alexxi19-ft-v1-nemo-ba_27407

developer_uid: azuruce

submission_id: alexxi19-ft-v1-nemo-ba_27407_v16

model_name: alexxi19-ft-v1-nemo-ba_27407_v16

model_group: alexxi19/ft-v1-nemo-base

status: torndown

timestamp: 2025-02-25T08:54:14+00:00

num_battles: 5223

num_wins: 2645

celo_rating: 1271.34

family_friendly_score: 0.5538000000000001

family_friendly_standard_error: 0.0070300150782199615

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': 0.600780605959965, 'latency_mean': 1.6644392395019532, 'latency_p50': 1.6675288677215576, 'latency_p90': 1.8289714574813842}, {'batch_size': 3, 'throughput': 1.0912294119053734, 'latency_mean': 2.7374734652042387, 'latency_p50': 2.7364487648010254, 'latency_p90': 2.9589938640594484}, {'batch_size': 5, 'throughput': 1.3185941166268489, 'latency_mean': 3.776225448846817, 'latency_p50': 3.791872978210449, 'latency_p90': 4.18813681602478}, {'batch_size': 6, 'throughput': 1.3964458816517822, 'latency_mean': 4.284839190244675, 'latency_p50': 4.284322142601013, 'latency_p90': 4.807310891151428}, {'batch_size': 8, 'throughput': 1.450884263441429, 'latency_mean': 5.489513186216354, 'latency_p50': 5.501376628875732, 'latency_p90': 6.1604265689849855}, {'batch_size': 10, 'throughput': 1.4825214884379958, 'latency_mean': 6.703663606643676, 'latency_p50': 6.71942400932312, 'latency_p90': 7.465859150886535}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: alexxi19-ft-v1-nemo-ba_27407_v16

is_internal_developer: False

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

model_size: 13B

ranking_group: single

throughput_3p7s: 1.31

us_pacific_date: 2025-02-25

win_ratio: 0.5064139383496075

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': '', 'prompt_template': '', '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-v16-mkmlizer
Waiting for job on alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer to finish
alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer: ║     _____            __           __                                ║
alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer: ║       /___/                                                         ║
alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer: ║  Version: 0.12.8                                                    ║
alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer: ║  https://mk1.ai                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer: ║  The license key for the current software has been verified as      ║
alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer: ║  belonging to:                                                      ║
alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer: ║  Chai Research Corp.                                                ║
alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer: Downloaded to shared memory in 139.410s
alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpk620ucw7, device:0
alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer: quantized model in 37.867s
alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer: Processed model alexxi19/ft-v1-nemo-base-merge-v1 in 177.277s
alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer: creating bucket guanaco-mkml-models
alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v16
alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v16/flywheel_model.0.safetensors
alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:28,  3.07s/it]
Loading 0:   1%|          | 3/363 [00:06<11:06,  1.85s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:11,  1.42it/s]
Loading 0:   3%|▎         | 11/363 [00:06<01:42,  3.42it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:05,  5.34it/s]
Loading 0:   5%|▌         | 19/363 [00:06<00:43,  7.82it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:31, 10.76it/s]
Loading 0:   7%|▋         | 27/363 [00:07<00:23, 14.11it/s]
Loading 0:   9%|▉         | 32/363 [00:07<00:17, 18.93it/s]
Loading 0:  10%|▉         | 36/363 [00:07<00:16, 19.99it/s]
Loading 0:  11%|█▏        | 41/363 [00:07<00:12, 25.16it/s]
Loading 0:  13%|█▎        | 47/363 [00:07<00:10, 29.69it/s]
Loading 0:  14%|█▍        | 51/363 [00:07<00:11, 27.07it/s]
Loading 0:  16%|█▋        | 59/363 [00:07<00:08, 37.01it/s]
Loading 0:  18%|█▊        | 65/363 [00:07<00:07, 38.76it/s]
Loading 0:  19%|█▉        | 70/363 [00:08<00:08, 32.97it/s]
Loading 0:  21%|██        | 76/363 [00:08<00:07, 36.96it/s]
Loading 0:  22%|██▏       | 81/363 [00:08<00:09, 30.65it/s]
Loading 0:  23%|██▎       | 85/363 [00:08<00:08, 31.58it/s]
Loading 0:  25%|██▍       | 89/363 [00:08<00:08, 30.54it/s]
Loading 0:  26%|██▌       | 93/363 [00:08<00:08, 31.45it/s]
Loading 0:  27%|██▋       | 97/363 [00:09<00:10, 25.79it/s]
Loading 0:  28%|██▊       | 103/363 [00:09<00:08, 31.37it/s]
Loading 0:  29%|██▉       | 107/363 [00:09<00:08, 31.88it/s]
Loading 0:  31%|███       | 112/363 [00:09<00:07, 35.21it/s]
Loading 0:  32%|███▏      | 116/363 [00:09<00:08, 29.44it/s]
Loading 0:  34%|███▎      | 122/363 [00:09<00:06, 35.41it/s]
Loading 0:  35%|███▌      | 128/363 [00:09<00:06, 38.26it/s]
Loading 0:  37%|███▋      | 133/363 [00:10<00:06, 34.73it/s]
Loading 0:  39%|███▊      | 140/363 [00:10<00:05, 41.61it/s]
Loading 0:  40%|███▉      | 145/363 [00:10<00:05, 38.52it/s]
Loading 0:  41%|████▏     | 150/363 [00:10<00:06, 34.52it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:04, 43.06it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:05, 38.59it/s]
Loading 0:  46%|████▋     | 168/363 [00:11<00:05, 35.07it/s]
Loading 0:  48%|████▊     | 175/363 [00:11<00:04, 41.25it/s]
Loading 0:  50%|████▉     | 180/363 [00:11<00:05, 32.03it/s]
Loading 0:  51%|█████     | 184/363 [00:11<00:05, 32.27it/s]
Loading 0:  52%|█████▏    | 188/363 [00:11<00:05, 32.52it/s]
Loading 0:  53%|█████▎    | 193/363 [00:11<00:05, 30.14it/s]
Loading 0:  54%|█████▍    | 197/363 [00:11<00:05, 31.31it/s]
Loading 0:  56%|█████▌    | 203/363 [00:12<00:04, 36.12it/s]
Loading 0:  57%|█████▋    | 207/363 [00:12<00:04, 31.48it/s]
Loading 0:  58%|█████▊    | 212/363 [00:12<00:04, 33.69it/s]
Loading 0:  60%|█████▉    | 216/363 [00:12<00:04, 34.69it/s]
Loading 0:  61%|██████    | 221/363 [00:12<00:03, 37.81it/s]
Loading 0:  62%|██████▏   | 225/363 [00:12<00:04, 31.71it/s]
Loading 0:  63%|██████▎   | 230/363 [00:12<00:03, 35.08it/s]
Loading 0:  65%|██████▌   | 236/363 [00:13<00:03, 36.96it/s]
Loading 0:  66%|██████▌   | 240/363 [00:13<00:04, 29.82it/s]
Loading 0:  68%|██████▊   | 248/363 [00:13<00:02, 38.91it/s]
Loading 0:  70%|██████▉   | 253/363 [00:13<00:02, 40.34it/s]
Loading 0:  71%|███████   | 258/363 [00:13<00:03, 28.15it/s]
Loading 0:  72%|███████▏  | 263/363 [00:13<00:03, 30.63it/s]
Loading 0:  74%|███████▎  | 267/363 [00:14<00:03, 29.96it/s]
Loading 0:  75%|███████▍  | 271/363 [00:14<00:02, 31.23it/s]
Loading 0:  76%|███████▌  | 275/363 [00:14<00:02, 31.37it/s]
Loading 0:  77%|███████▋  | 279/363 [00:14<00:02, 32.92it/s]
Loading 0:  78%|███████▊  | 284/363 [00:14<00:02, 35.72it/s]
Loading 0:  79%|███████▉  | 288/363 [00:14<00:02, 31.39it/s]
Loading 0:  80%|████████  | 292/363 [00:14<00:02, 33.26it/s]
Loading 0:  82%|████████▏ | 297/363 [00:14<00:01, 37.21it/s]
Loading 0:  83%|████████▎ | 302/363 [00:15<00:01, 34.32it/s]
Loading 0:  85%|████████▍ | 308/363 [00:15<00:01, 37.37it/s]
Loading 0:  86%|████████▌ | 312/363 [00:15<00:01, 36.61it/s]
Loading 0:  88%|████████▊ | 319/363 [00:15<00:01, 38.26it/s]
Loading 0:  89%|████████▉ | 323/363 [00:15<00:01, 38.48it/s]
Loading 0:  91%|█████████ | 329/363 [00:15<00:00, 43.09it/s]
Loading 0:  92%|█████████▏| 334/363 [00:15<00:00, 37.60it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:00, 36.14it/s]
Loading 0:  94%|█████████▍| 342/363 [00:16<00:00, 35.53it/s]
Loading 0:  95%|█████████▌| 346/363 [00:16<00:00, 34.27it/s]
Loading 0:  96%|█████████▋| 350/363 [00:16<00:00, 27.20it/s]
Loading 0:  98%|█████████▊| 355/363 [00:16<00:00, 31.42it/s]
Loading 0:  99%|█████████▉| 359/363 [00:16<00:00, 31.88it/s]
                                                            
Job alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer completed after 210.78s with status: succeeded
Stopping job with name alexxi19-ft-v1-nemo-ba-27407-v16-mkmlizer
Pipeline stage MKMLizer completed in 211.28s
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 alexxi19-ft-v1-nemo-ba-27407-v16
Waiting for inference service alexxi19-ft-v1-nemo-ba-27407-v16 to be ready
Inference service alexxi19-ft-v1-nemo-ba-27407-v16 ready after 511.58667516708374s
Pipeline stage MKMLDeployer completed in 512.12s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1899781227111816s
Received healthy response to inference request in 1.6116178035736084s
Received healthy response to inference request in 1.686215877532959s
Received healthy response to inference request in 1.760324478149414s
Received healthy response to inference request in 1.5846655368804932s
5 requests
0 failed requests
5th percentile: 1.5900559902191163
10th percentile: 1.5954464435577393
20th percentile: 1.6062273502349853
30th percentile: 1.6265374183654786
40th percentile: 1.6563766479492188
50th percentile: 1.686215877532959
60th percentile: 1.715859317779541
70th percentile: 1.745502758026123
80th percentile: 1.8462552070617677
90th percentile: 2.018116664886475
95th percentile: 2.104047393798828
99th percentile: 2.172791976928711
mean time: 1.7665603637695313
Pipeline stage StressChecker completed in 10.11s
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 0.63s
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_v16 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 2488.64s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-ba_27407_v16 status is now inactive due to auto deactivation removed underperforming models
alexxi19-ft-v1-nemo-ba_27407_v16 status is now torndown due to DeploymentManager action