developer_uid: NischayDnk
submission_id: chaiml-qwen32brpmax-ret_99687_v1
model_name: chaiml-qwen32brpmax-ret_99687_v1
model_group: ChaiML/qwen32brpmax-retr
status: torndown
timestamp: 2025-05-05T08:44:32+00:00
num_battles: 8563
num_wins: 4226
celo_rating: 1283.46
family_friendly_score: 0.5642
family_friendly_standard_error: 0.0070125367735221185
submission_type: basic
model_repo: ChaiML/qwen32brpmax-retryv2-sfts2-prefsftlextop50-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': 0.390660912334931, 'latency_mean': 2.559699295759201, 'latency_p50': 2.5487422943115234, 'latency_p90': 2.844329905509949}, {'batch_size': 3, 'throughput': 0.8791703260169044, 'latency_mean': 3.3984312319755556, 'latency_p50': 3.357669234275818, 'latency_p90': 3.7741775512695312}, {'batch_size': 5, 'throughput': 1.189204030901362, 'latency_mean': 4.172442177534103, 'latency_p50': 4.166434645652771, 'latency_p90': 4.697783374786377}, {'batch_size': 6, 'throughput': 1.3258934186256197, 'latency_mean': 4.50361505150795, 'latency_p50': 4.466479182243347, 'latency_p90': 5.028856611251831}, {'batch_size': 8, 'throughput': 1.490946712562055, 'latency_mean': 5.3192642879486085, 'latency_p50': 5.302827596664429, 'latency_p90': 5.967495083808899}, {'batch_size': 10, 'throughput': 1.6284310757294467, 'latency_mean': 6.060690220594406, 'latency_p50': 6.112627625465393, 'latency_p90': 6.86517915725708}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-qwen32brpmax-ret_99687_v1
is_internal_developer: False
language_model: ChaiML/qwen32brpmax-retryv2-sfts2-prefsftlextop50-sftexp1-1
model_size: 33B
ranking_group: single
throughput_3p7s: 1.02
us_pacific_date: 2025-05-05
win_ratio: 0.4935186266495387
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|>', '<|im_end|>', '\n'], '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-99687-v1-mkmlizer
Waiting for job on chaiml-qwen32brpmax-ret-99687-v1-mkmlizer to finish
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: ║ _____ __ __ ║
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: ║ /___/ ║
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: ║ ║
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: ║ ║
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: ║ belonging to: ║
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: ║ ║
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: ║ ║
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: Downloaded to shared memory in 104.073s
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0apncdrk, device:0
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: quantized model in 64.645s
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: Processed model ChaiML/qwen32brpmax-retryv2-sfts2-prefsftlextop50-sftexp1-1 in 168.719s
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen32brpmax-ret-99687-v1
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen32brpmax-ret-99687-v1/config.json
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen32brpmax-ret-99687-v1/added_tokens.json
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen32brpmax-ret-99687-v1/special_tokens_map.json
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen32brpmax-ret-99687-v1/tokenizer_config.json
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen32brpmax-ret-99687-v1/merges.txt
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen32brpmax-ret-99687-v1/vocab.json
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen32brpmax-ret-99687-v1/tokenizer.json
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-qwen32brpmax-ret-99687-v1/flywheel_model.2.safetensors
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen32brpmax-ret-99687-v1/flywheel_model.1.safetensors
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen32brpmax-ret-99687-v1/flywheel_model.0.safetensors
chaiml-qwen32brpmax-ret-99687-v1-mkmlizer: Loading 0: 0%| | 0/771 [00:00<?, ?it/s] Loading 0: 1%| | 5/771 [00:00<00:20, 37.18it/s] Loading 0: 2%|▏ | 16/771 [00:00<00:10, 71.86it/s] Loading 0: 4%|▎ | 27/771 [00:00<00:08, 85.44it/s] Loading 0: 5%|▍ | 36/771 [00:00<00:08, 85.49it/s] Loading 0: 6%|▌ | 46/771 [00:00<00:13, 53.32it/s] Loading 0: 7%|▋ | 53/771 [00:00<00:15, 45.27it/s] Loading 0: 8%|▊ | 64/771 [00:01<00:12, 57.83it/s] Loading 0: 10%|▉ | 75/771 [00:01<00:10, 68.37it/s] Loading 0: 11%|█ | 84/771 [00:01<00:09, 72.63it/s] Loading 0: 12%|█▏ | 93/771 [00:01<00:09, 69.60it/s] Loading 0: 14%|█▎ | 106/771 [00:01<00:11, 59.34it/s] Loading 0: 15%|█▍ | 113/771 [00:01<00:11, 57.00it/s] Loading 0: 16%|█▌ | 121/771 [00:01<00:11, 57.24it/s] Loading 0: 17%|█▋ | 132/771 [00:02<00:09, 67.62it/s] Loading 0: 18%|█▊ | 142/771 [00:02<00:08, 74.19it/s] Loading 0: 20%|█▉ | 152/771 [00:02<00:07, 79.24it/s] Loading 0: 21%|██ | 161/771 [00:02<00:08, 74.43it/s] Loading 0: 22%|██▏ | 169/771 [00:02<00:12, 49.35it/s] Loading 0: 23%|██▎ | 176/771 [00:02<00:11, 50.42it/s] Loading 0: 24%|██▍ | 185/771 [00:03<00:10, 53.98it/s] Loading 0: 25%|██▌ | 196/771 [00:03<00:08, 65.21it/s] Loading 0: 27%|██▋ | 207/771 [00:03<00:07, 74.90it/s] Loading 0: 28%|██▊ | 216/771 [00:03<00:07, 78.13it/s] Loading 0: 29%|██▉ | 226/771 [00:03<00:09, 59.79it/s] Loading 0: 30%|███ | 234/771 [00:03<00:10, 51.23it/s] Loading 0: 32%|███▏ | 244/771 [00:03<00:08, 60.46it/s] Loading 0: 33%|███▎ | 255/771 [00:04<00:07, 70.48it/s] Loading 0: 34%|███▍ | 264/771 [00:04<00:06, 74.44it/s] Loading 0: 35%|███▌ | 273/771 [00:04<00:06, 71.32it/s] Loading 0: 37%|███▋ | 286/771 [00:04<00:07, 61.25it/s] Loading 0: 38%|███▊ | 293/771 [00:04<00:09, 51.47it/s] Loading 0: 39%|███▉ | 303/771 [00:19<03:38, 2.14it/s] Loading 0: 40%|████ | 311/771 [00:19<02:39, 2.88it/s] Loading 0: 41%|████ | 318/771 [00:19<02:00, 3.76it/s] Loading 0: 43%|████▎ | 328/771 [00:19<01:19, 5.55it/s] Loading 0: 44%|████▍ | 338/771 [00:19<00:54, 7.98it/s] Loading 0: 45%|████▍ | 346/771 [00:19<00:42, 9.98it/s] Loading 0: 46%|████▌ | 353/771 [00:20<00:36, 11.55it/s] Loading 0: 47%|████▋ | 364/771 [00:20<00:23, 17.06it/s] Loading 0: 49%|████▊ | 375/771 [00:20<00:16, 23.86it/s] Loading 0: 50%|████▉ | 383/771 [00:20<00:13, 29.19it/s] Loading 0: 51%|█████ | 391/771 [00:20<00:11, 34.24it/s] Loading 0: 53%|█████▎ | 406/771 [00:21<00:09, 40.02it/s] Loading 0: 54%|█████▎ | 413/771 [00:21<00:09, 38.16it/s] Loading 0: 55%|█████▍ | 424/771 [00:21<00:07, 48.47it/s] Loading 0: 56%|█████▋ | 435/771 [00:21<00:05, 58.61it/s] Loading 0: 58%|█████▊ | 444/771 [00:21<00:05, 64.40it/s] Loading 0: 59%|█████▉ | 453/771 [00:21<00:04, 64.92it/s] Loading 0: 60%|██████ | 466/771 [00:21<00:05, 58.71it/s] Loading 0: 61%|██████▏ | 474/771 [00:22<00:05, 51.72it/s] Loading 0: 63%|██████▎ | 485/771 [00:22<00:04, 58.12it/s] Loading 0: 64%|██████▍ | 496/771 [00:22<00:04, 67.56it/s] Loading 0: 66%|██████▌ | 507/771 [00:22<00:03, 76.32it/s] Loading 0: 67%|██████▋ | 516/771 [00:22<00:03, 79.21it/s] Loading 0: 68%|██████▊ | 526/771 [00:22<00:04, 60.82it/s] Loading 0: 69%|██████▉ | 534/771 [00:23<00:04, 52.15it/s] Loading 0: 71%|███████ | 545/771 [00:23<00:03, 58.60it/s] Loading 0: 72%|███████▏ | 556/771 [00:23<00:03, 68.35it/s] Loading 0: 74%|███████▎ | 567/771 [00:23<00:02, 76.92it/s] Loading 0: 75%|███████▍ | 576/771 [00:23<00:02, 78.89it/s] Loading 0: 76%|███████▌ | 586/771 [00:23<00:03, 61.53it/s] Loading 0: 77%|███████▋ | 594/771 [00:23<00:03, 52.86it/s] Loading 0: 78%|███████▊ | 605/771 [00:24<00:02, 59.23it/s] Loading 0: 80%|███████▉ | 616/771 [00:24<00:02, 68.74it/s] Loading 0: 81%|████████▏ | 627/771 [00:39<01:02, 2.29it/s] Loading 0: 82%|████████▏ | 635/771 [00:39<00:45, 3.01it/s] Loading 0: 84%|████████▍ | 646/771 [00:39<00:29, 4.28it/s] Loading 0: 85%|████████▍ | 653/771 [00:39<00:22, 5.26it/s] Loading 0: 86%|████████▌ | 664/771 [00:39<00:13, 7.77it/s] Loading 0: 88%|████████▊ | 675/771 [00:40<00:08, 11.13it/s] Loading 0: 89%|████████▊ | 683/771 [00:40<00:06, 14.22it/s] Loading 0: 90%|████████▉ | 691/771 [00:40<00:04, 17.91it/s] Loading 0: 92%|█████████▏| 706/771 [00:40<00:02, 24.59it/s] Loading 0: 92%|█████████▏| 713/771 [00:40<00:02, 26.01it/s] Loading 0: 94%|█████████▍| 724/771 [00:40<00:01, 34.56it/s] Loading 0: 95%|█████████▌| 735/771 [00:41<00:00, 44.12it/s] Loading 0: 96%|█████████▋| 744/771 [00:41<00:00, 51.04it/s] Loading 0: 98%|█████████▊| 753/771 [00:41<00:00, 53.61it/s] Loading 0: 99%|█████████▉| 766/771 [00:49<00:01, 4.29it/s]
Job chaiml-qwen32brpmax-ret-99687-v1-mkmlizer completed after 207.5s with status: succeeded
Stopping job with name chaiml-qwen32brpmax-ret-99687-v1-mkmlizer
Pipeline stage MKMLizer completed in 208.03s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-qwen32brpmax-ret-99687-v1
Waiting for inference service chaiml-qwen32brpmax-ret-99687-v1 to be ready
Inference service chaiml-qwen32brpmax-ret-99687-v1 ready after 150.71810579299927s
Pipeline stage MKMLDeployer completed in 151.19s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0814924240112305s
Received healthy response to inference request in 2.493154764175415s
Received healthy response to inference request in 2.6493964195251465s
Received healthy response to inference request in 2.47231125831604s
Received healthy response to inference request in 2.5856499671936035s
5 requests
0 failed requests
5th percentile: 2.476479959487915
10th percentile: 2.48064866065979
20th percentile: 2.48898606300354
30th percentile: 2.5116538047790526
40th percentile: 2.5486518859863283
50th percentile: 2.5856499671936035
60th percentile: 2.611148548126221
70th percentile: 2.636647129058838
80th percentile: 2.7358156204223634
90th percentile: 2.9086540222167967
95th percentile: 2.9950732231140136
99th percentile: 3.064208583831787
mean time: 2.656400966644287
Pipeline stage StressChecker completed in 14.45s
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 0.65s
Shutdown handler de-registered
chaiml-qwen32brpmax-ret_99687_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3205.66s
Shutdown handler de-registered
chaiml-qwen32brpmax-ret_99687_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen32brpmax-ret_99687_v1 status is now torndown due to DeploymentManager action