developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v20_v11
model_name: cloudyu-nemo-dpo-v20_v1
model_group: cloudyu/Nemo-DPO-V20
status: inactive
timestamp: 2024-12-21T00:41:09+00:00
num_battles: 17337
num_wins: 9081
celo_rating: 1281.09
family_friendly_score: 0.5636
family_friendly_standard_error: 0.007013630158484265
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': 0.6163341714402757, 'latency_mean': 1.622434903383255, 'latency_p50': 1.6193066835403442, 'latency_p90': 1.7968248844146728}, {'batch_size': 3, 'throughput': 1.141112090032159, 'latency_mean': 2.6169365537166596, 'latency_p50': 2.6296204328536987, 'latency_p90': 2.8981326103210447}, {'batch_size': 5, 'throughput': 1.3855838258733977, 'latency_mean': 3.5890580105781553, 'latency_p50': 3.6189866065979004, 'latency_p90': 4.054974150657654}, {'batch_size': 6, 'throughput': 1.4563088424267836, 'latency_mean': 4.102622102499009, 'latency_p50': 4.111076235771179, 'latency_p90': 4.6089928388595585}, {'batch_size': 8, 'throughput': 1.529108156292787, 'latency_mean': 5.193445961475373, 'latency_p50': 5.195825457572937, 'latency_p90': 5.93378746509552}, {'batch_size': 10, 'throughput': 1.5668821404933746, 'latency_mean': 6.340046430826187, 'latency_p50': 6.340847730636597, 'latency_p90': 7.189081573486328}]
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: 1.41
us_pacific_date: 2024-12-20
win_ratio: 0.5237930437792006
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-v11-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v20-v11-mkmlizer to finish
cloudyu-nemo-dpo-v20-v11-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v20-v11-mkmlizer: ║ _____ __ __ ║
cloudyu-nemo-dpo-v20-v11-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-nemo-dpo-v20-v11-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-nemo-dpo-v20-v11-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-nemo-dpo-v20-v11-mkmlizer: ║ /___/ ║
cloudyu-nemo-dpo-v20-v11-mkmlizer: ║ ║
cloudyu-nemo-dpo-v20-v11-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-nemo-dpo-v20-v11-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-nemo-dpo-v20-v11-mkmlizer: ║ https://mk1.ai ║
cloudyu-nemo-dpo-v20-v11-mkmlizer: ║ ║
cloudyu-nemo-dpo-v20-v11-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-nemo-dpo-v20-v11-mkmlizer: ║ belonging to: ║
cloudyu-nemo-dpo-v20-v11-mkmlizer: ║ ║
cloudyu-nemo-dpo-v20-v11-mkmlizer: ║ Chai Research Corp. ║
cloudyu-nemo-dpo-v20-v11-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-nemo-dpo-v20-v11-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-nemo-dpo-v20-v11-mkmlizer: ║ ║
cloudyu-nemo-dpo-v20-v11-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v20-v11-mkmlizer: Downloaded to shared memory in 57.588s
cloudyu-nemo-dpo-v20-v11-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplvua0ei0, device:0
cloudyu-nemo-dpo-v20-v11-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v20-v11-mkmlizer: quantized model in 35.948s
cloudyu-nemo-dpo-v20-v11-mkmlizer: Processed model cloudyu/Nemo-DPO-V20 in 93.536s
cloudyu-nemo-dpo-v20-v11-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v20-v11-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v20-v11-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v11
cloudyu-nemo-dpo-v20-v11-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v11/config.json
cloudyu-nemo-dpo-v20-v11-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v11/special_tokens_map.json
cloudyu-nemo-dpo-v20-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v11/tokenizer_config.json
cloudyu-nemo-dpo-v20-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v11/tokenizer.json
cloudyu-nemo-dpo-v20-v11-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v11/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v20-v11-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 28.66it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 50.16it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 47.74it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:06, 48.48it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 51.30it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 48.90it/s] Loading 0: 12%|█▏ | 43/363 [00:00<00:06, 49.70it/s] Loading 0: 13%|█▎ | 49/363 [00:00<00:06, 52.09it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 48.52it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 35.98it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:08, 36.44it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 40.91it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:06, 41.63it/s] Loading 0: 23%|██▎ | 83/363 [00:01<00:06, 41.43it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:05, 46.03it/s] Loading 0: 26%|██▌ | 95/363 [00:02<00:05, 46.49it/s] Loading 0: 28%|██▊ | 100/363 [00:02<00:06, 37.87it/s] Loading 0: 29%|██▉ | 106/363 [00:02<00:06, 42.82it/s] Loading 0: 31%|███ | 112/363 [00:02<00:05, 46.78it/s] Loading 0: 33%|███▎ | 118/363 [00:02<00:06, 36.76it/s] Loading 0: 34%|███▍ | 125/363 [00:02<00:05, 43.55it/s] Loading 0: 36%|███▌ | 131/363 [00:02<00:05, 44.76it/s] Loading 0: 37%|███▋ | 136/363 [00:03<00:05, 38.55it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 32.74it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 33.40it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 32.08it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:05, 38.66it/s] Loading 0: 45%|████▍ | 162/363 [00:03<00:04, 40.97it/s] Loading 0: 46%|████▌ | 167/363 [00:04<00:05, 35.68it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 43.86it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:04, 42.61it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:04, 41.82it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 46.59it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 44.39it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 43.20it/s] Loading 0: 58%|█████▊ | 210/363 [00:04<00:03, 47.26it/s] Loading 0: 59%|█████▉ | 215/363 [00:05<00:03, 45.89it/s] Loading 0: 61%|██████ | 221/363 [00:05<00:02, 49.46it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:04, 32.42it/s] Loading 0: 64%|██████▍ | 232/363 [00:05<00:03, 33.87it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:03, 38.04it/s] Loading 0: 67%|██████▋ | 244/363 [00:05<00:02, 39.93it/s] Loading 0: 69%|██████▊ | 249/363 [00:06<00:02, 39.78it/s] Loading 0: 71%|███████ | 256/363 [00:06<00:02, 45.39it/s] Loading 0: 72%|███████▏ | 262/363 [00:06<00:02, 45.14it/s] Loading 0: 74%|███████▎ | 267/363 [00:06<00:02, 44.61it/s] Loading 0: 75%|███████▌ | 273/363 [00:06<00:01, 45.78it/s] Loading 0: 77%|███████▋ | 278/363 [00:06<00:01, 44.87it/s] Loading 0: 78%|███████▊ | 283/363 [00:06<00:01, 45.83it/s] Loading 0: 80%|███████▉ | 289/363 [00:06<00:01, 43.98it/s] Loading 0: 81%|████████ | 294/363 [00:07<00:01, 42.27it/s] Loading 0: 83%|████████▎ | 301/363 [00:07<00:01, 48.98it/s] Loading 0: 85%|████████▍ | 307/363 [00:14<00:20, 2.74it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:13, 3.65it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:07, 5.70it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:04, 7.59it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:03, 9.53it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 13.37it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:01, 16.62it/s] Loading 0: 96%|█████████▌| 349/363 [00:14<00:00, 19.33it/s] Loading 0: 98%|█████████▊| 355/363 [00:15<00:00, 24.35it/s] Loading 0: 99%|█████████▉| 360/363 [00:15<00:00, 27.23it/s]
Job cloudyu-nemo-dpo-v20-v11-mkmlizer completed after 125.13s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v20-v11-mkmlizer
Pipeline stage MKMLizer completed in 125.59s
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-v11
Waiting for inference service cloudyu-nemo-dpo-v20-v11 to be ready
Inference service cloudyu-nemo-dpo-v20-v11 ready after 250.93858909606934s
Pipeline stage MKMLDeployer completed in 251.47s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2257308959960938s
Received healthy response to inference request in 1.6781392097473145s
Received healthy response to inference request in 1.6694190502166748s
Received healthy response to inference request in 2.077882766723633s
Received healthy response to inference request in 1.7499444484710693s
5 requests
0 failed requests
5th percentile: 1.6711630821228027
10th percentile: 1.6729071140289307
20th percentile: 1.6763951778411865
30th percentile: 1.6925002574920653
40th percentile: 1.7212223529815673
50th percentile: 1.7499444484710693
60th percentile: 1.8811197757720948
70th percentile: 2.01229510307312
80th percentile: 2.107452392578125
90th percentile: 2.1665916442871094
95th percentile: 2.1961612701416016
99th percentile: 2.219816970825195
mean time: 1.880223274230957
Pipeline stage StressChecker completed in 10.74s
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 0.63s
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 0.65s
Shutdown handler de-registered
cloudyu-nemo-dpo-v20_v11 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 2550.78s
Shutdown handler de-registered
cloudyu-nemo-dpo-v20_v11 status is now inactive due to auto deactivation removed underperforming models