qwen-qwen2-5-32b

developer_uid: rirv938

submission_id: qwen-qwen2-5-32b_v9

model_name: qwen-qwen2-5-32b_v9

model_group: Qwen/Qwen2.5-32B

status: torndown

timestamp: 2025-01-03T03:28:31+00:00

num_battles: 16

num_wins: 8

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: Qwen/Qwen2.5-32B

model_architecture: Qwen2ForCausalLM

model_num_parameters: 32763417600.0

best_of: 4

max_input_tokens: 768

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.27955191939063073, 'latency_mean': 3.5770667886734007, 'latency_p50': 3.5994988679885864, 'latency_p90': 3.9606228351593016}, {'batch_size': 2, 'throughput': 0.4553383766411703, 'latency_mean': 4.3876743459701535, 'latency_p50': 4.386496424674988, 'latency_p90': 4.881080412864685}, {'batch_size': 3, 'throughput': 0.6112086988261713, 'latency_mean': 4.894066593647003, 'latency_p50': 4.905754923820496, 'latency_p90': 5.414439940452576}, {'batch_size': 4, 'throughput': 0.7265610577001899, 'latency_mean': 5.467192492485046, 'latency_p50': 5.459998250007629, 'latency_p90': 6.076439309120178}, {'batch_size': 5, 'throughput': 0.828996868022263, 'latency_mean': 6.02620272397995, 'latency_p50': 5.994216203689575, 'latency_p90': 6.673904204368591}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: qwen-qwen2-5-32b_v9

ineligible_reason: num_battles<5000

is_internal_developer: True

language_model: Qwen/Qwen2.5-32B

model_size: 33B

ranking_group: single

throughput_3p7s: 0.31

us_pacific_date: 2025-01-02

win_ratio: 0.5

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>', '<|end_of_text|>', 'You:'], 'max_input_tokens': 768, 'best_of': 4, '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 qwen-qwen2-5-32b-v9-mkmlizer
Waiting for job on qwen-qwen2-5-32b-v9-mkmlizer to finish
qwen-qwen2-5-32b-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
qwen-qwen2-5-32b-v9-mkmlizer: ║     _____            __           __                                ║
qwen-qwen2-5-32b-v9-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
qwen-qwen2-5-32b-v9-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
qwen-qwen2-5-32b-v9-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
qwen-qwen2-5-32b-v9-mkmlizer: ║       /___/                                                         ║
qwen-qwen2-5-32b-v9-mkmlizer: ║                                                                     ║
qwen-qwen2-5-32b-v9-mkmlizer: ║  Version: 0.11.38                                                   ║
qwen-qwen2-5-32b-v9-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
qwen-qwen2-5-32b-v9-mkmlizer: ║  https://mk1.ai                                                     ║
qwen-qwen2-5-32b-v9-mkmlizer: ║                                                                     ║
qwen-qwen2-5-32b-v9-mkmlizer: ║  The license key for the current software has been verified as      ║
qwen-qwen2-5-32b-v9-mkmlizer: ║  belonging to:                                                      ║
qwen-qwen2-5-32b-v9-mkmlizer: ║                                                                     ║
qwen-qwen2-5-32b-v9-mkmlizer: ║  Chai Research Corp.                                                ║
qwen-qwen2-5-32b-v9-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
qwen-qwen2-5-32b-v9-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
qwen-qwen2-5-32b-v9-mkmlizer: ║                                                                     ║
qwen-qwen2-5-32b-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
qwen-qwen2-5-32b-v9-mkmlizer: Downloaded to shared memory in 143.499s
qwen-qwen2-5-32b-v9-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0nbv1zpf, device:0
qwen-qwen2-5-32b-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
qwen-qwen2-5-32b-v9-mkmlizer: quantized model in 65.894s
qwen-qwen2-5-32b-v9-mkmlizer: Processed model Qwen/Qwen2.5-32B in 209.394s
qwen-qwen2-5-32b-v9-mkmlizer: creating bucket guanaco-mkml-models
qwen-qwen2-5-32b-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
qwen-qwen2-5-32b-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/qwen-qwen2-5-32b-v9
qwen-qwen2-5-32b-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/qwen-qwen2-5-32b-v9/config.json
qwen-qwen2-5-32b-v9-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/qwen-qwen2-5-32b-v9/added_tokens.json
qwen-qwen2-5-32b-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/qwen-qwen2-5-32b-v9/special_tokens_map.json
qwen-qwen2-5-32b-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/qwen-qwen2-5-32b-v9/tokenizer_config.json
qwen-qwen2-5-32b-v9-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/qwen-qwen2-5-32b-v9/merges.txt
qwen-qwen2-5-32b-v9-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/qwen-qwen2-5-32b-v9/vocab.json
qwen-qwen2-5-32b-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/qwen-qwen2-5-32b-v9/tokenizer.json
qwen-qwen2-5-32b-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/qwen-qwen2-5-32b-v9/flywheel_model.2.safetensors
qwen-qwen2-5-32b-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/qwen-qwen2-5-32b-v9/flywheel_model.1.safetensors
qwen-qwen2-5-32b-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/qwen-qwen2-5-32b-v9/flywheel_model.0.safetensors
qwen-qwen2-5-32b-v9-mkmlizer: 
Loading 0:   0%|          | 0/771 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/771 [00:00<00:20, 36.74it/s]
Loading 0:   2%|▏         | 16/771 [00:00<00:10, 72.28it/s]
Loading 0:   3%|▎         | 26/771 [00:00<00:09, 80.92it/s]
Loading 0:   5%|▍         | 35/771 [00:00<00:13, 54.57it/s]
Loading 0:   5%|▌         | 42/771 [00:00<00:14, 49.34it/s]
Loading 0:   7%|▋         | 52/771 [00:00<00:11, 60.67it/s]
Loading 0:   8%|▊         | 63/771 [00:00<00:09, 72.37it/s]
Loading 0:   9%|▉         | 73/771 [00:01<00:08, 79.23it/s]
Loading 0:  11%|█         | 82/771 [00:01<00:11, 58.32it/s]
Loading 0:  12%|█▏        | 92/771 [00:01<00:10, 65.96it/s]
Loading 0:  13%|█▎        | 100/771 [00:01<00:10, 64.27it/s]
Loading 0:  14%|█▍        | 108/771 [00:01<00:09, 67.87it/s]
Loading 0:  15%|█▌        | 119/771 [00:01<00:08, 77.36it/s]
Loading 0:  17%|█▋        | 128/771 [00:01<00:08, 80.07it/s]
Loading 0:  18%|█▊        | 137/771 [00:02<00:13, 47.04it/s]
Loading 0:  19%|█▉        | 149/771 [00:02<00:11, 56.42it/s]
Loading 0:  21%|██        | 161/771 [00:02<00:09, 63.96it/s]
Loading 0:  23%|██▎       | 178/771 [00:02<00:08, 67.51it/s]
Loading 0:  24%|██▍       | 186/771 [00:02<00:10, 56.54it/s]
Loading 0:  25%|██▌       | 196/771 [00:03<00:09, 63.39it/s]
Loading 0:  27%|██▋       | 207/771 [00:03<00:07, 71.58it/s]
Loading 0:  28%|██▊       | 216/771 [00:03<00:07, 74.89it/s]
Loading 0:  29%|██▉       | 226/771 [00:03<00:09, 60.51it/s]
Loading 0:  30%|███       | 234/771 [00:03<00:10, 50.44it/s]
Loading 0:  32%|███▏      | 244/771 [00:03<00:08, 59.06it/s]
Loading 0:  33%|███▎      | 255/771 [00:04<00:07, 68.72it/s]
Loading 0:  34%|███▍      | 264/771 [00:04<00:07, 72.37it/s]
Loading 0:  36%|███▌      | 274/771 [00:04<00:08, 59.22it/s]
Loading 0:  36%|███▋      | 281/771 [00:04<00:09, 49.12it/s]
Loading 0:  38%|███▊      | 292/771 [00:04<00:08, 59.50it/s]
Loading 0:  39%|███▉      | 303/771 [00:19<03:33,  2.19it/s]
Loading 0:  40%|████      | 309/771 [00:19<02:49,  2.73it/s]
Loading 0:  42%|████▏     | 322/771 [00:19<01:45,  4.26it/s]
Loading 0:  43%|████▎     | 328/771 [00:20<01:27,  5.08it/s]
Loading 0:  44%|████▍     | 339/771 [00:20<00:56,  7.59it/s]
Loading 0:  45%|████▌     | 347/771 [00:20<00:42,  9.98it/s]
Loading 0:  46%|████▌     | 354/771 [00:20<00:33, 12.45it/s]
Loading 0:  48%|████▊     | 370/771 [00:20<00:20, 19.26it/s]
Loading 0:  49%|████▉     | 377/771 [00:21<00:18, 21.00it/s]
Loading 0:  50%|█████     | 388/771 [00:21<00:13, 28.40it/s]
Loading 0:  52%|█████▏    | 399/771 [00:21<00:10, 36.91it/s]
Loading 0:  53%|█████▎    | 407/771 [00:21<00:08, 42.22it/s]
Loading 0:  54%|█████▍    | 418/771 [00:21<00:08, 43.20it/s]
Loading 0:  55%|█████▌    | 425/771 [00:21<00:08, 39.52it/s]
Loading 0:  57%|█████▋    | 436/771 [00:22<00:06, 50.33it/s]
Loading 0:  58%|█████▊    | 447/771 [00:22<00:05, 59.92it/s]
Loading 0:  59%|█████▉    | 455/771 [00:22<00:05, 62.68it/s]
Loading 0:  60%|██████    | 466/771 [00:22<00:05, 56.81it/s]
Loading 0:  61%|██████▏   | 473/771 [00:22<00:06, 47.94it/s]
Loading 0:  63%|██████▎   | 484/771 [00:22<00:04, 58.51it/s]
Loading 0:  64%|██████▍   | 495/771 [00:22<00:04, 68.56it/s]
Loading 0:  65%|██████▌   | 504/771 [00:23<00:03, 72.22it/s]
Loading 0:  67%|██████▋   | 514/771 [00:23<00:04, 60.58it/s]
Loading 0:  68%|██████▊   | 522/771 [00:23<00:04, 50.45it/s]
Loading 0:  69%|██████▉   | 532/771 [00:23<00:04, 58.37it/s]
Loading 0:  70%|███████   | 543/771 [00:23<00:03, 67.86it/s]
Loading 0:  71%|███████▏  | 551/771 [00:23<00:03, 69.07it/s]
Loading 0:  73%|███████▎  | 562/771 [00:24<00:03, 58.59it/s]
Loading 0:  74%|███████▍  | 569/771 [00:24<00:04, 48.65it/s]
Loading 0:  75%|███████▌  | 581/771 [00:24<00:03, 57.90it/s]
Loading 0:  77%|███████▋  | 592/771 [00:24<00:02, 68.27it/s]
Loading 0:  78%|███████▊  | 602/771 [00:24<00:02, 74.76it/s]
Loading 0:  79%|███████▉  | 611/771 [00:24<00:02, 61.20it/s]
Loading 0:  80%|████████  | 619/771 [00:25<00:02, 56.05it/s]
Loading 0:  81%|████████  | 626/771 [00:40<00:02, 56.05it/s]
Loading 0:  81%|████████▏ | 627/771 [00:40<01:16,  1.88it/s]
Loading 0:  82%|████████▏ | 635/771 [00:40<00:52,  2.59it/s]
Loading 0:  83%|████████▎ | 642/771 [00:40<00:37,  3.43it/s]
Loading 0:  85%|████████▌ | 658/771 [00:40<00:18,  5.95it/s]
Loading 0:  86%|████████▌ | 664/771 [00:41<00:15,  6.95it/s]
Loading 0:  88%|████████▊ | 675/771 [00:41<00:09, 10.18it/s]
Loading 0:  89%|████████▊ | 683/771 [00:41<00:06, 13.18it/s]
Loading 0:  89%|████████▉ | 690/771 [00:41<00:05, 16.09it/s]
Loading 0:  92%|█████████▏| 706/771 [00:41<00:02, 24.01it/s]
Loading 0:  92%|█████████▏| 713/771 [00:42<00:02, 25.24it/s]
Loading 0:  94%|█████████▍| 724/771 [00:42<00:01, 33.40it/s]
Loading 0:  95%|█████████▌| 735/771 [00:42<00:00, 42.43it/s]
Loading 0:  96%|█████████▋| 743/771 [00:42<00:00, 47.39it/s]
Loading 0:  98%|█████████▊| 754/771 [00:50<00:04,  4.03it/s]
Loading 0:  99%|█████████▊| 760/771 [00:50<00:02,  4.95it/s]
Loading 0: 100%|█████████▉| 768/771 [00:50<00:00,  6.70it/s]
                                                            
Job qwen-qwen2-5-32b-v9-mkmlizer completed after 370.47s with status: succeeded
Stopping job with name qwen-qwen2-5-32b-v9-mkmlizer
Pipeline stage MKMLizer completed in 370.99s
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 qwen-qwen2-5-32b-v9
Waiting for inference service qwen-qwen2-5-32b-v9 to be ready
Inference service qwen-qwen2-5-32b-v9 ready after 321.84257888793945s
Pipeline stage MKMLDeployer completed in 322.39s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.213250160217285s
Received healthy response to inference request in 2.572990655899048s
Received healthy response to inference request in 1.7755727767944336s
Received healthy response to inference request in 3.4388041496276855s
Received healthy response to inference request in 1.7835774421691895s
5 requests
0 failed requests
5th percentile: 1.7771737098693847
10th percentile: 1.7787746429443358
20th percentile: 1.7819765090942383
30th percentile: 1.941460084915161
40th percentile: 2.2572253704071046
50th percentile: 2.572990655899048
60th percentile: 2.8290944576263426
70th percentile: 3.085198259353638
80th percentile: 3.2583609580993653
90th percentile: 3.348582553863525
95th percentile: 3.3936933517456054
99th percentile: 3.4297819900512696
mean time: 2.556839036941528
Pipeline stage StressChecker completed in 14.23s
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 0.80s
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 0.71s
Shutdown handler de-registered
qwen-qwen2-5-32b_v9 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-qwen2-5-32b-v9-profiler
Waiting for inference service qwen-qwen2-5-32b-v9-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError("('http://qwen-qwen2-5-32b-v9-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')")
Shutdown handler de-registered
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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError("('http://qwen-qwen2-5-32b-v9-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')")
Shutdown handler de-registered
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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError("('http://qwen-qwen2-5-32b-v9-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')")
Shutdown handler de-registered
qwen-qwen2-5-32b_v9 status is now torndown due to DeploymentManager action
qwen-qwen2-5-32b_v9 status is now torndown due to DeploymentManager action
qwen-qwen2-5-32b_v9 status is now torndown due to DeploymentManager action

ChatRequest

Bot Name

Generation Params

Prompt Formatter

ChatMessage 1

Sender

Message

User Message