developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v20_v12
model_name: cloudyu-nemo-dpo-v20_v1
model_group: cloudyu/Nemo-DPO-V20
status: inactive
timestamp: 2024-12-21T09:00:22+00:00
num_battles: 19418
num_wins: 9866
celo_rating: 1272.3
family_friendly_score: 0.5598000000000001
family_friendly_standard_error: 0.007020312813543283
submission_type: basic
model_repo: cloudyu/Nemo-DPO-V20
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6120382419976107, 'latency_mean': 1.6337901067733764, 'latency_p50': 1.6341031789779663, 'latency_p90': 1.8018194913864136}, {'batch_size': 3, 'throughput': 1.134147703678857, 'latency_mean': 2.6382616090774538, 'latency_p50': 2.643797516822815, 'latency_p90': 2.881143665313721}, {'batch_size': 5, 'throughput': 1.396120278215287, 'latency_mean': 3.5676542210578917, 'latency_p50': 3.5663377046585083, 'latency_p90': 4.040744590759277}, {'batch_size': 6, 'throughput': 1.4584176264166062, 'latency_mean': 4.083790719509125, 'latency_p50': 4.071150541305542, 'latency_p90': 4.551339197158813}, {'batch_size': 8, 'throughput': 1.5201241541907324, 'latency_mean': 5.2366967248916625, 'latency_p50': 5.225389361381531, 'latency_p90': 5.929602694511414}, {'batch_size': 10, 'throughput': 1.5458583578583425, 'latency_mean': 6.421023881435394, 'latency_p50': 6.526673316955566, 'latency_p90': 7.179609966278076}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-nemo-dpo-v20_v1
is_internal_developer: False
language_model: cloudyu/Nemo-DPO-V20
model_size: 13B
ranking_group: single
throughput_3p7s: 1.42
us_pacific_date: 2024-12-21
win_ratio: 0.5080852816973942
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-v20-v12-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v20-v12-mkmlizer to finish
cloudyu-nemo-dpo-v20-v12-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v20-v12-mkmlizer: ║ _____ __ __ ║
cloudyu-nemo-dpo-v20-v12-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-nemo-dpo-v20-v12-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-nemo-dpo-v20-v12-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-nemo-dpo-v20-v12-mkmlizer: ║ /___/ ║
cloudyu-nemo-dpo-v20-v12-mkmlizer: ║ ║
cloudyu-nemo-dpo-v20-v12-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-nemo-dpo-v20-v12-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-nemo-dpo-v20-v12-mkmlizer: ║ https://mk1.ai ║
cloudyu-nemo-dpo-v20-v12-mkmlizer: ║ ║
cloudyu-nemo-dpo-v20-v12-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-nemo-dpo-v20-v12-mkmlizer: ║ belonging to: ║
cloudyu-nemo-dpo-v20-v12-mkmlizer: ║ ║
cloudyu-nemo-dpo-v20-v12-mkmlizer: ║ Chai Research Corp. ║
cloudyu-nemo-dpo-v20-v12-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-nemo-dpo-v20-v12-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-nemo-dpo-v20-v12-mkmlizer: ║ ║
cloudyu-nemo-dpo-v20-v12-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v20-v12-mkmlizer: Downloaded to shared memory in 46.827s
cloudyu-nemo-dpo-v20-v12-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8n031t9n, device:0
cloudyu-nemo-dpo-v20-v12-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v20-v12-mkmlizer: quantized model in 35.724s
cloudyu-nemo-dpo-v20-v12-mkmlizer: Processed model cloudyu/Nemo-DPO-V20 in 82.551s
cloudyu-nemo-dpo-v20-v12-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v20-v12-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v20-v12-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v12
cloudyu-nemo-dpo-v20-v12-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v12/config.json
cloudyu-nemo-dpo-v20-v12-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v12/special_tokens_map.json
cloudyu-nemo-dpo-v20-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v12/tokenizer_config.json
cloudyu-nemo-dpo-v20-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v12/tokenizer.json
cloudyu-nemo-dpo-v20-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v12/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v20-v12-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:11, 31.17it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 53.10it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 48.02it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:06, 49.93it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 52.46it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 48.23it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 45.19it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 50.11it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 46.35it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 36.82it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:07, 37.70it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:06, 41.92it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:06, 41.07it/s] Loading 0: 23%|██▎ | 83/363 [00:01<00:06, 41.34it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:05, 46.45it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:06, 43.71it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 43.08it/s] Loading 0: 30%|██▉ | 108/363 [00:02<00:05, 49.46it/s] Loading 0: 31%|███▏ | 114/363 [00:02<00:05, 44.79it/s] Loading 0: 33%|███▎ | 119/363 [00:02<00:05, 43.53it/s] Loading 0: 35%|███▍ | 126/363 [00:02<00:04, 47.85it/s] Loading 0: 36%|███▌ | 131/363 [00:02<00:05, 46.19it/s] Loading 0: 37%|███▋ | 136/363 [00:03<00:05, 38.21it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 34.18it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 34.95it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 34.14it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:05, 40.64it/s] Loading 0: 45%|████▍ | 163/363 [00:03<00:04, 40.25it/s] Loading 0: 46%|████▋ | 168/363 [00:03<00:04, 40.43it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 46.03it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:04, 43.34it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:04, 42.49it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 47.30it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 43.91it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 42.45it/s] Loading 0: 58%|█████▊ | 211/363 [00:04<00:03, 47.16it/s] Loading 0: 60%|█████▉ | 216/363 [00:04<00:03, 47.48it/s] Loading 0: 61%|██████ | 221/363 [00:05<00:02, 47.76it/s] Loading 0: 62%|██████▏ | 226/363 [00:05<00:04, 30.35it/s] Loading 0: 63%|██████▎ | 230/363 [00:05<00:04, 30.58it/s] Loading 0: 65%|██████▌ | 237/363 [00:05<00:03, 38.81it/s] Loading 0: 67%|██████▋ | 242/363 [00:05<00:03, 39.62it/s] Loading 0: 68%|██████▊ | 247/363 [00:05<00:02, 40.70it/s] Loading 0: 70%|██████▉ | 253/363 [00:06<00:02, 40.17it/s] Loading 0: 71%|███████ | 258/363 [00:06<00:02, 40.16it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 45.70it/s] Loading 0: 75%|███████▍ | 271/363 [00:06<00:02, 43.77it/s] Loading 0: 76%|███████▌ | 276/363 [00:06<00:02, 43.06it/s] Loading 0: 78%|███████▊ | 283/363 [00:06<00:01, 47.55it/s] Loading 0: 80%|███████▉ | 289/363 [00:06<00:01, 44.87it/s] Loading 0: 81%|████████ | 294/363 [00:06<00:01, 43.77it/s] Loading 0: 83%|████████▎ | 300/363 [00:07<00:01, 47.72it/s] Loading 0: 84%|████████▍ | 305/363 [00:13<00:21, 2.65it/s] Loading 0: 85%|████████▌ | 309/363 [00:13<00:15, 3.39it/s] Loading 0: 86%|████████▌ | 313/363 [00:13<00:11, 4.38it/s] Loading 0: 88%|████████▊ | 319/363 [00:14<00:06, 6.48it/s] Loading 0: 89%|████████▉ | 324/363 [00:14<00:04, 8.68it/s] Loading 0: 91%|█████████ | 329/363 [00:14<00:02, 11.47it/s] Loading 0: 92%|█████████▏| 334/363 [00:14<00:01, 14.85it/s] Loading 0: 93%|█████████▎| 339/363 [00:14<00:01, 17.25it/s] Loading 0: 96%|█████████▌| 347/363 [00:14<00:00, 24.79it/s] Loading 0: 97%|█████████▋| 352/363 [00:14<00:00, 28.37it/s] Loading 0: 98%|█████████▊| 357/363 [00:14<00:00, 27.79it/s]
Job cloudyu-nemo-dpo-v20-v12-mkmlizer completed after 104.52s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v20-v12-mkmlizer
Pipeline stage MKMLizer completed in 105.02s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-nemo-dpo-v20-v12
Waiting for inference service cloudyu-nemo-dpo-v20-v12 to be ready
Inference service cloudyu-nemo-dpo-v20-v12 ready after 261.078138589859s
Pipeline stage MKMLDeployer completed in 261.59s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.157973051071167s
Received healthy response to inference request in 1.6413395404815674s
Received healthy response to inference request in 1.6653265953063965s
Received healthy response to inference request in 1.8679518699645996s
Received healthy response to inference request in 1.7344584465026855s
5 requests
0 failed requests
5th percentile: 1.6461369514465332
10th percentile: 1.650934362411499
20th percentile: 1.6605291843414307
30th percentile: 1.6791529655456543
40th percentile: 1.70680570602417
50th percentile: 1.7344584465026855
60th percentile: 1.7878558158874511
70th percentile: 1.8412531852722167
80th percentile: 1.9259561061859132
90th percentile: 2.04196457862854
95th percentile: 2.0999688148498534
99th percentile: 2.146372203826904
mean time: 1.8134099006652833
Pipeline stage StressChecker completed in 10.68s
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 0.68s
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 0.70s
Shutdown handler de-registered
cloudyu-nemo-dpo-v20_v12 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 2748.36s
Shutdown handler de-registered
cloudyu-nemo-dpo-v20_v12 status is now inactive due to auto deactivation removed underperforming models