developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v21_v9
model_name: cloudyu-nemo-dpo-v21_v1
model_group: cloudyu/Nemo-DPO-V21
status: inactive
timestamp: 2024-12-18T03:51:25+00:00
num_battles: 16110
num_wins: 8508
celo_rating: 1282.12
family_friendly_score: 0.5552
family_friendly_standard_error: 0.007027844050631744
submission_type: basic
model_repo: cloudyu/Nemo-DPO-V21
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6213892460630415, 'latency_mean': 1.609240711927414, 'latency_p50': 1.6003409624099731, 'latency_p90': 1.7799664974212646}, {'batch_size': 3, 'throughput': 1.1345573126552122, 'latency_mean': 2.6353526663780213, 'latency_p50': 2.6385303735733032, 'latency_p90': 2.896246910095215}, {'batch_size': 5, 'throughput': 1.3915080296883826, 'latency_mean': 3.5844193983078, 'latency_p50': 3.5713967084884644, 'latency_p90': 3.9965147495269777}, {'batch_size': 6, 'throughput': 1.4580510993844458, 'latency_mean': 4.092883927822113, 'latency_p50': 4.089008927345276, 'latency_p90': 4.54094500541687}, {'batch_size': 8, 'throughput': 1.5119964909227557, 'latency_mean': 5.25352685213089, 'latency_p50': 5.226945996284485, 'latency_p90': 5.882047963142395}, {'batch_size': 10, 'throughput': 1.5629978078569533, 'latency_mean': 6.348972820043564, 'latency_p50': 6.3846235275268555, 'latency_p90': 7.147456431388855}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-nemo-dpo-v21_v1
is_internal_developer: False
language_model: cloudyu/Nemo-DPO-V21
model_size: 13B
ranking_group: single
throughput_3p7s: 1.41
us_pacific_date: 2024-12-17
win_ratio: 0.5281191806331471
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-v21-v9-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v21-v9-mkmlizer to finish
cloudyu-nemo-dpo-v21-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v21-v9-mkmlizer: ║ _____ __ __ ║
cloudyu-nemo-dpo-v21-v9-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-nemo-dpo-v21-v9-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-nemo-dpo-v21-v9-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-nemo-dpo-v21-v9-mkmlizer: ║ /___/ ║
cloudyu-nemo-dpo-v21-v9-mkmlizer: ║ ║
cloudyu-nemo-dpo-v21-v9-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-nemo-dpo-v21-v9-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-nemo-dpo-v21-v9-mkmlizer: ║ https://mk1.ai ║
cloudyu-nemo-dpo-v21-v9-mkmlizer: ║ ║
cloudyu-nemo-dpo-v21-v9-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-nemo-dpo-v21-v9-mkmlizer: ║ belonging to: ║
cloudyu-nemo-dpo-v21-v9-mkmlizer: ║ ║
cloudyu-nemo-dpo-v21-v9-mkmlizer: ║ Chai Research Corp. ║
cloudyu-nemo-dpo-v21-v9-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-nemo-dpo-v21-v9-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-nemo-dpo-v21-v9-mkmlizer: ║ ║
cloudyu-nemo-dpo-v21-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v21-v9-mkmlizer: Downloaded to shared memory in 32.610s
cloudyu-nemo-dpo-v21-v9-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5eyjuado, device:0
cloudyu-nemo-dpo-v21-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v21-v9-mkmlizer: quantized model in 37.029s
cloudyu-nemo-dpo-v21-v9-mkmlizer: Processed model cloudyu/Nemo-DPO-V21 in 69.640s
cloudyu-nemo-dpo-v21-v9-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v21-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v21-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v9
cloudyu-nemo-dpo-v21-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v9/config.json
cloudyu-nemo-dpo-v21-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v9/special_tokens_map.json
cloudyu-nemo-dpo-v21-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v9/tokenizer_config.json
cloudyu-nemo-dpo-v21-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v9/tokenizer.json
cloudyu-nemo-dpo-v21-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v9/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v21-v9-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 27.75it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 47.49it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 44.03it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:08, 41.92it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 48.35it/s] Loading 0: 10%|█ | 37/363 [00:00<00:07, 46.24it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 44.87it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 50.20it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 46.53it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 35.10it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:09, 33.04it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 39.23it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:07, 40.20it/s] Loading 0: 23%|██▎ | 83/363 [00:02<00:06, 40.75it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:05, 46.14it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:06, 43.61it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 43.07it/s] Loading 0: 30%|██▉ | 108/363 [00:02<00:05, 49.56it/s] Loading 0: 31%|███▏ | 114/363 [00:02<00:05, 45.43it/s] Loading 0: 33%|███▎ | 119/363 [00:02<00:05, 44.60it/s] Loading 0: 35%|███▍ | 126/363 [00:02<00:04, 49.54it/s] Loading 0: 36%|███▋ | 132/363 [00:03<00:04, 47.43it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:04, 46.64it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 35.41it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 35.87it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 35.05it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:04, 42.15it/s] Loading 0: 45%|████▍ | 163/363 [00:03<00:04, 42.87it/s] Loading 0: 46%|████▋ | 168/363 [00:03<00:04, 43.42it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:03, 48.28it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:03, 46.73it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:03, 44.52it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 49.15it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 46.09it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 42.10it/s] Loading 0: 58%|█████▊ | 211/363 [00:04<00:03, 46.26it/s] Loading 0: 60%|█████▉ | 216/363 [00:04<00:03, 46.65it/s] Loading 0: 61%|██████ | 222/363 [00:05<00:03, 44.38it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:04, 30.73it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:04, 28.79it/s] Loading 0: 65%|██████▌ | 237/363 [00:05<00:03, 33.60it/s] Loading 0: 66%|██████▋ | 241/363 [00:05<00:03, 32.76it/s] Loading 0: 68%|██████▊ | 246/363 [00:05<00:03, 35.17it/s] Loading 0: 69%|██████▉ | 250/363 [00:06<00:03, 34.57it/s] Loading 0: 71%|███████ | 256/363 [00:06<00:02, 38.83it/s] Loading 0: 72%|███████▏ | 261/363 [00:06<00:02, 41.09it/s] Loading 0: 73%|███████▎ | 266/363 [00:06<00:02, 35.08it/s] Loading 0: 75%|███████▌ | 273/363 [00:06<00:02, 42.87it/s] Loading 0: 77%|███████▋ | 278/363 [00:06<00:02, 42.26it/s] Loading 0: 78%|███████▊ | 283/363 [00:06<00:01, 42.36it/s] Loading 0: 79%|███████▉ | 288/363 [00:06<00:01, 43.51it/s] Loading 0: 81%|████████ | 293/363 [00:07<00:02, 33.97it/s] Loading 0: 82%|████████▏ | 299/363 [00:07<00:01, 38.68it/s] Loading 0: 84%|████████▎ | 304/363 [00:14<00:24, 2.42it/s] Loading 0: 85%|████████▍ | 308/363 [00:14<00:17, 3.12it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:12, 4.08it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:06, 6.82it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:03, 9.28it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:02, 11.76it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 16.48it/s] Loading 0: 95%|█████████▍| 344/363 [00:15<00:00, 19.95it/s] Loading 0: 96%|█████████▌| 349/363 [00:15<00:00, 22.79it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 28.98it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 31.35it/s]
Job cloudyu-nemo-dpo-v21-v9-mkmlizer completed after 94.31s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v21-v9-mkmlizer
Pipeline stage MKMLizer completed in 94.83s
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-v21-v9
Waiting for inference service cloudyu-nemo-dpo-v21-v9 to be ready
Inference service cloudyu-nemo-dpo-v21-v9 ready after 220.7363760471344s
Pipeline stage MKMLDeployer completed in 221.31s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.421143054962158s
Received healthy response to inference request in 1.9372637271881104s
Received healthy response to inference request in 1.8065757751464844s
Received healthy response to inference request in 1.7137987613677979s
Received healthy response to inference request in 1.784907341003418s
5 requests
0 failed requests
5th percentile: 1.728020477294922
10th percentile: 1.742242193222046
20th percentile: 1.770685625076294
30th percentile: 1.7892410278320312
40th percentile: 1.797908401489258
50th percentile: 1.8065757751464844
60th percentile: 1.8588509559631348
70th percentile: 1.9111261367797852
80th percentile: 2.03403959274292
90th percentile: 2.227591323852539
95th percentile: 2.3243671894073485
99th percentile: 2.401787881851196
mean time: 1.9327377319335937
Pipeline stage StressChecker completed in 11.00s
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 2.73s
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 2.29s
Shutdown handler de-registered
cloudyu-nemo-dpo-v21_v9 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-v21-v9-profiler
Waiting for inference service cloudyu-nemo-dpo-v21-v9-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 3400.96s
Shutdown handler de-registered
cloudyu-nemo-dpo-v21_v9 status is now inactive due to auto deactivation removed underperforming models