developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v22_v8
model_name: cloudyu-nemo-dpo-v22_v1
model_group: cloudyu/Nemo-DPO-V22
status: inactive
timestamp: 2024-12-19T00:33:08+00:00
num_battles: 11939
num_wins: 6273
celo_rating: 1282.19
family_friendly_score: 0.5604
family_friendly_standard_error: 0.007019285433717595
submission_type: basic
model_repo: cloudyu/Nemo-DPO-V22
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6172981525841617, 'latency_mean': 1.6199035358428955, 'latency_p50': 1.6138862371444702, 'latency_p90': 1.8090060949325562}, {'batch_size': 3, 'throughput': 1.1263601632589328, 'latency_mean': 2.658929113149643, 'latency_p50': 2.6544783115386963, 'latency_p90': 3.0018269062042235}, {'batch_size': 5, 'throughput': 1.3694402968195916, 'latency_mean': 3.6309447610378265, 'latency_p50': 3.628402829170227, 'latency_p90': 4.02414755821228}, {'batch_size': 6, 'throughput': 1.4521028178313409, 'latency_mean': 4.117184985876083, 'latency_p50': 4.118093013763428, 'latency_p90': 4.6162107467651365}, {'batch_size': 8, 'throughput': 1.527632882258601, 'latency_mean': 5.205260133743286, 'latency_p50': 5.158917665481567, 'latency_p90': 5.878300046920776}, {'batch_size': 10, 'throughput': 1.5494938013832826, 'latency_mean': 6.409444559812545, 'latency_p50': 6.399672627449036, 'latency_p90': 7.300743174552918}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-nemo-dpo-v22_v1
is_internal_developer: False
language_model: cloudyu/Nemo-DPO-V22
model_size: 13B
ranking_group: single
throughput_3p7s: 1.39
us_pacific_date: 2024-12-18
win_ratio: 0.5254208895217355
generation_params: {'temperature': 1.0, '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-v22-v8-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v22-v8-mkmlizer to finish
cloudyu-nemo-dpo-v22-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v22-v8-mkmlizer: ║ _____ __ __ ║
cloudyu-nemo-dpo-v22-v8-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-nemo-dpo-v22-v8-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-nemo-dpo-v22-v8-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-nemo-dpo-v22-v8-mkmlizer: ║ /___/ ║
cloudyu-nemo-dpo-v22-v8-mkmlizer: ║ ║
cloudyu-nemo-dpo-v22-v8-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-nemo-dpo-v22-v8-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-nemo-dpo-v22-v8-mkmlizer: ║ https://mk1.ai ║
cloudyu-nemo-dpo-v22-v8-mkmlizer: ║ ║
cloudyu-nemo-dpo-v22-v8-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-nemo-dpo-v22-v8-mkmlizer: ║ belonging to: ║
cloudyu-nemo-dpo-v22-v8-mkmlizer: ║ ║
cloudyu-nemo-dpo-v22-v8-mkmlizer: ║ Chai Research Corp. ║
cloudyu-nemo-dpo-v22-v8-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-nemo-dpo-v22-v8-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-nemo-dpo-v22-v8-mkmlizer: ║ ║
cloudyu-nemo-dpo-v22-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v22-v8-mkmlizer: Downloaded to shared memory in 31.642s
cloudyu-nemo-dpo-v22-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpx5zqyvdk, device:0
cloudyu-nemo-dpo-v22-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v22-v8-mkmlizer: quantized model in 35.934s
cloudyu-nemo-dpo-v22-v8-mkmlizer: Processed model cloudyu/Nemo-DPO-V22 in 67.577s
cloudyu-nemo-dpo-v22-v8-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v22-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v22-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v8
cloudyu-nemo-dpo-v22-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v8/config.json
cloudyu-nemo-dpo-v22-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v8/special_tokens_map.json
cloudyu-nemo-dpo-v22-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v8/tokenizer_config.json
cloudyu-nemo-dpo-v22-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v8/tokenizer.json
cloudyu-nemo-dpo-v22-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v8/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v22-v8-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 27.73it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 48.56it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 44.99it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 42.71it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 48.52it/s] Loading 0: 10%|█ | 37/363 [00:00<00:07, 46.29it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 42.56it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:06, 46.25it/s] Loading 0: 15%|█▍ | 53/363 [00:01<00:07, 44.19it/s] Loading 0: 16%|█▌ | 58/363 [00:01<00:06, 45.32it/s] Loading 0: 17%|█▋ | 63/363 [00:01<00:09, 30.54it/s] Loading 0: 19%|█▊ | 68/363 [00:01<00:08, 34.03it/s] Loading 0: 20%|██ | 73/363 [00:01<00:09, 31.61it/s] Loading 0: 22%|██▏ | 81/363 [00:01<00:06, 40.85it/s] Loading 0: 24%|██▍ | 87/363 [00:02<00:06, 41.75it/s] Loading 0: 25%|██▌ | 92/363 [00:02<00:06, 41.92it/s] Loading 0: 27%|██▋ | 99/363 [00:02<00:05, 46.83it/s] Loading 0: 29%|██▉ | 105/363 [00:02<00:05, 44.64it/s] Loading 0: 31%|███ | 112/363 [00:02<00:05, 48.91it/s] Loading 0: 33%|███▎ | 118/363 [00:02<00:05, 40.99it/s] Loading 0: 34%|███▍ | 125/363 [00:02<00:05, 47.24it/s] Loading 0: 36%|███▌ | 131/363 [00:03<00:04, 48.06it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:05, 43.31it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 34.01it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 34.30it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 33.27it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:05, 40.21it/s] Loading 0: 45%|████▍ | 163/363 [00:03<00:05, 39.96it/s] Loading 0: 46%|████▋ | 168/363 [00:04<00:04, 39.79it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 45.65it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:04, 44.16it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:04, 43.00it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 47.84it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 45.28it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 43.44it/s] Loading 0: 58%|█████▊ | 210/363 [00:04<00:03, 47.34it/s] Loading 0: 59%|█████▉ | 215/363 [00:05<00:03, 44.58it/s] Loading 0: 61%|██████ | 220/363 [00:05<00:03, 44.53it/s] Loading 0: 62%|██████▏ | 225/363 [00:05<00:05, 26.23it/s] Loading 0: 63%|██████▎ | 230/363 [00:05<00:04, 28.66it/s] Loading 0: 65%|██████▌ | 237/363 [00:05<00:03, 36.32it/s] Loading 0: 67%|██████▋ | 242/363 [00:05<00:03, 37.79it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:02, 39.12it/s] Loading 0: 69%|██████▉ | 252/363 [00:06<00:02, 41.64it/s] Loading 0: 71%|███████ | 257/363 [00:06<00:02, 36.03it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 43.86it/s] Loading 0: 75%|███████▍ | 271/363 [00:06<00:02, 42.31it/s] Loading 0: 76%|███████▌ | 276/363 [00:06<00:02, 41.29it/s] Loading 0: 78%|███████▊ | 282/363 [00:06<00:01, 45.51it/s] Loading 0: 79%|███████▉ | 287/363 [00:06<00:01, 44.70it/s] Loading 0: 80%|████████ | 292/363 [00:07<00:01, 44.60it/s] Loading 0: 82%|████████▏ | 297/363 [00:07<00:01, 44.62it/s] Loading 0: 83%|████████▎ | 303/363 [00:07<00:01, 42.85it/s] Loading 0: 85%|████████▍ | 308/363 [00:14<00:22, 2.50it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:15, 3.23it/s] Loading 0: 88%|████████▊ | 319/363 [00:14<00:08, 5.04it/s] Loading 0: 89%|████████▉ | 324/363 [00:14<00:05, 6.68it/s] Loading 0: 91%|█████████ | 330/363 [00:14<00:03, 8.98it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 13.39it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:01, 16.67it/s] Loading 0: 96%|█████████▌| 349/363 [00:15<00:00, 19.56it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 25.50it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 28.84it/s]
Job cloudyu-nemo-dpo-v22-v8-mkmlizer completed after 94.0s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v22-v8-mkmlizer
Pipeline stage MKMLizer completed in 94.47s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-nemo-dpo-v22-v8
Waiting for inference service cloudyu-nemo-dpo-v22-v8 to be ready
Inference service cloudyu-nemo-dpo-v22-v8 ready after 251.21527099609375s
Pipeline stage MKMLDeployer completed in 251.75s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0833828449249268s
Received healthy response to inference request in 1.6577410697937012s
Received healthy response to inference request in 1.6640214920043945s
Received healthy response to inference request in 2.4288806915283203s
Received healthy response to inference request in 1.7277982234954834s
5 requests
0 failed requests
5th percentile: 1.65899715423584
10th percentile: 1.6602532386779785
20th percentile: 1.6627654075622558
30th percentile: 1.6767768383026123
40th percentile: 1.702287530899048
50th percentile: 1.7277982234954834
60th percentile: 1.8700320720672607
70th percentile: 2.012265920639038
80th percentile: 2.1524824142456054
90th percentile: 2.290681552886963
95th percentile: 2.3597811222076417
99th percentile: 2.4150607776641846
mean time: 1.9123648643493651
Pipeline stage StressChecker completed in 11.12s
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 2.63s
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 2.42s
Shutdown handler de-registered
cloudyu-nemo-dpo-v22_v8 status is now deployed due to DeploymentManager action
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 3283.45s
Shutdown handler de-registered
cloudyu-nemo-dpo-v22_v8 status is now inactive due to auto deactivation removed underperforming models