cloudyu-chaiml-nemo-dpo-v5

developer_uid: cloudyu

submission_id: cloudyu-chaiml-nemo-dpo-v5_v1

model_name: cloudyu-chaiml-nemo-dpo-v5_v1

model_group: cloudyu/ChaiML-Nemo-DPO-

status: inactive

timestamp: 2024-11-24T09:52:14+00:00

num_battles: 15665

num_wins: 7795

celo_rating: 1255.52

family_friendly_score: 0.5654

family_friendly_standard_error: 0.007010318680345424

submission_type: basic

model_repo: cloudyu/ChaiML-Nemo-DPO-V5

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6193102425352099, 'latency_mean': 1.6146234595775604, 'latency_p50': 1.6129730939865112, 'latency_p90': 1.774145770072937}, {'batch_size': 3, 'throughput': 1.1444495548329316, 'latency_mean': 2.616577396392822, 'latency_p50': 2.5980929136276245, 'latency_p90': 2.8540401220321656}, {'batch_size': 5, 'throughput': 1.3753447574871638, 'latency_mean': 3.6199349510669707, 'latency_p50': 3.615546703338623, 'latency_p90': 4.029725956916809}, {'batch_size': 6, 'throughput': 1.4526432324628447, 'latency_mean': 4.102038463354111, 'latency_p50': 4.102054834365845, 'latency_p90': 4.594160413742065}, {'batch_size': 8, 'throughput': 1.5097553262284409, 'latency_mean': 5.270509643554687, 'latency_p50': 5.245238423347473, 'latency_p90': 5.922373247146607}, {'batch_size': 10, 'throughput': 1.5505757155190953, 'latency_mean': 6.405979138612747, 'latency_p50': 6.464808464050293, 'latency_p90': 7.332541036605835}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cloudyu-chaiml-nemo-dpo-v5_v1

is_internal_developer: False

language_model: cloudyu/ChaiML-Nemo-DPO-V5

model_size: 13B

ranking_group: single

throughput_3p7s: 1.4

us_pacific_date: 2024-11-24

win_ratio: 0.4976061283115225

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, '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-chaiml-nemo-dpo-v5-v1-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer to finish
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: ║     _____            __           __                                ║
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: ║       /___/                                                         ║
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: ║  belonging to:                                                      ║
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: Downloaded to shared memory in 49.189s
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvdc7gawj, device:0
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: quantized model in 36.216s
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V5 in 85.405s
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v5-v1
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v5-v1/config.json
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v5-v1/special_tokens_map.json
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v5-v1/tokenizer_config.json
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v5-v1/tokenizer.json
cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.34it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 48.43it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 45.39it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 44.14it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 50.76it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 48.17it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:06, 46.09it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 49.90it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 46.06it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 34.06it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 33.04it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 39.53it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 40.58it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 40.20it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 45.36it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 44.29it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 43.50it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 49.38it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:05, 45.81it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:05, 42.72it/s]
Loading 0:  34%|███▍      | 125/363 [00:02<00:05, 46.85it/s]
Loading 0:  36%|███▌      | 130/363 [00:02<00:05, 45.02it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:04, 45.90it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:05, 43.37it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:07, 30.09it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:07, 30.28it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 37.07it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:05, 37.97it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:05, 38.15it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:04, 42.43it/s]
Loading 0:  49%|████▉     | 179/363 [00:04<00:04, 41.83it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:04, 42.60it/s]
Loading 0:  52%|█████▏    | 190/363 [00:04<00:04, 42.32it/s]
Loading 0:  54%|█████▎    | 195/363 [00:04<00:03, 42.08it/s]
Loading 0:  56%|█████▌    | 202/363 [00:04<00:03, 46.77it/s]
Loading 0:  57%|█████▋    | 207/363 [00:04<00:03, 45.30it/s]
Loading 0:  58%|█████▊    | 212/363 [00:05<00:04, 37.26it/s]
Loading 0:  60%|██████    | 218/363 [00:05<00:03, 41.94it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:04, 32.02it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 32.84it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 32.06it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 38.38it/s]
Loading 0:  67%|██████▋   | 242/363 [00:05<00:03, 39.25it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 38.94it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 41.42it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:02, 35.44it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 43.96it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 42.32it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:02, 40.99it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 45.89it/s]
Loading 0:  79%|███████▉  | 288/363 [00:06<00:01, 46.82it/s]
Loading 0:  81%|████████  | 293/363 [00:07<00:01, 39.60it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 48.58it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:19,  2.83it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:13,  3.72it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.75it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  7.62it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:03,  9.62it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.43it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:01, 16.17it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 19.01it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 24.72it/s]
Loading 0:  99%|█████████▉| 361/363 [00:15<00:00, 28.25it/s]
                                                            
Job cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer completed after 115.18s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v5-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.68s
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-chaiml-nemo-dpo-v5-v1
Waiting for inference service cloudyu-chaiml-nemo-dpo-v5-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
Inference service cloudyu-chaiml-nemo-dpo-v5-v1 ready after 120.44619727134705s
Pipeline stage MKMLDeployer completed in 120.88s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.341726541519165s
Received healthy response to inference request in 1.9537391662597656s
Received healthy response to inference request in 2.1239471435546875s
Received healthy response to inference request in 1.6697702407836914s
5 requests
1 failed requests
5th percentile: 1.7265640258789063
10th percentile: 1.783357810974121
20th percentile: 1.8969453811645507
30th percentile: 1.98778076171875
40th percentile: 2.055863952636719
50th percentile: 2.1239471435546875
60th percentile: 2.2110589027404783
70th percentile: 2.2981706619262696
80th percentile: 5.898958873748782
90th percentile: 13.01342353820801
95th percentile: 16.57065587043762
99th percentile: 19.416441736221312
mean time: 5.643414258956909
%s, retrying in %s seconds...
Received healthy response to inference request in 1.685295581817627s
Received healthy response to inference request in 1.98569917678833s
Received healthy response to inference request in 1.116647720336914s
Received healthy response to inference request in 1.8452024459838867s
Received healthy response to inference request in 1.6685919761657715s
5 requests
0 failed requests
5th percentile: 1.2270365715026856
10th percentile: 1.337425422668457
20th percentile: 1.558203125
30th percentile: 1.6719326972961426
40th percentile: 1.6786141395568848
50th percentile: 1.685295581817627
60th percentile: 1.749258327484131
70th percentile: 1.8132210731506346
80th percentile: 1.8733017921447754
90th percentile: 1.9295004844665526
95th percentile: 1.9575998306274414
99th percentile: 1.9800793075561522
mean time: 1.6602873802185059
Pipeline stage StressChecker completed in 38.86s
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 2.13s
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 2.10s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v5_v1 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 2775.04s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v5_v1 status is now inactive due to auto deactivation removed underperforming models