developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v21_v12
model_name: cloudyu-nemo-dpo-v21_v1
model_group: cloudyu/Nemo-DPO-V21
status: inactive
timestamp: 2024-12-18T08:40:35+00:00
num_battles: 13763
num_wins: 7202
celo_rating: 1279.18
family_friendly_score: 0.5648
family_friendly_standard_error: 0.007011432949119602
submission_type: basic
model_repo: cloudyu/Nemo-DPO-V21
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.616719255572002, 'latency_mean': 1.6214160072803496, 'latency_p50': 1.620351791381836, 'latency_p90': 1.785651969909668}, {'batch_size': 3, 'throughput': 1.1336001380773002, 'latency_mean': 2.642783203125, 'latency_p50': 2.664863348007202, 'latency_p90': 2.887589430809021}, {'batch_size': 5, 'throughput': 1.3738157691849686, 'latency_mean': 3.619658677577972, 'latency_p50': 3.6210306882858276, 'latency_p90': 4.0645077466964725}, {'batch_size': 6, 'throughput': 1.4553290154843226, 'latency_mean': 4.097294495105744, 'latency_p50': 4.1372867822647095, 'latency_p90': 4.518213963508606}, {'batch_size': 8, 'throughput': 1.5245334040078182, 'latency_mean': 5.222697811126709, 'latency_p50': 5.167190790176392, 'latency_p90': 5.862568068504333}, {'batch_size': 10, 'throughput': 1.565564604931877, 'latency_mean': 6.334161719083786, 'latency_p50': 6.391916990280151, 'latency_p90': 7.094397068023682}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-nemo-dpo-v21_v1
is_internal_developer: False
language_model: cloudyu/Nemo-DPO-V21
model_size: 13B
ranking_group: single
throughput_3p7s: 1.4
us_pacific_date: 2024-12-18
win_ratio: 0.5232870740390904
generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.0, '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-v21-v12-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v21-v12-mkmlizer to finish
cloudyu-nemo-dpo-v21-v12-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v21-v12-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v21-v12-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v21-v12-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v21-v12-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v21-v12-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v21-v12-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v21-v12-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v21-v12-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v21-v12-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v21-v12-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v21-v12-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v21-v12-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v21-v12-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v21-v12-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v21-v12-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v21-v12-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-nemo-dpo-v21-v12-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v21-v12-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v21-v12-mkmlizer: Downloaded to shared memory in 32.536s
cloudyu-nemo-dpo-v21-v12-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpsdusq_ur, device:0
cloudyu-nemo-dpo-v21-v12-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v21-v12-mkmlizer: quantized model in 36.674s
cloudyu-nemo-dpo-v21-v12-mkmlizer: Processed model cloudyu/Nemo-DPO-V21 in 69.211s
cloudyu-nemo-dpo-v21-v12-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v21-v12-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v21-v12-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v12
cloudyu-nemo-dpo-v21-v12-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v12/config.json
cloudyu-nemo-dpo-v21-v12-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v12/special_tokens_map.json
cloudyu-nemo-dpo-v21-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v12/tokenizer_config.json
cloudyu-nemo-dpo-v21-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v12/tokenizer.json
cloudyu-nemo-dpo-v21-v12-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 27.33it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 46.80it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:08, 42.63it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 40.93it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 47.28it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 44.88it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 43.73it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 49.13it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 45.14it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 34.52it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 33.25it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 39.77it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 41.29it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:06, 42.06it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:05, 47.16it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 44.42it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 42.80it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:04, 51.07it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 46.00it/s]
Loading 0:  33%|███▎      | 120/363 [00:02<00:05, 44.02it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:05, 46.91it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:05, 45.36it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:05, 44.85it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 34.54it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 35.10it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 34.45it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:04, 41.51it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 41.98it/s]
Loading 0:  46%|████▋     | 168/363 [00:03<00:04, 42.53it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:04, 46.06it/s]
Loading 0:  49%|████▉     | 179/363 [00:04<00:04, 44.90it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:04, 44.35it/s]
Loading 0:  52%|█████▏    | 189/363 [00:04<00:03, 45.33it/s]
Loading 0:  53%|█████▎    | 194/363 [00:04<00:04, 39.69it/s]
Loading 0:  55%|█████▌    | 201/363 [00:04<00:03, 46.90it/s]
Loading 0:  57%|█████▋    | 206/363 [00:04<00:03, 45.43it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 45.83it/s]
Loading 0:  60%|█████▉    | 216/363 [00:05<00:03, 45.66it/s]
Loading 0:  61%|██████    | 221/363 [00:05<00:03, 46.22it/s]
Loading 0:  62%|██████▏   | 226/363 [00:05<00:04, 29.00it/s]
Loading 0:  63%|██████▎   | 230/363 [00:05<00:04, 29.44it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 37.60it/s]
Loading 0:  67%|██████▋   | 244/363 [00:05<00:03, 38.80it/s]
Loading 0:  69%|██████▊   | 249/363 [00:05<00:02, 39.70it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 45.16it/s]
Loading 0:  72%|███████▏  | 262/363 [00:06<00:02, 44.10it/s]
Loading 0:  74%|███████▎  | 267/363 [00:06<00:02, 41.82it/s]
Loading 0:  75%|███████▌  | 273/363 [00:06<00:02, 44.19it/s]
Loading 0:  77%|███████▋  | 278/363 [00:06<00:01, 44.88it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 44.95it/s]
Loading 0:  80%|███████▉  | 289/363 [00:06<00:01, 43.67it/s]
Loading 0:  81%|████████  | 294/363 [00:06<00:01, 42.88it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 49.45it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:20,  2.70it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:14,  3.59it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.60it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  7.49it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:03,  9.50it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.38it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:01, 16.80it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 19.55it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 25.29it/s]
Loading 0:  99%|█████████▉| 361/363 [00:15<00:00, 28.78it/s]
                                                            

Job cloudyu-nemo-dpo-v21-v12-mkmlizer completed after 94.66s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v21-v12-mkmlizer
Pipeline stage MKMLizer completed in 95.20s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-nemo-dpo-v21-v12
Waiting for inference service cloudyu-nemo-dpo-v21-v12 to be ready
Inference service cloudyu-nemo-dpo-v21-v12 ready after 241.11264085769653s
Pipeline stage MKMLDeployer completed in 241.72s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.103440523147583s
Received healthy response to inference request in 1.9389829635620117s
Received healthy response to inference request in 2.173975944519043s
Received healthy response to inference request in 1.6564970016479492s
Received healthy response to inference request in 1.6999738216400146s
5 requests
0 failed requests
5th percentile: 1.6651923656463623
10th percentile: 1.6738877296447754
20th percentile: 1.6912784576416016
30th percentile: 1.7477756500244142
40th percentile: 1.843379306793213
50th percentile: 1.9389829635620117
60th percentile: 2.0047659873962402
70th percentile: 2.0705490112304688
80th percentile: 2.117547607421875
90th percentile: 2.145761775970459
95th percentile: 2.159868860244751
99th percentile: 2.1711545276641844
mean time: 1.9145740509033202
Pipeline stage StressChecker completed in 10.93s
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 2.22s
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 2.08s
Shutdown handler de-registered
cloudyu-nemo-dpo-v21_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 3099.31s
Shutdown handler de-registered
cloudyu-nemo-dpo-v21_v12 status is now inactive due to auto deactivation removed underperforming models