alexxi19-ft-v1-nemo-ba_27407

developer_uid: huohuo12

submission_id: alexxi19-ft-v1-nemo-ba_27407_v11

model_name: alexxi19-ft-v1-nemo-ba_27407_v11

model_group: alexxi19/ft-v1-nemo-base

status: torndown

timestamp: 2025-02-21T08:54:10+00:00

num_battles: 6589

num_wins: 3309

celo_rating: 1271.71

family_friendly_score: 0.5609999999999999

family_friendly_standard_error: 0.007018247644533499

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': 0.5964865403398462, 'latency_mean': 1.6764193785190582, 'latency_p50': 1.676662802696228, 'latency_p90': 1.8341708183288574}, {'batch_size': 3, 'throughput': 1.085569478993832, 'latency_mean': 2.7474312937259673, 'latency_p50': 2.729846715927124, 'latency_p90': 3.0495739936828614}, {'batch_size': 5, 'throughput': 1.2856534105534274, 'latency_mean': 3.8784399032592773, 'latency_p50': 3.909735083580017, 'latency_p90': 4.321381545066833}, {'batch_size': 6, 'throughput': 1.3795613576637735, 'latency_mean': 4.327265682220459, 'latency_p50': 4.298965811729431, 'latency_p90': 4.982121515274048}, {'batch_size': 8, 'throughput': 1.420395498882948, 'latency_mean': 5.591516646146775, 'latency_p50': 5.632903695106506, 'latency_p90': 6.344458603858947}, {'batch_size': 10, 'throughput': 1.4727583634756836, 'latency_mean': 6.729395190477371, 'latency_p50': 6.752763152122498, 'latency_p90': 7.575667476654052}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: alexxi19-ft-v1-nemo-ba_27407_v11

is_internal_developer: False

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

model_size: 13B

ranking_group: single

throughput_3p7s: 1.27

us_pacific_date: 2025-02-21

win_ratio: 0.5022006374260131

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|>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-v11-mkmlizer
Waiting for job on alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer to finish
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: ║     _____            __           __                                ║
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: ║       /___/                                                         ║
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: ║  Version: 0.12.8                                                    ║
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: ║  https://mk1.ai                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: ║  The license key for the current software has been verified as      ║
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: ║  belonging to:                                                      ║
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: ║  Chai Research Corp.                                                ║
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: Downloaded to shared memory in 136.986s
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpn6m9fy3c, device:0
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: quantized model in 37.551s
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: Processed model alexxi19/ft-v1-nemo-base-merge-v1 in 174.538s
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: creating bucket guanaco-mkml-models
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v11
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v11/config.json
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v11/special_tokens_map.json
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v11/tokenizer_config.json
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v11/tokenizer.json
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v11/flywheel_model.0.safetensors
alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:16,  3.04s/it]
Loading 0:   1%|          | 3/363 [00:06<10:58,  1.83s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:06,  1.45it/s]
Loading 0:   3%|▎         | 11/363 [00:06<01:40,  3.50it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:04,  5.43it/s]
Loading 0:   5%|▍         | 18/363 [00:06<00:48,  7.17it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:30, 11.03it/s]
Loading 0:   8%|▊         | 28/363 [00:06<00:21, 15.51it/s]
Loading 0:   9%|▉         | 32/363 [00:07<00:17, 18.90it/s]
Loading 0:  10%|▉         | 36/363 [00:07<00:16, 19.40it/s]
Loading 0:  11%|█▏        | 41/363 [00:07<00:13, 24.04it/s]
Loading 0:  12%|█▏        | 45/363 [00:07<00:11, 26.93it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:12, 25.32it/s]
Loading 0:  15%|█▌        | 55/363 [00:07<00:10, 29.82it/s]
Loading 0:  16%|█▋        | 59/363 [00:07<00:09, 31.56it/s]
Loading 0:  18%|█▊        | 64/363 [00:08<00:08, 35.31it/s]
Loading 0:  19%|█▊        | 68/363 [00:08<00:09, 30.47it/s]
Loading 0:  20%|█▉        | 72/363 [00:08<00:08, 32.46it/s]
Loading 0:  21%|██        | 77/363 [00:08<00:08, 35.51it/s]
Loading 0:  22%|██▏       | 81/363 [00:08<00:09, 30.75it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:08, 34.37it/s]
Loading 0:  25%|██▌       | 91/363 [00:08<00:07, 38.11it/s]
Loading 0:  26%|██▋       | 96/363 [00:09<00:09, 27.36it/s]
Loading 0:  28%|██▊       | 103/363 [00:09<00:07, 34.86it/s]
Loading 0:  30%|██▉       | 108/363 [00:09<00:07, 35.69it/s]
Loading 0:  31%|███       | 113/363 [00:09<00:08, 31.04it/s]
Loading 0:  33%|███▎      | 118/363 [00:09<00:07, 34.58it/s]
Loading 0:  34%|███▎      | 122/363 [00:09<00:06, 35.22it/s]
Loading 0:  35%|███▍      | 126/363 [00:09<00:06, 36.21it/s]
Loading 0:  36%|███▌      | 130/363 [00:10<00:07, 31.38it/s]
Loading 0:  37%|███▋      | 134/363 [00:10<00:07, 32.10it/s]
Loading 0:  38%|███▊      | 139/363 [00:10<00:06, 35.47it/s]
Loading 0:  39%|███▉      | 143/363 [00:10<00:06, 34.91it/s]
Loading 0:  40%|████      | 147/363 [00:10<00:06, 32.67it/s]
Loading 0:  42%|████▏     | 151/363 [00:10<00:06, 32.48it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:05, 40.20it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:05, 35.77it/s]
Loading 0:  46%|████▌     | 167/363 [00:11<00:05, 36.69it/s]
Loading 0:  48%|████▊     | 173/363 [00:11<00:05, 36.51it/s]
Loading 0:  49%|████▉     | 177/363 [00:11<00:06, 29.92it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:04, 39.30it/s]
Loading 0:  53%|█████▎    | 191/363 [00:11<00:04, 39.73it/s]
Loading 0:  54%|█████▍    | 196/363 [00:11<00:04, 34.25it/s]
Loading 0:  56%|█████▌    | 203/363 [00:11<00:03, 40.52it/s]
Loading 0:  57%|█████▋    | 208/363 [00:12<00:04, 36.14it/s]
Loading 0:  58%|█████▊    | 212/363 [00:12<00:04, 36.07it/s]
Loading 0:  60%|██████    | 218/363 [00:12<00:03, 37.44it/s]
Loading 0:  61%|██████    | 222/363 [00:12<00:04, 31.36it/s]
Loading 0:  63%|██████▎   | 229/363 [00:12<00:03, 39.18it/s]
Loading 0:  64%|██████▍   | 234/363 [00:12<00:03, 40.39it/s]
Loading 0:  66%|██████▌   | 239/363 [00:13<00:03, 34.22it/s]
Loading 0:  67%|██████▋   | 243/363 [00:13<00:03, 35.26it/s]
Loading 0:  68%|██████▊   | 248/363 [00:13<00:03, 37.10it/s]
Loading 0:  69%|██████▉   | 252/363 [00:13<00:02, 37.54it/s]
Loading 0:  71%|███████   | 256/363 [00:13<00:03, 32.21it/s]
Loading 0:  72%|███████▏  | 260/363 [00:13<00:03, 32.68it/s]
Loading 0:  73%|███████▎  | 265/363 [00:13<00:02, 36.69it/s]
Loading 0:  74%|███████▍  | 269/363 [00:13<00:02, 36.39it/s]
Loading 0:  75%|███████▌  | 273/363 [00:14<00:02, 32.39it/s]
Loading 0:  76%|███████▋  | 277/363 [00:14<00:02, 31.36it/s]
Loading 0:  78%|███████▊  | 284/363 [00:14<00:02, 38.68it/s]
Loading 0:  79%|███████▉  | 288/363 [00:14<00:02, 32.78it/s]
Loading 0:  81%|████████  | 293/363 [00:14<00:01, 36.00it/s]
Loading 0:  82%|████████▏ | 298/363 [00:14<00:01, 39.37it/s]
Loading 0:  83%|████████▎ | 303/363 [00:14<00:02, 29.40it/s]
Loading 0:  85%|████████▌ | 310/363 [00:15<00:01, 36.78it/s]
Loading 0:  87%|████████▋ | 315/363 [00:15<00:01, 37.34it/s]
Loading 0:  88%|████████▊ | 320/363 [00:15<00:01, 33.65it/s]
Loading 0:  89%|████████▉ | 324/363 [00:15<00:01, 34.63it/s]
Loading 0:  91%|█████████ | 329/363 [00:15<00:00, 37.54it/s]
Loading 0:  92%|█████████▏| 334/363 [00:15<00:00, 33.99it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:00, 34.50it/s]
Loading 0:  94%|█████████▍| 343/363 [00:15<00:00, 37.93it/s]
Loading 0:  96%|█████████▌| 347/363 [00:16<00:00, 37.92it/s]
Loading 0:  97%|█████████▋| 351/363 [00:16<00:00, 29.79it/s]
Loading 0:  98%|█████████▊| 356/363 [00:16<00:00, 32.93it/s]
Loading 0:  99%|█████████▉| 361/363 [00:16<00:00, 36.45it/s]
                                                            
Job alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer completed after 206.3s with status: succeeded
Stopping job with name alexxi19-ft-v1-nemo-ba-27407-v11-mkmlizer
Pipeline stage MKMLizer completed in 206.76s
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-v11
Waiting for inference service alexxi19-ft-v1-nemo-ba-27407-v11 to be ready
Retrying (%r) after connection broken by '%r': %s
Inference service alexxi19-ft-v1-nemo-ba-27407-v11 ready after 221.08222579956055s
Pipeline stage MKMLDeployer completed in 221.59s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3218400478363037s
Received healthy response to inference request in 1.6561806201934814s
Received healthy response to inference request in 1.5636241436004639s
Received healthy response to inference request in 1.5383186340332031s
Received healthy response to inference request in 1.4826486110687256s
5 requests
0 failed requests
5th percentile: 1.4937826156616212
10th percentile: 1.5049166202545166
20th percentile: 1.5271846294403075
30th percentile: 1.5433797359466552
40th percentile: 1.5535019397735597
50th percentile: 1.5636241436004639
60th percentile: 1.600646734237671
70th percentile: 1.637669324874878
80th percentile: 1.789312505722046
90th percentile: 2.055576276779175
95th percentile: 2.1887081623077393
99th percentile: 2.295213670730591
mean time: 1.7125224113464355
Pipeline stage StressChecker completed in 9.80s
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 0.62s
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 0.60s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-ba_27407_v11 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service alexxi19-ft-v1-nemo-ba-27407-v11-profiler
Waiting for inference service alexxi19-ft-v1-nemo-ba-27407-v11-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 2823.10s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-ba_27407_v11 status is now inactive due to auto deactivation removed underperforming models
alexxi19-ft-v1-nemo-ba_27407_v11 status is now torndown due to DeploymentManager action