developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v22_v9
model_name: cloudyu-nemo-dpo-v22_v1
model_group: cloudyu/Nemo-DPO-V22
status: inactive
timestamp: 2024-12-19T11:32:08+00:00
num_battles: 16366
num_wins: 8496
celo_rating: 1277.09
family_friendly_score: 0.5662
family_friendly_standard_error: 0.007008816733229655
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': 0.613801182549492, 'latency_mean': 1.6291345536708832, 'latency_p50': 1.6131465435028076, 'latency_p90': 1.8054450750350952}, {'batch_size': 3, 'throughput': 1.1026773522414053, 'latency_mean': 2.7155385959148406, 'latency_p50': 2.726646900177002, 'latency_p90': 3.0052675724029543}, {'batch_size': 5, 'throughput': 1.3075619457426593, 'latency_mean': 3.806919742822647, 'latency_p50': 3.8432825803756714, 'latency_p90': 4.298455667495728}, {'batch_size': 6, 'throughput': 1.3748433940616986, 'latency_mean': 4.339555381536484, 'latency_p50': 4.35456919670105, 'latency_p90': 4.864085984230042}, {'batch_size': 8, 'throughput': 1.4341737920658564, 'latency_mean': 5.534240416288376, 'latency_p50': 5.573627471923828, 'latency_p90': 6.208909296989441}, {'batch_size': 10, 'throughput': 1.4731349669178555, 'latency_mean': 6.728190897703171, 'latency_p50': 6.695837497711182, 'latency_p90': 7.7026667356491085}]
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: 1.3
us_pacific_date: 2024-12-19
win_ratio: 0.5191250152755713
generation_params: {'temperature': 1.25, 'top_p': 0.95, '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-v9-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v22-v9-mkmlizer to finish
cloudyu-nemo-dpo-v22-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v22-v9-mkmlizer: ║ _____ __ __ ║
cloudyu-nemo-dpo-v22-v9-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-nemo-dpo-v22-v9-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-nemo-dpo-v22-v9-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-nemo-dpo-v22-v9-mkmlizer: ║ /___/ ║
cloudyu-nemo-dpo-v22-v9-mkmlizer: ║ ║
cloudyu-nemo-dpo-v22-v9-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-nemo-dpo-v22-v9-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-nemo-dpo-v22-v9-mkmlizer: ║ https://mk1.ai ║
cloudyu-nemo-dpo-v22-v9-mkmlizer: ║ ║
cloudyu-nemo-dpo-v22-v9-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-nemo-dpo-v22-v9-mkmlizer: ║ belonging to: ║
cloudyu-nemo-dpo-v22-v9-mkmlizer: ║ ║
cloudyu-nemo-dpo-v22-v9-mkmlizer: ║ Chai Research Corp. ║
cloudyu-nemo-dpo-v22-v9-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-nemo-dpo-v22-v9-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-nemo-dpo-v22-v9-mkmlizer: ║ ║
cloudyu-nemo-dpo-v22-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v22-v9-mkmlizer: Downloaded to shared memory in 41.585s
cloudyu-nemo-dpo-v22-v9-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0gsqax_m, device:0
cloudyu-nemo-dpo-v22-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v22-v9-mkmlizer: quantized model in 35.697s
cloudyu-nemo-dpo-v22-v9-mkmlizer: Processed model cloudyu/Nemo-DPO-V22 in 77.282s
cloudyu-nemo-dpo-v22-v9-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v22-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v22-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v9
cloudyu-nemo-dpo-v22-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v9/config.json
cloudyu-nemo-dpo-v22-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v9/special_tokens_map.json
cloudyu-nemo-dpo-v22-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v9/tokenizer_config.json
cloudyu-nemo-dpo-v22-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v9/tokenizer.json
cloudyu-nemo-dpo-v22-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v9/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v22-v9-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 29.18it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 50.61it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 47.11it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:07, 48.16it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 50.93it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 48.24it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 45.83it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 51.12it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 47.82it/s] Loading 0: 17%|█▋ | 60/363 [00:01<00:06, 48.18it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:09, 31.29it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 37.51it/s] Loading 0: 21%|██ | 77/363 [00:01<00:07, 39.84it/s] Loading 0: 23%|██▎ | 82/363 [00:01<00:07, 36.89it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:06, 45.18it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:06, 44.06it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 42.96it/s] Loading 0: 30%|██▉ | 108/363 [00:02<00:05, 49.37it/s] Loading 0: 31%|███▏ | 114/363 [00:02<00:05, 44.98it/s] Loading 0: 33%|███▎ | 119/363 [00:02<00:05, 43.90it/s] Loading 0: 35%|███▍ | 126/363 [00:02<00:04, 49.28it/s] Loading 0: 36%|███▋ | 132/363 [00:02<00:04, 47.09it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:04, 46.54it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 36.16it/s] Loading 0: 40%|████ | 147/363 [00:03<00:05, 36.67it/s] Loading 0: 42%|████▏ | 151/363 [00:03<00:05, 36.65it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:05, 40.81it/s] Loading 0: 45%|████▍ | 162/363 [00:03<00:04, 42.70it/s] Loading 0: 46%|████▌ | 167/363 [00:03<00:05, 36.99it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 45.52it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:04, 43.99it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:04, 42.65it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 46.98it/s] Loading 0: 55%|█████▍ | 198/363 [00:04<00:03, 47.56it/s] Loading 0: 56%|█████▌ | 203/363 [00:04<00:03, 40.19it/s] Loading 0: 58%|█████▊ | 210/363 [00:04<00:03, 46.87it/s] Loading 0: 60%|█████▉ | 216/363 [00:04<00:03, 46.68it/s] Loading 0: 61%|██████ | 221/363 [00:05<00:03, 44.93it/s] Loading 0: 62%|██████▏ | 226/363 [00:05<00:04, 27.67it/s] Loading 0: 63%|██████▎ | 230/363 [00:05<00:04, 28.83it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:03, 38.22it/s] Loading 0: 67%|██████▋ | 244/363 [00:05<00:02, 40.17it/s] Loading 0: 69%|██████▊ | 249/363 [00:05<00:02, 39.71it/s] Loading 0: 71%|███████ | 256/363 [00:06<00:02, 45.65it/s] Loading 0: 72%|███████▏ | 262/363 [00:06<00:02, 44.76it/s] Loading 0: 74%|███████▎ | 267/363 [00:06<00:02, 43.55it/s] Loading 0: 75%|███████▌ | 273/363 [00:06<00:01, 46.23it/s] Loading 0: 77%|███████▋ | 278/363 [00:06<00:01, 45.73it/s] Loading 0: 78%|███████▊ | 284/363 [00:06<00:01, 42.47it/s] Loading 0: 80%|████████ | 291/363 [00:06<00:01, 48.86it/s] Loading 0: 82%|████████▏ | 297/363 [00:06<00:01, 48.90it/s] Loading 0: 83%|████████▎ | 303/363 [00:07<00:01, 45.70it/s] Loading 0: 85%|████████▍ | 308/363 [00:13<00:20, 2.68it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:14, 3.40it/s] Loading 0: 88%|████████▊ | 319/363 [00:14<00:08, 5.20it/s] Loading 0: 89%|████████▉ | 324/363 [00:14<00:05, 6.81it/s] Loading 0: 91%|█████████ | 329/363 [00:14<00:03, 8.92it/s] Loading 0: 92%|█████████▏| 334/363 [00:14<00:02, 11.56it/s] Loading 0: 93%|█████████▎| 339/363 [00:14<00:01, 13.87it/s] Loading 0: 95%|█████████▌| 346/363 [00:14<00:00, 19.62it/s] Loading 0: 97%|█████████▋| 351/363 [00:14<00:00, 23.00it/s] Loading 0: 98%|█████████▊| 356/363 [00:14<00:00, 27.01it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 30.35it/s]
Job cloudyu-nemo-dpo-v22-v9-mkmlizer completed after 105.18s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v22-v9-mkmlizer
Pipeline stage MKMLizer completed in 105.69s
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-v9
Waiting for inference service cloudyu-nemo-dpo-v22-v9 to be ready
Inference service cloudyu-nemo-dpo-v22-v9 ready after 252.0884177684784s
Pipeline stage MKMLDeployer completed in 252.60s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0969557762145996s
Received healthy response to inference request in 1.5192253589630127s
Received healthy response to inference request in 1.6733927726745605s
Received healthy response to inference request in 1.864881992340088s
Received healthy response to inference request in 1.913693904876709s
5 requests
0 failed requests
5th percentile: 1.5500588417053223
10th percentile: 1.5808923244476318
20th percentile: 1.642559289932251
30th percentile: 1.711690616607666
40th percentile: 1.788286304473877
50th percentile: 1.864881992340088
60th percentile: 1.8844067573547363
70th percentile: 1.9039315223693847
80th percentile: 1.9503462791442872
90th percentile: 2.0236510276794433
95th percentile: 2.0603034019470217
99th percentile: 2.089625301361084
mean time: 1.813629961013794
Pipeline stage StressChecker completed in 10.30s
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 2.45s
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 2.36s
Shutdown handler de-registered
cloudyu-nemo-dpo-v22_v9 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 3421.57s
Shutdown handler de-registered
cloudyu-nemo-dpo-v22_v9 status is now inactive due to auto deactivation removed underperforming models