alexxi19-ft-v1-nemo-ba_27407

developer_uid: azuruce

submission_id: alexxi19-ft-v1-nemo-ba_27407_v17

model_name: alexxi19-ft-v1-nemo-ba_27407_v17

model_group: alexxi19/ft-v1-nemo-base

status: torndown

timestamp: 2025-02-25T08:56:27+00:00

num_battles: 5284

num_wins: 2693

celo_rating: 1270.0

family_friendly_score: 0.5698

family_friendly_standard_error: 0.007001827761377739

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

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6050529709428547, 'latency_mean': 1.6526860511302948, 'latency_p50': 1.6545085906982422, 'latency_p90': 1.8381168842315674}, {'batch_size': 3, 'throughput': 1.1073099320306314, 'latency_mean': 2.7036184954643248, 'latency_p50': 2.7062798738479614, 'latency_p90': 2.9509623289108275}, {'batch_size': 5, 'throughput': 1.3299898615124603, 'latency_mean': 3.7521672797203065, 'latency_p50': 3.7404617071151733, 'latency_p90': 4.175768136978149}, {'batch_size': 6, 'throughput': 1.3880985792960445, 'latency_mean': 4.303612307310105, 'latency_p50': 4.314552664756775, 'latency_p90': 4.848230361938477}, {'batch_size': 8, 'throughput': 1.4572667166300823, 'latency_mean': 5.450943276882172, 'latency_p50': 5.451282739639282, 'latency_p90': 6.128880286216735}, {'batch_size': 10, 'throughput': 1.4884209623645668, 'latency_mean': 6.662542783021927, 'latency_p50': 6.681743741035461, 'latency_p90': 7.527935481071472}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: alexxi19-ft-v1-nemo-ba_27407_v17

is_internal_developer: False

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

model_size: 13B

ranking_group: single

throughput_3p7s: 1.32

us_pacific_date: 2025-02-25

win_ratio: 0.5096517789553369

generation_params: {'temperature': 0.8, 'top_p': 0.9, 'min_p': 0.1, 'top_k': 55, 'presence_penalty': 0.7, 'frequency_penalty': 0.2, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|im_start|>', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\\N', 'user_template': 'user\n{user_name}: {message}\n', 'response_template': '<|im_end|>{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-v17-mkmlizer
Waiting for job on alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer to finish
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: ║     _____            __           __                                ║
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: ║       /___/                                                         ║
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: ║  Version: 0.12.8                                                    ║
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: ║  https://mk1.ai                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: ║  The license key for the current software has been verified as      ║
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: ║  belonging to:                                                      ║
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: ║  Chai Research Corp.                                                ║
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: Downloaded to shared memory in 111.942s
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmptf0uxmfn, device:0
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: quantized model in 38.484s
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: Processed model alexxi19/ft-v1-nemo-base-merge-v1 in 150.426s
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: creating bucket guanaco-mkml-models
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v17
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v17/config.json
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v17/special_tokens_map.json
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v17/tokenizer_config.json
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v17/tokenizer.json
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v17/flywheel_model.0.safetensors
alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:51,  3.14s/it]
Loading 0:   1%|          | 3/363 [00:06<11:16,  1.88s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:12,  1.41it/s]
Loading 0:   3%|▎         | 11/363 [00:06<01:43,  3.40it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:06,  5.25it/s]
Loading 0:   5%|▍         | 18/363 [00:06<00:49,  6.93it/s]
Loading 0:   6%|▌         | 22/363 [00:07<00:34,  9.83it/s]
Loading 0:   7%|▋         | 25/363 [00:07<00:28, 11.78it/s]
Loading 0:   9%|▊         | 31/363 [00:07<00:18, 17.94it/s]
Loading 0:  10%|▉         | 35/363 [00:07<00:18, 17.94it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:14, 22.60it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:13, 24.51it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:10, 28.85it/s]
Loading 0:  15%|█▍        | 53/363 [00:08<00:12, 24.72it/s]
Loading 0:  16%|█▌        | 58/363 [00:08<00:10, 29.34it/s]
Loading 0:  17%|█▋        | 62/363 [00:08<00:10, 29.81it/s]
Loading 0:  18%|█▊        | 67/363 [00:08<00:10, 27.92it/s]
Loading 0:  20%|█▉        | 71/363 [00:08<00:10, 29.09it/s]
Loading 0:  21%|██        | 77/363 [00:08<00:08, 34.98it/s]
Loading 0:  22%|██▏       | 81/363 [00:08<00:09, 31.07it/s]
Loading 0:  24%|██▎       | 86/363 [00:09<00:07, 34.92it/s]
Loading 0:  25%|██▌       | 92/363 [00:09<00:07, 37.03it/s]
Loading 0:  26%|██▋       | 96/363 [00:09<00:08, 30.79it/s]
Loading 0:  28%|██▊       | 103/363 [00:09<00:06, 38.25it/s]
Loading 0:  30%|██▉       | 108/363 [00:09<00:06, 39.75it/s]
Loading 0:  31%|███       | 113/363 [00:09<00:07, 35.08it/s]
Loading 0:  33%|███▎      | 119/363 [00:09<00:06, 36.65it/s]
Loading 0:  34%|███▍      | 123/363 [00:10<00:06, 34.96it/s]
Loading 0:  36%|███▌      | 130/363 [00:10<00:06, 36.24it/s]
Loading 0:  37%|███▋      | 134/363 [00:10<00:06, 34.71it/s]
Loading 0:  38%|███▊      | 138/363 [00:10<00:06, 35.49it/s]
Loading 0:  39%|███▉      | 142/363 [00:10<00:07, 30.59it/s]
Loading 0:  40%|████      | 146/363 [00:10<00:08, 26.54it/s]
Loading 0:  41%|████▏     | 150/363 [00:11<00:08, 26.62it/s]
Loading 0:  43%|████▎     | 157/363 [00:11<00:05, 34.91it/s]
Loading 0:  44%|████▍     | 161/363 [00:11<00:06, 28.93it/s]
Loading 0:  46%|████▌     | 167/363 [00:11<00:05, 33.99it/s]
Loading 0:  48%|████▊     | 173/363 [00:11<00:05, 36.16it/s]
Loading 0:  49%|████▉     | 177/363 [00:11<00:06, 30.96it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:04, 40.07it/s]
Loading 0:  53%|█████▎    | 191/363 [00:12<00:04, 40.64it/s]
Loading 0:  54%|█████▍    | 196/363 [00:12<00:04, 35.66it/s]
Loading 0:  56%|█████▌    | 203/363 [00:12<00:03, 41.76it/s]
Loading 0:  57%|█████▋    | 208/363 [00:12<00:04, 37.47it/s]
Loading 0:  59%|█████▊    | 213/363 [00:12<00:04, 34.43it/s]
Loading 0:  61%|██████    | 221/363 [00:12<00:03, 42.67it/s]
Loading 0:  62%|██████▏   | 226/363 [00:13<00:03, 35.52it/s]
Loading 0:  63%|██████▎   | 230/363 [00:13<00:03, 33.48it/s]
Loading 0:  64%|██████▍   | 234/363 [00:13<00:04, 31.91it/s]
Loading 0:  66%|██████▌   | 238/363 [00:13<00:03, 32.58it/s]
Loading 0:  67%|██████▋   | 242/363 [00:13<00:04, 27.47it/s]
Loading 0:  68%|██████▊   | 247/363 [00:13<00:03, 31.78it/s]
Loading 0:  69%|██████▉   | 251/363 [00:13<00:03, 32.28it/s]
Loading 0:  71%|███████   | 256/363 [00:14<00:03, 29.97it/s]
Loading 0:  72%|███████▏  | 260/363 [00:14<00:03, 31.15it/s]
Loading 0:  73%|███████▎  | 266/363 [00:14<00:02, 36.62it/s]
Loading 0:  74%|███████▍  | 270/363 [00:14<00:02, 31.41it/s]
Loading 0:  76%|███████▌  | 275/363 [00:14<00:02, 33.69it/s]
Loading 0:  77%|███████▋  | 279/363 [00:14<00:02, 34.64it/s]
Loading 0:  78%|███████▊  | 284/363 [00:14<00:02, 37.34it/s]
Loading 0:  79%|███████▉  | 288/363 [00:14<00:02, 31.41it/s]
Loading 0:  81%|████████  | 293/363 [00:15<00:02, 34.87it/s]
Loading 0:  82%|████████▏ | 299/363 [00:15<00:01, 36.95it/s]
Loading 0:  83%|████████▎ | 303/363 [00:15<00:01, 30.31it/s]
Loading 0:  86%|████████▌ | 311/363 [00:15<00:01, 39.39it/s]
Loading 0:  87%|████████▋ | 316/363 [00:15<00:01, 40.32it/s]
Loading 0:  88%|████████▊ | 321/363 [00:16<00:01, 25.92it/s]
Loading 0:  90%|█████████ | 328/363 [00:16<00:01, 32.38it/s]
Loading 0:  92%|█████████▏| 333/363 [00:16<00:01, 28.79it/s]
Loading 0:  93%|█████████▎| 337/363 [00:16<00:00, 30.36it/s]
Loading 0:  94%|█████████▍| 341/363 [00:16<00:00, 31.49it/s]
Loading 0:  96%|█████████▌| 347/363 [00:16<00:00, 36.83it/s]
Loading 0:  97%|█████████▋| 352/363 [00:16<00:00, 34.76it/s]
Loading 0:  98%|█████████▊| 357/363 [00:17<00:00, 33.17it/s]
                                                            
Job alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer completed after 185.39s with status: succeeded
Stopping job with name alexxi19-ft-v1-nemo-ba-27407-v17-mkmlizer
Pipeline stage MKMLizer completed in 185.83s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service alexxi19-ft-v1-nemo-ba-27407-v17
Waiting for inference service alexxi19-ft-v1-nemo-ba-27407-v17 to be ready
Inference service alexxi19-ft-v1-nemo-ba-27407-v17 ready after 401.38053917884827s
Pipeline stage MKMLDeployer completed in 401.89s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0729992389678955s
Received healthy response to inference request in 1.5796864032745361s
Received healthy response to inference request in 1.5374164581298828s
Received healthy response to inference request in 1.49379563331604s
Received healthy response to inference request in 1.97444486618042s
5 requests
0 failed requests
5th percentile: 1.5025197982788085
10th percentile: 1.511243963241577
20th percentile: 1.5286922931671143
30th percentile: 1.5458704471588134
40th percentile: 1.5627784252166748
50th percentile: 1.5796864032745361
60th percentile: 1.7375897884368896
70th percentile: 1.895493173599243
80th percentile: 1.9941557407379151
90th percentile: 2.033577489852905
95th percentile: 2.0532883644104003
99th percentile: 2.0690570640563966
mean time: 1.731668519973755
Pipeline stage StressChecker completed in 9.76s
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 0.61s
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 0.59s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-ba_27407_v17 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service alexxi19-ft-v1-nemo-ba-27407-v17-profiler
Waiting for inference service alexxi19-ft-v1-nemo-ba-27407-v17-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 2494.70s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-ba_27407_v17 status is now inactive due to auto deactivation removed underperforming models
alexxi19-ft-v1-nemo-ba_27407_v17 status is now torndown due to DeploymentManager action