chaiml-qwen32b-simpoexp_49898

developer_uid: NischayDnk

submission_id: chaiml-qwen32b-simpoexp_49898_v1

model_name: chaiml-qwen32b-simpoexp_49898_v1

model_group: ChaiML/qwen32b-simpoexp5

status: torndown

timestamp: 2025-04-22T09:55:15+00:00

num_battles: 11287

num_wins: 6472

celo_rating: 1342.48

family_friendly_score: 0.44020000000000004

family_friendly_standard_error: 0.007020312813543282

submission_type: basic

model_repo: ChaiML/qwen32b-simpoexp5-s2-pref1340

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': 0.38568670312680553, 'latency_mean': 2.592722874879837, 'latency_p50': 2.6034083366394043, 'latency_p90': 2.8632868766784667}, {'batch_size': 3, 'throughput': 0.8689145847895937, 'latency_mean': 3.4442766487598417, 'latency_p50': 3.447976231575012, 'latency_p90': 3.8081292629241945}, {'batch_size': 5, 'throughput': 1.1843004896849003, 'latency_mean': 4.1780647122859955, 'latency_p50': 4.145879507064819, 'latency_p90': 4.601008462905884}, {'batch_size': 6, 'throughput': 1.309198065431424, 'latency_mean': 4.549707180261612, 'latency_p50': 4.530921220779419, 'latency_p90': 5.074303865432739}, {'batch_size': 8, 'throughput': 1.4709306137374365, 'latency_mean': 5.3931881713867185, 'latency_p50': 5.3979644775390625, 'latency_p90': 6.063301229476928}, {'batch_size': 10, 'throughput': 1.6131419867411685, 'latency_mean': 6.1397865295410154, 'latency_p50': 6.096864938735962, 'latency_p90': 7.041500234603881}]

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

display_name: chaiml-qwen32b-simpoexp_49898_v1

is_internal_developer: False

language_model: ChaiML/qwen32b-simpoexp5-s2-pref1340

model_size: 33B

ranking_group: single

throughput_3p7s: 1.0

us_pacific_date: 2025-04-22

win_ratio: 0.5734030300345531

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-49898-v1-mkmlizer
Waiting for job on chaiml-qwen32b-simpoexp-49898-v1-mkmlizer to finish
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: ║       /___/                                                         ║
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: ║                                                                     ║
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: ║                                                                     ║
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: ║                                                                     ║
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: ║                                                                     ║
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: Downloaded to shared memory in 110.948s
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpqq1svs2r, device:0
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission blend_ridut_2025-04-14: ('http://rirv938-0sw-96p-4ff-cha-93234-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:48370->127.0.0.1:8080: read: connection reset by peer\n')
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: quantized model in 63.457s
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: Processed model ChaiML/qwen32b-simpoexp5-s2-pref1340 in 174.405s
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-49898-v1
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-49898-v1/config.json
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-49898-v1/added_tokens.json
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-49898-v1/special_tokens_map.json
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-49898-v1/tokenizer_config.json
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-49898-v1/merges.txt
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-49898-v1/vocab.json
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-49898-v1/tokenizer.json
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-49898-v1/flywheel_model.2.safetensors
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-49898-v1/flywheel_model.1.safetensors
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-49898-v1/flywheel_model.0.safetensors
chaiml-qwen32b-simpoexp-49898-v1-mkmlizer: 
Loading 0:   0%|          | 0/771 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/771 [00:00<00:19, 38.69it/s]
Loading 0:   2%|▏         | 16/771 [00:00<00:10, 73.47it/s]
Loading 0:   4%|▎         | 27/771 [00:00<00:08, 86.95it/s]
Loading 0:   5%|▍         | 36/771 [00:00<00:08, 86.83it/s]
Loading 0:   6%|▌         | 46/771 [00:00<00:13, 55.06it/s]
Loading 0:   7%|▋         | 53/771 [00:00<00:15, 46.88it/s]
Loading 0:   8%|▊         | 64/771 [00:01<00:11, 59.50it/s]
Loading 0:  10%|▉         | 75/771 [00:01<00:09, 70.30it/s]
Loading 0:  11%|█         | 84/771 [00:01<00:09, 74.72it/s]
Loading 0:  12%|█▏        | 93/771 [00:01<00:09, 71.72it/s]
Loading 0:  14%|█▎        | 106/771 [00:01<00:10, 62.00it/s]
Loading 0:  15%|█▍        | 114/771 [00:01<00:10, 60.74it/s]
Loading 0:  16%|█▌        | 121/771 [00:01<00:10, 59.14it/s]
Loading 0:  17%|█▋        | 133/771 [00:02<00:09, 67.20it/s]
Loading 0:  20%|█▉        | 151/771 [00:02<00:06, 89.27it/s]
Loading 0:  21%|██        | 161/771 [00:02<00:07, 77.02it/s]
Loading 0:  22%|██▏       | 170/771 [00:02<00:10, 58.25it/s]
Loading 0:  23%|██▎       | 177/771 [00:02<00:10, 56.77it/s]
Loading 0:  24%|██▍       | 185/771 [00:02<00:10, 57.76it/s]
Loading 0:  25%|██▌       | 196/771 [00:02<00:08, 68.39it/s]
Loading 0:  27%|██▋       | 207/771 [00:03<00:07, 77.94it/s]
Loading 0:  28%|██▊       | 216/771 [00:03<00:06, 80.65it/s]
Loading 0:  29%|██▉       | 226/771 [00:03<00:08, 61.83it/s]
Loading 0:  30%|███       | 234/771 [00:03<00:10, 53.29it/s]
Loading 0:  32%|███▏      | 245/771 [00:03<00:08, 59.78it/s]
Loading 0:  33%|███▎      | 256/771 [00:03<00:07, 69.68it/s]
Loading 0:  35%|███▍      | 267/771 [00:03<00:06, 78.59it/s]
Loading 0:  36%|███▌      | 276/771 [00:04<00:06, 81.02it/s]
Loading 0:  37%|███▋      | 286/771 [00:04<00:07, 63.47it/s]
Loading 0:  38%|███▊      | 294/771 [00:04<00:08, 54.14it/s]
Loading 0:  39%|███▉      | 303/771 [00:18<03:41,  2.11it/s]
Loading 0:  40%|████      | 311/771 [00:18<02:40,  2.86it/s]
Loading 0:  41%|████      | 318/771 [00:19<02:00,  3.76it/s]
Loading 0:  43%|████▎     | 329/771 [00:19<01:17,  5.73it/s]
Loading 0:  45%|████▍     | 346/771 [00:19<00:44,  9.56it/s]
Loading 0:  46%|████▌     | 353/771 [00:19<00:38, 10.78it/s]
Loading 0:  47%|████▋     | 364/771 [00:19<00:26, 15.09it/s]
Loading 0:  49%|████▊     | 375/771 [00:19<00:19, 20.60it/s]
Loading 0:  50%|████▉     | 384/771 [00:20<00:14, 25.93it/s]
Loading 0:  51%|█████     | 393/771 [00:20<00:12, 31.20it/s]
Loading 0:  53%|█████▎    | 406/771 [00:20<00:10, 35.90it/s]
Loading 0:  54%|█████▎    | 413/771 [00:20<00:10, 35.43it/s]
Loading 0:  55%|█████▌    | 425/771 [00:20<00:07, 44.96it/s]
Loading 0:  57%|█████▋    | 437/771 [00:20<00:06, 53.68it/s]
Loading 0:  58%|█████▊    | 448/771 [00:21<00:05, 63.33it/s]
Loading 0:  59%|█████▉    | 458/771 [00:21<00:04, 70.50it/s]
Loading 0:  61%|██████    | 467/771 [00:21<00:05, 58.47it/s]
Loading 0:  62%|██████▏   | 475/771 [00:21<00:05, 55.06it/s]
Loading 0:  63%|██████▎   | 484/771 [00:21<00:04, 62.02it/s]
Loading 0:  64%|██████▍   | 495/771 [00:21<00:03, 72.42it/s]
Loading 0:  65%|██████▌   | 504/771 [00:21<00:03, 76.39it/s]
Loading 0:  67%|██████▋   | 513/771 [00:22<00:03, 73.71it/s]
Loading 0:  68%|██████▊   | 526/771 [00:22<00:03, 62.87it/s]
Loading 0:  69%|██████▉   | 534/771 [00:22<00:04, 54.31it/s]
Loading 0:  71%|███████   | 545/771 [00:22<00:03, 60.45it/s]
Loading 0:  72%|███████▏  | 556/771 [00:22<00:03, 70.09it/s]
Loading 0:  74%|███████▎  | 567/771 [00:22<00:02, 78.80it/s]
Loading 0:  75%|███████▍  | 576/771 [00:22<00:02, 81.37it/s]
Loading 0:  76%|███████▌  | 586/771 [00:23<00:02, 63.67it/s]
Loading 0:  77%|███████▋  | 594/771 [00:23<00:03, 54.50it/s]
Loading 0:  78%|███████▊  | 605/771 [00:23<00:02, 60.72it/s]
Loading 0:  80%|███████▉  | 616/771 [00:23<00:02, 70.88it/s]
Loading 0:  81%|████████▏ | 627/771 [00:38<01:01,  2.33it/s]
Loading 0:  82%|████████▏ | 635/771 [00:38<00:44,  3.06it/s]
Loading 0:  84%|████████▍ | 646/771 [00:38<00:28,  4.40it/s]
Loading 0:  85%|████████▍ | 653/771 [00:38<00:22,  5.36it/s]
Loading 0:  86%|████████▌ | 664/771 [00:39<00:13,  7.92it/s]
Loading 0:  88%|████████▊ | 675/771 [00:39<00:08, 11.35it/s]
Loading 0:  89%|████████▊ | 684/771 [00:39<00:05, 14.96it/s]
Loading 0:  90%|████████▉ | 693/771 [00:39<00:04, 19.17it/s]
Loading 0:  92%|█████████▏| 706/771 [00:39<00:02, 25.12it/s]
Loading 0:  93%|█████████▎| 714/771 [00:39<00:02, 27.51it/s]
Loading 0:  94%|█████████▍| 725/771 [00:39<00:01, 34.87it/s]
Loading 0:  95%|█████████▌| 736/771 [00:40<00:00, 44.41it/s]
Loading 0:  97%|█████████▋| 748/771 [00:40<00:00, 52.84it/s]
Loading 0:  98%|█████████▊| 758/771 [00:40<00:00, 60.94it/s]
Loading 0:  99%|█████████▉| 767/771 [00:48<00:00,  4.17it/s]
                                                            
Job chaiml-qwen32b-simpoexp-49898-v1-mkmlizer completed after 206.64s with status: succeeded
Stopping job with name chaiml-qwen32b-simpoexp-49898-v1-mkmlizer
Pipeline stage MKMLizer completed in 207.14s
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-49898-v1
Waiting for inference service chaiml-qwen32b-simpoexp-49898-v1 to be ready
Inference service chaiml-qwen32b-simpoexp-49898-v1 ready after 200.72930884361267s
Pipeline stage MKMLDeployer completed in 201.27s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.550170421600342s
Received healthy response to inference request in 2.5604617595672607s
Received healthy response to inference request in 2.793548822402954s
Received healthy response to inference request in 2.7459537982940674s
Received healthy response to inference request in 2.8025424480438232s
5 requests
0 failed requests
5th percentile: 2.597560167312622
10th percentile: 2.6346585750579834
20th percentile: 2.708855390548706
30th percentile: 2.7554728031158446
40th percentile: 2.7745108127593996
50th percentile: 2.793548822402954
60th percentile: 2.797146272659302
70th percentile: 2.8007437229156493
80th percentile: 2.952068042755127
90th percentile: 3.2511192321777345
95th percentile: 3.400644826889038
99th percentile: 3.520265302658081
mean time: 2.8905354499816895
Pipeline stage StressChecker completed in 15.90s
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 0.72s
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 0.70s
Shutdown handler de-registered
chaiml-qwen32b-simpoexp_49898_v1 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 0.11s
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-49898-v1-profiler
Waiting for inference service chaiml-qwen32b-simpoexp-49898-v1-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
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 4085.21s
Shutdown handler de-registered
chaiml-qwen32b-simpoexp_49898_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen32b-simpoexp_49898_v1 status is now torndown due to DeploymentManager action