developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v21_v3
model_name: cloudyu-nemo-dpo-v21_v1
model_group: cloudyu/Nemo-DPO-V21
status: inactive
timestamp: 2024-12-17T13:17:18+00:00
num_battles: 16174
num_wins: 8507
celo_rating: 1281.67
family_friendly_score: 0.5606
family_friendly_standard_error: 0.007018940660812
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': 0.6042258351768874, 'latency_mean': 1.654914721250534, 'latency_p50': 1.6539244651794434, 'latency_p90': 1.8270907640457152}, {'batch_size': 3, 'throughput': 1.1247112667643255, 'latency_mean': 2.665473860502243, 'latency_p50': 2.65657639503479, 'latency_p90': 2.9542254209518433}, {'batch_size': 5, 'throughput': 1.3569432103486434, 'latency_mean': 3.6747532153129576, 'latency_p50': 3.672035813331604, 'latency_p90': 4.134225630760192}, {'batch_size': 6, 'throughput': 1.4173883220857946, 'latency_mean': 4.212535711526871, 'latency_p50': 4.220951676368713, 'latency_p90': 4.730537939071655}, {'batch_size': 8, 'throughput': 1.4739353695085204, 'latency_mean': 5.398421485424041, 'latency_p50': 5.397704601287842, 'latency_p90': 6.091842269897461}, {'batch_size': 10, 'throughput': 1.5206990076323588, 'latency_mean': 6.522659238576889, 'latency_p50': 6.5383689403533936, 'latency_p90': 7.44913489818573}]
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: 1.36
us_pacific_date: 2024-12-17
win_ratio: 0.5259676023247187
generation_params: {'temperature': 0.99, '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-v3-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v21-v3-mkmlizer to finish
cloudyu-nemo-dpo-v21-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v21-v3-mkmlizer: ║ _____ __ __ ║
cloudyu-nemo-dpo-v21-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-nemo-dpo-v21-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-nemo-dpo-v21-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-nemo-dpo-v21-v3-mkmlizer: ║ /___/ ║
cloudyu-nemo-dpo-v21-v3-mkmlizer: ║ ║
cloudyu-nemo-dpo-v21-v3-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-nemo-dpo-v21-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-nemo-dpo-v21-v3-mkmlizer: ║ https://mk1.ai ║
cloudyu-nemo-dpo-v21-v3-mkmlizer: ║ ║
cloudyu-nemo-dpo-v21-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-nemo-dpo-v21-v3-mkmlizer: ║ belonging to: ║
cloudyu-nemo-dpo-v21-v3-mkmlizer: ║ ║
cloudyu-nemo-dpo-v21-v3-mkmlizer: ║ Chai Research Corp. ║
cloudyu-nemo-dpo-v21-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-nemo-dpo-v21-v3-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-nemo-dpo-v21-v3-mkmlizer: ║ ║
cloudyu-nemo-dpo-v21-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
cloudyu-nemo-dpo-v21-v3-mkmlizer: Downloaded to shared memory in 47.634s
cloudyu-nemo-dpo-v21-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpb3fdzhho, device:0
cloudyu-nemo-dpo-v21-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v21-v3-mkmlizer: quantized model in 36.943s
cloudyu-nemo-dpo-v21-v3-mkmlizer: Processed model cloudyu/Nemo-DPO-V21 in 84.577s
cloudyu-nemo-dpo-v21-v3-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v21-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v21-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v3
cloudyu-nemo-dpo-v21-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v3/tokenizer_config.json
cloudyu-nemo-dpo-v21-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v3/tokenizer.json
cloudyu-nemo-dpo-v21-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v3/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v21-v3-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 27.99it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 48.01it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 43.61it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:08, 42.31it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 48.32it/s] Loading 0: 10%|█ | 37/363 [00:00<00:07, 44.71it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 42.71it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 47.92it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 44.56it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 34.11it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:09, 32.86it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 38.90it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:07, 39.90it/s] Loading 0: 23%|██▎ | 83/363 [00:02<00:06, 40.47it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:05, 45.55it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:06, 44.41it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 43.45it/s] Loading 0: 30%|██▉ | 108/363 [00:02<00:05, 49.62it/s] Loading 0: 31%|███▏ | 114/363 [00:02<00:05, 45.01it/s] Loading 0: 33%|███▎ | 119/363 [00:02<00:05, 44.41it/s] Loading 0: 35%|███▍ | 126/363 [00:02<00:04, 49.64it/s] Loading 0: 36%|███▋ | 132/363 [00:03<00:04, 47.66it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:05, 44.93it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 34.41it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 34.72it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 34.33it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:04, 41.61it/s] Loading 0: 45%|████▍ | 163/363 [00:03<00:04, 41.90it/s] Loading 0: 46%|████▋ | 168/363 [00:04<00:04, 42.27it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:03, 47.80it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:03, 46.52it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:04, 42.33it/s] Loading 0: 53%|█████▎ | 192/363 [00:04<00:03, 45.75it/s] Loading 0: 54%|█████▍ | 197/363 [00:04<00:03, 43.38it/s] Loading 0: 56%|█████▌ | 202/363 [00:04<00:03, 43.54it/s] Loading 0: 57%|█████▋ | 208/363 [00:04<00:03, 43.61it/s] Loading 0: 59%|█████▊ | 213/363 [00:05<00:03, 43.64it/s] Loading 0: 61%|██████ | 220/363 [00:05<00:02, 49.92it/s] Loading 0: 62%|██████▏ | 226/363 [00:05<00:04, 32.23it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:03, 34.17it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:03, 40.44it/s] Loading 0: 67%|██████▋ | 244/363 [00:05<00:03, 39.49it/s] Loading 0: 69%|██████▊ | 249/363 [00:05<00:02, 40.03it/s] Loading 0: 70%|███████ | 255/363 [00:06<00:02, 44.48it/s] Loading 0: 72%|███████▏ | 260/363 [00:06<00:02, 43.49it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 43.52it/s] Loading 0: 74%|███████▍ | 270/363 [00:06<00:02, 44.52it/s] Loading 0: 76%|███████▌ | 275/363 [00:06<00:02, 36.84it/s] Loading 0: 78%|███████▊ | 282/363 [00:06<00:01, 42.27it/s] Loading 0: 79%|███████▉ | 287/363 [00:06<00:01, 40.72it/s] Loading 0: 80%|████████ | 292/363 [00:06<00:01, 39.83it/s] Loading 0: 82%|████████▏ | 297/363 [00:07<00:01, 38.60it/s] Loading 0: 83%|████████▎ | 302/363 [00:07<00:01, 40.94it/s] Loading 0: 85%|████████▍ | 307/363 [00:14<00:24, 2.33it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:15, 3.23it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:08, 5.26it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:05, 7.17it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:03, 9.20it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 13.10it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:01, 16.51it/s] Loading 0: 96%|█████████▌| 349/363 [00:15<00:00, 19.73it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 25.80it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 29.26it/s]
Job cloudyu-nemo-dpo-v21-v3-mkmlizer completed after 115.49s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v21-v3-mkmlizer
Pipeline stage MKMLizer completed in 116.01s
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-v21-v3
Waiting for inference service cloudyu-nemo-dpo-v21-v3 to be ready
Inference service cloudyu-nemo-dpo-v21-v3 ready after 231.43423557281494s
Pipeline stage MKMLDeployer completed in 231.96s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.30002760887146s
Received healthy response to inference request in 1.6376655101776123s
Received healthy response to inference request in 1.6691200733184814s
Received healthy response to inference request in 2.472179412841797s
Received healthy response to inference request in 1.7644987106323242s
5 requests
0 failed requests
5th percentile: 1.6439564228057861
10th percentile: 1.65024733543396
20th percentile: 1.6628291606903076
30th percentile: 1.68819580078125
40th percentile: 1.7263472557067872
50th percentile: 1.7644987106323242
60th percentile: 1.9787102699279784
70th percentile: 2.1929218292236325
80th percentile: 2.3344579696655274
90th percentile: 2.403318691253662
95th percentile: 2.4377490520477294
99th percentile: 2.4652933406829836
mean time: 1.968698263168335
Pipeline stage StressChecker completed in 11.20s
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 2.18s
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 1.97s
Shutdown handler de-registered
cloudyu-nemo-dpo-v21_v3 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 3377.84s
Shutdown handler de-registered
cloudyu-nemo-dpo-v21_v3 status is now inactive due to auto deactivation removed underperforming models