cloudyu-nemo-dpo-v20

developer_uid: cloudyu

submission_id: cloudyu-nemo-dpo-v20_v14

model_name: cloudyu-nemo-dpo-v20_v1

model_group: cloudyu/Nemo-DPO-V20

status: inactive

timestamp: 2024-12-24T23:01:09+00:00

num_battles: 20132

num_wins: 10336

celo_rating: 1272.61

family_friendly_score: 0.5794

family_friendly_standard_error: 0.0069813414183808545

submission_type: basic

model_repo: cloudyu/Nemo-DPO-V20

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6144217786719625, 'latency_mean': 1.6274607717990874, 'latency_p50': 1.627173900604248, 'latency_p90': 1.79455246925354}, {'batch_size': 3, 'throughput': 1.13085936125844, 'latency_mean': 2.6511717796325684, 'latency_p50': 2.6587857007980347, 'latency_p90': 2.909176564216614}, {'batch_size': 5, 'throughput': 1.3812924545189154, 'latency_mean': 3.6040817201137543, 'latency_p50': 3.5907288789749146, 'latency_p90': 4.036141753196716}, {'batch_size': 6, 'throughput': 1.4343879096990284, 'latency_mean': 4.162289712429047, 'latency_p50': 4.1358115673065186, 'latency_p90': 4.699355864524842}, {'batch_size': 8, 'throughput': 1.500750904290741, 'latency_mean': 5.296217722892761, 'latency_p50': 5.310680150985718, 'latency_p90': 5.889406013488769}, {'batch_size': 10, 'throughput': 1.5394733465346022, 'latency_mean': 6.445419489145279, 'latency_p50': 6.449408769607544, 'latency_p90': 7.267524528503418}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cloudyu-nemo-dpo-v20_v1

is_internal_developer: False

language_model: cloudyu/Nemo-DPO-V20

model_size: 13B

ranking_group: single

throughput_3p7s: 1.4

us_pacific_date: 2024-12-24

win_ratio: 0.513411484204252

generation_params: {'temperature': 0.95, '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-v20-v14-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v20-v14-mkmlizer to finish
cloudyu-nemo-dpo-v20-v14-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v20-v14-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v20-v14-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v20-v14-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v20-v14-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v20-v14-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v20-v14-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v20-v14-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v20-v14-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v20-v14-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v20-v14-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v20-v14-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v20-v14-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v20-v14-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v20-v14-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v20-v14-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v20-v14-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-nemo-dpo-v20-v14-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v20-v14-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v20-v14-mkmlizer: Downloaded to shared memory in 50.668s
cloudyu-nemo-dpo-v20-v14-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwa5fk4g0, device:0
cloudyu-nemo-dpo-v20-v14-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
cloudyu-nemo-dpo-v20-v14-mkmlizer: quantized model in 35.643s
cloudyu-nemo-dpo-v20-v14-mkmlizer: Processed model cloudyu/Nemo-DPO-V20 in 86.312s
cloudyu-nemo-dpo-v20-v14-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v20-v14-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v20-v14-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v14
cloudyu-nemo-dpo-v20-v14-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v14/special_tokens_map.json
cloudyu-nemo-dpo-v20-v14-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v14/config.json
cloudyu-nemo-dpo-v20-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v14/tokenizer_config.json
cloudyu-nemo-dpo-v20-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v14/tokenizer.json
cloudyu-nemo-dpo-v20-v14-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 27.67it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 50.08it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 47.31it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:06, 49.48it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 52.02it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 49.43it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:06, 50.12it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:06, 52.08it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 48.21it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 37.26it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 36.78it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 40.91it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:06, 42.57it/s]
Loading 0:  23%|██▎       | 82/363 [00:01<00:07, 37.80it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:05, 45.72it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 44.22it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 42.17it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 48.24it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:05, 45.30it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:05, 44.19it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:04, 49.47it/s]
Loading 0:  36%|███▋      | 132/363 [00:02<00:04, 47.05it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:04, 45.48it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 36.07it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:05, 36.21it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 34.97it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:04, 42.35it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 42.81it/s]
Loading 0:  46%|████▋     | 168/363 [00:03<00:04, 42.90it/s]
Loading 0:  48%|████▊     | 175/363 [00:03<00:03, 48.17it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 45.41it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 42.88it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 46.91it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 44.91it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 43.38it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 48.29it/s]
Loading 0:  60%|█████▉    | 217/363 [00:04<00:03, 47.37it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:03, 37.46it/s]
Loading 0:  63%|██████▎   | 228/363 [00:05<00:03, 36.77it/s]
Loading 0:  64%|██████▍   | 232/363 [00:05<00:03, 36.98it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 41.62it/s]
Loading 0:  67%|██████▋   | 244/363 [00:05<00:02, 41.61it/s]
Loading 0:  69%|██████▊   | 249/363 [00:05<00:02, 41.10it/s]
Loading 0:  71%|███████   | 256/363 [00:05<00:02, 46.30it/s]
Loading 0:  72%|███████▏  | 262/363 [00:06<00:02, 44.32it/s]
Loading 0:  74%|███████▎  | 267/363 [00:06<00:02, 42.35it/s]
Loading 0:  75%|███████▌  | 273/363 [00:06<00:01, 46.42it/s]
Loading 0:  77%|███████▋  | 278/363 [00:06<00:01, 46.25it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 47.06it/s]
Loading 0:  80%|███████▉  | 289/363 [00:06<00:01, 44.79it/s]
Loading 0:  81%|████████  | 294/363 [00:06<00:01, 42.49it/s]
Loading 0:  83%|████████▎ | 301/363 [00:06<00:01, 49.05it/s]
Loading 0:  85%|████████▍ | 307/363 [00:13<00:20,  2.71it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:14,  3.61it/s]
Loading 0:  88%|████████▊ | 319/363 [00:14<00:08,  5.38it/s]
Loading 0:  89%|████████▉ | 324/363 [00:14<00:05,  6.97it/s]
Loading 0:  91%|█████████ | 329/363 [00:14<00:03,  9.06it/s]
Loading 0:  92%|█████████▏| 335/363 [00:14<00:02, 12.05it/s]
Loading 0:  94%|█████████▎| 340/363 [00:14<00:01, 14.91it/s]
Loading 0:  95%|█████████▌| 346/363 [00:14<00:00, 19.59it/s]
Loading 0:  97%|█████████▋| 351/363 [00:14<00:00, 23.20it/s]
Loading 0:  98%|█████████▊| 357/363 [00:14<00:00, 25.50it/s]
                                                            
Job cloudyu-nemo-dpo-v20-v14-mkmlizer completed after 115.19s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v20-v14-mkmlizer
Pipeline stage MKMLizer completed in 115.72s
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-v20-v14
Waiting for inference service cloudyu-nemo-dpo-v20-v14 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
Inference service cloudyu-nemo-dpo-v20-v14 ready after 281.08430433273315s
Pipeline stage MKMLDeployer completed in 281.63s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2683284282684326s
Received healthy response to inference request in 1.603734016418457s
Received healthy response to inference request in 1.7901780605316162s
Received healthy response to inference request in 1.6771321296691895s
Received healthy response to inference request in 2.128864049911499s
5 requests
0 failed requests
5th percentile: 1.6184136390686035
10th percentile: 1.63309326171875
20th percentile: 1.662452507019043
30th percentile: 1.6997413158416748
40th percentile: 1.7449596881866456
50th percentile: 1.7901780605316162
60th percentile: 1.9256524562835693
70th percentile: 2.0611268520355224
80th percentile: 2.1567569255828856
90th percentile: 2.212542676925659
95th percentile: 2.240435552597046
99th percentile: 2.262749853134155
mean time: 1.8936473369598388
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 0.79s
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 0.69s
Shutdown handler de-registered
cloudyu-nemo-dpo-v20_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 0.10s
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-v20-v14-profiler
Waiting for inference service cloudyu-nemo-dpo-v20-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 2629.81s
Shutdown handler de-registered
cloudyu-nemo-dpo-v20_v14 status is now inactive due to auto deactivation removed underperforming models