developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v21_v6
model_name: cloudyu-nemo-dpo-v21_v1
model_group: cloudyu/Nemo-DPO-V21
status: inactive
timestamp: 2024-12-18T00:14:38+00:00
num_battles: 9441
num_wins: 4904
celo_rating: 1276.41
family_friendly_score: 0.5631999999999999
family_friendly_standard_error: 0.007014353284515972
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': 0.6188421521589169, 'latency_mean': 1.615863517522812, 'latency_p50': 1.6125274896621704, 'latency_p90': 1.7870323419570924}, {'batch_size': 3, 'throughput': 1.1441096927890282, 'latency_mean': 2.6087844240665437, 'latency_p50': 2.608742594718933, 'latency_p90': 2.8900152921676634}, {'batch_size': 5, 'throughput': 1.3832079209909935, 'latency_mean': 3.596412764787674, 'latency_p50': 3.6149791479110718, 'latency_p90': 3.9803748607635496}, {'batch_size': 6, 'throughput': 1.4602152060214757, 'latency_mean': 4.090182739496231, 'latency_p50': 4.089295148849487, 'latency_p90': 4.540035891532898}, {'batch_size': 8, 'throughput': 1.5214447363974997, 'latency_mean': 5.218623951673508, 'latency_p50': 5.237783670425415, 'latency_p90': 5.879187965393067}, {'batch_size': 10, 'throughput': 1.5752951441349081, 'latency_mean': 6.299908738136292, 'latency_p50': 6.282160520553589, 'latency_p90': 7.168408274650574}]
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: 1.41
us_pacific_date: 2024-12-17
win_ratio: 0.5194365003707234
generation_params: {'temperature': 0.99, '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-v21-v6-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v21-v6-mkmlizer to finish
cloudyu-nemo-dpo-v21-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v21-v6-mkmlizer: ║ _____ __ __ ║
cloudyu-nemo-dpo-v21-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-nemo-dpo-v21-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-nemo-dpo-v21-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-nemo-dpo-v21-v6-mkmlizer: ║ /___/ ║
cloudyu-nemo-dpo-v21-v6-mkmlizer: ║ ║
cloudyu-nemo-dpo-v21-v6-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-nemo-dpo-v21-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-nemo-dpo-v21-v6-mkmlizer: ║ https://mk1.ai ║
cloudyu-nemo-dpo-v21-v6-mkmlizer: ║ ║
cloudyu-nemo-dpo-v21-v6-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-nemo-dpo-v21-v6-mkmlizer: ║ belonging to: ║
cloudyu-nemo-dpo-v21-v6-mkmlizer: ║ ║
cloudyu-nemo-dpo-v21-v6-mkmlizer: ║ Chai Research Corp. ║
cloudyu-nemo-dpo-v21-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-nemo-dpo-v21-v6-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-nemo-dpo-v21-v6-mkmlizer: ║ ║
cloudyu-nemo-dpo-v21-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v21-v6-mkmlizer: Downloaded to shared memory in 33.097s
cloudyu-nemo-dpo-v21-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_bphl7lc, device:0
cloudyu-nemo-dpo-v21-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v21-v6-mkmlizer: quantized model in 37.017s
cloudyu-nemo-dpo-v21-v6-mkmlizer: Processed model cloudyu/Nemo-DPO-V21 in 70.114s
cloudyu-nemo-dpo-v21-v6-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v21-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v21-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v6
cloudyu-nemo-dpo-v21-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v6/config.json
cloudyu-nemo-dpo-v21-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v6/special_tokens_map.json
cloudyu-nemo-dpo-v21-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v6/tokenizer_config.json
cloudyu-nemo-dpo-v21-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v6/tokenizer.json
cloudyu-nemo-dpo-v21-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v6/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v21-v6-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:13, 25.72it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 45.50it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 43.59it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:08, 40.92it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:07, 47.18it/s] Loading 0: 10%|█ | 37/363 [00:00<00:07, 46.23it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 44.60it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 49.39it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 46.83it/s] Loading 0: 17%|█▋ | 60/363 [00:01<00:06, 46.44it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:10, 28.92it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:08, 35.09it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:07, 36.41it/s] Loading 0: 23%|██▎ | 83/363 [00:02<00:07, 36.75it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:06, 42.29it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:06, 40.72it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 39.57it/s] Loading 0: 29%|██▉ | 107/363 [00:02<00:05, 44.00it/s] Loading 0: 31%|███ | 112/363 [00:02<00:05, 45.32it/s] Loading 0: 32%|███▏ | 117/363 [00:02<00:05, 43.32it/s] Loading 0: 34%|███▍ | 123/363 [00:02<00:05, 42.63it/s] Loading 0: 35%|███▌ | 128/363 [00:03<00:05, 40.32it/s] Loading 0: 37%|███▋ | 134/363 [00:03<00:05, 45.00it/s] Loading 0: 38%|███▊ | 139/363 [00:03<00:05, 44.37it/s] Loading 0: 40%|███▉ | 144/363 [00:03<00:08, 26.11it/s] Loading 0: 41%|████ | 149/363 [00:03<00:07, 28.07it/s] Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 35.70it/s] Loading 0: 44%|████▍ | 161/363 [00:04<00:05, 36.51it/s] Loading 0: 46%|████▌ | 166/363 [00:04<00:05, 38.52it/s] Loading 0: 47%|████▋ | 172/363 [00:04<00:04, 38.86it/s] Loading 0: 49%|████▉ | 177/363 [00:04<00:04, 39.10it/s] Loading 0: 50%|█████ | 183/363 [00:04<00:04, 43.51it/s] Loading 0: 52%|█████▏ | 188/363 [00:04<00:04, 42.21it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 42.78it/s] Loading 0: 55%|█████▍ | 198/363 [00:04<00:03, 44.07it/s] Loading 0: 56%|█████▌ | 203/363 [00:05<00:04, 35.86it/s] Loading 0: 58%|█████▊ | 210/363 [00:05<00:03, 41.57it/s] Loading 0: 59%|█████▉ | 215/363 [00:05<00:03, 40.55it/s] Loading 0: 61%|██████ | 220/363 [00:05<00:03, 42.31it/s] Loading 0: 62%|██████▏ | 225/363 [00:05<00:05, 25.48it/s] Loading 0: 63%|██████▎ | 230/363 [00:06<00:04, 27.74it/s] Loading 0: 66%|██████▌ | 238/363 [00:06<00:03, 36.27it/s] Loading 0: 67%|██████▋ | 244/363 [00:06<00:03, 37.45it/s] Loading 0: 69%|██████▊ | 249/363 [00:06<00:02, 38.11it/s] Loading 0: 71%|███████ | 256/363 [00:06<00:02, 43.45it/s] Loading 0: 72%|███████▏ | 261/363 [00:06<00:02, 44.54it/s] Loading 0: 73%|███████▎ | 266/363 [00:06<00:02, 38.48it/s] Loading 0: 75%|███████▌ | 273/363 [00:06<00:02, 44.95it/s] Loading 0: 77%|███████▋ | 278/363 [00:07<00:01, 43.21it/s] Loading 0: 78%|███████▊ | 283/363 [00:07<00:01, 41.39it/s] Loading 0: 79%|███████▉ | 288/363 [00:07<00:01, 42.81it/s] Loading 0: 81%|████████ | 293/363 [00:07<00:01, 35.96it/s] Loading 0: 82%|████████▏ | 299/363 [00:07<00:01, 41.34it/s] Loading 0: 84%|████████▎ | 304/363 [00:14<00:24, 2.43it/s] Loading 0: 85%|████████▍ | 308/363 [00:14<00:17, 3.14it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:12, 4.09it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:06, 6.82it/s] Loading 0: 90%|████████▉ | 326/363 [00:15<00:04, 9.17it/s] Loading 0: 91%|█████████ | 331/363 [00:15<00:02, 11.61it/s] Loading 0: 93%|█████████▎| 338/363 [00:15<00:01, 16.22it/s] Loading 0: 94%|█████████▍| 343/363 [00:15<00:01, 19.34it/s] Loading 0: 96%|█████████▌| 348/363 [00:15<00:00, 21.24it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 29.06it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 31.26it/s]
Job cloudyu-nemo-dpo-v21-v6-mkmlizer completed after 94.57s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v21-v6-mkmlizer
Pipeline stage MKMLizer completed in 95.06s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-nemo-dpo-v21-v6
Waiting for inference service cloudyu-nemo-dpo-v21-v6 to be ready
Inference service cloudyu-nemo-dpo-v21-v6 ready after 220.88840317726135s
Pipeline stage MKMLDeployer completed in 221.43s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.078420639038086s
Received healthy response to inference request in 1.7784523963928223s
Received healthy response to inference request in 2.064535140991211s
Received healthy response to inference request in 1.659865140914917s
Received healthy response to inference request in 2.319049596786499s
5 requests
0 failed requests
5th percentile: 1.683582592010498
10th percentile: 1.7073000431060792
20th percentile: 1.7547349452972412
30th percentile: 1.8356689453125
40th percentile: 1.9501020431518554
50th percentile: 2.064535140991211
60th percentile: 2.070089340209961
70th percentile: 2.075643539428711
80th percentile: 2.1265464305877684
90th percentile: 2.2227980136871337
95th percentile: 2.2709238052368166
99th percentile: 2.3094244384765625
mean time: 1.980064582824707
Pipeline stage StressChecker completed in 11.74s
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 2.58s
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 2.27s
Shutdown handler de-registered
cloudyu-nemo-dpo-v21_v6 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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cloudyu-nemo-dpo-v21-v6-profiler
Waiting for inference service cloudyu-nemo-dpo-v21-v6-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 3104.82s
Shutdown handler de-registered
cloudyu-nemo-dpo-v21_v6 status is now inactive due to auto deactivation removed underperforming models