developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v10_v1
model_name: cloudyu-nemo-dpo-v10_v1
model_group: cloudyu/Nemo-DPO-v10
status: inactive
timestamp: 2024-11-27T04:39:03+00:00
num_battles: 12258
num_wins: 5978
celo_rating: 1245.22
family_friendly_score: 0.5828
family_friendly_standard_error: 0.006973437602789603
submission_type: basic
model_repo: cloudyu/Nemo-DPO-v10
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6066222223520357, 'latency_mean': 1.6483721470832824, 'latency_p50': 1.6500556468963623, 'latency_p90': 1.8181476831436156}, {'batch_size': 3, 'throughput': 1.134183099756637, 'latency_mean': 2.6405413126945496, 'latency_p50': 2.617515444755554, 'latency_p90': 2.9097314834594727}, {'batch_size': 5, 'throughput': 1.3604230122389303, 'latency_mean': 3.6564109325408936, 'latency_p50': 3.6307809352874756, 'latency_p90': 4.162900590896607}, {'batch_size': 6, 'throughput': 1.4268772986115175, 'latency_mean': 4.182577956914901, 'latency_p50': 4.189863324165344, 'latency_p90': 4.633682036399842}, {'batch_size': 8, 'throughput': 1.4900903552619746, 'latency_mean': 5.319389306306839, 'latency_p50': 5.317777514457703, 'latency_p90': 6.022138404846191}, {'batch_size': 10, 'throughput': 1.5287067847618472, 'latency_mean': 6.495145539045334, 'latency_p50': 6.464674472808838, 'latency_p90': 7.333442831039428}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-nemo-dpo-v10_v1
is_internal_developer: False
language_model: cloudyu/Nemo-DPO-v10
model_size: 13B
ranking_group: single
throughput_3p7s: 1.37
us_pacific_date: 2024-11-26
win_ratio: 0.4876815141132322
generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, '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-v10-v1-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v10-v1-mkmlizer to finish
cloudyu-nemo-dpo-v10-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v10-v1-mkmlizer: ║ _____ __ __ ║
cloudyu-nemo-dpo-v10-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-nemo-dpo-v10-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-nemo-dpo-v10-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-nemo-dpo-v10-v1-mkmlizer: ║ /___/ ║
cloudyu-nemo-dpo-v10-v1-mkmlizer: ║ ║
cloudyu-nemo-dpo-v10-v1-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-nemo-dpo-v10-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-nemo-dpo-v10-v1-mkmlizer: ║ https://mk1.ai ║
cloudyu-nemo-dpo-v10-v1-mkmlizer: ║ ║
cloudyu-nemo-dpo-v10-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-nemo-dpo-v10-v1-mkmlizer: ║ belonging to: ║
cloudyu-nemo-dpo-v10-v1-mkmlizer: ║ ║
cloudyu-nemo-dpo-v10-v1-mkmlizer: ║ Chai Research Corp. ║
cloudyu-nemo-dpo-v10-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-nemo-dpo-v10-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-nemo-dpo-v10-v1-mkmlizer: ║ ║
cloudyu-nemo-dpo-v10-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v10-v1-mkmlizer: Downloaded to shared memory in 52.948s
cloudyu-nemo-dpo-v10-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp87y5bm_g, device:0
cloudyu-nemo-dpo-v10-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v10-v1-mkmlizer: quantized model in 36.347s
cloudyu-nemo-dpo-v10-v1-mkmlizer: Processed model cloudyu/Nemo-DPO-v10 in 89.295s
cloudyu-nemo-dpo-v10-v1-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v10-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v10-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v10-v1
cloudyu-nemo-dpo-v10-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v10-v1/config.json
cloudyu-nemo-dpo-v10-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v10-v1/special_tokens_map.json
cloudyu-nemo-dpo-v10-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v10-v1/tokenizer_config.json
cloudyu-nemo-dpo-v10-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v10-v1/tokenizer.json
cloudyu-nemo-dpo-v10-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 27.62it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 47.14it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 43.04it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:08, 41.45it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:07, 47.19it/s] Loading 0: 10%|█ | 37/363 [00:00<00:07, 44.10it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 42.17it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:06, 46.33it/s] Loading 0: 15%|█▍ | 53/363 [00:01<00:06, 45.15it/s] Loading 0: 16%|█▋ | 59/363 [00:01<00:06, 48.61it/s] Loading 0: 18%|█▊ | 64/363 [00:01<00:10, 28.18it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:08, 36.07it/s] Loading 0: 21%|██ | 77/363 [00:01<00:07, 37.92it/s] Loading 0: 23%|██▎ | 82/363 [00:02<00:08, 34.43it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:06, 42.06it/s] Loading 0: 26%|██▌ | 95/363 [00:02<00:06, 43.03it/s] Loading 0: 28%|██▊ | 100/363 [00:02<00:07, 36.58it/s] Loading 0: 29%|██▉ | 107/363 [00:02<00:05, 43.66it/s] Loading 0: 31%|███ | 112/363 [00:02<00:05, 45.07it/s] Loading 0: 32%|███▏ | 117/363 [00:02<00:05, 42.66it/s] Loading 0: 34%|███▎ | 122/363 [00:02<00:05, 44.24it/s] Loading 0: 35%|███▍ | 127/363 [00:03<00:06, 36.15it/s] Loading 0: 37%|███▋ | 134/363 [00:03<00:05, 43.59it/s] Loading 0: 38%|███▊ | 139/363 [00:03<00:05, 43.69it/s] Loading 0: 40%|███▉ | 144/363 [00:03<00:07, 27.89it/s] Loading 0: 41%|████ | 149/363 [00:03<00:07, 29.61it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:05, 37.78it/s] Loading 0: 45%|████▍ | 162/363 [00:04<00:05, 39.39it/s] Loading 0: 46%|████▌ | 167/363 [00:04<00:05, 35.53it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 43.20it/s] Loading 0: 50%|████▉ | 180/363 [00:04<00:04, 44.72it/s] Loading 0: 51%|█████ | 185/363 [00:04<00:04, 38.35it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 45.91it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 43.73it/s] Loading 0: 56%|█████▌ | 204/363 [00:05<00:03, 42.67it/s] Loading 0: 58%|█████▊ | 211/363 [00:05<00:03, 47.01it/s] Loading 0: 60%|█████▉ | 217/363 [00:05<00:03, 44.58it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:04, 34.77it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:03, 34.83it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:03, 33.74it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:03, 40.48it/s] Loading 0: 67%|██████▋ | 244/363 [00:06<00:02, 40.39it/s] Loading 0: 69%|██████▊ | 249/363 [00:06<00:02, 40.00it/s] Loading 0: 71%|███████ | 256/363 [00:06<00:02, 44.78it/s] Loading 0: 72%|███████▏ | 262/363 [00:06<00:02, 43.44it/s] Loading 0: 74%|███████▎ | 267/363 [00:06<00:02, 41.21it/s] Loading 0: 75%|███████▌ | 274/363 [00:06<00:01, 45.65it/s] Loading 0: 77%|███████▋ | 280/363 [00:06<00:01, 44.13it/s] Loading 0: 79%|███████▊ | 285/363 [00:07<00:01, 42.68it/s] Loading 0: 80%|████████ | 291/363 [00:07<00:01, 46.82it/s] Loading 0: 82%|████████▏ | 296/363 [00:07<00:01, 45.74it/s] Loading 0: 83%|████████▎ | 302/363 [00:07<00:01, 49.42it/s] Loading 0: 85%|████████▍ | 308/363 [00:14<00:20, 2.68it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:15, 3.38it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:07, 5.42it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:05, 7.30it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:03, 9.30it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 13.15it/s] Loading 0: 95%|█████████▍| 344/363 [00:15<00:01, 16.44it/s] Loading 0: 96%|█████████▌| 349/363 [00:15<00:00, 19.38it/s] Loading 0: 98%|█████████▊| 355/363 [00:15<00:00, 24.46it/s] Loading 0: 99%|█████████▉| 360/363 [00:15<00:00, 27.83it/s]
Job cloudyu-nemo-dpo-v10-v1-mkmlizer completed after 114.47s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v10-v1-mkmlizer
Pipeline stage MKMLizer completed in 114.95s
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-v10-v1
Waiting for inference service cloudyu-nemo-dpo-v10-v1 to be ready
Inference service cloudyu-nemo-dpo-v10-v1 ready after 130.54448986053467s
Pipeline stage MKMLDeployer completed in 131.07s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2055866718292236s
Received healthy response to inference request in 1.7519679069519043s
Received healthy response to inference request in 1.7074577808380127s
Received healthy response to inference request in 1.6045408248901367s
Received healthy response to inference request in 1.8643755912780762s
5 requests
0 failed requests
5th percentile: 1.625124216079712
10th percentile: 1.645707607269287
20th percentile: 1.6868743896484375
30th percentile: 1.716359806060791
40th percentile: 1.7341638565063477
50th percentile: 1.7519679069519043
60th percentile: 1.796930980682373
70th percentile: 1.8418940544128417
80th percentile: 1.9326178073883058
90th percentile: 2.069102239608765
95th percentile: 2.1373444557189942
99th percentile: 2.1919382286071776
mean time: 1.8267857551574707
Pipeline stage StressChecker completed in 10.39s
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 2.25s
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 2.45s
Shutdown handler de-registered
cloudyu-nemo-dpo-v10_v1 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 2747.44s
Shutdown handler de-registered
cloudyu-nemo-dpo-v10_v1 status is now inactive due to auto deactivation removed underperforming models