cloudyu-nemo-dpo-v16

developer_uid: cloudyu

submission_id: cloudyu-nemo-dpo-v16_v2

model_name: cloudyu-nemo-dpo-v16_v1

model_group: cloudyu/Nemo-DPO-V16

status: inactive

timestamp: 2024-12-06T02:54:30+00:00

num_battles: 7445

num_wins: 3857

celo_rating: 1278.29

family_friendly_score: 0.5518000000000001

family_friendly_standard_error: 0.007033018697543751

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': 0.6122450434829283, 'latency_mean': 1.6332722866535188, 'latency_p50': 1.6370497941970825, 'latency_p90': 1.7818987131118775}, {'batch_size': 3, 'throughput': 1.146112714920334, 'latency_mean': 2.608150976896286, 'latency_p50': 2.5910892486572266, 'latency_p90': 2.9129515647888184}, {'batch_size': 5, 'throughput': 1.3805702403683298, 'latency_mean': 3.599760357141495, 'latency_p50': 3.620307683944702, 'latency_p90': 3.9995550155639648}, {'batch_size': 6, 'throughput': 1.4505824288848863, 'latency_mean': 4.111931091547012, 'latency_p50': 4.128125905990601, 'latency_p90': 4.586785411834716}, {'batch_size': 8, 'throughput': 1.5234537816061875, 'latency_mean': 5.229185578823089, 'latency_p50': 5.217906355857849, 'latency_p90': 5.836396098136902}, {'batch_size': 10, 'throughput': 1.5487419921021692, 'latency_mean': 6.4164140665531155, 'latency_p50': 6.384597897529602, 'latency_p90': 7.184259963035584}]

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: 0.5180658159838818

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-v16-v2-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v16-v2-mkmlizer to finish
cloudyu-nemo-dpo-v16-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v16-v2-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v16-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v16-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v16-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v16-v2-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v16-v2-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v16-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v16-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v16-v2-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v16-v2-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v16-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v16-v2-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v16-v2-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v16-v2-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v16-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v16-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-nemo-dpo-v16-v2-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v16-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v16-v2-mkmlizer: Downloaded to shared memory in 37.619s
cloudyu-nemo-dpo-v16-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzsde89eu, device:0
cloudyu-nemo-dpo-v16-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v16-v2-mkmlizer: quantized model in 37.511s
cloudyu-nemo-dpo-v16-v2-mkmlizer: Processed model cloudyu/Nemo-DPO-V16 in 75.131s
cloudyu-nemo-dpo-v16-v2-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v16-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v16-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v2
cloudyu-nemo-dpo-v16-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v2/config.json
cloudyu-nemo-dpo-v16-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v2/special_tokens_map.json
cloudyu-nemo-dpo-v16-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v2/tokenizer_config.json
cloudyu-nemo-dpo-v16-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v2/tokenizer.json
cloudyu-nemo-dpo-v16-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 26.70it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 41.83it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:08, 40.17it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:08, 40.53it/s]
Loading 0:   7%|▋         | 27/363 [00:00<00:07, 42.16it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 33.67it/s]
Loading 0:  11%|█         | 39/363 [00:00<00:07, 41.79it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:07, 41.20it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:07, 41.29it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:07, 41.88it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:07, 42.88it/s]
Loading 0:  18%|█▊        | 64/363 [00:01<00:12, 24.23it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:09, 31.29it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:08, 33.70it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 36.45it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 39.21it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 34.01it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 41.32it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 38.46it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:06, 38.27it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:07, 34.57it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:06, 35.01it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 42.02it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 42.31it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 43.90it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:05, 42.87it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:07, 30.78it/s]
Loading 0:  41%|████▏     | 150/363 [00:04<00:06, 30.63it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:05, 36.41it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 38.08it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:04, 40.45it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:04, 40.02it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 40.48it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:03, 45.42it/s]
Loading 0:  52%|█████▏    | 189/363 [00:04<00:03, 46.08it/s]
Loading 0:  53%|█████▎    | 194/363 [00:05<00:04, 37.37it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:03, 44.22it/s]
Loading 0:  57%|█████▋    | 206/363 [00:05<00:03, 42.96it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 43.61it/s]
Loading 0:  60%|█████▉    | 216/363 [00:05<00:03, 44.02it/s]
Loading 0:  61%|██████    | 222/363 [00:05<00:03, 41.98it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:04, 30.34it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 30.00it/s]
Loading 0:  66%|██████▌   | 238/363 [00:06<00:03, 36.97it/s]
Loading 0:  67%|██████▋   | 243/363 [00:06<00:03, 38.15it/s]
Loading 0:  68%|██████▊   | 248/363 [00:06<00:03, 33.55it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 41.24it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 41.43it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 42.49it/s]
Loading 0:  74%|███████▍  | 270/363 [00:07<00:02, 44.02it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 36.74it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:01, 42.78it/s]
Loading 0:  79%|███████▉  | 287/363 [00:07<00:01, 39.19it/s]
Loading 0:  80%|████████  | 292/363 [00:07<00:01, 39.35it/s]
Loading 0:  82%|████████▏ | 297/363 [00:07<00:01, 40.48it/s]
Loading 0:  83%|████████▎ | 302/363 [00:07<00:01, 42.14it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:23,  2.34it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:15,  3.24it/s]
Loading 0:  88%|████████▊ | 320/363 [00:15<00:08,  5.26it/s]
Loading 0:  90%|████████▉ | 325/363 [00:15<00:05,  6.88it/s]
Loading 0:  91%|█████████ | 330/363 [00:15<00:03,  8.60it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 12.99it/s]
Loading 0:  94%|█████████▍| 343/363 [00:15<00:01, 15.96it/s]
Loading 0:  96%|█████████▌| 348/363 [00:15<00:00, 17.55it/s]
Loading 0:  98%|█████████▊| 355/363 [00:15<00:00, 23.59it/s]
Loading 0:  99%|█████████▉| 360/363 [00:16<00:00, 26.42it/s]
                                                            
Job cloudyu-nemo-dpo-v16-v2-mkmlizer completed after 107.56s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v16-v2-mkmlizer
Pipeline stage MKMLizer completed in 109.93s
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-v16-v2
Waiting for inference service cloudyu-nemo-dpo-v16-v2 to be ready
Inference service cloudyu-nemo-dpo-v16-v2 ready after 205.40503358840942s
Pipeline stage MKMLDeployer completed in 208.55s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0675673484802246s
Received healthy response to inference request in 1.942300796508789s
Received healthy response to inference request in 2.088284492492676s
Received healthy response to inference request in 2.3228323459625244s
Received healthy response to inference request in 1.7164340019226074s
5 requests
0 failed requests
5th percentile: 1.7616073608398437
10th percentile: 1.80678071975708
20th percentile: 1.8971274375915528
30th percentile: 1.9673541069030762
40th percentile: 2.0174607276916503
50th percentile: 2.0675673484802246
60th percentile: 2.075854206085205
70th percentile: 2.0841410636901854
80th percentile: 2.1351940631866455
90th percentile: 2.229013204574585
95th percentile: 2.2759227752685547
99th percentile: 2.3134504318237306
mean time: 2.0274837970733643
Pipeline stage StressChecker completed in 11.56s
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 2.44s
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 2.39s
Shutdown handler de-registered
cloudyu-nemo-dpo-v16_v2 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cloudyu-nemo-dpo-v16-v2-profiler
Waiting for inference service cloudyu-nemo-dpo-v16-v2-profiler to be ready
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 2533.20s
Shutdown handler de-registered
cloudyu-nemo-dpo-v16_v2 status is now inactive due to auto deactivation removed underperforming models