developer_uid: NischayDnk
submission_id: qwen-qwen2-5-14b-instruct_v2
model_name: qwen-qwen2-5-14b-instruct_v2
model_group: Qwen/Qwen2.5-14B-Instruc
status: torndown
timestamp: 2025-05-13T08:22:10+00:00
num_battles: 9317
num_wins: 3857
celo_rating: 1211.82
family_friendly_score: 0.864
family_friendly_standard_error: 0.004847762370413798
submission_type: basic
model_repo: Qwen/Qwen2.5-14B-Instruct
model_architecture: Qwen2ForCausalLM
model_num_parameters: 14769689600.0
best_of: 5
max_input_tokens: 768
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.5189192067517804, 'latency_mean': 1.927015095949173, 'latency_p50': 1.922315239906311, 'latency_p90': 2.140319657325745}, {'batch_size': 3, 'throughput': 1.0603318059535742, 'latency_mean': 2.8192884910106657, 'latency_p50': 2.808828592300415, 'latency_p90': 3.094839334487915}, {'batch_size': 5, 'throughput': 1.3388684412359302, 'latency_mean': 3.720907428264618, 'latency_p50': 3.701935887336731, 'latency_p90': 4.19376151561737}, {'batch_size': 6, 'throughput': 1.4412601693675808, 'latency_mean': 4.131305358409882, 'latency_p50': 4.129803895950317, 'latency_p90': 4.639003396034241}, {'batch_size': 8, 'throughput': 1.5870890573989926, 'latency_mean': 5.017802444696426, 'latency_p50': 5.024184584617615, 'latency_p90': 5.707226181030274}, {'batch_size': 10, 'throughput': 1.6325552322561967, 'latency_mean': 6.067455617189407, 'latency_p50': 6.068349599838257, 'latency_p90': 6.880301356315613}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: qwen-qwen2-5-14b-instruct_v2
is_internal_developer: False
language_model: Qwen/Qwen2.5-14B-Instruct
model_size: 15B
ranking_group: single
throughput_3p7s: 1.34
us_pacific_date: 2025-05-13
win_ratio: 0.41397445529676935
generation_params: {'temperature': 0.8, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 40, 'presence_penalty': 0.1, 'frequency_penalty': 0.1, 'stopping_words': ['<|im_end|>', '\n', '<|im_start|>'], 'max_input_tokens': 768, 'best_of': 5, '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 qwen-qwen2-5-14b-instruct-v2-mkmlizer
Waiting for job on qwen-qwen2-5-14b-instruct-v2-mkmlizer to finish
qwen-qwen2-5-14b-instruct-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
qwen-qwen2-5-14b-instruct-v2-mkmlizer: ║     _____            __           __                                ║
qwen-qwen2-5-14b-instruct-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
qwen-qwen2-5-14b-instruct-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
qwen-qwen2-5-14b-instruct-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
qwen-qwen2-5-14b-instruct-v2-mkmlizer: ║       /___/                                                         ║
qwen-qwen2-5-14b-instruct-v2-mkmlizer: ║                                                                     ║
qwen-qwen2-5-14b-instruct-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
qwen-qwen2-5-14b-instruct-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
qwen-qwen2-5-14b-instruct-v2-mkmlizer: ║  https://mk1.ai                                                     ║
qwen-qwen2-5-14b-instruct-v2-mkmlizer: ║                                                                     ║
qwen-qwen2-5-14b-instruct-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
qwen-qwen2-5-14b-instruct-v2-mkmlizer: ║  belonging to:                                                      ║
qwen-qwen2-5-14b-instruct-v2-mkmlizer: ║                                                                     ║
qwen-qwen2-5-14b-instruct-v2-mkmlizer: ║  Chai Research Corp.                                                ║
qwen-qwen2-5-14b-instruct-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
qwen-qwen2-5-14b-instruct-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
qwen-qwen2-5-14b-instruct-v2-mkmlizer: ║                                                                     ║
qwen-qwen2-5-14b-instruct-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
qwen-qwen2-5-14b-instruct-v2-mkmlizer: Downloaded to shared memory in 57.213s
qwen-qwen2-5-14b-instruct-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3ss2_hop, device:0
qwen-qwen2-5-14b-instruct-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
qwen-qwen2-5-14b-instruct-v2-mkmlizer: quantized model in 36.618s
qwen-qwen2-5-14b-instruct-v2-mkmlizer: Processed model Qwen/Qwen2.5-14B-Instruct in 93.832s
qwen-qwen2-5-14b-instruct-v2-mkmlizer: creating bucket guanaco-mkml-models
qwen-qwen2-5-14b-instruct-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
qwen-qwen2-5-14b-instruct-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/qwen-qwen2-5-14b-instruct-v2
qwen-qwen2-5-14b-instruct-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/qwen-qwen2-5-14b-instruct-v2/config.json
qwen-qwen2-5-14b-instruct-v2-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/qwen-qwen2-5-14b-instruct-v2/added_tokens.json
qwen-qwen2-5-14b-instruct-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/qwen-qwen2-5-14b-instruct-v2/special_tokens_map.json
qwen-qwen2-5-14b-instruct-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/qwen-qwen2-5-14b-instruct-v2/tokenizer_config.json
qwen-qwen2-5-14b-instruct-v2-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/qwen-qwen2-5-14b-instruct-v2/merges.txt
qwen-qwen2-5-14b-instruct-v2-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/qwen-qwen2-5-14b-instruct-v2/vocab.json
qwen-qwen2-5-14b-instruct-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/qwen-qwen2-5-14b-instruct-v2/tokenizer.json
qwen-qwen2-5-14b-instruct-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/qwen-qwen2-5-14b-instruct-v2/flywheel_model.0.safetensors
qwen-qwen2-5-14b-instruct-v2-mkmlizer: 
Loading 0:   0%|          | 0/579 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 15/579 [00:00<00:03, 142.70it/s]
Loading 0:   5%|▌         | 30/579 [00:00<00:04, 130.08it/s]
Loading 0:   8%|▊         | 48/579 [00:00<00:03, 150.93it/s]
Loading 0:  11%|█         | 64/579 [00:00<00:05, 92.59it/s] 
Loading 0:  14%|█▍        | 83/579 [00:00<00:04, 111.20it/s]
Loading 0:  17%|█▋        | 98/579 [00:00<00:04, 115.65it/s]
Loading 0:  20%|█▉        | 114/579 [00:00<00:03, 126.67it/s]
Loading 0:  23%|██▎       | 133/579 [00:01<00:03, 138.90it/s]
Loading 0:  26%|██▌       | 148/579 [00:01<00:04, 90.96it/s] 
Loading 0:  28%|██▊       | 161/579 [00:01<00:04, 97.28it/s]
Loading 0:  31%|███▏      | 181/579 [00:01<00:03, 119.59it/s]
Loading 0:  34%|███▍      | 196/579 [00:01<00:03, 121.04it/s]
Loading 0:  36%|███▋      | 210/579 [00:01<00:02, 125.29it/s]
Loading 0:  40%|███▉      | 229/579 [00:02<00:03, 99.60it/s] 
Loading 0:  42%|████▏     | 243/579 [00:02<00:03, 107.44it/s]
Loading 0:  44%|████▍     | 256/579 [00:02<00:02, 112.14it/s]
Loading 0:  46%|████▋     | 269/579 [00:02<00:02, 115.60it/s]
Loading 0:  50%|█████     | 291/579 [00:02<00:02, 136.11it/s]
Loading 0:  53%|█████▎    | 306/579 [00:02<00:02, 132.67it/s]
Loading 0:  55%|█████▌    | 320/579 [00:02<00:02, 97.69it/s] 
Loading 0:  58%|█████▊    | 337/579 [00:02<00:02, 112.97it/s]
Loading 0:  61%|██████    | 351/579 [00:03<00:01, 118.77it/s]
Loading 0:  63%|██████▎   | 365/579 [00:03<00:01, 115.64it/s]
Loading 0:  66%|██████▌   | 383/579 [00:03<00:01, 130.45it/s]
Loading 0:  70%|██████▉   | 405/579 [00:03<00:01, 153.60it/s]
Loading 0:  73%|███████▎  | 422/579 [00:03<00:01, 97.89it/s] 
Loading 0:  75%|███████▌  | 436/579 [00:03<00:01, 102.10it/s]
Loading 0:  78%|███████▊  | 449/579 [00:03<00:01, 107.94it/s]
Loading 0:  81%|████████  | 468/579 [00:04<00:00, 126.81it/s]
Loading 0:  83%|████████▎ | 483/579 [00:04<00:00, 131.20it/s]
Loading 0:  86%|████████▌ | 498/579 [00:04<00:00, 92.23it/s] 
Loading 0:  90%|████████▉ | 519/579 [00:04<00:00, 111.18it/s]
Loading 0:  92%|█████████▏| 533/579 [00:19<00:12,  3.65it/s] 
Loading 0:  96%|█████████▌| 555/579 [00:19<00:04,  5.70it/s]
Loading 0:  99%|█████████▊| 571/579 [00:19<00:01,  7.76it/s]
                                                            

Job qwen-qwen2-5-14b-instruct-v2-mkmlizer completed after 115.78s with status: succeeded
Stopping job with name qwen-qwen2-5-14b-instruct-v2-mkmlizer
Pipeline stage MKMLizer completed in 116.28s
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 qwen-qwen2-5-14b-instruct-v2
Waiting for inference service qwen-qwen2-5-14b-instruct-v2 to be ready
Inference service qwen-qwen2-5-14b-instruct-v2 ready after 120.48159050941467s
Pipeline stage MKMLDeployer completed in 121.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.36531400680542s
Received healthy response to inference request in 1.7993369102478027s
Received healthy response to inference request in 1.9254908561706543s
Received healthy response to inference request in 1.922377347946167s
Received healthy response to inference request in 1.7473571300506592s
5 requests
0 failed requests
5th percentile: 1.7577530860900878
10th percentile: 1.7681490421295165
20th percentile: 1.788940954208374
30th percentile: 1.8239449977874755
40th percentile: 1.8731611728668214
50th percentile: 1.922377347946167
60th percentile: 1.9236227512359618
70th percentile: 1.9248681545257569
80th percentile: 2.0134554862976075
90th percentile: 2.1893847465515135
95th percentile: 2.2773493766784667
99th percentile: 2.3477210807800293
mean time: 1.9519752502441405
Pipeline stage StressChecker completed in 11.14s
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 0.74s
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
qwen-qwen2-5-14b-instruct_v2 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 2786.90s
Shutdown handler de-registered
qwen-qwen2-5-14b-instruct_v2 status is now inactive due to auto deactivation removed underperforming models
qwen-qwen2-5-14b-instruct_v2 status is now torndown due to DeploymentManager action