developer_uid: NischayDnk
submission_id: chaiml-qwen32brpmax-ret_60943_v1
model_name: chaiml-qwen32brpmax-ret_60943_v1
model_group: ChaiML/qwen32brpmax-retr
status: torndown
timestamp: 2025-05-05T03:55:53+00:00
num_battles: 10441
num_wins: 5061
celo_rating: 1274.05
family_friendly_score: 0.5956
family_friendly_standard_error: 0.006940614382026997
submission_type: basic
model_repo: ChaiML/qwen32brpmax-retryv2-lexicaltop50-sftexp1-1
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': 0.3864089443841035, 'latency_mean': 2.587875759601593, 'latency_p50': 2.6009438037872314, 'latency_p90': 2.876116490364075}, {'batch_size': 3, 'throughput': 0.8708020119885902, 'latency_mean': 3.435815031528473, 'latency_p50': 3.4379340410232544, 'latency_p90': 3.769310712814331}, {'batch_size': 5, 'throughput': 1.1961469725256113, 'latency_mean': 4.171183372735977, 'latency_p50': 4.164974212646484, 'latency_p90': 4.711270117759705}, {'batch_size': 6, 'throughput': 1.3039856516759778, 'latency_mean': 4.583670210838318, 'latency_p50': 4.571977853775024, 'latency_p90': 5.09637303352356}, {'batch_size': 8, 'throughput': 1.4642751027013816, 'latency_mean': 5.389735236167907, 'latency_p50': 5.398137927055359, 'latency_p90': 5.961699891090393}, {'batch_size': 10, 'throughput': 1.5983502867112165, 'latency_mean': 6.1867066872119905, 'latency_p50': 6.1695332527160645, 'latency_p90': 6.986004066467285}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-qwen32brpmax-ret_60943_v1
is_internal_developer: False
language_model: ChaiML/qwen32brpmax-retryv2-lexicaltop50-sftexp1-1
model_size: 33B
ranking_group: single
throughput_3p7s: 1.01
us_pacific_date: 2025-05-04
win_ratio: 0.48472368547074035
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': ['<|im_start|>', '\n', '<|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-qwen32brpmax-ret-60943-v1-mkmlizer
Waiting for job on chaiml-qwen32brpmax-ret-60943-v1-mkmlizer to finish
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: ║ _____ __ __ ║
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: ║ /___/ ║
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: ║ ║
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: ║ ║
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: ║ belonging to: ║
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: ║ ║
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: ║ ║
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: Downloaded to shared memory in 111.148s
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpeffuyteb, device:0
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: quantized model in 63.827s
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: Processed model ChaiML/qwen32brpmax-retryv2-lexicaltop50-sftexp1-1 in 174.975s
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen32brpmax-ret-60943-v1
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen32brpmax-ret-60943-v1/config.json
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen32brpmax-ret-60943-v1/added_tokens.json
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen32brpmax-ret-60943-v1/vocab.json
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen32brpmax-ret-60943-v1/tokenizer.json
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-qwen32brpmax-ret-60943-v1/flywheel_model.2.safetensors
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen32brpmax-ret-60943-v1/flywheel_model.1.safetensors
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen32brpmax-ret-60943-v1/flywheel_model.0.safetensors
chaiml-qwen32brpmax-ret-60943-v1-mkmlizer: Loading 0: 0%| | 0/771 [00:00<?, ?it/s] Loading 0: 1%| | 5/771 [00:00<00:18, 41.30it/s] Loading 0: 2%|▏ | 17/771 [00:00<00:10, 69.78it/s] Loading 0: 4%|▍ | 29/771 [00:00<00:09, 77.80it/s] Loading 0: 6%|▌ | 46/771 [00:00<00:11, 65.75it/s] Loading 0: 7%|▋ | 53/771 [00:00<00:13, 54.78it/s] Loading 0: 8%|▊ | 64/771 [00:00<00:10, 66.06it/s] Loading 0: 10%|▉ | 76/771 [00:01<00:09, 72.01it/s] Loading 0: 11%|█▏ | 88/771 [00:01<00:08, 76.68it/s] Loading 0: 13%|█▎ | 100/771 [00:01<00:07, 86.74it/s] Loading 0: 14%|█▍ | 110/771 [00:01<00:11, 58.47it/s] Loading 0: 16%|█▌ | 121/771 [00:01<00:10, 64.36it/s] Loading 0: 17%|█▋ | 133/771 [00:01<00:08, 71.28it/s] Loading 0: 20%|█▉ | 151/771 [00:02<00:06, 91.38it/s] Loading 0: 21%|██ | 162/771 [00:02<00:07, 82.40it/s] Loading 0: 22%|██▏ | 172/771 [00:02<00:10, 55.92it/s] Loading 0: 24%|██▍ | 184/771 [00:02<00:09, 62.71it/s] Loading 0: 25%|██▌ | 196/771 [00:02<00:08, 68.71it/s] Loading 0: 27%|██▋ | 208/771 [00:02<00:07, 73.27it/s] Loading 0: 28%|██▊ | 218/771 [00:03<00:07, 78.74it/s] Loading 0: 29%|██▉ | 227/771 [00:03<00:08, 61.93it/s] Loading 0: 30%|███ | 235/771 [00:03<00:09, 58.40it/s] Loading 0: 32%|███▏ | 245/771 [00:03<00:08, 62.12it/s] Loading 0: 33%|███▎ | 257/771 [00:03<00:07, 68.81it/s] Loading 0: 35%|███▍ | 269/771 [00:03<00:06, 73.40it/s] Loading 0: 37%|███▋ | 286/771 [00:04<00:06, 70.43it/s] Loading 0: 38%|███▊ | 294/771 [00:04<00:07, 60.07it/s] Loading 0: 39%|███▉ | 303/771 [00:18<03:15, 2.39it/s] Loading 0: 41%|████ | 315/771 [00:18<02:10, 3.50it/s] Loading 0: 42%|████▏ | 327/771 [00:19<01:28, 5.03it/s] Loading 0: 44%|████▍ | 338/771 [00:19<01:02, 6.94it/s] Loading 0: 45%|████▍ | 346/771 [00:19<00:49, 8.55it/s] Loading 0: 46%|████▌ | 353/771 [00:19<00:42, 9.88it/s] Loading 0: 47%|████▋ | 365/771 [00:19<00:28, 14.44it/s] Loading 0: 49%|████▉ | 377/771 [00:20<00:19, 20.11it/s] Loading 0: 50%|█████ | 389/771 [00:20<00:14, 26.84it/s] Loading 0: 53%|█████▎ | 406/771 [00:20<00:10, 35.16it/s] Loading 0: 54%|█████▎ | 414/771 [00:20<00:09, 36.00it/s] Loading 0: 55%|█████▌ | 425/771 [00:20<00:08, 43.06it/s] Loading 0: 57%|█████▋ | 437/771 [00:20<00:06, 51.32it/s] Loading 0: 58%|█████▊ | 449/771 [00:21<00:05, 59.02it/s] Loading 0: 60%|██████ | 466/771 [00:21<00:04, 61.16it/s] Loading 0: 61%|██████▏ | 474/771 [00:21<00:05, 54.79it/s] Loading 0: 63%|██████▎ | 485/771 [00:21<00:04, 60.16it/s] Loading 0: 64%|██████▍ | 497/771 [00:21<00:04, 66.48it/s] Loading 0: 66%|██████▌ | 509/771 [00:21<00:03, 71.62it/s] Loading 0: 68%|██████▊ | 526/771 [00:22<00:03, 67.80it/s] Loading 0: 69%|██████▉ | 534/771 [00:22<00:04, 58.95it/s] Loading 0: 71%|███████ | 544/771 [00:22<00:03, 66.02it/s] Loading 0: 72%|███████▏ | 556/771 [00:22<00:03, 71.66it/s] Loading 0: 74%|███████▎ | 568/771 [00:22<00:02, 76.50it/s] Loading 0: 75%|███████▌ | 579/771 [00:22<00:02, 83.63it/s] Loading 0: 76%|███████▋ | 588/771 [00:23<00:03, 60.37it/s] Loading 0: 77%|███████▋ | 596/771 [00:23<00:02, 60.90it/s] Loading 0: 78%|███████▊ | 605/771 [00:23<00:02, 62.60it/s] Loading 0: 80%|████████ | 617/771 [00:23<00:02, 70.01it/s] Loading 0: 81%|████████▏ | 627/771 [00:38<01:04, 2.23it/s] Loading 0: 83%|████████▎ | 638/771 [00:38<00:41, 3.22it/s] Loading 0: 84%|████████▍ | 646/771 [00:38<00:30, 4.15it/s] Loading 0: 85%|████████▍ | 653/771 [00:39<00:22, 5.13it/s] Loading 0: 86%|████████▋ | 665/771 [00:39<00:13, 7.84it/s] Loading 0: 88%|████████▊ | 677/771 [00:39<00:08, 11.41it/s] Loading 0: 89%|████████▉ | 689/771 [00:39<00:05, 16.05it/s] Loading 0: 92%|█████████▏| 706/771 [00:39<00:02, 23.35it/s] Loading 0: 93%|█████████▎| 714/771 [00:39<00:02, 25.57it/s] Loading 0: 94%|█████████▍| 725/771 [00:40<00:01, 32.31it/s] Loading 0: 96%|█████████▌| 737/771 [00:40<00:00, 40.60it/s] Loading 0: 97%|█████████▋| 749/771 [00:40<00:00, 48.73it/s] Loading 0: 99%|█████████▉| 766/771 [00:48<00:00, 5.20it/s]
Job chaiml-qwen32brpmax-ret-60943-v1-mkmlizer completed after 207.23s with status: succeeded
Stopping job with name chaiml-qwen32brpmax-ret-60943-v1-mkmlizer
Pipeline stage MKMLizer completed in 207.74s
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-qwen32brpmax-ret-60943-v1
Waiting for inference service chaiml-qwen32brpmax-ret-60943-v1 to be ready
Unable to record family friendly update due to error: Invalid JSON input: JSON must contain 'User Safety' and 'Response Safety' fields
Inference service chaiml-qwen32brpmax-ret-60943-v1 ready after 140.5711317062378s
Pipeline stage MKMLDeployer completed in 141.15s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.446744441986084s
Received healthy response to inference request in 2.745875835418701s
Received healthy response to inference request in 2.724125623703003s
Received healthy response to inference request in 2.4483532905578613s
Received healthy response to inference request in 2.76772141456604s
5 requests
0 failed requests
5th percentile: 2.5035077571868896
10th percentile: 2.558662223815918
20th percentile: 2.6689711570739747
30th percentile: 2.7284756660461427
40th percentile: 2.7371757507324217
50th percentile: 2.745875835418701
60th percentile: 2.754614067077637
70th percentile: 2.763352298736572
80th percentile: 2.903526020050049
90th percentile: 3.1751352310180665
95th percentile: 3.310939836502075
99th percentile: 3.419583520889282
mean time: 2.8265641212463377
Pipeline stage StressChecker completed in 15.46s
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 0.75s
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 1.49s
Shutdown handler de-registered
chaiml-qwen32brpmax-ret_60943_v1 status is now deployed due to DeploymentManager action
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 5284.83s
Shutdown handler de-registered
chaiml-qwen32brpmax-ret_60943_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen32brpmax-ret_60943_v1 status is now torndown due to DeploymentManager action