developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v16_v6
model_name: cloudyu-nemo-dpo-v16_v1
model_group: cloudyu/Nemo-DPO-V16
status: inactive
timestamp: 2024-12-06T10:13:33+00:00
num_battles: 13458
num_wins: 6911
celo_rating: 1273.25
family_friendly_score: 0.5492
family_friendly_standard_error: 0.007036751523252757
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': 0.6054828253061356, 'latency_mean': 1.6515196537971497, 'latency_p50': 1.647281527519226, 'latency_p90': 1.8244188785552977}, {'batch_size': 3, 'throughput': 1.1175836886877748, 'latency_mean': 2.6723747193813323, 'latency_p50': 2.700922131538391, 'latency_p90': 3.017772889137268}, {'batch_size': 5, 'throughput': 1.3489676247371256, 'latency_mean': 3.685742210149765, 'latency_p50': 3.697176218032837, 'latency_p90': 4.14194962978363}, {'batch_size': 6, 'throughput': 1.4129714329186067, 'latency_mean': 4.22410088300705, 'latency_p50': 4.263251066207886, 'latency_p90': 4.784583401679993}, {'batch_size': 8, 'throughput': 1.4871618288332369, 'latency_mean': 5.32701241850853, 'latency_p50': 5.331974506378174, 'latency_p90': 6.053825569152832}, {'batch_size': 10, 'throughput': 1.5220314559834895, 'latency_mean': 6.511765568256378, 'latency_p50': 6.533768177032471, 'latency_p90': 7.4980569124221805}]
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: 1.36
us_pacific_date: 2024-12-06
win_ratio: 0.5135235547629663
generation_params: {'temperature': 1.25, 'top_p': 0.99, 'min_p': 0.01, 'top_k': 80, 'presence_penalty': 0.1, 'frequency_penalty': 0.05, '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-v6-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v16-v6-mkmlizer to finish
cloudyu-nemo-dpo-v16-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v16-v6-mkmlizer: ║ _____ __ __ ║
cloudyu-nemo-dpo-v16-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-nemo-dpo-v16-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-nemo-dpo-v16-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-nemo-dpo-v16-v6-mkmlizer: ║ /___/ ║
cloudyu-nemo-dpo-v16-v6-mkmlizer: ║ ║
cloudyu-nemo-dpo-v16-v6-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-nemo-dpo-v16-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-nemo-dpo-v16-v6-mkmlizer: ║ https://mk1.ai ║
cloudyu-nemo-dpo-v16-v6-mkmlizer: ║ ║
cloudyu-nemo-dpo-v16-v6-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-nemo-dpo-v16-v6-mkmlizer: ║ belonging to: ║
cloudyu-nemo-dpo-v16-v6-mkmlizer: ║ ║
cloudyu-nemo-dpo-v16-v6-mkmlizer: ║ Chai Research Corp. ║
cloudyu-nemo-dpo-v16-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-nemo-dpo-v16-v6-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-nemo-dpo-v16-v6-mkmlizer: ║ ║
cloudyu-nemo-dpo-v16-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
cloudyu-nemo-dpo-v16-v6-mkmlizer: Downloaded to shared memory in 27.137s
cloudyu-nemo-dpo-v16-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplj6u8ada, device:0
cloudyu-nemo-dpo-v16-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v16-v6-mkmlizer: quantized model in 36.360s
cloudyu-nemo-dpo-v16-v6-mkmlizer: Processed model cloudyu/Nemo-DPO-V16 in 63.497s
cloudyu-nemo-dpo-v16-v6-mkmlizer: creating bucket guanaco-mkml-models
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
cloudyu-nemo-dpo-v16-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v6/special_tokens_map.json
cloudyu-nemo-dpo-v16-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v6/config.json
cloudyu-nemo-dpo-v16-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v6/tokenizer_config.json
cloudyu-nemo-dpo-v16-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v6/tokenizer.json
cloudyu-nemo-dpo-v16-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v6/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v16-v6-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:13, 25.73it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:08, 41.90it/s] Loading 0: 5%|▍ | 17/363 [00:00<00:08, 39.92it/s] Loading 0: 6%|▌ | 22/363 [00:00<00:08, 39.69it/s] Loading 0: 7%|▋ | 27/363 [00:00<00:08, 40.83it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:10, 32.39it/s] Loading 0: 11%|█ | 39/363 [00:01<00:08, 39.87it/s] Loading 0: 12%|█▏ | 44/363 [00:01<00:07, 39.91it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:07, 40.22it/s] Loading 0: 15%|█▍ | 54/363 [00:01<00:07, 42.07it/s] Loading 0: 17%|█▋ | 60/363 [00:01<00:07, 40.04it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:10, 27.18it/s] Loading 0: 20%|█▉ | 71/363 [00:01<00:09, 32.27it/s] Loading 0: 21%|██ | 75/363 [00:02<00:08, 32.11it/s] Loading 0: 22%|██▏ | 81/363 [00:02<00:07, 36.76it/s] Loading 0: 24%|██▎ | 86/363 [00:02<00:07, 38.92it/s] Loading 0: 25%|██▌ | 91/363 [00:02<00:08, 33.69it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:06, 41.00it/s] Loading 0: 28%|██▊ | 103/363 [00:02<00:06, 42.23it/s] Loading 0: 30%|███ | 110/363 [00:02<00:05, 44.74it/s] Loading 0: 32%|███▏ | 116/363 [00:03<00:05, 46.01it/s] Loading 0: 33%|███▎ | 121/363 [00:03<00:05, 46.23it/s] Loading 0: 35%|███▍ | 126/363 [00:03<00:05, 46.21it/s] Loading 0: 36%|███▌ | 131/363 [00:03<00:04, 46.93it/s] Loading 0: 37%|███▋ | 136/363 [00:03<00:05, 39.25it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 32.88it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 33.86it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 32.99it/s] Loading 0: 43%|████▎ | 157/363 [00:04<00:05, 39.99it/s] Loading 0: 45%|████▍ | 163/363 [00:04<00:05, 39.76it/s] Loading 0: 46%|████▋ | 168/363 [00:04<00:04, 39.43it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 45.17it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:04, 44.27it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:04, 42.48it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 47.15it/s] Loading 0: 55%|█████▍ | 198/363 [00:04<00:03, 47.28it/s] Loading 0: 56%|█████▌ | 203/363 [00:05<00:04, 38.46it/s] Loading 0: 58%|█████▊ | 210/363 [00:05<00:03, 45.49it/s] Loading 0: 59%|█████▉ | 215/363 [00:05<00:03, 44.62it/s] Loading 0: 61%|██████ | 220/363 [00:05<00:03, 45.83it/s] Loading 0: 62%|██████▏ | 225/363 [00:05<00:05, 27.55it/s] Loading 0: 63%|██████▎ | 230/363 [00:06<00:04, 28.58it/s] Loading 0: 65%|██████▌ | 237/363 [00:06<00:03, 36.34it/s] Loading 0: 67%|██████▋ | 242/363 [00:06<00:03, 37.32it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:03, 38.01it/s] Loading 0: 70%|██████▉ | 253/363 [00:06<00:02, 38.32it/s] Loading 0: 71%|███████ | 258/363 [00:06<00:02, 38.12it/s] Loading 0: 73%|███████▎ | 264/363 [00:06<00:02, 42.81it/s] Loading 0: 74%|███████▍ | 269/363 [00:06<00:02, 42.24it/s] Loading 0: 75%|███████▌ | 274/363 [00:07<00:02, 43.29it/s] Loading 0: 77%|███████▋ | 279/363 [00:07<00:01, 43.89it/s] Loading 0: 78%|███████▊ | 284/363 [00:07<00:02, 36.20it/s] Loading 0: 80%|████████ | 291/363 [00:07<00:01, 43.55it/s] Loading 0: 82%|████████▏ | 296/363 [00:07<00:01, 44.16it/s] Loading 0: 83%|████████▎ | 302/363 [00:07<00:01, 47.93it/s] Loading 0: 85%|████████▍ | 308/363 [00:14<00:20, 2.67it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:15, 3.39it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:07, 5.45it/s] Loading 0: 90%|████████▉ | 325/363 [00:14<00:05, 7.10it/s] Loading 0: 91%|█████████ | 330/363 [00:15<00:03, 8.92it/s] Loading 0: 93%|█████████▎| 337/363 [00:15<00:02, 12.85it/s] Loading 0: 94%|█████████▍| 342/363 [00:15<00:01, 15.74it/s] Loading 0: 96%|█████████▌| 347/363 [00:15<00:00, 19.33it/s] Loading 0: 97%|█████████▋| 353/363 [00:15<00:00, 22.90it/s] Loading 0: 99%|█████████▊| 358/363 [00:15<00:00, 26.44it/s]
Job cloudyu-nemo-dpo-v16-v6-mkmlizer completed after 99.02s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v16-v6-mkmlizer
Pipeline stage MKMLizer completed in 101.31s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.23s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-nemo-dpo-v16-v6
Waiting for inference service cloudyu-nemo-dpo-v16-v6 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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cloudyu-nemo-dpo-v16-v6 ready after 186.65588545799255s
Pipeline stage MKMLDeployer completed in 188.77s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.132735013961792s
Received healthy response to inference request in 1.9430201053619385s
Received healthy response to inference request in 1.5363459587097168s
Received healthy response to inference request in 1.6993074417114258s
Received healthy response to inference request in 1.6530656814575195s
5 requests
0 failed requests
5th percentile: 1.5596899032592773
10th percentile: 1.583033847808838
20th percentile: 1.629721736907959
30th percentile: 1.6623140335083009
40th percentile: 1.6808107376098633
50th percentile: 1.6993074417114258
60th percentile: 1.7967925071716309
70th percentile: 1.894277572631836
80th percentile: 1.9809630870819093
90th percentile: 2.0568490505218504
95th percentile: 2.094792032241821
99th percentile: 2.1251464176177977
mean time: 1.7928948402404785
Pipeline stage StressChecker completed in 10.35s
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 2.31s
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 2.06s
Shutdown handler de-registered
cloudyu-nemo-dpo-v16_v6 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 2751.13s
Shutdown handler de-registered
cloudyu-nemo-dpo-v16_v6 status is now inactive due to auto deactivation removed underperforming models