developer_uid: NischayDnk
submission_id: chaiml-qwen32b-simpoexp_21972_v6
model_name: chaiml-qwen32b-simpoexp_21972_v6
model_group: ChaiML/qwen32b-simpoexp1
status: torndown
timestamp: 2025-05-09T19:35:20+00:00
num_battles: 8946
num_wins: 4606
celo_rating: 1295.34
family_friendly_score: 0.4032
family_friendly_standard_error: 0.006937287077813632
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': 0.3884921223893678, 'latency_mean': 2.5739870047569275, 'latency_p50': 2.5604876279830933, 'latency_p90': 2.8614787101745605}, {'batch_size': 3, 'throughput': 0.8802378676926517, 'latency_mean': 3.3940555930137633, 'latency_p50': 3.4044193029403687, 'latency_p90': 3.772055459022522}, {'batch_size': 5, 'throughput': 1.1885770511964802, 'latency_mean': 4.178130017518997, 'latency_p50': 4.162874698638916, 'latency_p90': 4.63807475566864}, {'batch_size': 6, 'throughput': 1.3060498676971468, 'latency_mean': 4.547687847614288, 'latency_p50': 4.567586064338684, 'latency_p90': 5.1235730171203615}, {'batch_size': 8, 'throughput': 1.481849939941025, 'latency_mean': 5.3443683862686155, 'latency_p50': 5.346414685249329, 'latency_p90': 5.921303367614746}, {'batch_size': 10, 'throughput': 1.6223918187310387, 'latency_mean': 6.090635888576507, 'latency_p50': 6.050069093704224, 'latency_p90': 6.91884217262268}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-qwen32b-simpoexp_21972_v6
is_internal_developer: False
language_model: ChaiML/qwen32b-simpoexp1-s2-ftsimpoexp4-1330pref
model_size: 33B
ranking_group: single
throughput_3p7s: 1.02
us_pacific_date: 2025-05-09
win_ratio: 0.514866979655712
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_start|>', '<|im_end|>'], '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-v6-mkmlizer
Waiting for job on chaiml-qwen32b-simpoexp-21972-v6-mkmlizer to finish
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: ║ _____ __ __ ║
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: ║ /___/ ║
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: ║ ║
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: ║ Version: 0.12.8 ║
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: ║ https://mk1.ai ║
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: ║ ║
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: ║ belonging to: ║
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: ║ ║
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: ║ Chai Research Corp. ║
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: ║ ║
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: Downloaded to shared memory in 90.043s
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpoj8zkeyz, device:0
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: quantized model in 64.016s
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: Processed model ChaiML/qwen32b-simpoexp1-s2-ftsimpoexp4-1330pref in 154.060s
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v6
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v6/config.json
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v6/added_tokens.json
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v6/special_tokens_map.json
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v6/tokenizer_config.json
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v6/merges.txt
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v6/vocab.json
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v6/tokenizer.json
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v6/flywheel_model.2.safetensors
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v6/flywheel_model.1.safetensors
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v6/flywheel_model.0.safetensors
chaiml-qwen32b-simpoexp-21972-v6-mkmlizer: Loading 0: 0%| | 0/771 [00:00<?, ?it/s] Loading 0: 1%| | 5/771 [00:00<00:18, 40.73it/s] Loading 0: 2%|▏ | 16/771 [00:00<00:09, 77.32it/s] Loading 0: 4%|▎ | 27/771 [00:00<00:08, 90.69it/s] Loading 0: 5%|▍ | 37/771 [00:00<00:07, 93.72it/s] Loading 0: 6%|▌ | 47/771 [00:00<00:13, 54.97it/s] Loading 0: 7%|▋ | 55/771 [00:00<00:13, 52.79it/s] Loading 0: 8%|▊ | 65/771 [00:01<00:12, 58.21it/s] Loading 0: 10%|▉ | 77/771 [00:01<00:10, 66.25it/s] Loading 0: 11%|█▏ | 88/771 [00:01<00:09, 74.10it/s] Loading 0: 13%|█▎ | 99/771 [00:01<00:08, 82.45it/s] Loading 0: 14%|█▍ | 108/771 [00:01<00:11, 57.93it/s] Loading 0: 15%|█▌ | 119/771 [00:01<00:09, 68.16it/s] Loading 0: 17%|█▋ | 129/771 [00:01<00:08, 75.13it/s] Loading 0: 18%|█▊ | 138/771 [00:02<00:08, 73.35it/s] Loading 0: 20%|█▉ | 151/771 [00:02<00:07, 85.24it/s] Loading 0: 21%|██ | 161/771 [00:02<00:08, 75.07it/s] Loading 0: 22%|██▏ | 170/771 [00:02<00:11, 54.63it/s] Loading 0: 23%|██▎ | 177/771 [00:02<00:10, 54.55it/s] Loading 0: 24%|██▍ | 185/771 [00:02<00:10, 56.18it/s] Loading 0: 26%|██▌ | 197/771 [00:02<00:08, 64.59it/s] Loading 0: 27%|██▋ | 208/771 [00:03<00:07, 74.60it/s] Loading 0: 28%|██▊ | 219/771 [00:03<00:06, 82.67it/s] Loading 0: 30%|██▉ | 228/771 [00:03<00:09, 58.10it/s] Loading 0: 31%|███ | 236/771 [00:03<00:08, 59.45it/s] Loading 0: 32%|███▏ | 245/771 [00:03<00:08, 61.23it/s] Loading 0: 33%|███▎ | 257/771 [00:03<00:07, 68.17it/s] Loading 0: 35%|███▍ | 269/771 [00:04<00:06, 73.02it/s] Loading 0: 37%|███▋ | 286/771 [00:04<00:07, 69.07it/s] Loading 0: 38%|███▊ | 294/771 [00:04<00:08, 59.46it/s] Loading 0: 39%|███▉ | 303/771 [00:19<03:22, 2.31it/s] Loading 0: 41%|████ | 315/771 [00:19<02:14, 3.40it/s] Loading 0: 42%|████▏ | 324/771 [00:19<01:38, 4.53it/s] Loading 0: 43%|████▎ | 332/771 [00:19<01:14, 5.90it/s] Loading 0: 45%|████▍ | 346/771 [00:19<00:47, 8.89it/s] Loading 0: 46%|████▌ | 353/771 [00:20<00:41, 10.18it/s] Loading 0: 47%|████▋ | 365/771 [00:20<00:27, 14.62it/s] Loading 0: 49%|████▉ | 377/771 [00:20<00:19, 20.15it/s] Loading 0: 50%|█████ | 388/771 [00:20<00:14, 26.73it/s] Loading 0: 52%|█████▏ | 398/771 [00:20<00:11, 33.63it/s] Loading 0: 53%|█████▎ | 407/771 [00:20<00:10, 33.84it/s] Loading 0: 54%|█████▍ | 415/771 [00:21<00:09, 36.60it/s] Loading 0: 55%|█████▌ | 425/771 [00:21<00:07, 43.34it/s] Loading 0: 57%|█████▋ | 436/771 [00:21<00:06, 53.85it/s] Loading 0: 58%|█████▊ | 447/771 [00:21<00:05, 64.32it/s] Loading 0: 59%|█████▉ | 457/771 [00:21<00:04, 71.82it/s] Loading 0: 61%|██████ | 467/771 [00:21<00:05, 55.45it/s] Loading 0: 62%|██████▏ | 475/771 [00:21<00:05, 53.63it/s] Loading 0: 63%|██████▎ | 485/771 [00:22<00:04, 58.49it/s] Loading 0: 64%|██████▍ | 497/771 [00:22<00:04, 66.27it/s] Loading 0: 66%|██████▌ | 508/771 [00:22<00:03, 75.56it/s] Loading 0: 67%|██████▋ | 518/771 [00:22<00:03, 81.16it/s] Loading 0: 68%|██████▊ | 527/771 [00:22<00:03, 61.23it/s] Loading 0: 69%|██████▉ | 535/771 [00:22<00:04, 57.57it/s] Loading 0: 71%|███████ | 545/771 [00:22<00:03, 61.31it/s] Loading 0: 72%|███████▏ | 557/771 [00:23<00:03, 68.68it/s] Loading 0: 74%|███████▍ | 569/771 [00:23<00:02, 73.53it/s] Loading 0: 76%|███████▌ | 586/771 [00:23<00:02, 70.20it/s] Loading 0: 77%|███████▋ | 594/771 [00:23<00:02, 59.95it/s] Loading 0: 78%|███████▊ | 604/771 [00:23<00:02, 67.38it/s] Loading 0: 80%|███████▉ | 616/771 [00:23<00:02, 72.70it/s] Loading 0: 81%|████████▏ | 627/771 [00:38<00:58, 2.46it/s] Loading 0: 82%|████████▏ | 635/771 [00:38<00:42, 3.19it/s] Loading 0: 84%|████████▍ | 646/771 [00:39<00:27, 4.51it/s] Loading 0: 85%|████████▍ | 653/771 [00:39<00:21, 5.46it/s] Loading 0: 86%|████████▌ | 664/771 [00:39<00:13, 7.98it/s] Loading 0: 88%|████████▊ | 676/771 [00:39<00:08, 11.59it/s] Loading 0: 89%|████████▉ | 688/771 [00:39<00:05, 16.19it/s] Loading 0: 91%|█████████ | 699/771 [00:39<00:03, 21.77it/s] Loading 0: 92%|█████████▏| 708/771 [00:40<00:02, 23.79it/s] Loading 0: 93%|█████████▎| 716/771 [00:40<00:01, 28.15it/s] Loading 0: 94%|█████████▍| 725/771 [00:40<00:01, 33.74it/s] Loading 0: 95%|█████████▌| 736/771 [00:40<00:00, 43.77it/s] Loading 0: 97%|█████████▋| 747/771 [00:40<00:00, 54.25it/s] Loading 0: 98%|█████████▊| 757/771 [00:40<00:00, 62.64it/s] Loading 0: 99%|█████████▉| 767/771 [00:48<00:00, 4.12it/s]
Job chaiml-qwen32b-simpoexp-21972-v6-mkmlizer completed after 186.73s with status: succeeded
Stopping job with name chaiml-qwen32b-simpoexp-21972-v6-mkmlizer
Pipeline stage MKMLizer completed in 187.22s
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-v6
Waiting for inference service chaiml-qwen32b-simpoexp-21972-v6 to be ready
Inference service chaiml-qwen32b-simpoexp-21972-v6 ready after 130.45681953430176s
Pipeline stage MKMLDeployer completed in 131.22s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.3121509552001953s
Received healthy response to inference request in 2.9626662731170654s
Received healthy response to inference request in 2.5027506351470947s
Received healthy response to inference request in 2.433424472808838s
Received healthy response to inference request in 2.7824461460113525s
5 requests
0 failed requests
5th percentile: 2.4472897052764893
10th percentile: 2.4611549377441406
20th percentile: 2.4888854026794434
30th percentile: 2.558689737319946
40th percentile: 2.6705679416656496
50th percentile: 2.7824461460113525
60th percentile: 2.8545341968536375
70th percentile: 2.926622247695923
80th percentile: 3.0325632095336914
90th percentile: 3.1723570823669434
95th percentile: 3.2422540187835693
99th percentile: 3.29817156791687
mean time: 2.798687696456909
Pipeline stage StressChecker completed in 15.30s
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 0.68s
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 0.97s
Shutdown handler de-registered
chaiml-qwen32b-simpoexp_21972_v6 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
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 3292.57s
Shutdown handler de-registered
chaiml-qwen32b-simpoexp_21972_v6 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen32b-simpoexp_21972_v6 status is now torndown due to DeploymentManager action