developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v21_v11
model_name: cloudyu-nemo-dpo-v21_v1
model_group: cloudyu/Nemo-DPO-V21
status: inactive
timestamp: 2024-12-18T07:59:54+00:00
num_battles: 16840
num_wins: 8925
celo_rating: 1283.98
family_friendly_score: 0.5606
family_friendly_standard_error: 0.007018940660812
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': 0.609470787457143, 'latency_mean': 1.6407114577293396, 'latency_p50': 1.631679654121399, 'latency_p90': 1.8143225193023682}, {'batch_size': 3, 'throughput': 1.1360850668093183, 'latency_mean': 2.636524785757065, 'latency_p50': 2.6475131511688232, 'latency_p90': 2.9047574281692503}, {'batch_size': 5, 'throughput': 1.3691626991151464, 'latency_mean': 3.639561049938202, 'latency_p50': 3.665473461151123, 'latency_p90': 4.0382084608078}, {'batch_size': 6, 'throughput': 1.443653778319851, 'latency_mean': 4.134421738386155, 'latency_p50': 4.144326448440552, 'latency_p90': 4.6608617305755615}, {'batch_size': 8, 'throughput': 1.51527059696601, 'latency_mean': 5.238367748260498, 'latency_p50': 5.22299063205719, 'latency_p90': 5.8916136741638185}, {'batch_size': 10, 'throughput': 1.5420263441767643, 'latency_mean': 6.419567221403122, 'latency_p50': 6.439322590827942, 'latency_p90': 7.251019906997681}]
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: 1.38
us_pacific_date: 2024-12-17
win_ratio: 0.5299881235154394
generation_params: {'temperature': 0.95, 'top_p': 0.95, '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-v21-v11-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v21-v11-mkmlizer to finish
cloudyu-nemo-dpo-v21-v11-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v21-v11-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v21-v11-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v21-v11-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v21-v11-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v21-v11-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v21-v11-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v21-v11-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v21-v11-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v21-v11-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v21-v11-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v21-v11-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v21-v11-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v21-v11-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v21-v11-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v21-v11-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v21-v11-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-nemo-dpo-v21-v11-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v21-v11-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v21-v11-mkmlizer: Downloaded to shared memory in 31.745s
cloudyu-nemo-dpo-v21-v11-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2ziwblon, device:0
cloudyu-nemo-dpo-v21-v11-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v21-v11-mkmlizer: quantized model in 36.444s
cloudyu-nemo-dpo-v21-v11-mkmlizer: Processed model cloudyu/Nemo-DPO-V21 in 68.189s
cloudyu-nemo-dpo-v21-v11-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v21-v11-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v21-v11-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v11
cloudyu-nemo-dpo-v21-v11-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v11/config.json
cloudyu-nemo-dpo-v21-v11-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v11/special_tokens_map.json
cloudyu-nemo-dpo-v21-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v11/tokenizer_config.json
cloudyu-nemo-dpo-v21-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v11/tokenizer.json
cloudyu-nemo-dpo-v21-v11-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.32it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 49.10it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 45.12it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 43.49it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 49.58it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 46.28it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 43.49it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 48.20it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:06, 48.00it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:06, 44.51it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:10, 29.72it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 35.42it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 37.85it/s]
Loading 0:  22%|██▏       | 81/363 [00:01<00:07, 39.91it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:07, 39.39it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:06, 39.37it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 43.32it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 43.26it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:05, 46.89it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:06, 40.99it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:06, 40.57it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:05, 46.18it/s]
Loading 0:  36%|███▌      | 131/363 [00:03<00:04, 46.91it/s]
Loading 0:  37%|███▋      | 136/363 [00:03<00:05, 40.09it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 33.49it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 34.15it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 32.71it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 39.81it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 40.64it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:04, 41.34it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 46.90it/s]
Loading 0:  50%|████▉     | 180/363 [00:04<00:03, 46.96it/s]
Loading 0:  51%|█████     | 185/363 [00:04<00:04, 39.82it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 48.07it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 45.50it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 43.57it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 46.61it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 45.34it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 46.10it/s]
Loading 0:  62%|██████▏   | 225/363 [00:05<00:04, 28.85it/s]
Loading 0:  63%|██████▎   | 230/363 [00:05<00:04, 31.60it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 40.41it/s]
Loading 0:  67%|██████▋   | 243/363 [00:05<00:02, 42.47it/s]
Loading 0:  68%|██████▊   | 248/363 [00:06<00:03, 37.57it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 44.37it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 45.27it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 45.98it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 45.08it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:02, 42.74it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 47.75it/s]
Loading 0:  80%|███████▉  | 289/363 [00:06<00:01, 46.53it/s]
Loading 0:  81%|████████  | 294/363 [00:07<00:01, 45.20it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 51.52it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:20,  2.77it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:13,  3.68it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.71it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  7.63it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:03,  9.69it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.60it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:01, 17.04it/s]
Loading 0:  96%|█████████▋| 350/363 [00:14<00:00, 21.10it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 25.92it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 29.49it/s]
                                                            

Job cloudyu-nemo-dpo-v21-v11-mkmlizer completed after 94.04s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v21-v11-mkmlizer
Pipeline stage MKMLizer completed in 94.58s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-nemo-dpo-v21-v11
Waiting for inference service cloudyu-nemo-dpo-v21-v11 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
Inference service cloudyu-nemo-dpo-v21-v11 ready after 231.2992126941681s
Pipeline stage MKMLDeployer completed in 231.82s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.101706027984619s
Received healthy response to inference request in 1.7525689601898193s
Received healthy response to inference request in 1.6673963069915771s
Received healthy response to inference request in 1.7997920513153076s
Received healthy response to inference request in 1.7309379577636719s
5 requests
0 failed requests
5th percentile: 1.680104637145996
10th percentile: 1.692812967300415
20th percentile: 1.718229627609253
30th percentile: 1.7352641582489015
40th percentile: 1.7439165592193604
50th percentile: 1.7525689601898193
60th percentile: 1.7714581966400147
70th percentile: 1.79034743309021
80th percentile: 1.8601748466491699
90th percentile: 1.9809404373168946
95th percentile: 2.0413232326507567
99th percentile: 2.0896294689178467
mean time: 1.810480260848999
Pipeline stage StressChecker completed in 10.38s
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 2.14s
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 2.01s
Shutdown handler de-registered
cloudyu-nemo-dpo-v21_v11 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 0.11s
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-v11-profiler
Waiting for inference service cloudyu-nemo-dpo-v21-v11-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 3117.86s
Shutdown handler de-registered
cloudyu-nemo-dpo-v21_v11 status is now inactive due to auto deactivation removed underperforming models