cloudyu-nemo-dpo-v20

developer_uid: cloudyu

submission_id: cloudyu-nemo-dpo-v20_v8

model_name: cloudyu-nemo-dpo-v20_v1

model_group: cloudyu/Nemo-DPO-V20

status: inactive

timestamp: 2024-12-17T09:35:01+00:00

num_battles: 15538

num_wins: 8003

celo_rating: 1273.01

family_friendly_score: 0.5609999999999999

family_friendly_standard_error: 0.007018247644533499

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': 0.629836872893527, 'latency_mean': 1.5876547396183014, 'latency_p50': 1.5775578022003174, 'latency_p90': 1.7347957611083984}, {'batch_size': 3, 'throughput': 1.1588374927343752, 'latency_mean': 2.5813486301898956, 'latency_p50': 2.563001275062561, 'latency_p90': 2.8904324769973755}, {'batch_size': 5, 'throughput': 1.4023059771920499, 'latency_mean': 3.5505293548107146, 'latency_p50': 3.5584022998809814, 'latency_p90': 3.9711008787155153}, {'batch_size': 6, 'throughput': 1.483951244285811, 'latency_mean': 4.029947298765182, 'latency_p50': 4.020354390144348, 'latency_p90': 4.547895693778992}, {'batch_size': 8, 'throughput': 1.5403576609168812, 'latency_mean': 5.154815113544464, 'latency_p50': 5.156967520713806, 'latency_p90': 5.777157878875732}, {'batch_size': 10, 'throughput': 1.5900773445288603, 'latency_mean': 6.243298954963684, 'latency_p50': 6.223657846450806, 'latency_p90': 7.1823710918426515}]

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: 1.44

us_pacific_date: 2024-12-17

win_ratio: 0.5150598532629682

generation_params: {'temperature': 0.95, 'top_p': 1.0, '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-v20-v8-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v20-v8-mkmlizer to finish
cloudyu-nemo-dpo-v20-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v20-v8-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v20-v8-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v20-v8-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v20-v8-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v20-v8-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v20-v8-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v20-v8-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v20-v8-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v20-v8-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v20-v8-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v20-v8-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v20-v8-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v20-v8-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v20-v8-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v20-v8-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v20-v8-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-nemo-dpo-v20-v8-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v20-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v20-v8-mkmlizer: Downloaded to shared memory in 33.032s
cloudyu-nemo-dpo-v20-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkmsh_1kj, device:0
cloudyu-nemo-dpo-v20-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v20-v8-mkmlizer: quantized model in 36.616s
cloudyu-nemo-dpo-v20-v8-mkmlizer: Processed model cloudyu/Nemo-DPO-V20 in 69.648s
cloudyu-nemo-dpo-v20-v8-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v20-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v20-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v8
cloudyu-nemo-dpo-v20-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v8/config.json
cloudyu-nemo-dpo-v20-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v8/special_tokens_map.json
cloudyu-nemo-dpo-v20-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v8/tokenizer_config.json
cloudyu-nemo-dpo-v20-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v8/tokenizer.json
cloudyu-nemo-dpo-v20-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v8/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v20-v8-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 25.88it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 42.64it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:08, 40.53it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:08, 39.90it/s]
Loading 0:   7%|▋         | 27/363 [00:00<00:08, 41.64it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 35.88it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 44.79it/s]
Loading 0:  12%|█▏        | 45/363 [00:01<00:06, 45.92it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:07, 39.21it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:06, 48.38it/s]
Loading 0:  18%|█▊        | 64/363 [00:01<00:10, 29.86it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 37.51it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:07, 38.22it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:07, 38.23it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 42.89it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 41.10it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:06, 41.50it/s]
Loading 0:  29%|██▊       | 104/363 [00:02<00:06, 42.85it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:05, 42.46it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:06, 35.91it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:07, 33.78it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 41.57it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 41.05it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 41.76it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:05, 41.81it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:07, 29.74it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:07, 29.87it/s]
Loading 0:  43%|████▎     | 157/363 [00:04<00:05, 36.68it/s]
Loading 0:  45%|████▍     | 162/363 [00:04<00:05, 39.57it/s]
Loading 0:  46%|████▌     | 167/363 [00:04<00:05, 33.58it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 41.93it/s]
Loading 0:  50%|████▉     | 180/363 [00:04<00:04, 43.76it/s]
Loading 0:  51%|█████     | 185/363 [00:04<00:04, 38.03it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 46.10it/s]
Loading 0:  55%|█████▍    | 199/363 [00:05<00:03, 43.93it/s]
Loading 0:  56%|█████▌    | 204/363 [00:05<00:03, 40.92it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 46.11it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 44.26it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:04, 34.30it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 33.98it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 32.55it/s]
Loading 0:  66%|██████▌   | 238/363 [00:06<00:03, 39.48it/s]
Loading 0:  67%|██████▋   | 244/363 [00:06<00:02, 40.38it/s]
Loading 0:  69%|██████▊   | 249/363 [00:06<00:02, 41.10it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 46.60it/s]
Loading 0:  72%|███████▏  | 262/363 [00:06<00:02, 45.94it/s]
Loading 0:  74%|███████▎  | 267/363 [00:06<00:02, 45.55it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:01, 48.86it/s]
Loading 0:  77%|███████▋  | 279/363 [00:06<00:01, 46.13it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 38.26it/s]
Loading 0:  80%|████████  | 292/363 [00:07<00:01, 45.93it/s]
Loading 0:  82%|████████▏ | 298/363 [00:07<00:01, 45.14it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:20,  2.82it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:15,  3.54it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:11,  4.48it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:05,  7.23it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:03,  9.71it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:02, 12.28it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 17.08it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:00, 20.44it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 23.79it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 30.27it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 33.17it/s]
                                                            
Job cloudyu-nemo-dpo-v20-v8-mkmlizer completed after 94.74s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v20-v8-mkmlizer
Pipeline stage MKMLizer completed in 95.30s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-nemo-dpo-v20-v8
Waiting for inference service cloudyu-nemo-dpo-v20-v8 to be ready
Inference service cloudyu-nemo-dpo-v20-v8 ready after 230.7886643409729s
Pipeline stage MKMLDeployer completed in 231.40s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.059241771697998s
Received healthy response to inference request in 1.7221417427062988s
Received healthy response to inference request in 1.755629301071167s
Received healthy response to inference request in 1.7328460216522217s
Received healthy response to inference request in 2.0617165565490723s
5 requests
0 failed requests
5th percentile: 1.7242825984954835
10th percentile: 1.726423454284668
20th percentile: 1.730705165863037
30th percentile: 1.7374026775360107
40th percentile: 1.7465159893035889
50th percentile: 1.755629301071167
60th percentile: 1.8770742893218995
70th percentile: 1.9985192775726317
80th percentile: 2.059736728668213
90th percentile: 2.0607266426086426
95th percentile: 2.0612215995788574
99th percentile: 2.0616175651550295
mean time: 1.8663150787353515
Pipeline stage StressChecker completed in 10.64s
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 2.13s
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 2.10s
Shutdown handler de-registered
cloudyu-nemo-dpo-v20_v8 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-v8-profiler
Waiting for inference service cloudyu-nemo-dpo-v20-v8-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 3145.58s
Shutdown handler de-registered
cloudyu-nemo-dpo-v20_v8 status is now inactive due to auto deactivation removed underperforming models