cloudyu-nemo-dpo-v14

developer_uid: cloudyu

submission_id: cloudyu-nemo-dpo-v14_v1

model_name: cloudyu-nemo-dpo-v14_v1

model_group: cloudyu/Nemo-DPO-v14

status: inactive

timestamp: 2024-12-04T07:58:08+00:00

num_battles: 10651

num_wins: 4974

celo_rating: 1237.88

family_friendly_score: 0.5538000000000001

family_friendly_standard_error: 0.0070300150782199615

submission_type: basic

model_repo: cloudyu/Nemo-DPO-v14

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6107263171886947, 'latency_mean': 1.6373258352279663, 'latency_p50': 1.6280990839004517, 'latency_p90': 1.8108002185821532}, {'batch_size': 3, 'throughput': 1.128674383870056, 'latency_mean': 2.6470031464099884, 'latency_p50': 2.633095145225525, 'latency_p90': 2.9180907011032104}, {'batch_size': 5, 'throughput': 1.3580931473409223, 'latency_mean': 3.6656463503837586, 'latency_p50': 3.651212215423584, 'latency_p90': 4.10306396484375}, {'batch_size': 6, 'throughput': 1.427652206418332, 'latency_mean': 4.177871743440628, 'latency_p50': 4.191251993179321, 'latency_p90': 4.744070768356323}, {'batch_size': 8, 'throughput': 1.4915616092841608, 'latency_mean': 5.323107079267502, 'latency_p50': 5.318302273750305, 'latency_p90': 6.05344066619873}, {'batch_size': 10, 'throughput': 1.5449590993805016, 'latency_mean': 6.425307754278183, 'latency_p50': 6.466793179512024, 'latency_p90': 7.240386867523193}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cloudyu-nemo-dpo-v14_v1

is_internal_developer: False

language_model: cloudyu/Nemo-DPO-v14

model_size: 13B

ranking_group: single

throughput_3p7s: 1.37

us_pacific_date: 2024-12-03

win_ratio: 0.46699840390573655

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-v14-v1-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v14-v1-mkmlizer to finish
cloudyu-nemo-dpo-v14-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v14-v1-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v14-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v14-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v14-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v14-v1-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v14-v1-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v14-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v14-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v14-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v14-v1-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v14-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v14-v1-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v14-v1-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v14-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v14-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v14-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-nemo-dpo-v14-v1-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v14-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v14-v1-mkmlizer: Downloaded to shared memory in 47.502s
cloudyu-nemo-dpo-v14-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpx2ayo8v3, device:0
cloudyu-nemo-dpo-v14-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v14-v1-mkmlizer: quantized model in 35.360s
cloudyu-nemo-dpo-v14-v1-mkmlizer: Processed model cloudyu/Nemo-DPO-v14 in 82.863s
cloudyu-nemo-dpo-v14-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v14-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v14-v1
cloudyu-nemo-dpo-v14-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v14-v1/config.json
cloudyu-nemo-dpo-v14-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v14-v1/special_tokens_map.json
cloudyu-nemo-dpo-v14-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v14-v1/tokenizer_config.json
cloudyu-nemo-dpo-v14-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v14-v1/tokenizer.json
cloudyu-nemo-dpo-v14-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v14-v1/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v14-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 27.07it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 46.25it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 46.22it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 45.66it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 52.30it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 50.37it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:06, 51.00it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:05, 53.15it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 50.16it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 36.46it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 36.98it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:06, 41.72it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 42.87it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 43.48it/s]
Loading 0:  25%|██▍       | 90/363 [00:01<00:05, 49.27it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 47.93it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:05, 45.32it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 50.84it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:05, 46.28it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:05, 43.48it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:04, 47.52it/s]
Loading 0:  36%|███▌      | 131/363 [00:02<00:04, 47.64it/s]
Loading 0:  37%|███▋      | 136/363 [00:03<00:05, 40.74it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 34.62it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 35.18it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 34.78it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:04, 42.02it/s]
Loading 0:  45%|████▍     | 162/363 [00:03<00:04, 43.53it/s]
Loading 0:  46%|████▌     | 167/363 [00:03<00:05, 36.86it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 45.59it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:03, 45.55it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:03, 44.44it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 49.37it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 47.67it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 45.31it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 49.75it/s]
Loading 0:  60%|█████▉    | 217/363 [00:04<00:03, 45.32it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:03, 35.01it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:03, 35.06it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:03, 33.69it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 40.38it/s]
Loading 0:  67%|██████▋   | 244/363 [00:05<00:02, 39.99it/s]
Loading 0:  69%|██████▊   | 249/363 [00:05<00:02, 38.99it/s]
Loading 0:  71%|███████   | 256/363 [00:05<00:02, 44.19it/s]
Loading 0:  72%|███████▏  | 261/363 [00:06<00:02, 44.98it/s]
Loading 0:  73%|███████▎  | 266/363 [00:06<00:02, 38.71it/s]
Loading 0:  75%|███████▌  | 273/363 [00:06<00:01, 45.87it/s]
Loading 0:  77%|███████▋  | 278/363 [00:06<00:01, 45.49it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 46.53it/s]
Loading 0:  80%|███████▉  | 289/363 [00:06<00:01, 44.13it/s]
Loading 0:  81%|████████  | 294/363 [00:06<00:01, 39.53it/s]
Loading 0:  82%|████████▏ | 299/363 [00:06<00:01, 39.81it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:24,  2.45it/s]
Loading 0:  85%|████████▍ | 307/363 [00:13<00:18,  2.99it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:11,  4.26it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  7.08it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:03,  9.57it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:02, 12.12it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 16.96it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 20.66it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 23.91it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 30.40it/s]
Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 32.84it/s]
                                                            
Job cloudyu-nemo-dpo-v14-v1-mkmlizer completed after 115.53s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v14-v1-mkmlizer
Pipeline stage MKMLizer completed in 116.56s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-nemo-dpo-v14-v1
Waiting for inference service cloudyu-nemo-dpo-v14-v1 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
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
Inference service cloudyu-nemo-dpo-v14-v1 ready after 150.71501636505127s
Pipeline stage MKMLDeployer completed in 151.29s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4993882179260254s
Received healthy response to inference request in 1.7579588890075684s
Received healthy response to inference request in 2.0654420852661133s
Received healthy response to inference request in 1.7099204063415527s
Received healthy response to inference request in 1.678520917892456s
5 requests
0 failed requests
5th percentile: 1.6848008155822753
10th percentile: 1.6910807132720946
20th percentile: 1.7036405086517334
30th percentile: 1.7195281028747558
40th percentile: 1.738743495941162
50th percentile: 1.7579588890075684
60th percentile: 1.8809521675109864
70th percentile: 2.0039454460144044
80th percentile: 2.152231311798096
90th percentile: 2.3258097648620604
95th percentile: 2.412598991394043
99th percentile: 2.482030372619629
mean time: 1.942246103286743
Pipeline stage StressChecker completed in 11.50s
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 2.24s
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 2.03s
Shutdown handler de-registered
cloudyu-nemo-dpo-v14_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 1.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cloudyu-nemo-dpo-v14-v1-profiler
Waiting for inference service cloudyu-nemo-dpo-v14-v1-profiler to be ready
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 2627.75s
Shutdown handler de-registered
cloudyu-nemo-dpo-v14_v1 status is now inactive due to auto deactivation removed underperforming models