developer_uid: NischayDnk
submission_id: qwen-qwen2-5-14b-instruct_v1
model_name: qwen-qwen2-5-14b-instruct_v1
model_group: Qwen/Qwen2.5-14B-Instruc
status: torndown
timestamp: 2025-02-19T18:34:04+00:00
num_battles: 6628
num_wins: 3056
celo_rating: 1237.86
family_friendly_score: 0.6348
family_friendly_standard_error: 0.006809243129746507
submission_type: basic
model_repo: Qwen/Qwen2.5-14B-Instruct
model_architecture: Qwen2ForCausalLM
model_num_parameters: 14769689600.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.46707368932263327, 'latency_mean': 2.1409168434143067, 'latency_p50': 2.1313462257385254, 'latency_p90': 2.343235921859741}, {'batch_size': 3, 'throughput': 0.8724376155386443, 'latency_mean': 3.4258251214027404, 'latency_p50': 3.4228949546813965, 'latency_p90': 3.7992980003356935}, {'batch_size': 5, 'throughput': 1.066434222214042, 'latency_mean': 4.665308111906052, 'latency_p50': 4.642070293426514, 'latency_p90': 5.178853702545166}, {'batch_size': 6, 'throughput': 1.1196385878529267, 'latency_mean': 5.331926604509354, 'latency_p50': 5.379949450492859, 'latency_p90': 5.897451376914978}, {'batch_size': 10, 'throughput': 1.2092655682944, 'latency_mean': 8.210320004224776, 'latency_p50': 8.205541491508484, 'latency_p90': 9.27096140384674}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: qwen-qwen2-5-14b-instruct_v1
is_internal_developer: False
language_model: Qwen/Qwen2.5-14B-Instruct
model_size: 15B
ranking_group: single
throughput_3p7s: 0.93
us_pacific_date: 2025-02-19
win_ratio: 0.46107423053711527
generation_params: {'temperature': 0.8, 'top_p': 0.95, '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': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', '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 qwen-qwen2-5-14b-instruct-v1-mkmlizer
Waiting for job on qwen-qwen2-5-14b-instruct-v1-mkmlizer to finish
Failed to get response for submission chaiml-20250219-c-4epoc_80755_v1: HTTPConnectionPool(host='chaiml-20250219-c-4epoc-80755-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
qwen-qwen2-5-14b-instruct-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
qwen-qwen2-5-14b-instruct-v1-mkmlizer: ║     _____            __           __                                ║
qwen-qwen2-5-14b-instruct-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
qwen-qwen2-5-14b-instruct-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
qwen-qwen2-5-14b-instruct-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
qwen-qwen2-5-14b-instruct-v1-mkmlizer: ║       /___/                                                         ║
qwen-qwen2-5-14b-instruct-v1-mkmlizer: ║                                                                     ║
qwen-qwen2-5-14b-instruct-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
qwen-qwen2-5-14b-instruct-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
qwen-qwen2-5-14b-instruct-v1-mkmlizer: ║  https://mk1.ai                                                     ║
qwen-qwen2-5-14b-instruct-v1-mkmlizer: ║                                                                     ║
qwen-qwen2-5-14b-instruct-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
qwen-qwen2-5-14b-instruct-v1-mkmlizer: ║  belonging to:                                                      ║
qwen-qwen2-5-14b-instruct-v1-mkmlizer: ║                                                                     ║
qwen-qwen2-5-14b-instruct-v1-mkmlizer: ║  Chai Research Corp.                                                ║
qwen-qwen2-5-14b-instruct-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
qwen-qwen2-5-14b-instruct-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
qwen-qwen2-5-14b-instruct-v1-mkmlizer: ║                                                                     ║
qwen-qwen2-5-14b-instruct-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission mistralai-mistral-nem_93303_v369: HTTPConnectionPool(host='mistralai-mistral-nem-93303-v369-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-20250219-c-4epoc_80755_v1: HTTPConnectionPool(host='chaiml-20250219-c-4epoc-80755-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
qwen-qwen2-5-14b-instruct-v1-mkmlizer: Downloaded to shared memory in 40.413s
qwen-qwen2-5-14b-instruct-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkhmxhrye, device:0
qwen-qwen2-5-14b-instruct-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission chaiml-20250219-c-4epoc_80755_v1: HTTPConnectionPool(host='chaiml-20250219-c-4epoc-80755-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
qwen-qwen2-5-14b-instruct-v1-mkmlizer: quantized model in 37.505s
qwen-qwen2-5-14b-instruct-v1-mkmlizer: Processed model Qwen/Qwen2.5-14B-Instruct in 77.919s
qwen-qwen2-5-14b-instruct-v1-mkmlizer: creating bucket guanaco-mkml-models
qwen-qwen2-5-14b-instruct-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
qwen-qwen2-5-14b-instruct-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/qwen-qwen2-5-14b-instruct-v1
qwen-qwen2-5-14b-instruct-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/qwen-qwen2-5-14b-instruct-v1/config.json
qwen-qwen2-5-14b-instruct-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/qwen-qwen2-5-14b-instruct-v1/added_tokens.json
qwen-qwen2-5-14b-instruct-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/qwen-qwen2-5-14b-instruct-v1/special_tokens_map.json
qwen-qwen2-5-14b-instruct-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/qwen-qwen2-5-14b-instruct-v1/tokenizer_config.json
qwen-qwen2-5-14b-instruct-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/qwen-qwen2-5-14b-instruct-v1/merges.txt
qwen-qwen2-5-14b-instruct-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/qwen-qwen2-5-14b-instruct-v1/vocab.json
qwen-qwen2-5-14b-instruct-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/qwen-qwen2-5-14b-instruct-v1/tokenizer.json
qwen-qwen2-5-14b-instruct-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/qwen-qwen2-5-14b-instruct-v1/flywheel_model.1.safetensors
qwen-qwen2-5-14b-instruct-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/qwen-qwen2-5-14b-instruct-v1/flywheel_model.0.safetensors
qwen-qwen2-5-14b-instruct-v1-mkmlizer: 
Loading 0:   0%|          | 0/579 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 15/579 [00:00<00:03, 145.66it/s]
Loading 0:   5%|▌         | 30/579 [00:00<00:04, 135.13it/s]
Loading 0:   8%|▊         | 47/579 [00:00<00:03, 148.35it/s]
Loading 0:  11%|█         | 62/579 [00:00<00:05, 89.88it/s] 
Loading 0:  14%|█▍        | 82/579 [00:00<00:04, 116.12it/s]
Loading 0:  17%|█▋        | 97/579 [00:00<00:04, 118.08it/s]
Loading 0:  19%|█▉        | 111/579 [00:00<00:03, 118.20it/s]
Loading 0:  23%|██▎       | 133/579 [00:01<00:03, 138.70it/s]
Loading 0:  26%|██▌       | 148/579 [00:01<00:04, 93.33it/s] 
Loading 0:  28%|██▊       | 161/579 [00:01<00:04, 100.53it/s]
Loading 0:  32%|███▏      | 183/579 [00:01<00:03, 122.74it/s]
Loading 0:  34%|███▍      | 198/579 [00:01<00:03, 124.47it/s]
Loading 0:  37%|███▋      | 215/579 [00:01<00:02, 135.36it/s]
Loading 0:  40%|███▉      | 230/579 [00:02<00:03, 99.89it/s] 
Loading 0:  42%|████▏     | 243/579 [00:02<00:03, 103.96it/s]
Loading 0:  44%|████▍     | 256/579 [00:02<00:02, 108.53it/s]
Loading 0:  46%|████▋     | 269/579 [00:02<00:02, 113.59it/s]
Loading 0:  50%|█████     | 291/579 [00:02<00:02, 135.75it/s]
Loading 0:  53%|█████▎    | 306/579 [00:02<00:02, 133.56it/s]
Loading 0:  55%|█████▌    | 320/579 [00:02<00:02, 98.79it/s] 
Loading 0:  58%|█████▊    | 337/579 [00:02<00:02, 113.77it/s]
Loading 0:  61%|██████    | 351/579 [00:03<00:01, 119.48it/s]
Loading 0:  63%|██████▎   | 365/579 [00:03<00:01, 117.93it/s]
Loading 0:  66%|██████▌   | 383/579 [00:03<00:01, 133.62it/s]
Loading 0:  70%|██████▉   | 404/579 [00:03<00:01, 151.32it/s]
Loading 0:  73%|███████▎  | 420/579 [00:03<00:01, 95.44it/s] 
Loading 0:  75%|███████▌  | 435/579 [00:03<00:01, 103.76it/s]
Loading 0:  77%|███████▋  | 448/579 [00:03<00:01, 109.28it/s]
Loading 0:  80%|███████▉  | 461/579 [00:03<00:01, 112.99it/s]
Loading 0:  83%|████████▎ | 479/579 [00:04<00:00, 128.90it/s]
Loading 0:  85%|████████▌ | 494/579 [00:04<00:00, 94.66it/s] 
Loading 0:  88%|████████▊ | 507/579 [00:04<00:00, 101.36it/s]
Loading 0:  90%|████████▉ | 520/579 [00:04<00:00, 107.72it/s]
Loading 0:  92%|█████████▏| 533/579 [00:19<00:15,  3.01it/s] 
Loading 0:  96%|█████████▌| 555/579 [00:19<00:04,  5.00it/s]
Loading 0:  98%|█████████▊| 570/579 [00:19<00:01,  6.88it/s]
                                                            

Job qwen-qwen2-5-14b-instruct-v1-mkmlizer completed after 104.84s with status: succeeded
Stopping job with name qwen-qwen2-5-14b-instruct-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.35s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service qwen-qwen2-5-14b-instruct-v1
Waiting for inference service qwen-qwen2-5-14b-instruct-v1 to be ready
Failed to get response for submission blend_lidos_2025-02-16: HTTPConnectionPool(host='blend-rosit-2025-02-16-predictor.tenant-chaiml-guanaco.k2.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service qwen-qwen2-5-14b-instruct-v1 ready after 160.84435892105103s
Pipeline stage MKMLDeployer completed in 161.34s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6617112159729004s
Received healthy response to inference request in 2.096785068511963s
Received healthy response to inference request in 2.05375337600708s
Received healthy response to inference request in 2.252242088317871s
Received healthy response to inference request in 1.5470123291015625s
5 requests
0 failed requests
5th percentile: 1.648360538482666
10th percentile: 1.7497087478637696
20th percentile: 1.9524051666259765
30th percentile: 2.0623597145080566
40th percentile: 2.07957239151001
50th percentile: 2.096785068511963
60th percentile: 2.158967876434326
70th percentile: 2.2211506843566893
80th percentile: 2.334135913848877
90th percentile: 2.497923564910889
95th percentile: 2.5798173904418946
99th percentile: 2.6453324508666993
mean time: 2.1223008155822756
Pipeline stage StressChecker completed in 11.78s
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 0.61s
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
qwen-qwen2-5-14b-instruct_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service qwen-qwen2-5-14b-instruct-v1-profiler
Waiting for inference service qwen-qwen2-5-14b-instruct-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 2883.83s
Shutdown handler de-registered
qwen-qwen2-5-14b-instruct_v1 status is now inactive due to auto deactivation removed underperforming models
qwen-qwen2-5-14b-instruct_v1 status is now torndown due to DeploymentManager action
qwen-qwen2-5-14b-instruct_v1 status is now torndown due to DeploymentManager action
qwen-qwen2-5-14b-instruct_v1 status is now torndown due to DeploymentManager action