cloudyu-nemo-dpo-v22

developer_uid: cloudyu

submission_id: cloudyu-nemo-dpo-v22_v2

model_name: cloudyu-nemo-dpo-v22_v1

model_group: cloudyu/Nemo-DPO-V22

status: inactive

timestamp: 2024-12-18T10:51:50+00:00

num_battles: 14623

num_wins: 7592

celo_rating: 1277.13

family_friendly_score: 0.5666

family_friendly_standard_error: 0.0070080587897077455

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': 0.6110050845020114, 'latency_mean': 1.636593440771103, 'latency_p50': 1.6334079504013062, 'latency_p90': 1.8148651838302612}, {'batch_size': 3, 'throughput': 1.0924179779359646, 'latency_mean': 2.7398313593864443, 'latency_p50': 2.7519280910491943, 'latency_p90': 2.9847118616104127}, {'batch_size': 5, 'throughput': 1.314820302036816, 'latency_mean': 3.776080619096756, 'latency_p50': 3.7800456285476685, 'latency_p90': 4.197079849243164}, {'batch_size': 6, 'throughput': 1.3904711921897517, 'latency_mean': 4.292454979419708, 'latency_p50': 4.26731812953949, 'latency_p90': 4.836795592308045}, {'batch_size': 8, 'throughput': 1.4362372601629583, 'latency_mean': 5.533975758552551, 'latency_p50': 5.594167470932007, 'latency_p90': 6.136122727394104}, {'batch_size': 10, 'throughput': 1.4801043149481266, 'latency_mean': 6.696271337270737, 'latency_p50': 6.675015211105347, 'latency_p90': 7.662957978248596}]

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: 1.31

us_pacific_date: 2024-12-18

win_ratio: 0.5191821103740683

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-v22-v2-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v22-v2-mkmlizer to finish
cloudyu-nemo-dpo-v22-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v22-v2-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v22-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v22-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v22-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v22-v2-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v22-v2-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v22-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v22-v2-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v22-v2-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v22-v2-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v22-v2-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v2-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v22-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v22-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-nemo-dpo-v22-v2-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v22-v2-mkmlizer: Downloaded to shared memory in 44.501s
cloudyu-nemo-dpo-v22-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpued5gad_, device:0
cloudyu-nemo-dpo-v22-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v22-v2-mkmlizer: quantized model in 36.560s
cloudyu-nemo-dpo-v22-v2-mkmlizer: Processed model cloudyu/Nemo-DPO-V22 in 81.062s
cloudyu-nemo-dpo-v22-v2-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v22-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v22-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v2
cloudyu-nemo-dpo-v22-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v2/config.json
cloudyu-nemo-dpo-v22-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v2/special_tokens_map.json
cloudyu-nemo-dpo-v22-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v2/tokenizer_config.json
cloudyu-nemo-dpo-v22-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v2/tokenizer.json
cloudyu-nemo-dpo-v22-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v2/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v22-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:14, 24.02it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 41.97it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:07, 44.19it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:07, 45.80it/s]
Loading 0:   8%|▊         | 28/363 [00:00<00:07, 43.01it/s]
Loading 0:   9%|▉         | 33/363 [00:00<00:08, 41.06it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:06, 46.17it/s]
Loading 0:  12%|█▏        | 45/363 [00:01<00:06, 46.56it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:08, 38.39it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:07, 43.57it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 31.56it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 30.59it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 37.33it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:07, 39.75it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:08, 34.02it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 41.30it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 41.28it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:06, 42.06it/s]
Loading 0:  29%|██▊       | 104/363 [00:02<00:05, 43.85it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:06, 42.12it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 43.83it/s]
Loading 0:  33%|███▎      | 120/363 [00:02<00:05, 40.87it/s]
Loading 0:  35%|███▍      | 126/363 [00:03<00:05, 43.68it/s]
Loading 0:  36%|███▌      | 131/363 [00:03<00:05, 44.45it/s]
Loading 0:  37%|███▋      | 136/363 [00:03<00:06, 36.42it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:07, 30.50it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 31.68it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 31.92it/s]
Loading 0:  43%|████▎     | 157/363 [00:04<00:05, 39.01it/s]
Loading 0:  45%|████▍     | 163/363 [00:04<00:04, 40.09it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:04, 41.11it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 45.77it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 43.95it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 42.47it/s]
Loading 0:  53%|█████▎    | 192/363 [00:04<00:03, 46.12it/s]
Loading 0:  54%|█████▍    | 197/363 [00:04<00:03, 42.49it/s]
Loading 0:  56%|█████▌    | 202/363 [00:05<00:03, 42.31it/s]
Loading 0:  57%|█████▋    | 208/363 [00:05<00:03, 42.28it/s]
Loading 0:  59%|█████▊    | 213/363 [00:05<00:03, 42.41it/s]
Loading 0:  60%|██████    | 219/363 [00:05<00:03, 46.70it/s]
Loading 0:  62%|██████▏   | 224/363 [00:05<00:04, 33.78it/s]
Loading 0:  63%|██████▎   | 228/363 [00:05<00:04, 33.67it/s]
Loading 0:  64%|██████▍   | 232/363 [00:05<00:03, 34.94it/s]
Loading 0:  66%|██████▌   | 238/363 [00:06<00:03, 40.08it/s]
Loading 0:  67%|██████▋   | 244/363 [00:06<00:02, 39.88it/s]
Loading 0:  69%|██████▊   | 249/363 [00:06<00:02, 40.43it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 45.66it/s]
Loading 0:  72%|███████▏  | 262/363 [00:06<00:02, 44.18it/s]
Loading 0:  74%|███████▎  | 267/363 [00:06<00:02, 44.35it/s]
Loading 0:  75%|███████▌  | 273/363 [00:06<00:01, 47.73it/s]
Loading 0:  77%|███████▋  | 278/363 [00:06<00:01, 47.44it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 47.12it/s]
Loading 0:  79%|███████▉  | 288/363 [00:07<00:01, 47.60it/s]
Loading 0:  81%|████████  | 293/363 [00:07<00:01, 40.24it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 49.60it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:20,  2.76it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:13,  3.65it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.67it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:05,  7.29it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:03,  8.97it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.35it/s]
Loading 0:  94%|█████████▍| 343/363 [00:15<00:01, 16.17it/s]
Loading 0:  96%|█████████▌| 348/363 [00:15<00:00, 17.89it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 24.81it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 27.91it/s]
                                                            
Job cloudyu-nemo-dpo-v22-v2-mkmlizer completed after 105.23s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v22-v2-mkmlizer
Pipeline stage MKMLizer completed in 105.73s
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-v2
Waiting for inference service cloudyu-nemo-dpo-v22-v2 to be ready
Inference service cloudyu-nemo-dpo-v22-v2 ready after 240.82874512672424s
Pipeline stage MKMLDeployer completed in 241.40s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7905874252319336s
Received healthy response to inference request in 1.7448475360870361s
Received healthy response to inference request in 2.9314253330230713s
Received healthy response to inference request in 1.6838188171386719s
Received healthy response to inference request in 1.7949542999267578s
5 requests
0 failed requests
5th percentile: 1.6960245609283446
10th percentile: 1.7082303047180176
20th percentile: 1.7326417922973634
30th percentile: 1.7548688888549804
40th percentile: 1.774911594390869
50th percentile: 1.7949542999267578
60th percentile: 2.193207550048828
70th percentile: 2.591460800170898
80th percentile: 2.818755006790161
90th percentile: 2.875090169906616
95th percentile: 2.9032577514648437
99th percentile: 2.925791816711426
mean time: 2.1891266822814943
Pipeline stage StressChecker completed in 12.35s
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 2.47s
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 2.42s
Shutdown handler de-registered
cloudyu-nemo-dpo-v22_v2 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 3281.95s
Shutdown handler de-registered
cloudyu-nemo-dpo-v22_v2 status is now inactive due to auto deactivation removed underperforming models