cloudyu-nemo-dpo-v21

developer_uid: azuruce

submission_id: cloudyu-nemo-dpo-v21_v14

model_name: cloudyu-nemo-dpo-v21_v14

model_group: cloudyu/Nemo-DPO-V21

status: torndown

timestamp: 2025-01-09T23:17:59+00:00

num_battles: 7006

num_wins: 3643

celo_rating: 1262.59

family_friendly_score: 0.5718

family_friendly_standard_error: 0.006997781934298896

submission_type: basic

model_repo: cloudyu/Nemo-DPO-V21

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6400664204667509, 'latency_mean': 1.5622752618789673, 'latency_p50': 1.543060302734375, 'latency_p90': 1.7347295999526977}, {'batch_size': 4, 'throughput': 1.48740419890936, 'latency_mean': 2.6849565827846527, 'latency_p50': 2.6895400285720825, 'latency_p90': 3.0161031246185304}, {'batch_size': 5, 'throughput': 1.6113252975621482, 'latency_mean': 3.090989855527878, 'latency_p50': 3.063247323036194, 'latency_p90': 3.5058188915252684}, {'batch_size': 8, 'throughput': 1.8780682868837626, 'latency_mean': 4.235475397109985, 'latency_p50': 4.226984739303589, 'latency_p90': 4.72686812877655}, {'batch_size': 10, 'throughput': 1.9854731367842562, 'latency_mean': 4.996709867715835, 'latency_p50': 4.9867576360702515, 'latency_p90': 5.732269620895385}, {'batch_size': 12, 'throughput': 2.0416436246961616, 'latency_mean': 5.8331482422351835, 'latency_p50': 5.854301691055298, 'latency_p90': 6.565435600280762}, {'batch_size': 15, 'throughput': 2.0830496704093417, 'latency_mean': 7.132239336967468, 'latency_p50': 7.141940712928772, 'latency_p90': 8.02523639202118}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cloudyu-nemo-dpo-v21_v14

is_internal_developer: False

language_model: cloudyu/Nemo-DPO-V21

model_size: 13B

ranking_group: single

throughput_3p7s: 1.78

us_pacific_date: 2025-01-09

win_ratio: 0.5199828718241507

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.001, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['####', 'Me:', 'You:', '<|eot_id|>', 'User:', '</s>', '\n', '<|im_end|>', 'Bot:'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', '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-v14-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v21-v14-mkmlizer to finish
cloudyu-nemo-dpo-v21-v14-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v21-v14-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v21-v14-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v21-v14-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v21-v14-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v21-v14-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v21-v14-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v21-v14-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v21-v14-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v21-v14-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v21-v14-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v21-v14-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v21-v14-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v21-v14-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v21-v14-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v21-v14-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v21-v14-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
cloudyu-nemo-dpo-v21-v14-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v21-v14-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v21-v14-mkmlizer: Downloaded to shared memory in 50.128s
cloudyu-nemo-dpo-v21-v14-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpml5ztio9, device:0
cloudyu-nemo-dpo-v21-v14-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v21-v14-mkmlizer: quantized model in 37.124s
cloudyu-nemo-dpo-v21-v14-mkmlizer: Processed model cloudyu/Nemo-DPO-V21 in 87.252s
cloudyu-nemo-dpo-v21-v14-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v21-v14-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v21-v14-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v14
cloudyu-nemo-dpo-v21-v14-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v14/config.json
cloudyu-nemo-dpo-v21-v14-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v14/special_tokens_map.json
cloudyu-nemo-dpo-v21-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v14/tokenizer_config.json
cloudyu-nemo-dpo-v21-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v14/tokenizer.json
cloudyu-nemo-dpo-v21-v14-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v14/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v21-v14-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 26.85it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 44.56it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 45.16it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 33.57it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:08, 40.95it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:08, 40.25it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:08, 39.99it/s]
Loading 0:  12%|█▏        | 45/363 [00:01<00:07, 40.81it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:09, 32.22it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:08, 35.70it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:08, 37.09it/s]
Loading 0:  18%|█▊        | 64/363 [00:01<00:12, 23.75it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:10, 28.25it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:10, 27.74it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:08, 32.22it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:09, 30.21it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:07, 37.36it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:07, 37.33it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:07, 35.94it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:07, 35.79it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:07, 35.64it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:06, 37.27it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 34.94it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 33.24it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:06, 35.86it/s]
Loading 0:  36%|███▌      | 129/363 [00:03<00:06, 34.34it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:06, 36.33it/s]
Loading 0:  38%|███▊      | 138/363 [00:03<00:06, 35.16it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:08, 25.38it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:08, 24.96it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:08, 24.81it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 33.21it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:06, 33.51it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 38.40it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 41.07it/s]
Loading 0:  48%|████▊     | 176/363 [00:05<00:05, 36.78it/s]
Loading 0:  50%|█████     | 183/363 [00:05<00:04, 44.13it/s]
Loading 0:  52%|█████▏    | 188/363 [00:05<00:03, 44.55it/s]
Loading 0:  53%|█████▎    | 194/363 [00:05<00:04, 41.31it/s]
Loading 0:  56%|█████▌    | 202/363 [00:05<00:03, 48.77it/s]
Loading 0:  57%|█████▋    | 208/363 [00:05<00:03, 46.91it/s]
Loading 0:  59%|█████▊    | 213/363 [00:05<00:03, 45.78it/s]
Loading 0:  61%|██████    | 220/363 [00:06<00:02, 51.52it/s]
Loading 0:  62%|██████▏   | 226/363 [00:06<00:04, 32.95it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:03, 34.64it/s]
Loading 0:  66%|██████▌   | 238/363 [00:06<00:03, 40.98it/s]
Loading 0:  67%|██████▋   | 244/363 [00:06<00:02, 41.91it/s]
Loading 0:  69%|██████▊   | 249/363 [00:06<00:02, 42.14it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 47.47it/s]
Loading 0:  72%|███████▏  | 262/363 [00:07<00:02, 45.88it/s]
Loading 0:  74%|███████▎  | 267/363 [00:07<00:02, 43.39it/s]
Loading 0:  75%|███████▌  | 273/363 [00:07<00:01, 46.93it/s]
Loading 0:  77%|███████▋  | 278/363 [00:07<00:01, 46.83it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:01, 46.75it/s]
Loading 0:  80%|███████▉  | 289/363 [00:07<00:01, 44.89it/s]
Loading 0:  81%|████████  | 294/363 [00:07<00:01, 43.45it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 50.04it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:20,  2.75it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:13,  3.65it/s]
Loading 0:  88%|████████▊ | 319/363 [00:15<00:08,  5.44it/s]
Loading 0:  89%|████████▉ | 324/363 [00:15<00:05,  7.03it/s]
Loading 0:  91%|█████████ | 329/363 [00:15<00:03,  9.10it/s]
Loading 0:  92%|█████████▏| 334/363 [00:15<00:02, 11.73it/s]
Loading 0:  93%|█████████▎| 339/363 [00:15<00:01, 13.58it/s]
Loading 0:  95%|█████████▌| 346/363 [00:15<00:00, 18.91it/s]
Loading 0:  97%|█████████▋| 351/363 [00:15<00:00, 21.84it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 25.15it/s]
Loading 0:  99%|█████████▉| 361/363 [00:16<00:00, 28.56it/s]
                                                            
Job cloudyu-nemo-dpo-v21-v14-mkmlizer completed after 114.63s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v21-v14-mkmlizer
Pipeline stage MKMLizer completed in 115.22s
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-v21-v14
Waiting for inference service cloudyu-nemo-dpo-v21-v14 to be ready
Inference service cloudyu-nemo-dpo-v21-v14 ready after 361.7629280090332s
Pipeline stage MKMLDeployer completed in 362.38s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6063127517700195s
Received healthy response to inference request in 1.5596365928649902s
Received healthy response to inference request in 1.8317229747772217s
Received healthy response to inference request in 1.3873615264892578s
Received healthy response to inference request in 1.2479257583618164s
5 requests
0 failed requests
5th percentile: 1.2758129119873047
10th percentile: 1.303700065612793
20th percentile: 1.3594743728637695
30th percentile: 1.4218165397644043
40th percentile: 1.4907265663146974
50th percentile: 1.5596365928649902
60th percentile: 1.5783070564270019
70th percentile: 1.5969775199890137
80th percentile: 1.65139479637146
90th percentile: 1.741558885574341
95th percentile: 1.7866409301757813
99th percentile: 1.8227065658569337
mean time: 1.526591920852661
Pipeline stage StressChecker completed in 9.48s
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 0.92s
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 0.68s
Shutdown handler de-registered
cloudyu-nemo-dpo-v21_v14 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cloudyu-nemo-dpo-v21-v14-profiler
Waiting for inference service cloudyu-nemo-dpo-v21-v14-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 2361.57s
Shutdown handler de-registered
cloudyu-nemo-dpo-v21_v14 status is now inactive due to auto deactivation removed underperforming models
cloudyu-nemo-dpo-v21_v14 status is now torndown due to DeploymentManager action