developer_uid: azuruce
submission_id: yamatazen-ayla-light-extra_v2
model_name: yamatazen-ayla-light-extra_v2
model_group: yamatazen/Ayla-Light-Ext
status: torndown
timestamp: 2025-02-27T01:04:46+00:00
num_battles: 5950
num_wins: 2945
celo_rating: 1254.29
family_friendly_score: 0.5626
family_friendly_standard_error: 0.0070154292812343285
submission_type: basic
model_repo: yamatazen/Ayla-Light-Extra
model_architecture: MistralForCausalLM
model_num_parameters: 15058048000.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.5077411607952144, 'latency_mean': 1.9694080984592437, 'latency_p50': 1.9756557941436768, 'latency_p90': 2.1681202173233034}, {'batch_size': 3, 'throughput': 0.9336036811190332, 'latency_mean': 3.1997646403312685, 'latency_p50': 3.2010138034820557, 'latency_p90': 3.5315136432647702}, {'batch_size': 5, 'throughput': 1.1310983511393982, 'latency_mean': 4.389419727325439, 'latency_p50': 4.409202575683594, 'latency_p90': 4.949831342697143}, {'batch_size': 6, 'throughput': 1.185745774719973, 'latency_mean': 5.021166589260101, 'latency_p50': 5.046069025993347, 'latency_p90': 5.68178973197937}, {'batch_size': 10, 'throughput': 1.2643042118670766, 'latency_mean': 7.8423918282985685, 'latency_p50': 7.924710035324097, 'latency_p90': 8.771259331703186}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: yamatazen-ayla-light-extra_v2
is_internal_developer: False
language_model: yamatazen/Ayla-Light-Extra
model_size: 15B
ranking_group: single
throughput_3p7s: 1.04
us_pacific_date: 2025-02-26
win_ratio: 0.49495798319327733
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|im_end|>', 'You:', '###', 'Bot:', '</s>', '<|eot_id|>', 'Me:', '####', '<|end_of_text|>', 'User:'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{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 yamatazen-ayla-light-extra-v2-mkmlizer
Waiting for job on yamatazen-ayla-light-extra-v2-mkmlizer to finish
yamatazen-ayla-light-extra-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
yamatazen-ayla-light-extra-v2-mkmlizer: ║     _____            __           __                                ║
yamatazen-ayla-light-extra-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
yamatazen-ayla-light-extra-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
yamatazen-ayla-light-extra-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
yamatazen-ayla-light-extra-v2-mkmlizer: ║       /___/                                                         ║
yamatazen-ayla-light-extra-v2-mkmlizer: ║                                                                     ║
yamatazen-ayla-light-extra-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
yamatazen-ayla-light-extra-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
yamatazen-ayla-light-extra-v2-mkmlizer: ║  https://mk1.ai                                                     ║
yamatazen-ayla-light-extra-v2-mkmlizer: ║                                                                     ║
yamatazen-ayla-light-extra-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
yamatazen-ayla-light-extra-v2-mkmlizer: ║  belonging to:                                                      ║
yamatazen-ayla-light-extra-v2-mkmlizer: ║                                                                     ║
yamatazen-ayla-light-extra-v2-mkmlizer: ║  Chai Research Corp.                                                ║
yamatazen-ayla-light-extra-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
yamatazen-ayla-light-extra-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
yamatazen-ayla-light-extra-v2-mkmlizer: ║                                                                     ║
yamatazen-ayla-light-extra-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
yamatazen-ayla-light-extra-v2-mkmlizer: Downloaded to shared memory in 43.097s
yamatazen-ayla-light-extra-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmptmaxkfsu, device:0
yamatazen-ayla-light-extra-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
yamatazen-ayla-light-extra-v2-mkmlizer: quantized model in 44.025s
yamatazen-ayla-light-extra-v2-mkmlizer: Processed model yamatazen/Ayla-Light-Extra in 87.123s
yamatazen-ayla-light-extra-v2-mkmlizer: creating bucket guanaco-mkml-models
yamatazen-ayla-light-extra-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
yamatazen-ayla-light-extra-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/yamatazen-ayla-light-extra-v2
yamatazen-ayla-light-extra-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/yamatazen-ayla-light-extra-v2/tokenizer_config.json
yamatazen-ayla-light-extra-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/yamatazen-ayla-light-extra-v2/tokenizer.json
yamatazen-ayla-light-extra-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/yamatazen-ayla-light-extra-v2/flywheel_model.1.safetensors
yamatazen-ayla-light-extra-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/yamatazen-ayla-light-extra-v2/flywheel_model.0.safetensors
yamatazen-ayla-light-extra-v2-mkmlizer: 
Loading 0:   0%|          | 0/435 [00:00<?, ?it/s]
Loading 0:   0%|          | 2/435 [00:06<22:40,  3.14s/it]
Loading 0:   1%|▏         | 6/435 [00:06<06:05,  1.17it/s]
Loading 0:   3%|▎         | 11/435 [00:06<02:40,  2.63it/s]
Loading 0:   3%|▎         | 15/435 [00:06<01:42,  4.10it/s]
Loading 0:   5%|▌         | 22/435 [00:06<00:54,  7.64it/s]
Loading 0:   6%|▌         | 26/435 [00:06<00:41,  9.78it/s]
Loading 0:   7%|▋         | 30/435 [00:07<00:32, 12.54it/s]
Loading 0:   8%|▊         | 34/435 [00:07<00:27, 14.82it/s]
Loading 0:   9%|▉         | 40/435 [00:07<00:25, 15.58it/s]
Loading 0:  10%|▉         | 43/435 [00:07<00:23, 16.66it/s]
Loading 0:  11%|█▏        | 49/435 [00:07<00:17, 22.29it/s]
Loading 0:  12%|█▏        | 53/435 [00:07<00:15, 24.20it/s]
Loading 0:  13%|█▎        | 58/435 [00:08<00:13, 28.11it/s]
Loading 0:  14%|█▍        | 62/435 [00:08<00:13, 28.55it/s]
Loading 0:  15%|█▌        | 66/435 [00:08<00:11, 30.98it/s]
Loading 0:  16%|█▌        | 70/435 [00:08<00:12, 29.55it/s]
Loading 0:  17%|█▋        | 74/435 [00:08<00:11, 31.95it/s]
Loading 0:  18%|█▊        | 78/435 [00:08<00:11, 30.17it/s]
Loading 0:  19%|█▉        | 83/435 [00:08<00:10, 34.35it/s]
Loading 0:  20%|██        | 87/435 [00:09<00:11, 30.27it/s]
Loading 0:  21%|██        | 92/435 [00:09<00:10, 34.12it/s]
Loading 0:  23%|██▎       | 99/435 [00:09<00:09, 34.23it/s]
Loading 0:  24%|██▍       | 106/435 [00:09<00:08, 39.77it/s]
Loading 0:  26%|██▌       | 111/435 [00:09<00:08, 38.61it/s]
Loading 0:  26%|██▋       | 115/435 [00:09<00:08, 37.37it/s]
Loading 0:  27%|██▋       | 119/435 [00:10<00:13, 23.26it/s]
Loading 0:  28%|██▊       | 123/435 [00:10<00:11, 26.08it/s]
Loading 0:  29%|██▉       | 127/435 [00:10<00:12, 24.83it/s]
Loading 0:  30%|███       | 131/435 [00:10<00:11, 27.11it/s]
Loading 0:  31%|███       | 135/435 [00:10<00:11, 26.83it/s]
Loading 0:  33%|███▎      | 142/435 [00:10<00:08, 33.83it/s]
Loading 0:  34%|███▎      | 146/435 [00:10<00:08, 33.13it/s]
Loading 0:  35%|███▍      | 151/435 [00:10<00:07, 36.16it/s]
Loading 0:  36%|███▌      | 155/435 [00:11<00:07, 35.46it/s]
Loading 0:  37%|███▋      | 160/435 [00:11<00:07, 38.41it/s]
Loading 0:  38%|███▊      | 164/435 [00:11<00:07, 37.14it/s]
Loading 0:  39%|███▉      | 169/435 [00:11<00:06, 38.71it/s]
Loading 0:  40%|███▉      | 173/435 [00:11<00:06, 37.54it/s]
Loading 0:  41%|████      | 178/435 [00:11<00:06, 39.02it/s]
Loading 0:  42%|████▏     | 182/435 [00:11<00:06, 37.19it/s]
Loading 0:  43%|████▎     | 187/435 [00:11<00:06, 38.69it/s]
Loading 0:  44%|████▍     | 191/435 [00:12<00:06, 36.50it/s]
Loading 0:  45%|████▌     | 196/435 [00:12<00:06, 38.15it/s]
Loading 0:  46%|████▌     | 200/435 [00:12<00:09, 24.08it/s]
Loading 0:  47%|████▋     | 205/435 [00:12<00:08, 28.17it/s]
Loading 0:  48%|████▊     | 209/435 [00:12<00:07, 29.53it/s]
Loading 0:  49%|████▉     | 214/435 [00:12<00:06, 32.90it/s]
Loading 0:  50%|█████     | 218/435 [00:12<00:06, 32.80it/s]
Loading 0:  51%|█████▏    | 223/435 [00:13<00:06, 35.12it/s]
Loading 0:  52%|█████▏    | 227/435 [00:13<00:06, 34.35it/s]
Loading 0:  53%|█████▎    | 232/435 [00:13<00:05, 37.08it/s]
Loading 0:  54%|█████▍    | 236/435 [00:13<00:05, 36.12it/s]
Loading 0:  55%|█████▌    | 241/435 [00:13<00:04, 39.01it/s]
Loading 0:  56%|█████▋    | 245/435 [00:13<00:05, 37.95it/s]
Loading 0:  57%|█████▋    | 250/435 [00:13<00:04, 38.25it/s]
Loading 0:  58%|█████▊    | 254/435 [00:13<00:04, 37.06it/s]
Loading 0:  60%|█████▉    | 259/435 [00:14<00:04, 39.21it/s]
Loading 0:  60%|██████    | 263/435 [00:14<00:04, 38.02it/s]
Loading 0:  62%|██████▏   | 268/435 [00:14<00:04, 35.12it/s]
Loading 0:  63%|██████▎   | 275/435 [00:14<00:03, 41.47it/s]
Loading 0:  64%|██████▍   | 280/435 [00:14<00:03, 40.84it/s]
Loading 0:  66%|██████▌   | 285/435 [00:14<00:06, 24.40it/s]
Loading 0:  67%|██████▋   | 292/435 [00:15<00:04, 31.03it/s]
Loading 0:  68%|██████▊   | 297/435 [00:15<00:04, 33.27it/s]
Loading 0:  69%|██████▉   | 302/435 [00:15<00:03, 35.36it/s]
Loading 0:  71%|███████   | 307/435 [00:15<00:03, 37.65it/s]
Loading 0:  72%|███████▏  | 312/435 [00:15<00:03, 31.40it/s]
Loading 0:  73%|███████▎  | 319/435 [00:15<00:03, 38.54it/s]
Loading 0:  74%|███████▍  | 324/435 [00:15<00:02, 39.56it/s]
Loading 0:  76%|███████▌  | 329/435 [00:16<00:02, 39.02it/s]
Loading 0:  77%|███████▋  | 334/435 [00:16<00:02, 40.75it/s]
Loading 0:  78%|███████▊  | 339/435 [00:16<00:02, 34.24it/s]
Loading 0:  80%|███████▉  | 346/435 [00:16<00:02, 40.52it/s]
Loading 0:  81%|████████  | 351/435 [00:16<00:02, 39.76it/s]
Loading 0:  82%|████████▏ | 356/435 [00:16<00:01, 40.29it/s]
Loading 0:  83%|████████▎ | 361/435 [00:16<00:01, 41.70it/s]
Loading 0:  84%|████████▍ | 366/435 [00:17<00:02, 25.03it/s]
Loading 0:  86%|████████▌ | 373/435 [00:17<00:01, 32.13it/s]
Loading 0:  87%|████████▋ | 378/435 [00:17<00:01, 33.36it/s]
Loading 0:  88%|████████▊ | 381/435 [00:31<00:01, 33.36it/s]
Loading 0:  88%|████████▊ | 382/435 [00:31<00:46,  1.13it/s]
Loading 0:  88%|████████▊ | 384/435 [00:32<00:39,  1.30it/s]
Loading 0:  89%|████████▉ | 389/435 [00:32<00:23,  1.94it/s]
Loading 0:  90%|█████████ | 393/435 [00:32<00:16,  2.56it/s]
Loading 0:  91%|█████████▏| 398/435 [00:32<00:09,  3.75it/s]
Loading 0:  92%|█████████▏| 402/435 [00:32<00:06,  4.89it/s]
Loading 0:  94%|█████████▍| 409/435 [00:32<00:03,  7.82it/s]
Loading 0:  95%|█████████▍| 413/435 [00:33<00:02,  9.63it/s]
Loading 0:  96%|█████████▌| 418/435 [00:33<00:01, 12.68it/s]
Loading 0:  97%|█████████▋| 422/435 [00:33<00:00, 15.17it/s]
Loading 0:  98%|█████████▊| 427/435 [00:33<00:00, 19.24it/s]
Loading 0:  99%|█████████▉| 431/435 [00:33<00:00, 21.49it/s]
                                                            

Job yamatazen-ayla-light-extra-v2-mkmlizer completed after 124.6s with status: succeeded
Stopping job with name yamatazen-ayla-light-extra-v2-mkmlizer
Pipeline stage MKMLizer completed in 125.09s
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 yamatazen-ayla-light-extra-v2
Waiting for inference service yamatazen-ayla-light-extra-v2 to be ready
Failed to get response for submission nischaydnk-mistral24bas_99124_v4: HTTPConnectionPool(host='nischaydnk-mistral24bas-99124-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service yamatazen-ayla-light-extra-v2 ready after 270.9099190235138s
Pipeline stage MKMLDeployer completed in 271.45s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.164268970489502s
Received healthy response to inference request in 1.1623828411102295s
Received healthy response to inference request in 1.721367359161377s
Received healthy response to inference request in 1.6991608142852783s
Received healthy response to inference request in 1.8099510669708252s
5 requests
0 failed requests
5th percentile: 1.2697384357452393
10th percentile: 1.377094030380249
20th percentile: 1.5918052196502686
30th percentile: 1.703602123260498
40th percentile: 1.7124847412109374
50th percentile: 1.721367359161377
60th percentile: 1.7568008422851562
70th percentile: 1.7922343254089355
80th percentile: 1.8808146476745606
90th percentile: 2.022541809082031
95th percentile: 2.0934053897857665
99th percentile: 2.150096254348755
mean time: 1.7114262104034423
Pipeline stage StressChecker completed in 9.79s
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 0.67s
Shutdown handler de-registered
yamatazen-ayla-light-extra_v2 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service yamatazen-ayla-light-extra-v2-profiler
Waiting for inference service yamatazen-ayla-light-extra-v2-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 2674.26s
Shutdown handler de-registered
yamatazen-ayla-light-extra_v2 status is now inactive due to auto deactivation removed underperforming models
yamatazen-ayla-light-extra_v2 status is now torndown due to DeploymentManager action