developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v22_v3
model_name: cloudyu-nemo-dpo-v22_v1
model_group: cloudyu/Nemo-DPO-V22
status: inactive
timestamp: 2024-12-18T11:53:06+00:00
num_battles: 15383
num_wins: 8161
celo_rating: 1284.17
family_friendly_score: 0.5640000000000001
family_friendly_standard_error: 0.007012902394871898
submission_type: basic
model_repo: cloudyu/Nemo-DPO-V22
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6168737358199249, 'latency_mean': 1.6209873509407045, 'latency_p50': 1.6230844259262085, 'latency_p90': 1.7828973293304444}, {'batch_size': 3, 'throughput': 1.1517314254614612, 'latency_mean': 2.597380248308182, 'latency_p50': 2.59621798992157, 'latency_p90': 2.8258816957473756}, {'batch_size': 5, 'throughput': 1.3995878472491288, 'latency_mean': 3.553202565908432, 'latency_p50': 3.561675786972046, 'latency_p90': 3.9968758821487427}, {'batch_size': 6, 'throughput': 1.4618314874810936, 'latency_mean': 4.08038852930069, 'latency_p50': 4.127041339874268, 'latency_p90': 4.542573118209839}, {'batch_size': 8, 'throughput': 1.549149088393778, 'latency_mean': 5.128663494586944, 'latency_p50': 5.161791205406189, 'latency_p90': 5.782051277160645}, {'batch_size': 10, 'throughput': 1.5708647917967762, 'latency_mean': 6.312762916088104, 'latency_p50': 6.329726457595825, 'latency_p90': 7.208192420005798}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-nemo-dpo-v22_v1
is_internal_developer: False
language_model: cloudyu/Nemo-DPO-V22
model_size: 13B
ranking_group: single
throughput_3p7s: 1.43
us_pacific_date: 2024-12-18
win_ratio: 0.5305207046739908
generation_params: {'temperature': 1.25, '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-v22-v3-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v22-v3-mkmlizer to finish
cloudyu-nemo-dpo-v22-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v22-v3-mkmlizer: ║ _____ __ __ ║
cloudyu-nemo-dpo-v22-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-nemo-dpo-v22-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-nemo-dpo-v22-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-nemo-dpo-v22-v3-mkmlizer: ║ /___/ ║
cloudyu-nemo-dpo-v22-v3-mkmlizer: ║ ║
cloudyu-nemo-dpo-v22-v3-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-nemo-dpo-v22-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-nemo-dpo-v22-v3-mkmlizer: ║ https://mk1.ai ║
cloudyu-nemo-dpo-v22-v3-mkmlizer: ║ ║
cloudyu-nemo-dpo-v22-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-nemo-dpo-v22-v3-mkmlizer: ║ belonging to: ║
cloudyu-nemo-dpo-v22-v3-mkmlizer: ║ ║
cloudyu-nemo-dpo-v22-v3-mkmlizer: ║ Chai Research Corp. ║
cloudyu-nemo-dpo-v22-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-nemo-dpo-v22-v3-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-nemo-dpo-v22-v3-mkmlizer: ║ ║
cloudyu-nemo-dpo-v22-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v22-v3-mkmlizer: Downloaded to shared memory in 47.258s
cloudyu-nemo-dpo-v22-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwfaxuki5, device:0
cloudyu-nemo-dpo-v22-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v22-v3-mkmlizer: quantized model in 36.236s
cloudyu-nemo-dpo-v22-v3-mkmlizer: Processed model cloudyu/Nemo-DPO-V22 in 83.495s
cloudyu-nemo-dpo-v22-v3-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v22-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v22-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v3
cloudyu-nemo-dpo-v22-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v3/config.json
cloudyu-nemo-dpo-v22-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v3/special_tokens_map.json
cloudyu-nemo-dpo-v22-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v3/tokenizer_config.json
cloudyu-nemo-dpo-v22-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v3/tokenizer.json
cloudyu-nemo-dpo-v22-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v3/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v22-v3-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:13, 26.76it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 46.64it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 45.44it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 43.99it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 49.31it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 47.18it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 45.80it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 50.15it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 45.76it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 33.60it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:09, 32.14it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 38.46it/s] Loading 0: 21%|██ | 77/363 [00:01<00:06, 40.87it/s] Loading 0: 23%|██▎ | 82/363 [00:02<00:07, 35.92it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:06, 44.46it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:06, 42.09it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 40.15it/s] Loading 0: 29%|██▉ | 106/363 [00:02<00:06, 41.33it/s] Loading 0: 31%|███ | 113/363 [00:02<00:05, 42.20it/s] Loading 0: 33%|███▎ | 118/363 [00:02<00:05, 41.32it/s] Loading 0: 35%|███▍ | 126/363 [00:02<00:04, 49.20it/s] Loading 0: 36%|███▋ | 132/363 [00:03<00:05, 43.12it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:05, 40.38it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:07, 30.18it/s] Loading 0: 40%|████ | 146/363 [00:03<00:07, 30.62it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:07, 29.85it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:05, 36.54it/s] Loading 0: 45%|████▍ | 163/363 [00:04<00:05, 38.06it/s] Loading 0: 46%|████▋ | 168/363 [00:04<00:04, 39.50it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 45.47it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:04, 44.45it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:04, 43.66it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 48.88it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 46.41it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 44.26it/s] Loading 0: 58%|█████▊ | 211/363 [00:05<00:03, 48.79it/s] Loading 0: 60%|█████▉ | 217/363 [00:05<00:03, 46.79it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:03, 35.54it/s] Loading 0: 63%|██████▎ | 228/363 [00:05<00:03, 35.37it/s] Loading 0: 64%|██████▍ | 232/363 [00:05<00:03, 34.70it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:03, 39.06it/s] Loading 0: 67%|██████▋ | 244/363 [00:06<00:02, 40.11it/s] Loading 0: 69%|██████▊ | 249/363 [00:06<00:02, 40.38it/s] Loading 0: 71%|███████ | 256/363 [00:06<00:02, 45.70it/s] Loading 0: 72%|███████▏ | 262/363 [00:06<00:02, 41.72it/s] Loading 0: 74%|███████▎ | 267/363 [00:06<00:02, 41.91it/s] Loading 0: 75%|███████▌ | 274/363 [00:06<00:01, 46.62it/s] Loading 0: 77%|███████▋ | 280/363 [00:06<00:01, 44.44it/s] Loading 0: 79%|███████▊ | 285/363 [00:06<00:01, 44.22it/s] Loading 0: 80%|████████ | 292/363 [00:07<00:01, 48.77it/s] Loading 0: 82%|████████▏ | 298/363 [00:07<00:01, 47.43it/s] Loading 0: 84%|████████▎ | 304/363 [00:14<00:20, 2.83it/s] Loading 0: 85%|████████▍ | 308/363 [00:14<00:15, 3.54it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:11, 4.49it/s] Loading 0: 88%|████████▊ | 319/363 [00:14<00:06, 6.90it/s] Loading 0: 89%|████████▉ | 324/363 [00:14<00:04, 9.00it/s] Loading 0: 91%|█████████ | 329/363 [00:14<00:02, 11.71it/s] Loading 0: 92%|█████████▏| 335/363 [00:14<00:01, 15.30it/s] Loading 0: 94%|█████████▎| 340/363 [00:14<00:01, 18.67it/s] Loading 0: 96%|█████████▌| 347/363 [00:14<00:00, 25.00it/s] Loading 0: 97%|█████████▋| 352/363 [00:15<00:00, 28.82it/s] Loading 0: 98%|█████████▊| 357/363 [00:15<00:00, 29.19it/s]
Job cloudyu-nemo-dpo-v22-v3-mkmlizer completed after 114.88s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v22-v3-mkmlizer
Pipeline stage MKMLizer completed in 115.39s
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-v22-v3
Waiting for inference service cloudyu-nemo-dpo-v22-v3 to be ready
Inference service cloudyu-nemo-dpo-v22-v3 ready after 240.80322074890137s
Pipeline stage MKMLDeployer completed in 241.34s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.342042922973633s
Received healthy response to inference request in 2.3311426639556885s
Received healthy response to inference request in 1.7283799648284912s
Received healthy response to inference request in 1.8339424133300781s
Received healthy response to inference request in 1.9490981101989746s
5 requests
0 failed requests
5th percentile: 1.7494924545288086
10th percentile: 1.770604944229126
20th percentile: 1.8128299236297607
30th percentile: 1.8569735527038573
40th percentile: 1.903035831451416
50th percentile: 1.9490981101989746
60th percentile: 2.1019159317016602
70th percentile: 2.2547337532043454
80th percentile: 2.3333227157592775
90th percentile: 2.337682819366455
95th percentile: 2.3398628711700438
99th percentile: 2.341606912612915
mean time: 2.0369212150573732
Pipeline stage StressChecker completed in 11.70s
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 2.29s
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 2.16s
Shutdown handler de-registered
cloudyu-nemo-dpo-v22_v3 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cloudyu-nemo-dpo-v22-v3-profiler
Waiting for inference service cloudyu-nemo-dpo-v22-v3-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 3265.54s
Shutdown handler de-registered
cloudyu-nemo-dpo-v22_v3 status is now inactive due to auto deactivation removed underperforming models