aixonlab-zara-14b-v1-1

developer_uid: NischayDnk

submission_id: aixonlab-zara-14b-v1-1_v1

model_name: aixonlab-zara-14b-v1-1_v1

model_group: aixonlab/Zara-14b-v1.1

status: torndown

timestamp: 2025-05-17T05:15:12+00:00

num_battles: 9337

num_wins: 4287

celo_rating: 1251.99

family_friendly_score: 0.6382

family_friendly_standard_error: 0.006795597986932423

submission_type: basic

model_repo: aixonlab/Zara-14b-v1.1

model_architecture: Qwen2ForCausalLM

model_num_parameters: 14765603840.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.47336473856279915, 'latency_mean': 2.1124737703800203, 'latency_p50': 2.100332736968994, 'latency_p90': 2.3396003246307373}, {'batch_size': 3, 'throughput': 0.8647643009654246, 'latency_mean': 3.462080297470093, 'latency_p50': 3.4595009088516235, 'latency_p90': 3.8345730304718018}, {'batch_size': 5, 'throughput': 1.0526263720698623, 'latency_mean': 4.737481608390808, 'latency_p50': 4.728222012519836, 'latency_p90': 5.284392690658569}, {'batch_size': 6, 'throughput': 1.1069839695345254, 'latency_mean': 5.3856607592105865, 'latency_p50': 5.420198440551758, 'latency_p90': 5.986352896690368}, {'batch_size': 10, 'throughput': 1.1917028641603329, 'latency_mean': 8.311739938259125, 'latency_p50': 8.304067015647888, 'latency_p90': 9.486156940460205}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: aixonlab-zara-14b-v1-1_v1

is_internal_developer: False

language_model: aixonlab/Zara-14b-v1.1

model_size: 15B

ranking_group: single

throughput_3p7s: 0.91

us_pacific_date: 2025-05-16

win_ratio: 0.4591410517296776

generation_params: {'temperature': 0.85, 'top_p': 0.94, 'min_p': 0.02, 'top_k': 40, 'presence_penalty': 0.1, 'frequency_penalty': 0.1, 'stopping_words': ['<|im_end|>', '\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|system|>Family Friendly{memory}\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', '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 aixonlab-zara-14b-v1-1-v1-mkmlizer
Waiting for job on aixonlab-zara-14b-v1-1-v1-mkmlizer to finish
aixonlab-zara-14b-v1-1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
aixonlab-zara-14b-v1-1-v1-mkmlizer: ║     _____            __           __                                ║
aixonlab-zara-14b-v1-1-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
aixonlab-zara-14b-v1-1-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
aixonlab-zara-14b-v1-1-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
aixonlab-zara-14b-v1-1-v1-mkmlizer: ║       /___/                                                         ║
aixonlab-zara-14b-v1-1-v1-mkmlizer: ║                                                                     ║
aixonlab-zara-14b-v1-1-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
aixonlab-zara-14b-v1-1-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
aixonlab-zara-14b-v1-1-v1-mkmlizer: ║  https://mk1.ai                                                     ║
aixonlab-zara-14b-v1-1-v1-mkmlizer: ║                                                                     ║
aixonlab-zara-14b-v1-1-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
aixonlab-zara-14b-v1-1-v1-mkmlizer: ║  belonging to:                                                      ║
aixonlab-zara-14b-v1-1-v1-mkmlizer: ║                                                                     ║
aixonlab-zara-14b-v1-1-v1-mkmlizer: ║  Chai Research Corp.                                                ║
aixonlab-zara-14b-v1-1-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
aixonlab-zara-14b-v1-1-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
aixonlab-zara-14b-v1-1-v1-mkmlizer: ║                                                                     ║
aixonlab-zara-14b-v1-1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
aixonlab-zara-14b-v1-1-v1-mkmlizer: Downloaded to shared memory in 48.810s
aixonlab-zara-14b-v1-1-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwlpn00j_, device:0
aixonlab-zara-14b-v1-1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
aixonlab-zara-14b-v1-1-v1-mkmlizer: quantized model in 36.920s
aixonlab-zara-14b-v1-1-v1-mkmlizer: Processed model aixonlab/Zara-14b-v1.1 in 85.730s
aixonlab-zara-14b-v1-1-v1-mkmlizer: creating bucket guanaco-mkml-models
aixonlab-zara-14b-v1-1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
aixonlab-zara-14b-v1-1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/aixonlab-zara-14b-v1-1-v1
aixonlab-zara-14b-v1-1-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/aixonlab-zara-14b-v1-1-v1/merges.txt
aixonlab-zara-14b-v1-1-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/aixonlab-zara-14b-v1-1-v1/vocab.json
aixonlab-zara-14b-v1-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/aixonlab-zara-14b-v1-1-v1/tokenizer.json
aixonlab-zara-14b-v1-1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/aixonlab-zara-14b-v1-1-v1/flywheel_model.1.safetensors
aixonlab-zara-14b-v1-1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/aixonlab-zara-14b-v1-1-v1/flywheel_model.0.safetensors
aixonlab-zara-14b-v1-1-v1-mkmlizer: 
Loading 0:   0%|          | 0/579 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 15/579 [00:00<00:03, 141.30it/s]
Loading 0:   5%|▌         | 30/579 [00:00<00:04, 128.83it/s]
Loading 0:   8%|▊         | 49/579 [00:00<00:03, 153.73it/s]
Loading 0:  11%|█         | 65/579 [00:00<00:03, 135.30it/s]
Loading 0:  14%|█▍        | 81/579 [00:00<00:05, 99.53it/s] 
Loading 0:  16%|█▌        | 94/579 [00:00<00:04, 105.73it/s]
Loading 0:  18%|█▊        | 107/579 [00:00<00:04, 110.07it/s]
Loading 0:  21%|██        | 120/579 [00:01<00:04, 113.62it/s]
Loading 0:  24%|██▍       | 138/579 [00:01<00:03, 131.30it/s]
Loading 0:  27%|██▋       | 154/579 [00:01<00:03, 138.55it/s]
Loading 0:  29%|██▉       | 169/579 [00:01<00:03, 130.68it/s]
Loading 0:  32%|███▏      | 186/579 [00:01<00:02, 140.50it/s]
Loading 0:  35%|███▍      | 201/579 [00:01<00:04, 87.47it/s] 
Loading 0:  38%|███▊      | 219/579 [00:01<00:03, 102.53it/s]
Loading 0:  40%|████      | 232/579 [00:02<00:03, 106.91it/s]
Loading 0:  42%|████▏     | 245/579 [00:02<00:03, 111.21it/s]
Loading 0:  45%|████▌     | 263/579 [00:02<00:02, 127.96it/s]
Loading 0:  48%|████▊     | 279/579 [00:02<00:02, 135.04it/s]
Loading 0:  51%|█████▏    | 297/579 [00:02<00:02, 103.59it/s]
Loading 0:  54%|█████▎    | 310/579 [00:02<00:02, 99.61it/s] 
Loading 0:  56%|█████▋    | 327/579 [00:02<00:02, 111.21it/s]
Loading 0:  59%|█████▊    | 340/579 [00:02<00:02, 114.33it/s]
Loading 0:  61%|██████    | 353/579 [00:03<00:01, 117.33it/s]
Loading 0:  64%|██████▍   | 371/579 [00:03<00:01, 132.79it/s]
Loading 0:  67%|██████▋   | 387/579 [00:03<00:01, 137.45it/s]
Loading 0:  70%|██████▉   | 405/579 [00:03<00:01, 100.48it/s]
Loading 0:  72%|███████▏  | 417/579 [00:03<00:01, 96.56it/s] 
Loading 0:  75%|███████▌  | 435/579 [00:03<00:01, 111.65it/s]
Loading 0:  77%|███████▋  | 448/579 [00:03<00:01, 114.56it/s]
Loading 0:  80%|███████▉  | 461/579 [00:03<00:01, 116.66it/s]
Loading 0:  83%|████████▎ | 481/579 [00:04<00:00, 137.88it/s]
Loading 0:  86%|████████▌ | 496/579 [00:04<00:00, 133.15it/s]
Loading 0:  88%|████████▊ | 512/579 [00:22<00:00, 133.15it/s]
Loading 0:  89%|████████▊ | 513/579 [00:26<00:27,  2.42it/s] 
Loading 0:  90%|████████▉ | 521/579 [00:26<00:19,  2.92it/s]
Loading 0:  92%|█████████▏| 534/579 [00:26<00:11,  4.07it/s]
Loading 0:  95%|█████████▌| 552/579 [00:26<00:04,  6.31it/s]
Loading 0:  98%|█████████▊| 568/579 [00:26<00:01,  9.05it/s]
                                                            
Job aixonlab-zara-14b-v1-1-v1-mkmlizer completed after 115.51s with status: succeeded
Stopping job with name aixonlab-zara-14b-v1-1-v1-mkmlizer
Pipeline stage MKMLizer completed in 116.04s
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 aixonlab-zara-14b-v1-1-v1
Waiting for inference service aixonlab-zara-14b-v1-1-v1 to be ready
Inference service aixonlab-zara-14b-v1-1-v1 ready after 140.6025550365448s
Pipeline stage MKMLDeployer completed in 141.14s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.768618583679199s
Received healthy response to inference request in 2.148486375808716s
Received healthy response to inference request in 2.387909412384033s
Received healthy response to inference request in 1.9944140911102295s
Received healthy response to inference request in 2.072805881500244s
5 requests
0 failed requests
5th percentile: 2.0100924491882326
10th percentile: 2.0257708072662353
20th percentile: 2.057127523422241
30th percentile: 2.0879419803619386
40th percentile: 2.118214178085327
50th percentile: 2.148486375808716
60th percentile: 2.2442555904388426
70th percentile: 2.34002480506897
80th percentile: 2.4640512466430664
90th percentile: 2.616334915161133
95th percentile: 2.692476749420166
99th percentile: 2.7533902168273925
mean time: 2.2744468688964843
Pipeline stage StressChecker completed in 12.89s
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 0.87s
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 0.72s
Shutdown handler de-registered
aixonlab-zara-14b-v1-1_v1 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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service aixonlab-zara-14b-v1-1-v1-profiler
Waiting for inference service aixonlab-zara-14b-v1-1-v1-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 3028.37s
Shutdown handler de-registered
aixonlab-zara-14b-v1-1_v1 status is now inactive due to auto deactivation removed underperforming models
aixonlab-zara-14b-v1-1_v1 status is now torndown due to DeploymentManager action