cloudyu-nemo-dpo-v19

developer_uid: cloudyu

submission_id: cloudyu-nemo-dpo-v19_v7

model_name: cloudyu-nemo-dpo-v19_v1

model_group: cloudyu/Nemo-DPO-V19

status: inactive

timestamp: 2024-12-16T22:24:52+00:00

num_battles: 15982

num_wins: 8209

celo_rating: 1272.91

family_friendly_score: 0.5660000000000001

family_friendly_standard_error: 0.007009193962218481

submission_type: basic

model_repo: cloudyu/Nemo-DPO-V19

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6103636675994127, 'latency_mean': 1.638301203250885, 'latency_p50': 1.6365890502929688, 'latency_p90': 1.7945550203323364}, {'batch_size': 3, 'throughput': 1.1197809128294027, 'latency_mean': 2.67050711274147, 'latency_p50': 2.6873689889907837, 'latency_p90': 2.9830686807632447}, {'batch_size': 5, 'throughput': 1.3454990696310904, 'latency_mean': 3.692894636392593, 'latency_p50': 3.709596276283264, 'latency_p90': 4.124754500389099}, {'batch_size': 6, 'throughput': 1.432407326462616, 'latency_mean': 4.1710800719261165, 'latency_p50': 4.181475758552551, 'latency_p90': 4.746959543228149}, {'batch_size': 8, 'throughput': 1.4946592477810137, 'latency_mean': 5.3155301308631895, 'latency_p50': 5.331188082695007, 'latency_p90': 5.948486566543579}, {'batch_size': 10, 'throughput': 1.517195176977033, 'latency_mean': 6.544417246580124, 'latency_p50': 6.53095281124115, 'latency_p90': 7.358718419075012}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cloudyu-nemo-dpo-v19_v1

is_internal_developer: False

language_model: cloudyu/Nemo-DPO-V19

model_size: 13B

ranking_group: single

throughput_3p7s: 1.36

us_pacific_date: 2024-12-16

win_ratio: 0.5136403453885622

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-v19-v7-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v19-v7-mkmlizer to finish
cloudyu-nemo-dpo-v19-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v19-v7-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v19-v7-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v19-v7-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v19-v7-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v19-v7-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v19-v7-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v19-v7-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v19-v7-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v19-v7-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v19-v7-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v19-v7-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v19-v7-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v19-v7-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v19-v7-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v19-v7-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v19-v7-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-nemo-dpo-v19-v7-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v19-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v19-v7-mkmlizer: Downloaded to shared memory in 34.423s
cloudyu-nemo-dpo-v19-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp72vsvkp4, device:0
cloudyu-nemo-dpo-v19-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v19-v7-mkmlizer: quantized model in 35.344s
cloudyu-nemo-dpo-v19-v7-mkmlizer: Processed model cloudyu/Nemo-DPO-V19 in 69.768s
cloudyu-nemo-dpo-v19-v7-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v19-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v19-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v7
cloudyu-nemo-dpo-v19-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v7/config.json
cloudyu-nemo-dpo-v19-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v7/special_tokens_map.json
cloudyu-nemo-dpo-v19-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v7/tokenizer_config.json
cloudyu-nemo-dpo-v19-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v7/tokenizer.json
cloudyu-nemo-dpo-v19-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v7/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v19-v7-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 30.50it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 51.38it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 47.04it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 45.78it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 51.89it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 48.26it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:06, 46.55it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 51.60it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 47.11it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 34.90it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 36.14it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 40.62it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 41.17it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 41.79it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:05, 47.37it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 45.13it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:05, 43.84it/s]
Loading 0:  29%|██▉       | 107/363 [00:02<00:05, 47.60it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:05, 42.40it/s]
Loading 0:  33%|███▎      | 118/363 [00:02<00:05, 41.75it/s]
Loading 0:  34%|███▍      | 125/363 [00:02<00:04, 48.16it/s]
Loading 0:  36%|███▌      | 131/363 [00:02<00:04, 49.15it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:05, 43.84it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 34.79it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 35.71it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 34.63it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:04, 41.56it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 41.05it/s]
Loading 0:  46%|████▋     | 168/363 [00:03<00:04, 41.38it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 46.62it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 44.21it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 43.64it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 48.51it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 45.29it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 44.05it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 48.65it/s]
Loading 0:  60%|█████▉    | 217/363 [00:04<00:03, 45.00it/s]
Loading 0:  61%|██████    | 222/363 [00:05<00:03, 46.17it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 33.57it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 32.14it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 38.88it/s]
Loading 0:  67%|██████▋   | 244/363 [00:05<00:03, 38.87it/s]
Loading 0:  69%|██████▊   | 249/363 [00:05<00:02, 39.47it/s]
Loading 0:  70%|███████   | 255/363 [00:05<00:02, 43.94it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 44.66it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 45.94it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 44.19it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:02, 42.03it/s]
Loading 0:  78%|███████▊  | 282/363 [00:06<00:01, 45.64it/s]
Loading 0:  79%|███████▉  | 287/363 [00:06<00:01, 44.37it/s]
Loading 0:  80%|████████  | 292/363 [00:06<00:01, 44.26it/s]
Loading 0:  82%|████████▏ | 297/363 [00:06<00:01, 45.53it/s]
Loading 0:  83%|████████▎ | 303/363 [00:07<00:01, 42.78it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:21,  2.50it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:15,  3.24it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:08,  5.34it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:05,  7.25it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:03,  9.33it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.28it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:01, 16.59it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 19.71it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 25.76it/s]
Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 28.82it/s]
                                                            
Job cloudyu-nemo-dpo-v19-v7-mkmlizer completed after 94.92s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v19-v7-mkmlizer
Pipeline stage MKMLizer completed in 95.44s
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-v19-v7
Waiting for inference service cloudyu-nemo-dpo-v19-v7 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cloudyu-nemo-dpo-v19-v7 ready after 222.03991889953613s
Pipeline stage MKMLDeployer completed in 222.63s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.450103521347046s
Received healthy response to inference request in 1.8075814247131348s
Received healthy response to inference request in 2.1373558044433594s
Received healthy response to inference request in 1.7712435722351074s
Received healthy response to inference request in 2.008181095123291s
5 requests
0 failed requests
5th percentile: 1.778511142730713
10th percentile: 1.7857787132263183
20th percentile: 1.8003138542175292
30th percentile: 1.847701358795166
40th percentile: 1.9279412269592284
50th percentile: 2.008181095123291
60th percentile: 2.059850978851318
70th percentile: 2.111520862579346
80th percentile: 2.199905347824097
90th percentile: 2.3250044345855714
95th percentile: 2.3875539779663084
99th percentile: 2.4375936126708986
mean time: 2.0348930835723875
Pipeline stage StressChecker completed in 11.50s
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 2.15s
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 2.27s
Shutdown handler de-registered
cloudyu-nemo-dpo-v19_v7 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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cloudyu-nemo-dpo-v19-v7-profiler
Waiting for inference service cloudyu-nemo-dpo-v19-v7-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 3184.28s
Shutdown handler de-registered
cloudyu-nemo-dpo-v19_v7 status is now inactive due to auto deactivation removed underperforming models