chaiml-qwen32b-simpoexp_21972

developer_uid: NischayDnk

submission_id: chaiml-qwen32b-simpoexp_21972_v1

model_name: chaiml-qwen32b-simpoexp_21972_v1

model_group: ChaiML/qwen32b-simpoexp1

status: torndown

timestamp: 2025-04-20T15:54:58+00:00

num_battles: 9523

num_wins: 5675

celo_rating: 1359.75

family_friendly_score: 0.38280000000000003

family_friendly_standard_error: 0.006874069537035539

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': 0.2748056506897509, 'latency_mean': 3.6388421964645388, 'latency_p50': 3.6404727697372437, 'latency_p90': 4.049040651321411}, {'batch_size': 2, 'throughput': 0.4469143320155351, 'latency_mean': 4.464848983287811, 'latency_p50': 4.47574257850647, 'latency_p90': 4.939103484153748}, {'batch_size': 3, 'throughput': 0.5928483757865446, 'latency_mean': 5.045225518941879, 'latency_p50': 5.061910390853882, 'latency_p90': 5.550740647315979}, {'batch_size': 5, 'throughput': 0.7909242808551925, 'latency_mean': 6.290199863910675, 'latency_p50': 6.329623579978943, 'latency_p90': 7.00531268119812}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-qwen32b-simpoexp_21972_v1

is_internal_developer: False

language_model: ChaiML/qwen32b-simpoexp1-s2-ftsimpoexp4-1330pref

model_size: 33B

ranking_group: single

throughput_3p7s: 0.29

us_pacific_date: 2025-04-20

win_ratio: 0.5959256536805628

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_end|>', '<|im_start|>', '\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-qwen32b-simpoexp-21972-v1-mkmlizer
Waiting for job on chaiml-qwen32b-simpoexp-21972-v1-mkmlizer to finish
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: ║       /___/                                                         ║
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: ║                                                                     ║
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: ║                                                                     ║
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: ║                                                                     ║
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: ║                                                                     ║
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: Downloaded to shared memory in 110.132s
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpya1x5c2p, device:0
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: quantized model in 65.762s
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: Processed model ChaiML/qwen32b-simpoexp1-s2-ftsimpoexp4-1330pref in 175.896s
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v1
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v1/added_tokens.json
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v1/config.json
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v1/special_tokens_map.json
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v1/tokenizer_config.json
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v1/merges.txt
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v1/vocab.json
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v1/tokenizer.json
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v1/flywheel_model.2.safetensors
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v1/flywheel_model.1.safetensors
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v1/flywheel_model.0.safetensors
chaiml-qwen32b-simpoexp-21972-v1-mkmlizer: 
Loading 0:   0%|          | 0/771 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/771 [00:00<00:20, 37.32it/s]
Loading 0:   2%|▏         | 16/771 [00:00<00:10, 70.93it/s]
Loading 0:   4%|▎         | 27/771 [00:00<00:08, 82.99it/s]
Loading 0:   5%|▍         | 36/771 [00:00<00:08, 82.82it/s]
Loading 0:   6%|▌         | 46/771 [00:00<00:15, 47.90it/s]
Loading 0:   7%|▋         | 53/771 [00:01<00:17, 42.00it/s]
Loading 0:   8%|▊         | 64/771 [00:01<00:13, 53.58it/s]
Loading 0:  10%|▉         | 75/771 [00:01<00:10, 64.14it/s]
Loading 0:  11%|█         | 83/771 [00:01<00:10, 66.68it/s]
Loading 0:  12%|█▏        | 91/771 [00:01<00:10, 64.82it/s]
Loading 0:  14%|█▎        | 106/771 [00:01<00:11, 59.25it/s]
Loading 0:  15%|█▍        | 113/771 [00:01<00:11, 56.88it/s]
Loading 0:  16%|█▌        | 121/771 [00:02<00:11, 57.20it/s]
Loading 0:  17%|█▋        | 132/771 [00:02<00:09, 67.34it/s]
Loading 0:  18%|█▊        | 142/771 [00:02<00:08, 73.98it/s]
Loading 0:  20%|█▉        | 152/771 [00:02<00:07, 79.90it/s]
Loading 0:  21%|██        | 161/771 [00:02<00:08, 74.99it/s]
Loading 0:  22%|██▏       | 169/771 [00:02<00:11, 51.33it/s]
Loading 0:  23%|██▎       | 176/771 [00:02<00:11, 51.59it/s]
Loading 0:  24%|██▍       | 184/771 [00:03<00:10, 57.05it/s]
Loading 0:  25%|██▌       | 195/771 [00:03<00:08, 67.96it/s]
Loading 0:  26%|██▋       | 203/771 [00:03<00:08, 69.06it/s]
Loading 0:  27%|██▋       | 211/771 [00:03<00:08, 66.41it/s]
Loading 0:  29%|██▉       | 226/771 [00:03<00:09, 58.14it/s]
Loading 0:  30%|███       | 233/771 [00:03<00:10, 49.30it/s]
Loading 0:  32%|███▏      | 244/771 [00:04<00:08, 59.86it/s]
Loading 0:  33%|███▎      | 255/771 [00:04<00:07, 69.50it/s]
Loading 0:  34%|███▍      | 264/771 [00:04<00:07, 72.08it/s]
Loading 0:  35%|███▌      | 273/771 [00:04<00:07, 68.93it/s]
Loading 0:  37%|███▋      | 286/771 [00:04<00:08, 58.78it/s]
Loading 0:  38%|███▊      | 293/771 [00:04<00:09, 49.73it/s]
Loading 0:  39%|███▉      | 303/771 [00:19<03:40,  2.12it/s]
Loading 0:  40%|████      | 311/771 [00:19<02:41,  2.84it/s]
Loading 0:  41%|████      | 318/771 [00:19<02:02,  3.71it/s]
Loading 0:  43%|████▎     | 328/771 [00:19<01:21,  5.47it/s]
Loading 0:  44%|████▍     | 338/771 [00:20<00:55,  7.87it/s]
Loading 0:  45%|████▍     | 346/771 [00:20<00:42,  9.92it/s]
Loading 0:  46%|████▌     | 353/771 [00:20<00:36, 11.48it/s]
Loading 0:  47%|████▋     | 364/771 [00:20<00:24, 16.90it/s]
Loading 0:  49%|████▊     | 375/771 [00:20<00:16, 23.62it/s]
Loading 0:  50%|████▉     | 383/771 [00:20<00:13, 28.83it/s]
Loading 0:  51%|█████     | 391/771 [00:21<00:11, 33.77it/s]
Loading 0:  53%|█████▎    | 406/771 [00:21<00:09, 40.18it/s]
Loading 0:  54%|█████▎    | 413/771 [00:21<00:09, 38.22it/s]
Loading 0:  55%|█████▍    | 424/771 [00:21<00:07, 48.43it/s]
Loading 0:  56%|█████▋    | 435/771 [00:21<00:05, 58.62it/s]
Loading 0:  58%|█████▊    | 444/771 [00:21<00:05, 64.26it/s]
Loading 0:  59%|█████▉    | 453/771 [00:22<00:04, 64.88it/s]
Loading 0:  60%|██████    | 466/771 [00:22<00:05, 58.72it/s]
Loading 0:  61%|██████▏   | 473/771 [00:22<00:06, 49.60it/s]
Loading 0:  63%|██████▎   | 484/771 [00:22<00:04, 60.18it/s]
Loading 0:  64%|██████▍   | 495/771 [00:22<00:03, 70.13it/s]
Loading 0:  65%|██████▌   | 504/771 [00:22<00:03, 73.62it/s]
Loading 0:  67%|██████▋   | 513/771 [00:22<00:03, 70.62it/s]
Loading 0:  68%|██████▊   | 526/771 [00:23<00:04, 59.79it/s]
Loading 0:  69%|██████▉   | 533/771 [00:23<00:04, 50.62it/s]
Loading 0:  71%|███████   | 544/771 [00:23<00:03, 61.42it/s]
Loading 0:  72%|███████▏  | 555/771 [00:23<00:03, 70.83it/s]
Loading 0:  73%|███████▎  | 564/771 [00:23<00:02, 74.20it/s]
Loading 0:  74%|███████▍  | 573/771 [00:23<00:02, 71.07it/s]
Loading 0:  76%|███████▌  | 586/771 [00:24<00:03, 60.76it/s]
Loading 0:  77%|███████▋  | 593/771 [00:24<00:03, 51.18it/s]
Loading 0:  78%|███████▊  | 604/771 [00:24<00:02, 61.78it/s]
Loading 0:  80%|███████▉  | 615/771 [00:24<00:02, 71.53it/s]
Loading 0:  81%|████████  | 624/771 [00:24<00:01, 74.99it/s]
Loading 0:  82%|████████▏ | 633/771 [00:39<01:06,  2.07it/s]
Loading 0:  84%|████████▍ | 646/771 [00:40<00:39,  3.18it/s]
Loading 0:  85%|████████▍ | 654/771 [00:40<00:29,  4.03it/s]
Loading 0:  86%|████████▌ | 664/771 [00:40<00:18,  5.68it/s]
Loading 0:  88%|████████▊ | 675/771 [00:40<00:11,  8.19it/s]
Loading 0:  89%|████████▊ | 684/771 [00:40<00:07, 10.90it/s]
Loading 0:  90%|████████▉ | 693/771 [00:40<00:05, 14.24it/s]
Loading 0:  92%|█████████▏| 706/771 [00:41<00:03, 19.42it/s]
Loading 0:  93%|█████████▎| 714/771 [00:41<00:02, 21.99it/s]
Loading 0:  94%|█████████▍| 724/771 [00:41<00:01, 28.79it/s]
Loading 0:  95%|█████████▌| 736/771 [00:41<00:00, 37.23it/s]
Loading 0:  97%|█████████▋| 747/771 [00:41<00:00, 46.57it/s]
Loading 0:  98%|█████████▊| 756/771 [00:41<00:00, 52.25it/s]
Loading 0:  99%|█████████▉| 766/771 [00:49<00:01,  3.96it/s]
                                                            
Job chaiml-qwen32b-simpoexp-21972-v1-mkmlizer completed after 218.1s with status: succeeded
Stopping job with name chaiml-qwen32b-simpoexp-21972-v1-mkmlizer
Pipeline stage MKMLizer completed in 218.60s
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-qwen32b-simpoexp-21972-v1
Waiting for inference service chaiml-qwen32b-simpoexp-21972-v1 to be ready
Failed to get response for submission blend_ridut_2025-04-14: ('http://rirv938-mistral-24b-dpo-29487-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:60210->127.0.0.1:8080: read: connection reset by peer\n')
Inference service chaiml-qwen32b-simpoexp-21972-v1 ready after 131.00698733329773s
Pipeline stage MKMLDeployer completed in 131.57s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.141756534576416s
Received healthy response to inference request in 3.4670779705047607s
Received healthy response to inference request in 3.4987566471099854s
Received healthy response to inference request in 3.544581174850464s
Received healthy response to inference request in 3.3384358882904053s
5 requests
0 failed requests
5th percentile: 3.3641643047332765
10th percentile: 3.3898927211761474
20th percentile: 3.4413495540618895
30th percentile: 3.4734137058258057
40th percentile: 3.4860851764678955
50th percentile: 3.4987566471099854
60th percentile: 3.517086458206177
70th percentile: 3.535416269302368
80th percentile: 3.6640162467956543
90th percentile: 3.902886390686035
95th percentile: 4.022321462631226
99th percentile: 4.117869520187378
mean time: 3.5981216430664062
Pipeline stage StressChecker completed in 19.51s
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 0.92s
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 0.69s
Shutdown handler de-registered
chaiml-qwen32b-simpoexp_21972_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-qwen32b-simpoexp-21972-v1-profiler
Waiting for inference service chaiml-qwen32b-simpoexp-21972-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3593.33s
Shutdown handler de-registered
chaiml-qwen32b-simpoexp_21972_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen32b-simpoexp_21972_v1 status is now torndown due to DeploymentManager action