alexxi19-ft-v1-nemo-bas_27407

developer_uid: leosheng

submission_id: alexxi19-ft-v1-nemo-bas_27407_v6

model_name: alexxi19-ft-v1-nemo-bas_27407_v6

model_group: alexxi19/ft-v1-nemo-base

status: torndown

timestamp: 2025-02-21T06:49:08+00:00

num_battles: 7983

num_wins: 3788

celo_rating: 1254.69

family_friendly_score: 0.5498000000000001

family_friendly_standard_error: 0.007035907333102107

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': 0.6030375696461505, 'latency_mean': 1.6581860375404358, 'latency_p50': 1.645536184310913, 'latency_p90': 1.8390715360641479}, {'batch_size': 3, 'throughput': 1.0834633743877293, 'latency_mean': 2.760867028236389, 'latency_p50': 2.747450590133667, 'latency_p90': 3.027084183692932}, {'batch_size': 5, 'throughput': 1.2836928047483178, 'latency_mean': 3.8817226350307465, 'latency_p50': 3.9245346784591675, 'latency_p90': 4.361363458633423}, {'batch_size': 6, 'throughput': 1.3424946478827509, 'latency_mean': 4.444542907476425, 'latency_p50': 4.465847373008728, 'latency_p90': 5.015130853652954}, {'batch_size': 8, 'throughput': 1.4174147982252245, 'latency_mean': 5.604112923145294, 'latency_p50': 5.647762656211853, 'latency_p90': 6.252218222618103}, {'batch_size': 10, 'throughput': 1.4469364114916952, 'latency_mean': 6.855032407045364, 'latency_p50': 6.913632869720459, 'latency_p90': 7.821299719810486}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: alexxi19-ft-v1-nemo-bas_27407_v6

is_internal_developer: False

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

model_size: 13B

ranking_group: single

throughput_3p7s: 1.26

us_pacific_date: 2025-02-20

win_ratio: 0.47450833020167854

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, '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-bas-27407-v6-mkmlizer
Waiting for job on alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer to finish
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: ║     _____            __           __                                ║
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: ║       /___/                                                         ║
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: ║  Version: 0.12.8                                                    ║
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: ║  https://mk1.ai                                                     ║
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: ║  belonging to:                                                      ║
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: ║  Chai Research Corp.                                                ║
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: Downloaded to shared memory in 147.632s
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpiv1l7t4_, device:0
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: quantized model in 37.250s
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: Processed model alexxi19/ft-v1-nemo-base-merge-v1 in 184.883s
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: creating bucket guanaco-mkml-models
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-bas-27407-v6
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-bas-27407-v6/config.json
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-bas-27407-v6/special_tokens_map.json
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-bas-27407-v6/tokenizer_config.json
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-bas-27407-v6/tokenizer.json
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-bas-27407-v6/flywheel_model.0.safetensors
alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:42,  3.11s/it]
Loading 0:   1%|          | 3/363 [00:06<11:12,  1.87s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:09,  1.43it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:21,  4.28it/s]
Loading 0:   5%|▍         | 18/363 [00:06<00:52,  6.55it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:35,  9.61it/s]
Loading 0:   8%|▊         | 29/363 [00:07<00:24, 13.76it/s]
Loading 0:   9%|▉         | 33/363 [00:07<00:22, 14.93it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:15, 21.34it/s]
Loading 0:  12%|█▏        | 45/363 [00:07<00:12, 24.97it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:12, 25.82it/s]
Loading 0:  15%|█▌        | 56/363 [00:07<00:10, 29.56it/s]
Loading 0:  17%|█▋        | 60/363 [00:07<00:10, 30.07it/s]
Loading 0:  18%|█▊        | 67/363 [00:08<00:08, 33.74it/s]
Loading 0:  20%|█▉        | 71/363 [00:08<00:08, 34.82it/s]
Loading 0:  21%|██        | 77/363 [00:08<00:07, 39.49it/s]
Loading 0:  23%|██▎       | 82/363 [00:08<00:07, 36.34it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:07, 36.74it/s]
Loading 0:  25%|██▍       | 90/363 [00:08<00:07, 37.31it/s]
Loading 0:  26%|██▌       | 95/363 [00:08<00:06, 39.32it/s]
Loading 0:  28%|██▊       | 100/363 [00:08<00:07, 36.08it/s]
Loading 0:  29%|██▉       | 105/363 [00:09<00:07, 34.05it/s]
Loading 0:  31%|███       | 112/363 [00:09<00:05, 42.29it/s]
Loading 0:  32%|███▏      | 117/363 [00:09<00:07, 34.93it/s]
Loading 0:  34%|███▎      | 122/363 [00:09<00:06, 37.87it/s]
Loading 0:  35%|███▍      | 127/363 [00:09<00:05, 40.70it/s]
Loading 0:  36%|███▋      | 132/363 [00:09<00:07, 30.27it/s]
Loading 0:  39%|███▊      | 140/363 [00:10<00:05, 38.67it/s]
Loading 0:  40%|███▉      | 145/363 [00:10<00:06, 35.72it/s]
Loading 0:  41%|████▏     | 150/363 [00:10<00:06, 32.16it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:05, 40.00it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:05, 36.17it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:05, 36.13it/s]
Loading 0:  47%|████▋     | 171/363 [00:10<00:05, 36.10it/s]
Loading 0:  48%|████▊     | 175/363 [00:11<00:05, 36.24it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:06, 27.93it/s]
Loading 0:  51%|█████     | 184/363 [00:11<00:05, 32.29it/s]
Loading 0:  52%|█████▏    | 188/363 [00:11<00:05, 33.95it/s]
Loading 0:  53%|█████▎    | 193/363 [00:11<00:05, 32.28it/s]
Loading 0:  54%|█████▍    | 197/363 [00:11<00:05, 32.65it/s]
Loading 0:  56%|█████▌    | 203/363 [00:11<00:04, 37.60it/s]
Loading 0:  57%|█████▋    | 207/363 [00:12<00:04, 33.04it/s]
Loading 0:  58%|█████▊    | 212/363 [00:12<00:04, 35.41it/s]
Loading 0:  60%|██████    | 218/363 [00:12<00:03, 37.48it/s]
Loading 0:  61%|██████    | 222/363 [00:12<00:04, 31.05it/s]
Loading 0:  63%|██████▎   | 229/363 [00:12<00:03, 39.30it/s]
Loading 0:  64%|██████▍   | 234/363 [00:12<00:03, 41.15it/s]
Loading 0:  66%|██████▌   | 239/363 [00:12<00:03, 36.38it/s]
Loading 0:  67%|██████▋   | 245/363 [00:12<00:03, 37.81it/s]
Loading 0:  69%|██████▉   | 250/363 [00:13<00:02, 38.15it/s]
Loading 0:  71%|███████   | 256/363 [00:13<00:02, 36.92it/s]
Loading 0:  72%|███████▏  | 260/363 [00:13<00:02, 35.54it/s]
Loading 0:  73%|███████▎  | 266/363 [00:13<00:02, 39.60it/s]
Loading 0:  75%|███████▍  | 271/363 [00:13<00:02, 35.43it/s]
Loading 0:  76%|███████▌  | 275/363 [00:13<00:02, 35.90it/s]
Loading 0:  77%|███████▋  | 281/363 [00:13<00:02, 37.98it/s]
Loading 0:  79%|███████▊  | 285/363 [00:14<00:02, 31.53it/s]
Loading 0:  81%|████████  | 293/363 [00:14<00:01, 40.25it/s]
Loading 0:  82%|████████▏ | 299/363 [00:14<00:01, 40.13it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:01, 35.22it/s]
Loading 0:  86%|████████▌ | 311/363 [00:14<00:01, 40.85it/s]
Loading 0:  87%|████████▋ | 317/363 [00:14<00:01, 40.93it/s]
Loading 0:  89%|████████▊ | 322/363 [00:15<00:01, 35.86it/s]
Loading 0:  90%|█████████ | 328/363 [00:15<00:00, 40.88it/s]
Loading 0:  92%|█████████▏| 333/363 [00:15<00:00, 34.55it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:00, 37.29it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:00, 36.97it/s]
Loading 0:  96%|█████████▌| 348/363 [00:15<00:00, 30.73it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 39.14it/s]
Loading 0: 100%|█████████▉| 362/363 [00:16<00:00, 40.25it/s]
                                                            
Job alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer completed after 216.02s with status: succeeded
Stopping job with name alexxi19-ft-v1-nemo-bas-27407-v6-mkmlizer
Pipeline stage MKMLizer completed in 216.49s
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-bas-27407-v6
Waiting for inference service alexxi19-ft-v1-nemo-bas-27407-v6 to be ready
Inference service alexxi19-ft-v1-nemo-bas-27407-v6 ready after 210.67538928985596s
Pipeline stage MKMLDeployer completed in 211.22s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4465749263763428s
Received healthy response to inference request in 1.609499216079712s
Received healthy response to inference request in 1.5919263362884521s
Received healthy response to inference request in 1.5872855186462402s
Received healthy response to inference request in 1.6078474521636963s
5 requests
0 failed requests
5th percentile: 1.5882136821746826
10th percentile: 1.589141845703125
20th percentile: 1.5909981727600098
30th percentile: 1.5951105594635009
40th percentile: 1.6014790058135986
50th percentile: 1.6078474521636963
60th percentile: 1.6085081577301026
70th percentile: 1.6091688632965089
80th percentile: 1.7769143581390383
90th percentile: 2.1117446422576904
95th percentile: 2.2791597843170166
99th percentile: 2.4130918979644775
mean time: 1.7686266899108887
Pipeline stage StressChecker completed in 10.08s
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 0.64s
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 0.65s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-bas_27407_v6 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service alexxi19-ft-v1-nemo-bas-27407-v6-profiler
Waiting for inference service alexxi19-ft-v1-nemo-bas-27407-v6-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4594.72s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-bas_27407_v6 status is now inactive due to auto deactivation removed underperforming models
alexxi19-ft-v1-nemo-bas_27407_v6 status is now torndown due to DeploymentManager action