developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v16_v8
model_name: cloudyu-nemo-dpo-v16_v1
model_group: cloudyu/Nemo-DPO-V16
status: inactive
timestamp: 2024-12-07T02:28:17+00:00
num_battles: 11684
num_wins: 5938
celo_rating: 1269.34
family_friendly_score: 0.5512
family_friendly_standard_error: 0.007033897354951947
submission_type: basic
model_repo: cloudyu/Nemo-DPO-V16
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6149511496676204, 'latency_mean': 1.626078609228134, 'latency_p50': 1.626153588294983, 'latency_p90': 1.7930387020111085}, {'batch_size': 3, 'throughput': 1.136311766373039, 'latency_mean': 2.6298000633716585, 'latency_p50': 2.6146684885025024, 'latency_p90': 2.900081515312195}, {'batch_size': 5, 'throughput': 1.3659850464887082, 'latency_mean': 3.639423063993454, 'latency_p50': 3.623233914375305, 'latency_p90': 4.040512466430664}, {'batch_size': 6, 'throughput': 1.4508443770971833, 'latency_mean': 4.117083660364151, 'latency_p50': 4.104596018791199, 'latency_p90': 4.645673632621765}, {'batch_size': 8, 'throughput': 1.5140706977424614, 'latency_mean': 5.245666288137436, 'latency_p50': 5.295562744140625, 'latency_p90': 5.879326701164246}, {'batch_size': 10, 'throughput': 1.5601185500754904, 'latency_mean': 6.349987500905991, 'latency_p50': 6.36890184879303, 'latency_p90': 7.195280408859253}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-nemo-dpo-v16_v1
is_internal_developer: False
language_model: cloudyu/Nemo-DPO-V16
model_size: 13B
ranking_group: single
throughput_3p7s: 1.39
us_pacific_date: 2024-12-06
win_ratio: 0.5082163642588154
generation_params: {'temperature': 1.3, '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-v16-v8-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v16-v8-mkmlizer to finish
cloudyu-nemo-dpo-v16-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v16-v8-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v16-v8-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v16-v8-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v16-v8-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v16-v8-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v16-v8-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v16-v8-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v16-v8-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v16-v8-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v16-v8-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v16-v8-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v16-v8-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v16-v8-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v16-v8-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v16-v8-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v16-v8-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-nemo-dpo-v16-v8-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v16-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v16-v8-mkmlizer: Downloaded to shared memory in 31.130s
cloudyu-nemo-dpo-v16-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpov6l9xh4, device:0
cloudyu-nemo-dpo-v16-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v16-v8-mkmlizer: quantized model in 34.924s
cloudyu-nemo-dpo-v16-v8-mkmlizer: Processed model cloudyu/Nemo-DPO-V16 in 66.055s
cloudyu-nemo-dpo-v16-v8-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v16-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v16-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v8
cloudyu-nemo-dpo-v16-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v8/config.json
cloudyu-nemo-dpo-v16-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v8/special_tokens_map.json
cloudyu-nemo-dpo-v16-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v8/tokenizer_config.json
cloudyu-nemo-dpo-v16-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v8/tokenizer.json
cloudyu-nemo-dpo-v16-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v8/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v16-v8-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 29.21it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:07, 44.05it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:06, 49.10it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:05, 57.24it/s]
Loading 0:  10%|█         | 38/363 [00:00<00:05, 54.26it/s]
Loading 0:  12%|█▏        | 44/363 [00:00<00:06, 52.61it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:06, 47.04it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:05, 54.20it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:07, 40.15it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:06, 43.87it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 44.92it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 44.83it/s]
Loading 0:  25%|██▍       | 90/363 [00:01<00:05, 48.91it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 44.77it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:05, 44.82it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:05, 50.36it/s]
Loading 0:  32%|███▏      | 116/363 [00:02<00:05, 49.09it/s]
Loading 0:  33%|███▎      | 121/363 [00:02<00:04, 49.27it/s]
Loading 0:  35%|███▍      | 127/363 [00:02<00:05, 45.68it/s]
Loading 0:  37%|███▋      | 135/363 [00:02<00:04, 53.30it/s]
Loading 0:  39%|███▉      | 141/363 [00:02<00:04, 51.61it/s]
Loading 0:  40%|████      | 147/363 [00:03<00:05, 37.43it/s]
Loading 0:  42%|████▏     | 152/363 [00:03<00:05, 38.66it/s]
Loading 0:  44%|████▎     | 158/363 [00:03<00:05, 37.84it/s]
Loading 0:  46%|████▌     | 166/363 [00:03<00:04, 45.95it/s]
Loading 0:  47%|████▋     | 172/363 [00:03<00:04, 45.16it/s]
Loading 0:  49%|████▉     | 177/363 [00:03<00:04, 44.36it/s]
Loading 0:  51%|█████     | 184/363 [00:03<00:03, 49.45it/s]
Loading 0:  52%|█████▏    | 190/363 [00:04<00:03, 47.79it/s]
Loading 0:  54%|█████▎    | 195/363 [00:04<00:03, 46.52it/s]
Loading 0:  56%|█████▌    | 202/363 [00:04<00:03, 50.09it/s]
Loading 0:  57%|█████▋    | 208/363 [00:04<00:03, 47.85it/s]
Loading 0:  59%|█████▊    | 213/363 [00:04<00:03, 47.69it/s]
Loading 0:  61%|██████    | 221/363 [00:04<00:02, 55.72it/s]
Loading 0:  63%|██████▎   | 227/363 [00:04<00:03, 38.37it/s]
Loading 0:  64%|██████▍   | 232/363 [00:05<00:03, 38.88it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:02, 43.34it/s]
Loading 0:  67%|██████▋   | 244/363 [00:05<00:02, 42.13it/s]
Loading 0:  69%|██████▊   | 249/363 [00:05<00:02, 40.02it/s]
Loading 0:  71%|███████   | 256/363 [00:05<00:02, 45.54it/s]
Loading 0:  72%|███████▏  | 262/363 [00:05<00:02, 44.83it/s]
Loading 0:  74%|███████▎  | 267/363 [00:05<00:02, 45.29it/s]
Loading 0:  75%|███████▌  | 274/363 [00:05<00:01, 50.35it/s]
Loading 0:  77%|███████▋  | 280/363 [00:06<00:01, 48.22it/s]
Loading 0:  79%|███████▊  | 285/363 [00:06<00:01, 43.97it/s]
Loading 0:  80%|████████  | 291/363 [00:06<00:01, 46.62it/s]
Loading 0:  82%|████████▏ | 296/363 [00:06<00:01, 45.68it/s]
Loading 0:  83%|████████▎ | 303/363 [00:06<00:01, 46.40it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:20,  2.69it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:14,  3.42it/s]
Loading 0:  88%|████████▊ | 321/363 [00:13<00:07,  5.70it/s]
Loading 0:  91%|█████████ | 330/363 [00:13<00:03,  8.64it/s]
Loading 0:  93%|█████████▎| 339/363 [00:13<00:01, 12.26it/s]
Loading 0:  96%|█████████▌| 347/363 [00:14<00:00, 16.51it/s]
Loading 0:  97%|█████████▋| 353/363 [00:14<00:00, 19.44it/s]
Loading 0:  99%|█████████▉| 359/363 [00:14<00:00, 23.34it/s]
                                                            

Job cloudyu-nemo-dpo-v16-v8-mkmlizer completed after 94.87s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v16-v8-mkmlizer
Pipeline stage MKMLizer completed in 95.77s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.62s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-nemo-dpo-v16-v8
Waiting for inference service cloudyu-nemo-dpo-v16-v8 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cloudyu-nemo-dpo-v16-v8 ready after 170.63581895828247s
Pipeline stage MKMLDeployer completed in 171.15s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0568044185638428s
Received healthy response to inference request in 1.6166670322418213s
Received healthy response to inference request in 1.6524252891540527s
Received healthy response to inference request in 1.7103633880615234s
Received healthy response to inference request in 1.743157148361206s
5 requests
0 failed requests
5th percentile: 1.6238186836242676
10th percentile: 1.630970335006714
20th percentile: 1.6452736377716064
30th percentile: 1.6640129089355469
40th percentile: 1.6871881484985352
50th percentile: 1.7103633880615234
60th percentile: 1.7234808921813964
70th percentile: 1.7365983963012694
80th percentile: 1.8058866024017335
90th percentile: 1.9313455104827881
95th percentile: 1.9940749645233153
99th percentile: 2.0442585277557375
mean time: 1.7558834552764893
Pipeline stage StressChecker completed in 10.03s
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 2.29s
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 2.22s
Shutdown handler de-registered
cloudyu-nemo-dpo-v16_v8 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 0.11s
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-v16-v8-profiler
Waiting for inference service cloudyu-nemo-dpo-v16-v8-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 2633.22s
Shutdown handler de-registered
cloudyu-nemo-dpo-v16_v8 status is now inactive due to auto deactivation removed underperforming models