developer_uid: NischayDnk
submission_id: chaiml-qwen25-32b-sftmo_55653_v3
model_name: chaiml-qwen25-32b-sftmo_55653_v3
model_group: ChaiML/qwen25-32b-sftmor
status: torndown
timestamp: 2025-05-13T21:54:08+00:00
num_battles: 9548
num_wins: 4779
celo_rating: 1272.67
family_friendly_score: 0.569
family_friendly_standard_error: 0.007003413453452538
submission_type: basic
model_repo: ChaiML/qwen25-32b-sftmorelora-retryv2-top20k-maskprompt-2e
model_architecture: Qwen2ForCausalLM
model_num_parameters: 32763417600.0
best_of: 5
max_input_tokens: 768
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.386965977363822, 'latency_mean': 2.5841506445407867, 'latency_p50': 2.584969162940979, 'latency_p90': 2.8812428951263427}, {'batch_size': 3, 'throughput': 0.8671343188590186, 'latency_mean': 3.4503077161312103, 'latency_p50': 3.4504947662353516, 'latency_p90': 3.7952553272247314}, {'batch_size': 5, 'throughput': 1.1790793300391222, 'latency_mean': 4.203234145641327, 'latency_p50': 4.180244565010071, 'latency_p90': 4.695051264762879}, {'batch_size': 6, 'throughput': 1.2896440069223527, 'latency_mean': 4.617326053380967, 'latency_p50': 4.605523705482483, 'latency_p90': 5.2255047082901}, {'batch_size': 8, 'throughput': 1.472260730734784, 'latency_mean': 5.399797590970993, 'latency_p50': 5.412125110626221, 'latency_p90': 5.993743872642517}, {'batch_size': 10, 'throughput': 1.5744360241850004, 'latency_mean': 6.27701811671257, 'latency_p50': 6.304771184921265, 'latency_p90': 7.066130685806274}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-qwen25-32b-sftmo_55653_v3
is_internal_developer: False
language_model: ChaiML/qwen25-32b-sftmorelora-retryv2-top20k-maskprompt-2e
model_size: 33B
ranking_group: single
throughput_3p7s: 0.99
us_pacific_date: 2025-05-13
win_ratio: 0.5005236698785086
generation_params: {'temperature': 0.9, '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-qwen25-32b-sftmo-55653-v3-mkmlizer
Waiting for job on chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer to finish
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: ║ _____ __ __ ║
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: ║ /___/ ║
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: ║ ║
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: ║ Version: 0.12.8 ║
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: ║ https://mk1.ai ║
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: ║ ║
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: ║ belonging to: ║
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: ║ ║
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: ║ Chai Research Corp. ║
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: ║ ║
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: Downloaded to shared memory in 109.578s
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9xmps07z, device:0
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: quantized model in 63.985s
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: Processed model ChaiML/qwen25-32b-sftmorelora-retryv2-top20k-maskprompt-2e in 173.564s
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen25-32b-sftmo-55653-v3
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen25-32b-sftmo-55653-v3/config.json
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen25-32b-sftmo-55653-v3/added_tokens.json
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen25-32b-sftmo-55653-v3/tokenizer_config.json
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen25-32b-sftmo-55653-v3/special_tokens_map.json
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen25-32b-sftmo-55653-v3/merges.txt
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen25-32b-sftmo-55653-v3/vocab.json
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen25-32b-sftmo-55653-v3/tokenizer.json
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-qwen25-32b-sftmo-55653-v3/flywheel_model.2.safetensors
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen25-32b-sftmo-55653-v3/flywheel_model.0.safetensors
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen25-32b-sftmo-55653-v3/flywheel_model.1.safetensors
chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer: Loading 0: 0%| | 0/771 [00:00<?, ?it/s] Loading 0: 1%| | 5/771 [00:00<00:19, 39.15it/s] Loading 0: 2%|▏ | 16/771 [00:00<00:09, 75.71it/s] Loading 0: 4%|▎ | 27/771 [00:00<00:08, 88.94it/s] Loading 0: 5%|▍ | 37/771 [00:00<00:08, 91.08it/s] Loading 0: 6%|▌ | 47/771 [00:00<00:14, 51.70it/s] Loading 0: 7%|▋ | 54/771 [00:00<00:14, 48.50it/s] Loading 0: 8%|▊ | 64/771 [00:01<00:12, 57.38it/s] Loading 0: 10%|▉ | 75/771 [00:01<00:10, 68.90it/s] Loading 0: 11%|█ | 84/771 [00:01<00:09, 73.79it/s] Loading 0: 12%|█▏ | 93/771 [00:01<00:09, 71.47it/s] Loading 0: 14%|█▎ | 106/771 [00:01<00:10, 60.97it/s] Loading 0: 15%|█▍ | 113/771 [00:01<00:11, 58.71it/s] Loading 0: 16%|█▌ | 121/771 [00:01<00:10, 59.68it/s] Loading 0: 17%|█▋ | 132/771 [00:02<00:09, 70.44it/s] Loading 0: 18%|█▊ | 142/771 [00:02<00:08, 77.02it/s] Loading 0: 20%|█▉ | 152/771 [00:02<00:07, 82.63it/s] Loading 0: 21%|██ | 161/771 [00:02<00:07, 77.11it/s] Loading 0: 22%|██▏ | 170/771 [00:02<00:10, 55.03it/s] Loading 0: 23%|██▎ | 177/771 [00:02<00:10, 54.69it/s] Loading 0: 24%|██▍ | 185/771 [00:02<00:10, 56.51it/s] Loading 0: 25%|██▌ | 196/771 [00:03<00:08, 68.35it/s] Loading 0: 27%|██▋ | 207/771 [00:03<00:07, 77.64it/s] Loading 0: 28%|██▊ | 216/771 [00:03<00:06, 80.64it/s] Loading 0: 29%|██▉ | 226/771 [00:03<00:08, 61.25it/s] Loading 0: 30%|███ | 234/771 [00:03<00:10, 52.96it/s] Loading 0: 32%|███▏ | 245/771 [00:03<00:08, 59.63it/s] Loading 0: 33%|███▎ | 256/771 [00:03<00:07, 69.92it/s] Loading 0: 35%|███▍ | 267/771 [00:04<00:06, 79.06it/s] Loading 0: 36%|███▌ | 277/771 [00:04<00:05, 83.96it/s] Loading 0: 37%|███▋ | 287/771 [00:04<00:08, 59.58it/s] Loading 0: 38%|███▊ | 295/771 [00:04<00:08, 56.52it/s] Loading 0: 39%|███▉ | 303/771 [00:18<03:48, 2.05it/s] Loading 0: 41%|████ | 314/771 [00:19<02:28, 3.08it/s] Loading 0: 42%|████▏ | 322/771 [00:19<01:49, 4.10it/s] Loading 0: 43%|████▎ | 330/771 [00:19<01:20, 5.50it/s] Loading 0: 45%|████▍ | 346/771 [00:19<00:46, 9.08it/s] Loading 0: 46%|████▌ | 353/771 [00:19<00:40, 10.37it/s] Loading 0: 47%|████▋ | 365/771 [00:20<00:27, 14.88it/s] Loading 0: 49%|████▉ | 377/771 [00:20<00:19, 20.48it/s] Loading 0: 50%|█████ | 388/771 [00:20<00:14, 27.13it/s] Loading 0: 52%|█████▏ | 399/771 [00:20<00:10, 35.02it/s] Loading 0: 53%|█████▎ | 408/771 [00:20<00:10, 33.88it/s] Loading 0: 54%|█████▍ | 416/771 [00:20<00:09, 38.21it/s] Loading 0: 55%|█████▌ | 425/771 [00:20<00:07, 43.43it/s] Loading 0: 57%|█████▋ | 436/771 [00:21<00:06, 54.03it/s] Loading 0: 58%|█████▊ | 447/771 [00:21<00:05, 64.05it/s] Loading 0: 59%|█████▉ | 456/771 [00:21<00:04, 69.47it/s] Loading 0: 60%|██████ | 466/771 [00:21<00:05, 57.58it/s] Loading 0: 61%|██████▏ | 474/771 [00:21<00:05, 51.15it/s] Loading 0: 63%|██████▎ | 485/771 [00:21<00:04, 58.05it/s] Loading 0: 64%|██████▍ | 497/771 [00:21<00:04, 65.53it/s] Loading 0: 66%|██████▌ | 509/771 [00:22<00:03, 70.96it/s] Loading 0: 68%|██████▊ | 526/771 [00:22<00:03, 68.23it/s] Loading 0: 69%|██████▉ | 534/771 [00:22<00:04, 58.75it/s] Loading 0: 71%|███████ | 545/771 [00:22<00:03, 63.44it/s] Loading 0: 72%|███████▏ | 557/771 [00:22<00:03, 69.15it/s] Loading 0: 74%|███████▍ | 569/771 [00:23<00:02, 73.46it/s] Loading 0: 76%|███████▌ | 586/771 [00:23<00:02, 70.13it/s] Loading 0: 77%|███████▋ | 594/771 [00:23<00:02, 60.01it/s] Loading 0: 78%|███████▊ | 605/771 [00:23<00:02, 64.73it/s] Loading 0: 80%|███████▉ | 616/771 [00:23<00:02, 73.52it/s] Loading 0: 81%|████████▏ | 627/771 [00:38<00:58, 2.47it/s] Loading 0: 83%|████████▎ | 638/771 [00:38<00:38, 3.47it/s] Loading 0: 84%|████████▍ | 647/771 [00:39<00:27, 4.44it/s] Loading 0: 85%|████████▍ | 654/771 [00:39<00:21, 5.53it/s] Loading 0: 86%|████████▋ | 665/771 [00:39<00:13, 8.01it/s] Loading 0: 88%|████████▊ | 676/771 [00:39<00:08, 11.42it/s] Loading 0: 89%|████████▉ | 688/771 [00:39<00:05, 16.08it/s] Loading 0: 91%|█████████ | 698/771 [00:39<00:03, 21.12it/s] Loading 0: 92%|█████████▏| 707/771 [00:39<00:02, 23.65it/s] Loading 0: 93%|█████████▎| 715/771 [00:40<00:02, 27.21it/s] Loading 0: 94%|█████████▍| 725/771 [00:40<00:01, 33.79it/s] Loading 0: 95%|█████████▌| 736/771 [00:40<00:00, 43.61it/s] Loading 0: 97%|█████████▋| 748/771 [00:40<00:00, 52.40it/s] Loading 0: 98%|█████████▊| 759/771 [00:40<00:00, 62.24it/s] Loading 0: 100%|█████████▉| 768/771 [00:48<00:00, 4.13it/s]
Job chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer completed after 206.77s with status: succeeded
Stopping job with name chaiml-qwen25-32b-sftmo-55653-v3-mkmlizer
Pipeline stage MKMLizer completed in 207.33s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-qwen25-32b-sftmo-55653-v3
Waiting for inference service chaiml-qwen25-32b-sftmo-55653-v3 to be ready
Inference service chaiml-qwen25-32b-sftmo-55653-v3 ready after 130.52963757514954s
Pipeline stage MKMLDeployer completed in 131.10s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.358116388320923s
Received healthy response to inference request in 2.7553536891937256s
Received healthy response to inference request in 2.5409064292907715s
Received healthy response to inference request in 2.919081926345825s
Received healthy response to inference request in 2.538224458694458s
5 requests
0 failed requests
5th percentile: 2.538760852813721
10th percentile: 2.5392972469329833
20th percentile: 2.5403700351715086
30th percentile: 2.5837958812713624
40th percentile: 2.6695747852325438
50th percentile: 2.7553536891937256
60th percentile: 2.8208449840545655
70th percentile: 2.8863362789154055
80th percentile: 3.006888818740845
90th percentile: 3.182502603530884
95th percentile: 3.270309495925903
99th percentile: 3.340555009841919
mean time: 2.8223365783691405
Pipeline stage StressChecker completed in 15.48s
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 0.66s
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
chaiml-qwen25-32b-sftmo_55653_v3 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-qwen25-32b-sftmo-55653-v3-profiler
Waiting for inference service chaiml-qwen25-32b-sftmo-55653-v3-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 3321.82s
Shutdown handler de-registered
chaiml-qwen25-32b-sftmo_55653_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen25-32b-sftmo_55653_v3 status is now torndown due to DeploymentManager action