developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v16_v4
model_name: cloudyu-nemo-dpo-v16_v1
model_group: cloudyu/Nemo-DPO-V16
status: inactive
timestamp: 2024-12-06T04:35:03+00:00
num_battles: 13309
num_wins: 6884
celo_rating: 1274.57
family_friendly_score: 0.5542
family_friendly_standard_error: 0.007029400543431851
submission_type: basic
model_repo: cloudyu/Nemo-DPO-V16
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6177679031955334, 'latency_mean': 1.618636156320572, 'latency_p50': 1.627987265586853, 'latency_p90': 1.7823185682296752}, {'batch_size': 3, 'throughput': 1.1461636826205368, 'latency_mean': 2.6097492790222168, 'latency_p50': 2.589469313621521, 'latency_p90': 2.9044151306152344}, {'batch_size': 5, 'throughput': 1.384488385891267, 'latency_mean': 3.59571426153183, 'latency_p50': 3.6184581518173218, 'latency_p90': 3.9653214693069456}, {'batch_size': 6, 'throughput': 1.4498818507122175, 'latency_mean': 4.127402926683426, 'latency_p50': 4.184349536895752, 'latency_p90': 4.630627512931824}, {'batch_size': 8, 'throughput': 1.5156013134165403, 'latency_mean': 5.253722168207169, 'latency_p50': 5.3096030950546265, 'latency_p90': 5.901028442382812}, {'batch_size': 10, 'throughput': 1.5759370575630347, 'latency_mean': 6.29467902302742, 'latency_p50': 6.219949245452881, 'latency_p90': 7.072510266304016}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-nemo-dpo-v16_v1
is_internal_developer: False
language_model: cloudyu/Nemo-DPO-V16
model_size: 13B
ranking_group: single
throughput_3p7s: 1.4
us_pacific_date: 2024-12-05
win_ratio: 0.5172439702456983
generation_params: {'temperature': 1.125, '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-v16-v4-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v16-v4-mkmlizer to finish
cloudyu-nemo-dpo-v16-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v16-v4-mkmlizer: ║ _____ __ __ ║
cloudyu-nemo-dpo-v16-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-nemo-dpo-v16-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-nemo-dpo-v16-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-nemo-dpo-v16-v4-mkmlizer: ║ /___/ ║
cloudyu-nemo-dpo-v16-v4-mkmlizer: ║ ║
cloudyu-nemo-dpo-v16-v4-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-nemo-dpo-v16-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-nemo-dpo-v16-v4-mkmlizer: ║ https://mk1.ai ║
cloudyu-nemo-dpo-v16-v4-mkmlizer: ║ ║
cloudyu-nemo-dpo-v16-v4-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-nemo-dpo-v16-v4-mkmlizer: ║ belonging to: ║
cloudyu-nemo-dpo-v16-v4-mkmlizer: ║ ║
cloudyu-nemo-dpo-v16-v4-mkmlizer: ║ Chai Research Corp. ║
cloudyu-nemo-dpo-v16-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-nemo-dpo-v16-v4-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-nemo-dpo-v16-v4-mkmlizer: ║ ║
cloudyu-nemo-dpo-v16-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v16-v4-mkmlizer: Downloaded to shared memory in 31.808s
cloudyu-nemo-dpo-v16-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkb5ojcs5, device:0
cloudyu-nemo-dpo-v16-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v16-v4-mkmlizer: quantized model in 36.700s
cloudyu-nemo-dpo-v16-v4-mkmlizer: Processed model cloudyu/Nemo-DPO-V16 in 68.508s
cloudyu-nemo-dpo-v16-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v16-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v4
cloudyu-nemo-dpo-v16-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v4/config.json
cloudyu-nemo-dpo-v16-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v4/special_tokens_map.json
cloudyu-nemo-dpo-v16-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v4/tokenizer_config.json
cloudyu-nemo-dpo-v16-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v4/tokenizer.json
cloudyu-nemo-dpo-v16-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v4/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v16-v4-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:13, 26.56it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:08, 43.32it/s] Loading 0: 5%|▍ | 17/363 [00:00<00:08, 42.41it/s] Loading 0: 6%|▌ | 22/363 [00:00<00:07, 42.98it/s] Loading 0: 8%|▊ | 28/363 [00:00<00:08, 40.54it/s] Loading 0: 9%|▉ | 33/363 [00:00<00:08, 38.82it/s] Loading 0: 11%|█ | 39/363 [00:00<00:07, 42.96it/s] Loading 0: 12%|█▏ | 44/363 [00:01<00:07, 41.16it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:07, 41.14it/s] Loading 0: 15%|█▍ | 54/363 [00:01<00:07, 40.90it/s] Loading 0: 16%|█▋ | 59/363 [00:01<00:07, 41.76it/s] Loading 0: 18%|█▊ | 64/363 [00:01<00:12, 24.36it/s] Loading 0: 20%|█▉ | 71/363 [00:01<00:09, 31.88it/s] Loading 0: 21%|██ | 76/363 [00:02<00:08, 34.23it/s] Loading 0: 22%|██▏ | 81/363 [00:02<00:07, 37.46it/s] Loading 0: 24%|██▍ | 87/363 [00:02<00:07, 37.77it/s] Loading 0: 25%|██▌ | 92/363 [00:02<00:07, 35.99it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:06, 40.31it/s] Loading 0: 28%|██▊ | 103/363 [00:02<00:06, 40.03it/s] Loading 0: 30%|██▉ | 108/363 [00:02<00:06, 41.87it/s] Loading 0: 31%|███ | 113/363 [00:03<00:06, 35.88it/s] Loading 0: 33%|███▎ | 118/363 [00:03<00:06, 36.54it/s] Loading 0: 35%|███▍ | 126/363 [00:03<00:05, 44.65it/s] Loading 0: 36%|███▌ | 131/363 [00:03<00:05, 44.91it/s] Loading 0: 37%|███▋ | 136/363 [00:03<00:05, 38.65it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 33.18it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 33.56it/s] Loading 0: 41%|████▏ | 150/363 [00:04<00:06, 31.87it/s] Loading 0: 43%|████▎ | 156/363 [00:04<00:05, 37.44it/s] Loading 0: 44%|████▍ | 161/363 [00:04<00:05, 37.36it/s] Loading 0: 45%|████▌ | 165/363 [00:04<00:05, 37.53it/s] Loading 0: 47%|████▋ | 169/363 [00:04<00:05, 35.90it/s] Loading 0: 48%|████▊ | 174/363 [00:04<00:04, 38.37it/s] Loading 0: 49%|████▉ | 178/363 [00:04<00:05, 36.09it/s] Loading 0: 50%|█████ | 183/363 [00:04<00:04, 38.96it/s] Loading 0: 52%|█████▏ | 187/363 [00:04<00:04, 38.36it/s] Loading 0: 53%|█████▎ | 193/363 [00:05<00:03, 42.74it/s] Loading 0: 55%|█████▍ | 198/363 [00:05<00:03, 43.86it/s] Loading 0: 56%|█████▌ | 203/363 [00:05<00:04, 34.84it/s] Loading 0: 58%|█████▊ | 210/363 [00:05<00:03, 41.61it/s] Loading 0: 59%|█████▉ | 215/363 [00:05<00:03, 40.77it/s] Loading 0: 61%|██████ | 220/363 [00:05<00:03, 42.36it/s] Loading 0: 62%|██████▏ | 225/363 [00:06<00:05, 25.80it/s] Loading 0: 63%|██████▎ | 230/363 [00:06<00:04, 27.69it/s] Loading 0: 66%|██████▌ | 238/363 [00:06<00:03, 36.03it/s] Loading 0: 67%|██████▋ | 243/363 [00:06<00:03, 38.73it/s] Loading 0: 68%|██████▊ | 248/363 [00:06<00:03, 35.00it/s] Loading 0: 70%|███████ | 255/363 [00:06<00:02, 41.62it/s] Loading 0: 72%|███████▏ | 260/363 [00:06<00:02, 41.55it/s] Loading 0: 73%|███████▎ | 265/363 [00:07<00:02, 42.65it/s] Loading 0: 74%|███████▍ | 270/363 [00:07<00:02, 43.52it/s] Loading 0: 76%|███████▌ | 275/363 [00:07<00:02, 36.12it/s] Loading 0: 78%|███████▊ | 283/363 [00:07<00:01, 44.01it/s] Loading 0: 79%|███████▉ | 288/363 [00:07<00:01, 45.28it/s] Loading 0: 81%|████████ | 293/363 [00:07<00:01, 38.17it/s] Loading 0: 83%|████████▎ | 300/363 [00:07<00:01, 45.32it/s] Loading 0: 84%|████████▍ | 305/363 [00:14<00:21, 2.66it/s] Loading 0: 85%|████████▌ | 309/363 [00:14<00:15, 3.38it/s] Loading 0: 86%|████████▌ | 313/363 [00:14<00:11, 4.33it/s] Loading 0: 88%|████████▊ | 319/363 [00:15<00:06, 6.38it/s] Loading 0: 89%|████████▉ | 323/363 [00:15<00:05, 7.99it/s] Loading 0: 90%|█████████ | 328/363 [00:15<00:03, 10.71it/s] Loading 0: 92%|█████████▏| 333/363 [00:15<00:02, 13.76it/s] Loading 0: 93%|█████████▎| 338/363 [00:15<00:01, 17.36it/s] Loading 0: 94%|█████████▍| 343/363 [00:15<00:00, 21.60it/s] Loading 0: 96%|█████████▌| 348/363 [00:15<00:00, 23.35it/s] Loading 0: 98%|█████████▊| 355/363 [00:15<00:00, 30.58it/s] Loading 0: 99%|█████████▉| 360/363 [00:15<00:00, 33.63it/s]
Job cloudyu-nemo-dpo-v16-v4-mkmlizer completed after 103.71s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v16-v4-mkmlizer
Pipeline stage MKMLizer completed in 105.44s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-nemo-dpo-v16-v4
Waiting for inference service cloudyu-nemo-dpo-v16-v4 to be ready
Inference service cloudyu-nemo-dpo-v16-v4 ready after 167.20228934288025s
Pipeline stage MKMLDeployer completed in 168.94s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.396195650100708s
Received healthy response to inference request in 1.817141056060791s
Received healthy response to inference request in 1.7794156074523926s
Received healthy response to inference request in 1.6562469005584717s
Received healthy response to inference request in 1.8124346733093262s
5 requests
0 failed requests
5th percentile: 1.680880641937256
10th percentile: 1.70551438331604
20th percentile: 1.7547818660736083
30th percentile: 1.7860194206237794
40th percentile: 1.7992270469665528
50th percentile: 1.8124346733093262
60th percentile: 1.814317226409912
70th percentile: 1.816199779510498
80th percentile: 1.9329519748687745
90th percentile: 2.164573812484741
95th percentile: 2.2803847312927243
99th percentile: 2.3730334663391113
mean time: 1.892286777496338
Pipeline stage StressChecker completed in 11.06s
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 2.50s
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 2.33s
Shutdown handler de-registered
cloudyu-nemo-dpo-v16_v4 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 2617.95s
Shutdown handler de-registered
cloudyu-nemo-dpo-v16_v4 status is now inactive due to auto deactivation removed underperforming models