alexxi19-ft-v1-nemo-ba_27407

developer_uid: huohuo12

submission_id: alexxi19-ft-v1-nemo-ba_27407_v12

model_name: alexxi19-ft-v1-nemo-ba_27407_v12

model_group: alexxi19/ft-v1-nemo-base

status: torndown

timestamp: 2025-02-21T08:56:34+00:00

num_battles: 6414

num_wins: 3160

celo_rating: 1263.4

family_friendly_score: 0.5484

family_friendly_standard_error: 0.007037861038696345

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': 0.6047425161099771, 'latency_mean': 1.6535260915756225, 'latency_p50': 1.6316468715667725, 'latency_p90': 1.8370075702667237}, {'batch_size': 3, 'throughput': 1.1150921618286518, 'latency_mean': 2.679013602733612, 'latency_p50': 2.675062656402588, 'latency_p90': 3.0273838520050047}, {'batch_size': 5, 'throughput': 1.3401568766467753, 'latency_mean': 3.717090411186218, 'latency_p50': 3.7180216312408447, 'latency_p90': 4.156327104568481}, {'batch_size': 6, 'throughput': 1.411994638101664, 'latency_mean': 4.233149530887604, 'latency_p50': 4.231144666671753, 'latency_p90': 4.717194747924805}, {'batch_size': 8, 'throughput': 1.485250716300011, 'latency_mean': 5.343760555982589, 'latency_p50': 5.3243690729141235, 'latency_p90': 5.984024882316589}, {'batch_size': 10, 'throughput': 1.5341035730735193, 'latency_mean': 6.4761735486984255, 'latency_p50': 6.489185690879822, 'latency_p90': 7.344013524055481}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: alexxi19-ft-v1-nemo-ba_27407_v12

is_internal_developer: False

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

model_size: 13B

ranking_group: single

throughput_3p7s: 1.34

us_pacific_date: 2025-02-21

win_ratio: 0.4926722793888369

generation_params: {'temperature': 0.82, 'top_p': 0.82, 'min_p': 0.13, 'top_k': 60, 'presence_penalty': 0.68, '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-v12-mkmlizer
Waiting for job on alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer to finish
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: ║     _____            __           __                                ║
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: ║       /___/                                                         ║
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: ║  Version: 0.12.8                                                    ║
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: ║  https://mk1.ai                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: ║  The license key for the current software has been verified as      ║
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: ║  belonging to:                                                      ║
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: ║  Chai Research Corp.                                                ║
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: Downloaded to shared memory in 123.280s
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2pqp4a2y, device:0
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: quantized model in 37.224s
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: Processed model alexxi19/ft-v1-nemo-base-merge-v1 in 160.504s
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: creating bucket guanaco-mkml-models
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v12
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v12/special_tokens_map.json
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v12/config.json
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v12/tokenizer_config.json
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v12/tokenizer.json
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v12/flywheel_model.0.safetensors
alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:20,  3.05s/it]
Loading 0:   1%|          | 3/363 [00:06<11:01,  1.84s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:09,  1.43it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:22,  4.26it/s]
Loading 0:   4%|▍         | 16/363 [00:06<01:01,  5.69it/s]
Loading 0:   5%|▌         | 19/363 [00:06<00:46,  7.48it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:32, 10.49it/s]
Loading 0:   7%|▋         | 27/363 [00:06<00:24, 13.99it/s]
Loading 0:   9%|▊         | 31/363 [00:07<00:18, 17.57it/s]
Loading 0:  10%|▉         | 35/363 [00:07<00:18, 17.61it/s]
Loading 0:  11%|█▏        | 41/363 [00:07<00:13, 23.98it/s]
Loading 0:  13%|█▎        | 47/363 [00:07<00:11, 28.05it/s]
Loading 0:  14%|█▍        | 51/363 [00:07<00:12, 25.31it/s]
Loading 0:  16%|█▋        | 59/363 [00:07<00:08, 34.34it/s]
Loading 0:  18%|█▊        | 64/363 [00:07<00:07, 37.56it/s]
Loading 0:  19%|█▉        | 69/363 [00:08<00:09, 29.86it/s]
Loading 0:  21%|██        | 76/363 [00:08<00:07, 37.54it/s]
Loading 0:  22%|██▏       | 81/363 [00:08<00:08, 33.71it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:07, 36.56it/s]
Loading 0:  25%|██▌       | 92/363 [00:08<00:07, 37.71it/s]
Loading 0:  27%|██▋       | 97/363 [00:08<00:08, 32.92it/s]
Loading 0:  28%|██▊       | 103/363 [00:09<00:06, 38.31it/s]
Loading 0:  30%|██▉       | 108/363 [00:09<00:06, 39.62it/s]
Loading 0:  31%|███       | 113/363 [00:09<00:07, 33.67it/s]
Loading 0:  33%|███▎      | 119/363 [00:09<00:06, 35.55it/s]
Loading 0:  34%|███▍      | 123/363 [00:09<00:07, 33.89it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:06, 35.49it/s]
Loading 0:  37%|███▋      | 134/363 [00:09<00:06, 35.90it/s]
Loading 0:  38%|███▊      | 139/363 [00:10<00:05, 38.45it/s]
Loading 0:  39%|███▉      | 143/363 [00:10<00:05, 37.98it/s]
Loading 0:  40%|████      | 147/363 [00:10<00:06, 33.49it/s]
Loading 0:  42%|████▏     | 151/363 [00:10<00:06, 31.79it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:05, 38.28it/s]
Loading 0:  45%|████▍     | 162/363 [00:10<00:06, 33.17it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:05, 36.18it/s]
Loading 0:  47%|████▋     | 172/363 [00:11<00:04, 39.33it/s]
Loading 0:  49%|████▉     | 177/363 [00:11<00:06, 30.03it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:04, 38.94it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:04, 40.54it/s]
Loading 0:  54%|█████▎    | 195/363 [00:11<00:05, 28.60it/s]
Loading 0:  56%|█████▌    | 202/363 [00:11<00:04, 35.60it/s]
Loading 0:  57%|█████▋    | 207/363 [00:12<00:05, 30.64it/s]
Loading 0:  58%|█████▊    | 211/363 [00:12<00:04, 32.11it/s]
Loading 0:  59%|█████▉    | 215/363 [00:12<00:04, 32.93it/s]
Loading 0:  61%|██████    | 221/363 [00:12<00:03, 37.82it/s]
Loading 0:  62%|██████▏   | 226/363 [00:12<00:04, 33.87it/s]
Loading 0:  63%|██████▎   | 230/363 [00:12<00:03, 34.23it/s]
Loading 0:  64%|██████▍   | 234/363 [00:12<00:03, 35.33it/s]
Loading 0:  66%|██████▌   | 239/363 [00:13<00:03, 31.01it/s]
Loading 0:  67%|██████▋   | 244/363 [00:13<00:03, 35.10it/s]
Loading 0:  68%|██████▊   | 248/363 [00:13<00:03, 35.64it/s]
Loading 0:  70%|██████▉   | 253/363 [00:13<00:02, 39.03it/s]
Loading 0:  71%|███████   | 258/363 [00:13<00:03, 30.00it/s]
Loading 0:  73%|███████▎  | 266/363 [00:13<00:02, 39.24it/s]
Loading 0:  75%|███████▍  | 271/363 [00:13<00:02, 36.33it/s]
Loading 0:  76%|███████▌  | 276/363 [00:14<00:02, 33.76it/s]
Loading 0:  78%|███████▊  | 284/363 [00:14<00:01, 42.10it/s]
Loading 0:  80%|███████▉  | 289/363 [00:14<00:02, 36.29it/s]
Loading 0:  81%|████████  | 294/363 [00:14<00:02, 34.00it/s]
Loading 0:  83%|████████▎ | 302/363 [00:14<00:01, 36.29it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:01, 38.14it/s]
Loading 0:  86%|████████▌ | 312/363 [00:15<00:01, 37.19it/s]
Loading 0:  88%|████████▊ | 319/363 [00:15<00:01, 38.80it/s]
Loading 0:  89%|████████▉ | 323/363 [00:15<00:01, 38.96it/s]
Loading 0:  91%|█████████ | 329/363 [00:15<00:00, 42.99it/s]
Loading 0:  92%|█████████▏| 334/363 [00:15<00:00, 36.45it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:00, 35.81it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:00, 37.76it/s]
Loading 0:  96%|█████████▌| 348/363 [00:16<00:00, 31.81it/s]
Loading 0:  98%|█████████▊| 355/363 [00:16<00:00, 39.87it/s]
Loading 0:  99%|█████████▉| 360/363 [00:16<00:00, 41.46it/s]
                                                            
Job alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer completed after 185.51s with status: succeeded
Stopping job with name alexxi19-ft-v1-nemo-ba-27407-v12-mkmlizer
Pipeline stage MKMLizer completed in 185.98s
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-v12
Waiting for inference service alexxi19-ft-v1-nemo-ba-27407-v12 to be ready
Inference service alexxi19-ft-v1-nemo-ba-27407-v12 ready after 200.69356179237366s
Pipeline stage MKMLDeployer completed in 201.21s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.578139543533325s
Received healthy response to inference request in 1.7205870151519775s
Received healthy response to inference request in 1.7912981510162354s
Received healthy response to inference request in 1.5575406551361084s
Received healthy response to inference request in 1.604452133178711s
5 requests
0 failed requests
5th percentile: 1.566922950744629
10th percentile: 1.5763052463531495
20th percentile: 1.5950698375701904
30th percentile: 1.6276791095733643
40th percentile: 1.674133062362671
50th percentile: 1.7205870151519775
60th percentile: 1.7488714694976806
70th percentile: 1.7771559238433838
80th percentile: 1.9486664295196534
90th percentile: 2.263402986526489
95th percentile: 2.420771265029907
99th percentile: 2.5466658878326416
mean time: 1.8504034996032714
Pipeline stage StressChecker completed in 10.80s
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 0.81s
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 0.69s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-ba_27407_v12 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 2816.98s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-ba_27407_v12 status is now inactive due to auto deactivation removed underperforming models
alexxi19-ft-v1-nemo-ba_27407_v12 status is now torndown due to DeploymentManager action