chaiml-mergev1-qwen-oldnew

developer_uid: NischayDnk

submission_id: chaiml-mergev1-qwen-oldnew_v1

model_name: chaiml-mergev1-qwen-oldnew_v1

model_group: ChaiML/mergev1_qwen_oldn

status: torndown

timestamp: 2025-04-08T21:18:36+00:00

num_battles: 10624

num_wins: 5274

celo_rating: 1274.37

family_friendly_score: 0.5992

family_friendly_standard_error: 0.0069305030120475385

submission_type: basic

model_repo: ChaiML/mergev1_qwen_oldnew

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': 0.4733040049657344, 'latency_mean': 2.1127396500110627, 'latency_p50': 2.1122690439224243, 'latency_p90': 2.3290047645568848}, {'batch_size': 3, 'throughput': 0.8638714551932504, 'latency_mean': 3.4518968796730043, 'latency_p50': 3.455303192138672, 'latency_p90': 3.9013557195663453}, {'batch_size': 5, 'throughput': 1.0433530969904548, 'latency_mean': 4.774170111417771, 'latency_p50': 4.7803308963775635, 'latency_p90': 5.309142208099365}, {'batch_size': 6, 'throughput': 1.1041808877129902, 'latency_mean': 5.403563841581344, 'latency_p50': 5.3897446393966675, 'latency_p90': 6.032121634483337}, {'batch_size': 10, 'throughput': 1.175765524685692, 'latency_mean': 8.44012476682663, 'latency_p50': 8.45797884464264, 'latency_p90': 9.406492400169373}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mergev1-qwen-oldnew_v1

is_internal_developer: False

language_model: ChaiML/mergev1_qwen_oldnew

model_size: 15B

ranking_group: single

throughput_3p7s: 0.91

us_pacific_date: 2025-04-08

win_ratio: 0.4964231927710843

generation_params: {'temperature': 0.75, 'top_p': 0.96, 'min_p': 0.02, 'top_k': 60, 'presence_penalty': 0.2, 'frequency_penalty': 0.2, 'stopping_words': ['<|im_end|>', '\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', '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 chaiml-mergev1-qwen-oldnew-v1-mkmlizer
Waiting for job on chaiml-mergev1-qwen-oldnew-v1-mkmlizer to finish
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: ║       /___/                                                         ║
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: ║                                                                     ║
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: ║                                                                     ║
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: ║                                                                     ║
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: ║                                                                     ║
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: Downloaded to shared memory in 53.948s
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5drbog56, device:0
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: quantized model in 37.585s
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: Processed model ChaiML/mergev1_qwen_oldnew in 91.534s
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mergev1-qwen-oldnew-v1
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mergev1-qwen-oldnew-v1/config.json
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-mergev1-qwen-oldnew-v1/added_tokens.json
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mergev1-qwen-oldnew-v1/tokenizer.json
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mergev1-qwen-oldnew-v1/flywheel_model.1.safetensors
chaiml-mergev1-qwen-oldnew-v1-mkmlizer: 
Loading 0:   0%|          | 0/579 [00:00<?, ?it/s]
Loading 0:   0%|          | 2/579 [00:07<33:41,  3.50s/it]
Loading 0:   3%|▎         | 16/579 [00:07<03:03,  3.07it/s]
Loading 0:   5%|▌         | 29/579 [00:07<01:23,  6.58it/s]
Loading 0:   7%|▋         | 41/579 [00:07<00:52, 10.17it/s]
Loading 0:   9%|▉         | 54/579 [00:07<00:32, 15.91it/s]
Loading 0:  12%|█▏        | 72/579 [00:07<00:19, 26.44it/s]
Loading 0:  15%|█▌        | 88/579 [00:07<00:13, 37.56it/s]
Loading 0:  18%|█▊        | 102/579 [00:07<00:10, 47.51it/s]
Loading 0:  21%|██        | 122/579 [00:08<00:06, 67.34it/s]
Loading 0:  24%|██▍       | 138/579 [00:08<00:05, 76.51it/s]
Loading 0:  26%|██▋       | 152/579 [00:08<00:06, 69.05it/s]
Loading 0:  30%|██▉       | 172/579 [00:08<00:04, 87.69it/s]
Loading 0:  32%|███▏      | 185/579 [00:08<00:04, 95.13it/s]
Loading 0:  34%|███▍      | 198/579 [00:08<00:03, 101.38it/s]
Loading 0:  37%|███▋      | 216/579 [00:08<00:03, 118.17it/s]
Loading 0:  40%|████      | 232/579 [00:08<00:02, 127.17it/s]
Loading 0:  43%|████▎     | 247/579 [00:09<00:02, 124.37it/s]
Loading 0:  45%|████▌     | 261/579 [00:09<00:03, 88.49it/s] 
Loading 0:  48%|████▊     | 280/579 [00:09<00:02, 104.93it/s]
Loading 0:  51%|█████     | 294/579 [00:09<00:02, 107.92it/s]
Loading 0:  54%|█████▍    | 314/579 [00:09<00:02, 128.77it/s]
Loading 0:  57%|█████▋    | 329/579 [00:09<00:01, 126.67it/s]
Loading 0:  59%|█████▉    | 343/579 [00:09<00:01, 129.43it/s]
Loading 0:  62%|██████▏   | 361/579 [00:10<00:01, 142.65it/s]
Loading 0:  65%|██████▌   | 377/579 [00:10<00:02, 92.16it/s] 
Loading 0:  67%|██████▋   | 390/579 [00:10<00:01, 98.99it/s]
Loading 0:  71%|███████   | 410/579 [00:10<00:01, 120.82it/s]
Loading 0:  73%|███████▎  | 425/579 [00:10<00:01, 121.71it/s]
Loading 0:  76%|███████▌  | 439/579 [00:10<00:01, 125.66it/s]
Loading 0:  79%|███████▉  | 456/579 [00:10<00:00, 136.59it/s]
Loading 0:  82%|████████▏ | 472/579 [00:10<00:00, 142.67it/s]
Loading 0:  84%|████████▍ | 485/579 [00:27<00:00, 142.67it/s]
Loading 0:  84%|████████▍ | 486/579 [00:27<00:29,  3.14it/s] 
Loading 0:  87%|████████▋ | 502/579 [00:27<00:17,  4.50it/s]
Loading 0:  90%|████████▉ | 520/579 [00:27<00:08,  6.63it/s]
Loading 0:  93%|█████████▎| 536/579 [00:27<00:04,  9.21it/s]
Loading 0:  95%|█████████▌| 551/579 [00:27<00:02, 12.55it/s]
Loading 0:  98%|█████████▊| 568/579 [00:27<00:00, 17.64it/s]
                                                            
Job chaiml-mergev1-qwen-oldnew-v1-mkmlizer completed after 125.45s with status: succeeded
Stopping job with name chaiml-mergev1-qwen-oldnew-v1-mkmlizer
Pipeline stage MKMLizer completed in 125.90s
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 chaiml-mergev1-qwen-oldnew-v1
Waiting for inference service chaiml-mergev1-qwen-oldnew-v1 to be ready
Inference service chaiml-mergev1-qwen-oldnew-v1 ready after 100.91664814949036s
Pipeline stage MKMLDeployer completed in 101.43s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7421810626983643s
Received healthy response to inference request in 1.9909303188323975s
Received healthy response to inference request in 2.2047278881073s
Received healthy response to inference request in 1.9393877983093262s
Received healthy response to inference request in 1.9078044891357422s
5 requests
0 failed requests
5th percentile: 1.914121150970459
10th percentile: 1.9204378128051758
20th percentile: 1.9330711364746094
30th percentile: 1.9496963024139404
40th percentile: 1.970313310623169
50th percentile: 1.9909303188323975
60th percentile: 2.0764493465423586
70th percentile: 2.1619683742523192
80th percentile: 2.312218523025513
90th percentile: 2.5271997928619383
95th percentile: 2.6346904277801513
99th percentile: 2.7206829357147218
mean time: 2.157006311416626
Pipeline stage StressChecker completed in 12.01s
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 0.62s
Shutdown handler de-registered
chaiml-mergev1-qwen-oldnew_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
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 4180.19s
Shutdown handler de-registered
chaiml-mergev1-qwen-oldnew_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mergev1-qwen-oldnew_v1 status is now torndown due to DeploymentManager action