alexxi19-ft-v1-nemo-ba_27407

developer_uid: huohuo12

submission_id: alexxi19-ft-v1-nemo-ba_27407_v10

model_name: alexxi19-ft-v1-nemo-ba_27407_v10

model_group: alexxi19/ft-v1-nemo-base

status: torndown

timestamp: 2025-02-21T08:53:22+00:00

num_battles: 6577

num_wins: 3230

celo_rating: 1263.19

family_friendly_score: 0.5584

family_friendly_standard_error: 0.007022669577874214

submission_type: basic

model_repo: alexxi19/ft-v1-nemo-base-merge-v1

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.5952814735336847, 'latency_mean': 1.679811304807663, 'latency_p50': 1.6734192371368408, 'latency_p90': 1.851542067527771}, {'batch_size': 3, 'throughput': 1.0769465315300806, 'latency_mean': 2.782802381515503, 'latency_p50': 2.7849230766296387, 'latency_p90': 3.119291806221008}, {'batch_size': 5, 'throughput': 1.3077051695065651, 'latency_mean': 3.805995557308197, 'latency_p50': 3.7712721824645996, 'latency_p90': 4.334582400321961}, {'batch_size': 6, 'throughput': 1.36044488552013, 'latency_mean': 4.394204277992248, 'latency_p50': 4.4052711725234985, 'latency_p90': 4.884441828727722}, {'batch_size': 8, 'throughput': 1.4324709698173552, 'latency_mean': 5.540498644113541, 'latency_p50': 5.556481838226318, 'latency_p90': 6.321233701705933}, {'batch_size': 10, 'throughput': 1.4625360041880033, 'latency_mean': 6.788840838670731, 'latency_p50': 6.792415142059326, 'latency_p90': 7.580352997779846}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: alexxi19-ft-v1-nemo-ba_27407_v10

is_internal_developer: False

language_model: alexxi19/ft-v1-nemo-base-merge-v1

model_size: 13B

ranking_group: single

throughput_3p7s: 1.3

us_pacific_date: 2025-02-21

win_ratio: 0.49110536718868786

generation_params: {'temperature': 0.85, 'top_p': 0.75, 'min_p': 0.15, 'top_k': 70, 'presence_penalty': 0.75, 'frequency_penalty': 0.05, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{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 alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer
Waiting for job on alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer to finish
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: ║     _____            __           __                                ║
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: ║       /___/                                                         ║
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: ║  Version: 0.12.8                                                    ║
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: ║  https://mk1.ai                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: ║  The license key for the current software has been verified as      ║
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: ║  belonging to:                                                      ║
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: ║  Chai Research Corp.                                                ║
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: Downloaded to shared memory in 116.474s
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_3mdx5p_, device:0
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: quantized model in 41.091s
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: Processed model alexxi19/ft-v1-nemo-base-merge-v1 in 157.565s
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: creating bucket guanaco-mkml-models
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v10
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v10/config.json
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v10/special_tokens_map.json
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v10/tokenizer_config.json
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v10/tokenizer.json
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v10/flywheel_model.0.safetensors
alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<19:04,  3.17s/it]
Loading 0:   1%|          | 3/363 [00:06<11:25,  1.91s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:16,  1.39it/s]
Loading 0:   3%|▎         | 11/363 [00:06<01:45,  3.34it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:07,  5.14it/s]
Loading 0:   5%|▍         | 18/363 [00:07<00:50,  6.77it/s]
Loading 0:   6%|▌         | 21/363 [00:07<00:38,  8.83it/s]
Loading 0:   7%|▋         | 24/363 [00:07<00:32, 10.50it/s]
Loading 0:   8%|▊         | 29/363 [00:07<00:21, 15.54it/s]
Loading 0:   9%|▉         | 33/363 [00:07<00:21, 15.49it/s]
Loading 0:  10%|█         | 38/363 [00:07<00:15, 20.73it/s]
Loading 0:  12%|█▏        | 42/363 [00:07<00:14, 22.05it/s]
Loading 0:  13%|█▎        | 47/363 [00:08<00:11, 27.06it/s]
Loading 0:  14%|█▍        | 51/363 [00:08<00:14, 22.17it/s]
Loading 0:  15%|█▌        | 56/363 [00:08<00:11, 27.23it/s]
Loading 0:  17%|█▋        | 60/363 [00:08<00:11, 26.49it/s]
Loading 0:  18%|█▊        | 65/363 [00:08<00:09, 30.92it/s]
Loading 0:  19%|█▉        | 69/363 [00:08<00:11, 24.70it/s]
Loading 0:  21%|██        | 76/363 [00:09<00:08, 31.96it/s]
Loading 0:  22%|██▏       | 80/363 [00:09<00:08, 31.64it/s]
Loading 0:  23%|██▎       | 84/363 [00:09<00:09, 28.11it/s]
Loading 0:  24%|██▍       | 88/363 [00:09<00:09, 27.78it/s]
Loading 0:  25%|██▌       | 92/363 [00:09<00:09, 29.62it/s]
Loading 0:  26%|██▋       | 96/363 [00:09<00:11, 23.96it/s]
Loading 0:  28%|██▊       | 101/363 [00:09<00:09, 29.08it/s]
Loading 0:  29%|██▉       | 105/363 [00:10<00:09, 28.32it/s]
Loading 0:  31%|███       | 112/363 [00:10<00:07, 35.73it/s]
Loading 0:  32%|███▏      | 116/363 [00:10<00:08, 28.62it/s]
Loading 0:  33%|███▎      | 121/363 [00:10<00:07, 31.67it/s]
Loading 0:  34%|███▍      | 125/363 [00:10<00:07, 31.65it/s]
Loading 0:  36%|███▌      | 130/363 [00:10<00:08, 28.35it/s]
Loading 0:  37%|███▋      | 134/363 [00:11<00:08, 28.62it/s]
Loading 0:  38%|███▊      | 138/363 [00:11<00:07, 30.95it/s]
Loading 0:  39%|███▉      | 142/363 [00:11<00:07, 29.01it/s]
Loading 0:  40%|████      | 146/363 [00:11<00:08, 25.64it/s]
Loading 0:  41%|████▏     | 150/363 [00:11<00:08, 25.69it/s]
Loading 0:  43%|████▎     | 157/363 [00:11<00:06, 33.43it/s]
Loading 0:  44%|████▍     | 161/363 [00:12<00:07, 27.00it/s]
Loading 0:  46%|████▌     | 166/363 [00:12<00:06, 30.13it/s]
Loading 0:  47%|████▋     | 170/363 [00:12<00:06, 30.26it/s]
Loading 0:  48%|████▊     | 175/363 [00:12<00:05, 33.05it/s]
Loading 0:  49%|████▉     | 179/363 [00:12<00:06, 26.51it/s]
Loading 0:  51%|█████     | 184/363 [00:12<00:06, 29.76it/s]
Loading 0:  52%|█████▏    | 188/363 [00:12<00:05, 29.62it/s]
Loading 0:  53%|█████▎    | 193/363 [00:13<00:06, 26.68it/s]
Loading 0:  54%|█████▍    | 196/363 [00:13<00:06, 26.01it/s]
Loading 0:  56%|█████▌    | 202/363 [00:13<00:05, 31.80it/s]
Loading 0:  57%|█████▋    | 206/363 [00:13<00:04, 31.69it/s]
Loading 0:  58%|█████▊    | 210/363 [00:13<00:05, 27.86it/s]
Loading 0:  59%|█████▊    | 213/363 [00:13<00:05, 25.34it/s]
Loading 0:  60%|██████    | 218/363 [00:13<00:04, 30.65it/s]
Loading 0:  61%|██████    | 222/363 [00:14<00:05, 24.19it/s]
Loading 0:  63%|██████▎   | 227/363 [00:14<00:04, 28.86it/s]
Loading 0:  64%|██████▎   | 231/363 [00:14<00:04, 28.12it/s]
Loading 0:  65%|██████▌   | 236/363 [00:14<00:03, 32.64it/s]
Loading 0:  66%|██████▌   | 240/363 [00:14<00:04, 25.29it/s]
Loading 0:  68%|██████▊   | 247/363 [00:14<00:03, 32.73it/s]
Loading 0:  69%|██████▉   | 251/363 [00:15<00:03, 31.83it/s]
Loading 0:  70%|███████   | 255/363 [00:15<00:03, 33.62it/s]
Loading 0:  71%|███████▏  | 259/363 [00:15<00:04, 24.55it/s]
Loading 0:  72%|███████▏  | 263/363 [00:15<00:03, 27.35it/s]
Loading 0:  74%|███████▎  | 267/363 [00:15<00:03, 27.36it/s]
Loading 0:  75%|███████▍  | 271/363 [00:15<00:03, 29.17it/s]
Loading 0:  76%|███████▌  | 275/363 [00:15<00:02, 29.38it/s]
Loading 0:  77%|███████▋  | 279/363 [00:16<00:02, 30.82it/s]
Loading 0:  78%|███████▊  | 283/363 [00:16<00:02, 32.43it/s]
Loading 0:  79%|███████▉  | 287/363 [00:16<00:02, 25.74it/s]
Loading 0:  80%|████████  | 292/363 [00:16<00:02, 29.69it/s]
Loading 0:  82%|████████▏ | 296/363 [00:16<00:02, 30.14it/s]
Loading 0:  83%|████████▎ | 301/363 [00:16<00:01, 33.50it/s]
Loading 0:  84%|████████▍ | 305/363 [00:17<00:02, 26.97it/s]
Loading 0:  85%|████████▌ | 310/363 [00:17<00:01, 30.40it/s]
Loading 0:  87%|████████▋ | 314/363 [00:17<00:01, 30.28it/s]
Loading 0:  88%|████████▊ | 319/363 [00:17<00:01, 27.48it/s]
Loading 0:  89%|████████▊ | 322/363 [00:17<00:01, 26.56it/s]
Loading 0:  90%|████████▉ | 326/363 [00:17<00:01, 29.29it/s]
Loading 0:  91%|█████████ | 330/363 [00:17<00:01, 27.51it/s]
Loading 0:  92%|█████████▏| 333/363 [00:17<00:01, 27.00it/s]
Loading 0:  93%|█████████▎| 337/363 [00:18<00:00, 28.36it/s]
Loading 0:  94%|█████████▎| 340/363 [00:18<00:00, 26.55it/s]
Loading 0:  95%|█████████▍| 344/363 [00:18<00:00, 29.49it/s]
Loading 0:  96%|█████████▌| 348/363 [00:18<00:00, 22.31it/s]
Loading 0:  97%|█████████▋| 353/363 [00:18<00:00, 27.66it/s]
Loading 0:  98%|█████████▊| 357/363 [00:18<00:00, 26.96it/s]
Loading 0: 100%|█████████▉| 362/363 [00:18<00:00, 31.71it/s]
                                                            
Job alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer completed after 185.37s with status: succeeded
Stopping job with name alexxi19-ft-v1-nemo-ba-27407-v10-mkmlizer
Pipeline stage MKMLizer completed in 185.81s
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 alexxi19-ft-v1-nemo-ba-27407-v10
Waiting for inference service alexxi19-ft-v1-nemo-ba-27407-v10 to be ready
Inference service alexxi19-ft-v1-nemo-ba-27407-v10 ready after 220.9368863105774s
Pipeline stage MKMLDeployer completed in 221.43s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6917402744293213s
Received healthy response to inference request in 1.533756971359253s
Received healthy response to inference request in 1.5689916610717773s
Received healthy response to inference request in 1.666320562362671s
Received healthy response to inference request in 1.5323247909545898s
5 requests
0 failed requests
5th percentile: 1.5326112270355225
10th percentile: 1.532897663116455
20th percentile: 1.5334705352783202
30th percentile: 1.5408039093017578
40th percentile: 1.5548977851867676
50th percentile: 1.5689916610717773
60th percentile: 1.6079232215881347
70th percentile: 1.646854782104492
80th percentile: 1.871404504776001
90th percentile: 2.2815723896026614
95th percentile: 2.486656332015991
99th percentile: 2.650723485946655
mean time: 1.7986268520355224
Pipeline stage StressChecker completed in 10.30s
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 0.64s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-ba_27407_v10 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 2834.89s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-ba_27407_v10 status is now inactive due to auto deactivation removed underperforming models
alexxi19-ft-v1-nemo-ba_27407_v10 status is now torndown due to DeploymentManager action