cloudyu-nemo-dpo-v15

developer_uid: cloudyu

submission_id: cloudyu-nemo-dpo-v15_v2

model_name: cloudyu-nemo-dpo-v15_v1

model_group: cloudyu/Nemo-DPO-v15

status: inactive

timestamp: 2024-12-04T10:33:39+00:00

num_battles: 12549

num_wins: 6263

celo_rating: 1261.38

family_friendly_score: 0.5586

family_friendly_standard_error: 0.0070223363633480276

submission_type: basic

model_repo: cloudyu/Nemo-DPO-v15

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6127072529097479, 'latency_mean': 1.631981198787689, 'latency_p50': 1.6228790283203125, 'latency_p90': 1.7877871513366699}, {'batch_size': 3, 'throughput': 1.13846157429035, 'latency_mean': 2.6208095383644103, 'latency_p50': 2.6115161180496216, 'latency_p90': 2.8952012062072754}, {'batch_size': 5, 'throughput': 1.3943790755745291, 'latency_mean': 3.5733840930461884, 'latency_p50': 3.5530357360839844, 'latency_p90': 3.98945689201355}, {'batch_size': 6, 'throughput': 1.4512483179399105, 'latency_mean': 4.1138992083072665, 'latency_p50': 4.14301061630249, 'latency_p90': 4.546388006210327}, {'batch_size': 8, 'throughput': 1.5247881787298339, 'latency_mean': 5.214263302087784, 'latency_p50': 5.202084422111511, 'latency_p90': 5.8415169477462765}, {'batch_size': 10, 'throughput': 1.5651235591628818, 'latency_mean': 6.341420209407806, 'latency_p50': 6.357134699821472, 'latency_p90': 7.137756705284119}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cloudyu-nemo-dpo-v15_v1

is_internal_developer: False

language_model: cloudyu/Nemo-DPO-v15

model_size: 13B

ranking_group: single

throughput_3p7s: 1.41

us_pacific_date: 2024-12-04

win_ratio: 0.499083592318113

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-v15-v2-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v15-v2-mkmlizer to finish
cloudyu-nemo-dpo-v15-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v15-v2-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v15-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v15-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v15-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v15-v2-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v15-v2-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v15-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v15-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v15-v2-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v15-v2-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v15-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v15-v2-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v15-v2-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v15-v2-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v15-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v15-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-nemo-dpo-v15-v2-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v15-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v15-v2-mkmlizer: Downloaded to shared memory in 32.423s
cloudyu-nemo-dpo-v15-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpejpwl7kj, device:0
cloudyu-nemo-dpo-v15-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v15-v2-mkmlizer: quantized model in 34.858s
cloudyu-nemo-dpo-v15-v2-mkmlizer: Processed model cloudyu/Nemo-DPO-v15 in 67.280s
cloudyu-nemo-dpo-v15-v2-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v15-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v15-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v15-v2
cloudyu-nemo-dpo-v15-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v15-v2/config.json
cloudyu-nemo-dpo-v15-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v15-v2/special_tokens_map.json
cloudyu-nemo-dpo-v15-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v15-v2/tokenizer_config.json
cloudyu-nemo-dpo-v15-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v15-v2/tokenizer.json
cloudyu-nemo-dpo-v15-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v15-v2/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v15-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 29.58it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:07, 43.92it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:06, 55.42it/s]
Loading 0:   8%|▊         | 28/363 [00:00<00:06, 52.73it/s]
Loading 0:   9%|▉         | 34/363 [00:00<00:06, 53.45it/s]
Loading 0:  11%|█▏        | 41/363 [00:00<00:06, 49.26it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:05, 57.02it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:05, 53.12it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:07, 41.11it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:07, 39.79it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:06, 43.43it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 43.50it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 43.58it/s]
Loading 0:  25%|██▍       | 90/363 [00:01<00:05, 48.72it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 46.96it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:05, 45.95it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:04, 53.40it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 47.25it/s]
Loading 0:  33%|███▎      | 120/363 [00:02<00:05, 44.12it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:05, 46.02it/s]
Loading 0:  36%|███▌      | 131/363 [00:02<00:05, 45.17it/s]
Loading 0:  37%|███▋      | 136/363 [00:02<00:05, 39.78it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 35.30it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 35.97it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 35.43it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:04, 42.48it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 42.98it/s]
Loading 0:  46%|████▋     | 168/363 [00:03<00:04, 43.58it/s]
Loading 0:  48%|████▊     | 175/363 [00:03<00:03, 49.27it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:03, 47.56it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:03, 45.78it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 50.89it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 48.46it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 45.67it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 50.14it/s]
Loading 0:  60%|█████▉    | 217/363 [00:04<00:03, 47.03it/s]
Loading 0:  61%|██████    | 222/363 [00:04<00:02, 47.67it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 33.29it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 32.13it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 38.67it/s]
Loading 0:  67%|██████▋   | 244/363 [00:05<00:02, 39.77it/s]
Loading 0:  69%|██████▊   | 249/363 [00:05<00:02, 40.03it/s]
Loading 0:  71%|███████   | 256/363 [00:05<00:02, 45.86it/s]
Loading 0:  72%|███████▏  | 262/363 [00:05<00:02, 45.22it/s]
Loading 0:  74%|███████▎  | 267/363 [00:06<00:02, 44.93it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:01, 50.05it/s]
Loading 0:  77%|███████▋  | 280/363 [00:06<00:01, 48.45it/s]
Loading 0:  79%|███████▊  | 285/363 [00:06<00:01, 47.88it/s]
Loading 0:  80%|████████  | 292/363 [00:06<00:01, 51.65it/s]
Loading 0:  82%|████████▏ | 298/363 [00:06<00:01, 49.73it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:20,  2.88it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:15,  3.61it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:11,  4.61it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:05,  7.46it/s]
Loading 0:  90%|████████▉ | 326/363 [00:13<00:03,  9.98it/s]
Loading 0:  91%|█████████ | 331/363 [00:13<00:02, 12.56it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 17.49it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 21.27it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 24.58it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 31.10it/s]
Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 33.73it/s]
                                                            
Job cloudyu-nemo-dpo-v15-v2-mkmlizer completed after 94.27s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v15-v2-mkmlizer
Pipeline stage MKMLizer completed in 94.79s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-nemo-dpo-v15-v2
Waiting for inference service cloudyu-nemo-dpo-v15-v2 to be ready
Inference service cloudyu-nemo-dpo-v15-v2 ready after 150.53327107429504s
Pipeline stage MKMLDeployer completed in 151.08s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.373129367828369s
Received healthy response to inference request in 1.8526864051818848s
Received healthy response to inference request in 1.9621703624725342s
Received healthy response to inference request in 1.581108808517456s
Received healthy response to inference request in 1.8401708602905273s
5 requests
0 failed requests
5th percentile: 1.6329212188720703
10th percentile: 1.6847336292266846
20th percentile: 1.788358449935913
30th percentile: 1.8426739692687988
40th percentile: 1.8476801872253419
50th percentile: 1.8526864051818848
60th percentile: 1.8964799880981444
70th percentile: 1.9402735710144043
80th percentile: 2.0443621635437013
90th percentile: 2.208745765686035
95th percentile: 2.290937566757202
99th percentile: 2.3566910076141356
mean time: 1.9218531608581544
Pipeline stage StressChecker completed in 11.05s
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 2.16s
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 2.07s
Shutdown handler de-registered
cloudyu-nemo-dpo-v15_v2 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 2659.40s
Shutdown handler de-registered
cloudyu-nemo-dpo-v15_v2 status is now inactive due to auto deactivation removed underperforming models