cloudyu-nemo-dpo-v22

developer_uid: azuruce

submission_id: cloudyu-nemo-dpo-v22_v18

model_name: cloudyu-nemo-dpo-v22_v18

model_group: cloudyu/Nemo-DPO-V22

status: torndown

timestamp: 2025-01-09T23:18:13+00:00

num_battles: 6667

num_wins: 3486

celo_rating: 1265.12

family_friendly_score: 0.5714

family_friendly_standard_error: 0.006998600431514861

submission_type: basic

model_repo: cloudyu/Nemo-DPO-V22

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.629587347601492, 'latency_mean': 1.588246965408325, 'latency_p50': 1.597478985786438, 'latency_p90': 1.7550203561782838}, {'batch_size': 3, 'throughput': 1.2575099951794297, 'latency_mean': 2.3742287969589233, 'latency_p50': 2.373865008354187, 'latency_p90': 2.6119139432907104}, {'batch_size': 5, 'throughput': 1.585591035819368, 'latency_mean': 3.1371466386318207, 'latency_p50': 3.113723635673523, 'latency_p90': 3.595658278465271}, {'batch_size': 6, 'throughput': 1.6956323371627167, 'latency_mean': 3.512343171834946, 'latency_p50': 3.4905245304107666, 'latency_p90': 3.996979808807373}, {'batch_size': 8, 'throughput': 1.8495393031864344, 'latency_mean': 4.2980675649642945, 'latency_p50': 4.290292739868164, 'latency_p90': 4.829623198509216}, {'batch_size': 10, 'throughput': 1.9448910321388635, 'latency_mean': 5.099507143497467, 'latency_p50': 5.062592148780823, 'latency_p90': 5.844147443771362}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cloudyu-nemo-dpo-v22_v18

is_internal_developer: False

language_model: cloudyu/Nemo-DPO-V22

model_size: 13B

ranking_group: single

throughput_3p7s: 1.75

us_pacific_date: 2025-01-09

win_ratio: 0.5228738563071846

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.001, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>', 'User:', '<|im_end|>', 'Bot:', 'You:', '####', 'Me:', '</s>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', '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-v22-v18-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v22-v18-mkmlizer to finish
cloudyu-nemo-dpo-v22-v18-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v22-v18-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v22-v18-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v22-v18-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v22-v18-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v22-v18-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v22-v18-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v18-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v22-v18-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v22-v18-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v22-v18-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v18-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v22-v18-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v22-v18-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v18-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v22-v18-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v22-v18-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
cloudyu-nemo-dpo-v22-v18-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v18-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v22-v18-mkmlizer: Downloaded to shared memory in 52.419s
cloudyu-nemo-dpo-v22-v18-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpdubr9koj, device:0
cloudyu-nemo-dpo-v22-v18-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
cloudyu-nemo-dpo-v22-v18-mkmlizer: quantized model in 37.186s
cloudyu-nemo-dpo-v22-v18-mkmlizer: Processed model cloudyu/Nemo-DPO-V22 in 89.604s
cloudyu-nemo-dpo-v22-v18-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v22-v18-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v22-v18-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v18
cloudyu-nemo-dpo-v22-v18-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v18/config.json
cloudyu-nemo-dpo-v22-v18-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v18/special_tokens_map.json
cloudyu-nemo-dpo-v22-v18-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v18/tokenizer_config.json
cloudyu-nemo-dpo-v22-v18-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v18/tokenizer.json
cloudyu-nemo-dpo-v22-v18-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v18/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v22-v18-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 27.29it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 47.07it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 44.17it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 38.31it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 43.67it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 43.76it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 43.46it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:07, 40.30it/s]
Loading 0:  14%|█▍        | 51/363 [00:01<00:07, 39.00it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:07, 40.20it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:10, 29.93it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:10, 28.56it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 33.87it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:08, 33.63it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:07, 37.21it/s]
Loading 0:  23%|██▎       | 84/363 [00:02<00:07, 35.93it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 39.28it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 38.99it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:06, 38.48it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 37.49it/s]
Loading 0:  29%|██▉       | 107/363 [00:02<00:06, 37.27it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:06, 38.05it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:06, 35.90it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:06, 35.24it/s]
Loading 0:  35%|███▍      | 126/363 [00:03<00:05, 39.87it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:05, 39.37it/s]
Loading 0:  37%|███▋      | 136/363 [00:03<00:06, 36.65it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 31.77it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 31.82it/s]
Loading 0:  41%|████▏     | 150/363 [00:04<00:06, 30.87it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:05, 36.72it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 36.55it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:04, 40.75it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 42.20it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 35.33it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 42.05it/s]
Loading 0:  52%|█████▏    | 188/363 [00:05<00:04, 41.46it/s]
Loading 0:  53%|█████▎    | 193/363 [00:05<00:03, 42.53it/s]
Loading 0:  55%|█████▍    | 198/363 [00:05<00:03, 43.54it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 35.91it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 43.67it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 42.92it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 44.28it/s]
Loading 0:  62%|██████▏   | 225/363 [00:06<00:05, 27.24it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 29.16it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 36.41it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 37.10it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 37.47it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 38.70it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:03, 31.50it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 38.58it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 39.07it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 39.52it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:02, 41.67it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 36.10it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 42.77it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 42.50it/s]
Loading 0:  83%|████████▎ | 302/363 [00:07<00:01, 46.39it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:22,  2.54it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:14,  3.44it/s]
Loading 0:  88%|████████▊ | 320/363 [00:15<00:07,  5.48it/s]
Loading 0:  90%|████████▉ | 325/363 [00:15<00:05,  7.10it/s]
Loading 0:  91%|█████████ | 330/363 [00:15<00:03,  8.77it/s]
Loading 0:  93%|█████████▎| 337/363 [00:15<00:02, 12.65it/s]
Loading 0:  94%|█████████▍| 342/363 [00:15<00:01, 15.41it/s]
Loading 0:  96%|█████████▌| 347/363 [00:15<00:00, 18.78it/s]
Loading 0:  97%|█████████▋| 352/363 [00:15<00:00, 22.72it/s]
Loading 0:  98%|█████████▊| 357/363 [00:16<00:00, 23.67it/s]
                                                            
Job cloudyu-nemo-dpo-v22-v18-mkmlizer completed after 114.88s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v22-v18-mkmlizer
Pipeline stage MKMLizer completed in 115.40s
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-v22-v18
Waiting for inference service cloudyu-nemo-dpo-v22-v18 to be ready
Inference service cloudyu-nemo-dpo-v22-v18 ready after 361.981107711792s
Pipeline stage MKMLDeployer completed in 362.52s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0534825325012207s
Received healthy response to inference request in 1.726121425628662s
Received healthy response to inference request in 1.3920111656188965s
Received healthy response to inference request in 1.805088758468628s
Received healthy response to inference request in 1.5954372882843018s
5 requests
0 failed requests
5th percentile: 1.4326963901519776
10th percentile: 1.4733816146850587
20th percentile: 1.5547520637512207
30th percentile: 1.6215741157531738
40th percentile: 1.673847770690918
50th percentile: 1.726121425628662
60th percentile: 1.7577083587646485
70th percentile: 1.7892952919006349
80th percentile: 1.8547675132751464
90th percentile: 1.9541250228881837
95th percentile: 2.003803777694702
99th percentile: 2.043546781539917
mean time: 1.7144282341003418
Pipeline stage StressChecker completed in 10.22s
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 0.67s
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 0.67s
Shutdown handler de-registered
cloudyu-nemo-dpo-v22_v18 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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cloudyu-nemo-dpo-v22-v18-profiler
Waiting for inference service cloudyu-nemo-dpo-v22-v18-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 2424.26s
Shutdown handler de-registered
cloudyu-nemo-dpo-v22_v18 status is now inactive due to auto deactivation removed underperforming models
cloudyu-nemo-dpo-v22_v18 status is now torndown due to DeploymentManager action