developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v19_v3
model_name: cloudyu-nemo-dpo-v19_v1
model_group: cloudyu/Nemo-DPO-V19
status: inactive
timestamp: 2024-12-16T08:12:38+00:00
num_battles: 14935
num_wins: 7869
celo_rating: 1282.13
family_friendly_score: 0.5671999999999999
family_friendly_standard_error: 0.007006913157732155
submission_type: basic
model_repo: cloudyu/Nemo-DPO-V19
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6163238826862295, 'latency_mean': 1.6224373483657837, 'latency_p50': 1.6240776777267456, 'latency_p90': 1.7839824676513671}, {'batch_size': 3, 'throughput': 1.124970448197369, 'latency_mean': 2.6591073870658875, 'latency_p50': 2.6496697664260864, 'latency_p90': 2.9104896545410157}, {'batch_size': 5, 'throughput': 1.3687671946156574, 'latency_mean': 3.641936491727829, 'latency_p50': 3.6350568532943726, 'latency_p90': 4.067271113395691}, {'batch_size': 6, 'throughput': 1.4293448585022186, 'latency_mean': 4.171845290660858, 'latency_p50': 4.1650389432907104, 'latency_p90': 4.660089421272278}, {'batch_size': 8, 'throughput': 1.5095315781104863, 'latency_mean': 5.282603081464767, 'latency_p50': 5.301026105880737, 'latency_p90': 6.028751945495605}, {'batch_size': 10, 'throughput': 1.5463481649399897, 'latency_mean': 6.413097273111344, 'latency_p50': 6.447825312614441, 'latency_p90': 7.319388484954834}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-nemo-dpo-v19_v1
is_internal_developer: False
language_model: cloudyu/Nemo-DPO-V19
model_size: 13B
ranking_group: single
throughput_3p7s: 1.38
us_pacific_date: 2024-12-16
win_ratio: 0.5268831603615668
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-v19-v3-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v19-v3-mkmlizer to finish
cloudyu-nemo-dpo-v19-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v19-v3-mkmlizer: ║ _____ __ __ ║
cloudyu-nemo-dpo-v19-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-nemo-dpo-v19-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-nemo-dpo-v19-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-nemo-dpo-v19-v3-mkmlizer: ║ /___/ ║
cloudyu-nemo-dpo-v19-v3-mkmlizer: ║ ║
cloudyu-nemo-dpo-v19-v3-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-nemo-dpo-v19-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-nemo-dpo-v19-v3-mkmlizer: ║ https://mk1.ai ║
cloudyu-nemo-dpo-v19-v3-mkmlizer: ║ ║
cloudyu-nemo-dpo-v19-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-nemo-dpo-v19-v3-mkmlizer: ║ belonging to: ║
cloudyu-nemo-dpo-v19-v3-mkmlizer: ║ ║
cloudyu-nemo-dpo-v19-v3-mkmlizer: ║ Chai Research Corp. ║
cloudyu-nemo-dpo-v19-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-nemo-dpo-v19-v3-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-nemo-dpo-v19-v3-mkmlizer: ║ ║
cloudyu-nemo-dpo-v19-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v19-v3-mkmlizer: Downloaded to shared memory in 46.835s
cloudyu-nemo-dpo-v19-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp553w79er, device:0
cloudyu-nemo-dpo-v19-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v19-v3-mkmlizer: quantized model in 36.477s
cloudyu-nemo-dpo-v19-v3-mkmlizer: Processed model cloudyu/Nemo-DPO-V19 in 83.312s
cloudyu-nemo-dpo-v19-v3-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v19-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v19-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v3
cloudyu-nemo-dpo-v19-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v3/config.json
cloudyu-nemo-dpo-v19-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v3/special_tokens_map.json
cloudyu-nemo-dpo-v19-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v3/tokenizer_config.json
cloudyu-nemo-dpo-v19-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v3/tokenizer.json
cloudyu-nemo-dpo-v19-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v3/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v19-v3-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:13, 27.31it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 47.33it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 44.45it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 42.75it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 47.80it/s] Loading 0: 10%|█ | 37/363 [00:00<00:07, 45.89it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 45.45it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 50.14it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 47.66it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 34.71it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:08, 35.26it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 39.83it/s] Loading 0: 21%|██ | 77/363 [00:01<00:06, 41.71it/s] Loading 0: 23%|██▎ | 82/363 [00:02<00:07, 36.97it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:06, 44.74it/s] Loading 0: 26%|██▌ | 95/363 [00:02<00:05, 45.86it/s] Loading 0: 28%|██▊ | 100/363 [00:02<00:07, 36.62it/s] Loading 0: 29%|██▉ | 106/363 [00:02<00:06, 40.08it/s] Loading 0: 31%|███ | 112/363 [00:02<00:05, 42.61it/s] Loading 0: 32%|███▏ | 117/363 [00:02<00:05, 41.46it/s] Loading 0: 34%|███▎ | 122/363 [00:02<00:05, 42.67it/s] Loading 0: 35%|███▍ | 127/363 [00:03<00:06, 37.23it/s] Loading 0: 37%|███▋ | 135/363 [00:03<00:04, 45.67it/s] Loading 0: 39%|███▉ | 141/363 [00:03<00:04, 44.93it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 31.67it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 31.29it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:05, 37.91it/s] Loading 0: 45%|████▍ | 162/363 [00:03<00:04, 40.26it/s] Loading 0: 46%|████▌ | 167/363 [00:04<00:05, 36.68it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 45.07it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:04, 43.73it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:04, 42.17it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 47.78it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 46.62it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 44.97it/s] Loading 0: 58%|█████▊ | 211/363 [00:05<00:03, 50.18it/s] Loading 0: 60%|█████▉ | 217/363 [00:05<00:03, 48.17it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:03, 35.58it/s] Loading 0: 63%|██████▎ | 228/363 [00:05<00:03, 35.26it/s] Loading 0: 64%|██████▍ | 232/363 [00:05<00:03, 36.10it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:03, 40.66it/s] Loading 0: 67%|██████▋ | 244/363 [00:05<00:02, 41.14it/s] Loading 0: 69%|██████▊ | 249/363 [00:06<00:02, 41.08it/s] Loading 0: 71%|███████ | 256/363 [00:06<00:02, 46.25it/s] Loading 0: 72%|███████▏ | 261/363 [00:06<00:02, 46.84it/s] Loading 0: 73%|███████▎ | 266/363 [00:06<00:02, 39.09it/s] Loading 0: 75%|███████▌ | 273/363 [00:06<00:01, 46.31it/s] Loading 0: 77%|███████▋ | 279/363 [00:06<00:01, 46.80it/s] Loading 0: 78%|███████▊ | 284/363 [00:06<00:01, 40.58it/s] Loading 0: 80%|████████ | 292/363 [00:06<00:01, 47.77it/s] Loading 0: 82%|████████▏ | 298/363 [00:07<00:01, 46.55it/s] Loading 0: 84%|████████▎ | 304/363 [00:14<00:20, 2.84it/s] Loading 0: 85%|████████▍ | 308/363 [00:14<00:15, 3.55it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:11, 4.50it/s] Loading 0: 88%|████████▊ | 319/363 [00:14<00:06, 6.90it/s] Loading 0: 90%|████████▉ | 325/363 [00:14<00:03, 9.53it/s] Loading 0: 91%|█████████ | 330/363 [00:14<00:02, 11.80it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 17.46it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:00, 21.15it/s] Loading 0: 96%|█████████▋| 350/363 [00:14<00:00, 25.53it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 30.43it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 33.26it/s]
Job cloudyu-nemo-dpo-v19-v3-mkmlizer completed after 104.65s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v19-v3-mkmlizer
Pipeline stage MKMLizer completed in 105.15s
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-v19-v3
Waiting for inference service cloudyu-nemo-dpo-v19-v3 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-v19-v3 ready after 210.75225496292114s
Pipeline stage MKMLDeployer completed in 211.27s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.052314519882202s
Received healthy response to inference request in 1.9493560791015625s
Received healthy response to inference request in 1.8081567287445068s
Received healthy response to inference request in 1.669602632522583s
Received healthy response to inference request in 1.6968963146209717s
5 requests
0 failed requests
5th percentile: 1.6750613689422607
10th percentile: 1.6805201053619385
20th percentile: 1.691437578201294
30th percentile: 1.7191483974456787
40th percentile: 1.7636525630950928
50th percentile: 1.8081567287445068
60th percentile: 1.8646364688873291
70th percentile: 1.9211162090301512
80th percentile: 1.9699477672576904
90th percentile: 2.0111311435699464
95th percentile: 2.031722831726074
99th percentile: 2.0481961822509764
mean time: 1.8352652549743653
Pipeline stage StressChecker completed in 10.48s
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 2.11s
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 1.98s
Shutdown handler de-registered
cloudyu-nemo-dpo-v19_v3 status is now deployed due to DeploymentManager action
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 3140.93s
Shutdown handler de-registered
cloudyu-nemo-dpo-v19_v3 status is now inactive due to auto deactivation removed underperforming models