chaiml-qwen32b-simpoexp_21972

developer_uid: NischayDnk

submission_id: chaiml-qwen32b-simpoexp_21972_v5

model_name: chaiml-qwen32b-simpoexp_21972_v5

model_group: ChaiML/qwen32b-simpoexp1

status: torndown

timestamp: 2025-05-08T19:58:23+00:00

num_battles: 9640

num_wins: 5120

celo_rating: 1306.5

family_friendly_score: 0.40480000000000005

family_friendly_standard_error: 0.006941713909403066

submission_type: basic

model_repo: ChaiML/qwen32b-simpoexp1-s2-ftsimpoexp4-1330pref

model_architecture: Qwen2ForCausalLM

model_num_parameters: 32759331840.0

best_of: 5

max_input_tokens: 768

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.3938479380628166, 'latency_mean': 2.5389849936962126, 'latency_p50': 2.528089761734009, 'latency_p90': 2.8298373222351074}, {'batch_size': 3, 'throughput': 0.8683041101792007, 'latency_mean': 3.4381235253810885, 'latency_p50': 3.447893500328064, 'latency_p90': 3.7753592014312742}, {'batch_size': 5, 'throughput': 1.176455479786216, 'latency_mean': 4.210912932157516, 'latency_p50': 4.22580361366272, 'latency_p90': 4.710861253738403}, {'batch_size': 6, 'throughput': 1.3156952770207675, 'latency_mean': 4.530416859388351, 'latency_p50': 4.54050600528717, 'latency_p90': 5.061538720130921}, {'batch_size': 8, 'throughput': 1.4945040665727578, 'latency_mean': 5.317322500944138, 'latency_p50': 5.2643803358078, 'latency_p90': 6.06119589805603}, {'batch_size': 10, 'throughput': 1.6166522539433612, 'latency_mean': 6.104961189031601, 'latency_p50': 6.078028678894043, 'latency_p90': 6.989222311973572}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: chaiml-qwen32b-simpoexp_21972_v5

is_internal_developer: False

language_model: ChaiML/qwen32b-simpoexp1-s2-ftsimpoexp4-1330pref

model_size: 33B

ranking_group: single

throughput_3p7s: 0.99

us_pacific_date: 2025-05-08

win_ratio: 0.5311203319502075

generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 40, 'presence_penalty': 0.35, 'frequency_penalty': 0.35, 'stopping_words': ['\n', '<|im_end|>', '<|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 chaiml-qwen32b-simpoexp-21972-v5-mkmlizer
Waiting for job on chaiml-qwen32b-simpoexp-21972-v5-mkmlizer to finish
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: ║     _____            __           __                                ║
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: ║       /___/                                                         ║
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: ║                                                                     ║
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: ║                                                                     ║
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: ║  belonging to:                                                      ║
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: ║                                                                     ║
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: ║                                                                     ║
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: Downloaded to shared memory in 113.011s
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4eaxh3ig, device:0
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: quantized model in 63.311s
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: Processed model ChaiML/qwen32b-simpoexp1-s2-ftsimpoexp4-1330pref in 176.322s
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v5
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v5/config.json
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v5/added_tokens.json
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v5/special_tokens_map.json
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v5/merges.txt
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v5/tokenizer_config.json
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v5/tokenizer.json
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v5/vocab.json
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v5/flywheel_model.2.safetensors
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v5/flywheel_model.1.safetensors
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v5/flywheel_model.0.safetensors
chaiml-qwen32b-simpoexp-21972-v5-mkmlizer: 
Loading 0:   0%|          | 0/771 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/771 [00:00<00:19, 39.55it/s]
Loading 0:   2%|▏         | 16/771 [00:00<00:09, 76.16it/s]
Loading 0:   4%|▎         | 27/771 [00:00<00:08, 90.35it/s]
Loading 0:   5%|▍         | 37/771 [00:00<00:07, 93.48it/s]
Loading 0:   6%|▌         | 47/771 [00:00<00:13, 54.59it/s]
Loading 0:   7%|▋         | 55/771 [00:00<00:13, 52.86it/s]
Loading 0:   8%|▊         | 65/771 [00:01<00:12, 58.22it/s]
Loading 0:  10%|▉         | 76/771 [00:01<00:09, 69.74it/s]
Loading 0:  11%|█▏        | 88/771 [00:01<00:09, 74.64it/s]
Loading 0:  13%|█▎        | 98/771 [00:01<00:08, 80.62it/s]
Loading 0:  14%|█▍        | 107/771 [00:01<00:10, 60.84it/s]
Loading 0:  15%|█▍        | 115/771 [00:01<00:10, 64.81it/s]
Loading 0:  16%|█▌        | 123/771 [00:01<00:10, 64.63it/s]
Loading 0:  17%|█▋        | 132/771 [00:01<00:09, 70.16it/s]
Loading 0:  18%|█▊        | 142/771 [00:02<00:08, 77.13it/s]
Loading 0:  20%|█▉        | 153/771 [00:02<00:07, 85.43it/s]
Loading 0:  21%|██        | 163/771 [00:02<00:07, 81.24it/s]
Loading 0:  22%|██▏       | 172/771 [00:02<00:11, 51.10it/s]
Loading 0:  24%|██▍       | 184/771 [00:02<00:09, 59.67it/s]
Loading 0:  25%|██▌       | 196/771 [00:02<00:08, 66.72it/s]
Loading 0:  27%|██▋       | 208/771 [00:03<00:07, 72.40it/s]
Loading 0:  28%|██▊       | 219/771 [00:03<00:06, 80.50it/s]
Loading 0:  30%|██▉       | 228/771 [00:03<00:09, 59.66it/s]
Loading 0:  31%|███       | 236/771 [00:03<00:08, 60.79it/s]
Loading 0:  32%|███▏      | 245/771 [00:03<00:08, 62.45it/s]
Loading 0:  33%|███▎      | 257/771 [00:03<00:07, 70.34it/s]
Loading 0:  35%|███▍      | 269/771 [00:03<00:06, 75.35it/s]
Loading 0:  37%|███▋      | 286/771 [00:04<00:06, 72.59it/s]
Loading 0:  38%|███▊      | 294/771 [00:04<00:07, 61.53it/s]
Loading 0:  39%|███▉      | 303/771 [00:18<03:15,  2.40it/s]
Loading 0:  41%|████      | 315/771 [00:18<02:09,  3.52it/s]
Loading 0:  42%|████▏     | 326/771 [00:18<01:29,  4.96it/s]
Loading 0:  43%|████▎     | 335/771 [00:19<01:06,  6.52it/s]
Loading 0:  45%|████▍     | 346/771 [00:19<00:47,  8.87it/s]
Loading 0:  46%|████▌     | 353/771 [00:19<00:41, 10.19it/s]
Loading 0:  47%|████▋     | 365/771 [00:19<00:27, 14.77it/s]
Loading 0:  49%|████▉     | 376/771 [00:19<00:19, 20.31it/s]
Loading 0:  50%|█████     | 387/771 [00:19<00:14, 27.17it/s]
Loading 0:  52%|█████▏    | 398/771 [00:20<00:10, 34.05it/s]
Loading 0:  53%|█████▎    | 407/771 [00:20<00:10, 35.32it/s]
Loading 0:  54%|█████▍    | 415/771 [00:20<00:09, 37.84it/s]
Loading 0:  55%|█████▌    | 425/771 [00:20<00:07, 44.43it/s]
Loading 0:  57%|█████▋    | 437/771 [00:20<00:06, 53.43it/s]
Loading 0:  58%|█████▊    | 449/771 [00:20<00:05, 61.56it/s]
Loading 0:  60%|██████    | 466/771 [00:21<00:04, 63.53it/s]
Loading 0:  61%|██████▏   | 474/771 [00:21<00:05, 56.29it/s]
Loading 0:  63%|██████▎   | 485/771 [00:21<00:04, 61.63it/s]
Loading 0:  64%|██████▍   | 496/771 [00:21<00:03, 70.71it/s]
Loading 0:  66%|██████▌   | 508/771 [00:21<00:03, 75.58it/s]
Loading 0:  68%|██████▊   | 521/771 [00:21<00:02, 86.67it/s]
Loading 0:  69%|██████▉   | 531/771 [00:22<00:03, 61.46it/s]
Loading 0:  70%|███████   | 541/771 [00:22<00:03, 68.74it/s]
Loading 0:  71%|███████▏  | 550/771 [00:22<00:03, 68.87it/s]
Loading 0:  72%|███████▏  | 558/771 [00:22<00:03, 67.05it/s]
Loading 0:  74%|███████▍  | 569/771 [00:22<00:02, 71.28it/s]
Loading 0:  76%|███████▌  | 586/771 [00:22<00:02, 69.08it/s]
Loading 0:  77%|███████▋  | 594/771 [00:23<00:02, 59.51it/s]
Loading 0:  78%|███████▊  | 605/771 [00:23<00:02, 64.39it/s]
Loading 0:  80%|████████  | 617/771 [00:23<00:02, 70.21it/s]
Loading 0:  81%|████████▏ | 627/771 [00:38<00:59,  2.41it/s]
Loading 0:  83%|████████▎ | 637/771 [00:38<00:40,  3.33it/s]
Loading 0:  84%|████████▍ | 646/771 [00:38<00:28,  4.36it/s]
Loading 0:  85%|████████▍ | 653/771 [00:38<00:22,  5.34it/s]
Loading 0:  86%|████████▋ | 665/771 [00:38<00:13,  8.05it/s]
Loading 0:  88%|████████▊ | 676/771 [00:38<00:08, 11.43it/s]
Loading 0:  89%|████████▉ | 687/771 [00:39<00:05, 15.90it/s]
Loading 0:  91%|█████████ | 698/771 [00:39<00:03, 21.13it/s]
Loading 0:  92%|█████████▏| 707/771 [00:39<00:02, 24.13it/s]
Loading 0:  93%|█████████▎| 715/771 [00:39<00:02, 27.73it/s]
Loading 0:  94%|█████████▍| 725/771 [00:39<00:01, 34.45it/s]
Loading 0:  96%|█████████▌| 737/771 [00:39<00:00, 43.64it/s]
Loading 0:  97%|█████████▋| 749/771 [00:40<00:00, 52.41it/s]
Loading 0:  99%|█████████▉| 766/771 [00:47<00:00,  5.10it/s]
                                                            
Job chaiml-qwen32b-simpoexp-21972-v5-mkmlizer completed after 208.22s with status: succeeded
Stopping job with name chaiml-qwen32b-simpoexp-21972-v5-mkmlizer
Pipeline stage MKMLizer completed in 208.71s
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 chaiml-qwen32b-simpoexp-21972-v5
Waiting for inference service chaiml-qwen32b-simpoexp-21972-v5 to be ready
Inference service chaiml-qwen32b-simpoexp-21972-v5 ready after 140.4888665676117s
Pipeline stage MKMLDeployer completed in 141.01s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.118086338043213s
Received healthy response to inference request in 2.848647117614746s
Received healthy response to inference request in 2.828308582305908s
Received healthy response to inference request in 2.5788207054138184s
Received healthy response to inference request in 2.741184711456299s
5 requests
0 failed requests
5th percentile: 2.6112935066223146
10th percentile: 2.6437663078308105
20th percentile: 2.7087119102478026
30th percentile: 2.758609485626221
40th percentile: 2.7934590339660645
50th percentile: 2.828308582305908
60th percentile: 2.8364439964294434
70th percentile: 2.8445794105529787
80th percentile: 2.9025349617004395
90th percentile: 3.010310649871826
95th percentile: 3.0641984939575195
99th percentile: 3.107308769226074
mean time: 2.823009490966797
Pipeline stage StressChecker completed in 15.36s
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 0.62s
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 0.64s
Shutdown handler de-registered
chaiml-qwen32b-simpoexp_21972_v5 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 0.09s
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 chaiml-qwen32b-simpoexp-21972-v5-profiler
Waiting for inference service chaiml-qwen32b-simpoexp-21972-v5-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 3204.95s
Shutdown handler de-registered
chaiml-qwen32b-simpoexp_21972_v5 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen32b-simpoexp_21972_v5 status is now torndown due to DeploymentManager action