▏  | 263/363 [00:12<00:02, 43.35it/s]
Loading 0:  74%|███████▍  | 268/363 [00:12<00:02, 41.59it/s]
Loading 0:  75%|███████▌  | 274/363 [00:12<00:01, 45.77it/s]
Loading 0:  77%|███████▋  | 279/363 [00:12<00:01, 43.81it/s]
Loading 0:  78%|███████▊  | 284/363 [00:13<00:02, 31.54it/s]
Loading 0:  80%|███████▉  | 289/363 [00:13<00:02, 34.99it/s]
Loading 0:  81%|████████  | 294/363 [00:13<00:02, 31.79it/s]
Loading 0:  83%|████████▎ | 301/363 [00:13<00:01, 38.63it/s]
Loading 0:  84%|████████▍ | 306/363 [00:13<00:01, 40.06it/s]
Loading 0:  86%|████████▌ | 311/363 [00:13<00:01, 42.30it/s]
Loading 0:  87%|████████▋ | 317/363 [00:13<00:01, 43.18it/s]
Loading 0:  89%|████████▊ | 322/363 [00:13<00:00, 43.28it/s]
Loading 0:  90%|█████████ | 328/363 [00:14<00:00, 47.55it/s]
Loading 0:  92%|█████████▏| 333/363 [00:14<00:00, 47.66it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:00, 47.95it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 45.99it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 43.85it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 48.40it/s]
Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 46.28it/s]
                                                            

Job cloudyu-nemo-dpo-v23-v4-mkmlizer completed after 94.04s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v23-v4-mkmlizer
Pipeline stage MKMLizer completed in 94.56s
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-v23-v4
Waiting for inference service cloudyu-nemo-dpo-v23-v4 to be ready
Inference service cloudyu-nemo-dpo-v23-v4 ready after 371.61452436447144s
Pipeline stage MKMLDeployer completed in 372.14s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 7.180203914642334s
Received healthy response to inference request in 1.6327412128448486s
Received healthy response to inference request in 1.7518718242645264s
Received healthy response to inference request in 2.1059374809265137s
Received healthy response to inference request in 1.8518931865692139s
5 requests
0 failed requests
5th percentile: 1.6565673351287842
10th percentile: 1.6803934574127197
20th percentile: 1.7280457019805908
30th percentile: 1.7718760967254639
40th percentile: 1.8118846416473389
50th percentile: 1.8518931865692139
60th percentile: 1.9535109043121337
70th percentile: 2.0551286220550535
80th percentile: 3.1207907676696784
90th percentile: 5.150497341156006
95th percentile: 6.165350627899169
99th percentile: 6.977233257293701
mean time: 2.9045295238494875
Pipeline stage StressChecker completed in 15.89s
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 0.78s
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 0.69s
Shutdown handler de-registered
cloudyu-nemo-dpo-v23_v4 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cloudyu-nemo-dpo-v23-v4-profiler
Waiting for inference service cloudyu-nemo-dpo-v23-v4-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 2715.11s
Shutdown handler de-registered
cloudyu-nemo-dpo-v23_v4 status is now inactive due to auto deactivation removed underperforming models
cloudyu-nemo-dpo-v23_v4 status is now torndown due to DeploymentManager action