chaiml-arliqwq32b-sftex_44089

developer_uid: NischayDnk

submission_id: chaiml-arliqwq32b-sftex_44089_v1

model_name: chaiml-arliqwq32b-sftex_44089_v1

model_group: ChaiML/Arliqwq32b-sftexp

status: torndown

timestamp: 2025-05-06T04:14:45+00:00

num_battles: 8131

num_wins: 3779

celo_rating: 1262.09

family_friendly_score: 0.5996

family_friendly_standard_error: 0.0069293555255882195

submission_type: basic

model_repo: ChaiML/Arliqwq32b-sftexp1-s1-retryv1-toplex50perc

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': 0.38859460622214076, 'latency_mean': 2.573320016860962, 'latency_p50': 2.5678566694259644, 'latency_p90': 2.8715125799179075}, {'batch_size': 3, 'throughput': 0.8752673730803368, 'latency_mean': 3.413720577955246, 'latency_p50': 3.3926647901535034, 'latency_p90': 3.784647583961487}, {'batch_size': 5, 'throughput': 1.1979281725917332, 'latency_mean': 4.154790431261063, 'latency_p50': 4.16532826423645, 'latency_p90': 4.6391996383667}, {'batch_size': 6, 'throughput': 1.312162768069087, 'latency_mean': 4.546551601886749, 'latency_p50': 4.5153162479400635, 'latency_p90': 5.075313997268676}, {'batch_size': 8, 'throughput': 1.4959889438807674, 'latency_mean': 5.3113544249534606, 'latency_p50': 5.278717398643494, 'latency_p90': 5.96288423538208}, {'batch_size': 10, 'throughput': 1.6260720459409672, 'latency_mean': 6.08525599360466, 'latency_p50': 6.052200675010681, 'latency_p90': 6.883667945861816}]

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

display_name: chaiml-arliqwq32b-sftex_44089_v1

is_internal_developer: False

language_model: ChaiML/Arliqwq32b-sftexp1-s1-retryv1-toplex50perc

model_size: 33B

ranking_group: single

throughput_3p7s: 1.02

us_pacific_date: 2025-05-05

win_ratio: 0.46476448161357764

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_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-arliqwq32b-sftex-44089-v1-mkmlizer
Waiting for job on chaiml-arliqwq32b-sftex-44089-v1-mkmlizer to finish
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: ║       /___/                                                         ║
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: ║                                                                     ║
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: ║                                                                     ║
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: ║                                                                     ║
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: ║                                                                     ║
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: Downloaded to shared memory in 114.436s
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxjvn4qx_, device:0
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-arliqwq32b-sftex-44089-v1
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-arliqwq32b-sftex-44089-v1/added_tokens.json
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-arliqwq32b-sftex-44089-v1/special_tokens_map.json
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-arliqwq32b-sftex-44089-v1/config.json
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-arliqwq32b-sftex-44089-v1/tokenizer_config.json
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-arliqwq32b-sftex-44089-v1/merges.txt
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-arliqwq32b-sftex-44089-v1/vocab.json
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-arliqwq32b-sftex-44089-v1/tokenizer.json
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-arliqwq32b-sftex-44089-v1/flywheel_model.2.safetensors
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-arliqwq32b-sftex-44089-v1/flywheel_model.0.safetensors
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-arliqwq32b-sftex-44089-v1/flywheel_model.1.safetensors
chaiml-arliqwq32b-sftex-44089-v1-mkmlizer: 
Loading 0:   0%|          | 0/771 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/771 [00:00<00:20, 38.18it/s]
Loading 0:   2%|▏         | 16/771 [00:00<00:10, 75.36it/s]
Loading 0:   4%|▎         | 28/771 [00:00<00:09, 81.10it/s]
Loading 0:   5%|▍         | 38/771 [00:00<00:08, 86.81it/s]
Loading 0:   6%|▌         | 47/771 [00:00<00:13, 53.56it/s]
Loading 0:   7%|▋         | 54/771 [00:00<00:14, 49.63it/s]
Loading 0:   8%|▊         | 65/771 [00:01<00:12, 57.77it/s]
Loading 0:  10%|▉         | 76/771 [00:01<00:10, 69.29it/s]
Loading 0:  11%|█▏        | 88/771 [00:01<00:09, 74.36it/s]
Loading 0:  13%|█▎        | 99/771 [00:01<00:08, 82.76it/s]
Loading 0:  14%|█▍        | 109/771 [00:01<00:11, 55.44it/s]
Loading 0:  16%|█▌        | 120/771 [00:01<00:09, 65.56it/s]
Loading 0:  17%|█▋        | 131/771 [00:01<00:08, 74.15it/s]
Loading 0:  18%|█▊        | 140/771 [00:02<00:08, 76.22it/s]
Loading 0:  20%|█▉        | 151/771 [00:02<00:07, 82.44it/s]
Loading 0:  21%|██        | 161/771 [00:02<00:08, 72.08it/s]
Loading 0:  22%|██▏       | 170/771 [00:02<00:11, 52.75it/s]
Loading 0:  23%|██▎       | 177/771 [00:02<00:11, 52.98it/s]
Loading 0:  24%|██▍       | 185/771 [00:02<00:10, 54.85it/s]
Loading 0:  25%|██▌       | 196/771 [00:03<00:08, 64.67it/s]
Loading 0:  27%|██▋       | 207/771 [00:03<00:07, 74.03it/s]
Loading 0:  28%|██▊       | 217/771 [00:03<00:06, 80.23it/s]
Loading 0:  29%|██▉       | 226/771 [00:03<00:09, 59.92it/s]
Loading 0:  30%|███       | 234/771 [00:03<00:10, 52.82it/s]
Loading 0:  32%|███▏      | 245/771 [00:03<00:08, 59.76it/s]
Loading 0:  33%|███▎      | 256/771 [00:03<00:07, 70.03it/s]
Loading 0:  35%|███▍      | 268/771 [00:04<00:06, 74.80it/s]
Loading 0:  36%|███▌      | 279/771 [00:04<00:05, 82.62it/s]
Loading 0:  37%|███▋      | 288/771 [00:04<00:08, 58.33it/s]
Loading 0:  38%|███▊      | 296/771 [00:04<00:07, 59.41it/s]
Loading 0:  39%|███▉      | 303/771 [00:19<04:00,  1.95it/s]
Loading 0:  41%|████      | 315/771 [00:19<02:29,  3.05it/s]
Loading 0:  42%|████▏     | 326/771 [00:19<01:39,  4.46it/s]
Loading 0:  43%|████▎     | 335/771 [00:19<01:12,  6.00it/s]
Loading 0:  45%|████▍     | 346/771 [00:19<00:51,  8.30it/s]
Loading 0:  46%|████▌     | 353/771 [00:20<00:43,  9.64it/s]
Loading 0:  47%|████▋     | 365/771 [00:20<00:28, 14.14it/s]
Loading 0:  49%|████▉     | 377/771 [00:20<00:19, 19.81it/s]
Loading 0:  50%|█████     | 389/771 [00:20<00:14, 26.61it/s]
Loading 0:  53%|█████▎    | 406/771 [00:20<00:10, 35.45it/s]
Loading 0:  54%|█████▎    | 414/771 [00:21<00:10, 34.95it/s]
Loading 0:  55%|█████▍    | 424/771 [00:21<00:08, 42.19it/s]
Loading 0:  56%|█████▋    | 435/771 [00:21<00:06, 51.09it/s]
Loading 0:  58%|█████▊    | 444/771 [00:21<00:05, 56.83it/s]
Loading 0:  59%|█████▉    | 453/771 [00:21<00:05, 58.44it/s]
Loading 0:  60%|██████    | 466/771 [00:21<00:05, 51.08it/s]
Loading 0:  61%|██████▏   | 473/771 [00:22<00:06, 45.52it/s]
Loading 0:  63%|██████▎   | 484/771 [00:22<00:05, 55.59it/s]
Loading 0:  64%|██████▍   | 495/771 [00:22<00:04, 65.06it/s]
Loading 0:  65%|██████▌   | 503/771 [00:22<00:03, 67.90it/s]
Loading 0:  66%|██████▋   | 511/771 [00:22<00:03, 66.40it/s]
Loading 0:  68%|██████▊   | 526/771 [00:22<00:04, 59.84it/s]
Loading 0:  69%|██████▉   | 533/771 [00:23<00:04, 50.65it/s]
Loading 0:  71%|███████   | 544/771 [00:23<00:03, 60.88it/s]
Loading 0:  72%|███████▏  | 555/771 [00:23<00:03, 70.19it/s]
Loading 0:  73%|███████▎  | 564/771 [00:23<00:02, 73.98it/s]
Loading 0:  74%|███████▍  | 573/771 [00:23<00:02, 71.32it/s]
Loading 0:  76%|███████▌  | 586/771 [00:23<00:03, 59.61it/s]
Loading 0:  77%|███████▋  | 593/771 [00:23<00:03, 51.25it/s]
Loading 0:  78%|███████▊  | 605/771 [00:24<00:02, 60.10it/s]
Loading 0:  80%|████████  | 617/771 [00:24<00:02, 67.27it/s]
Loading 0:  81%|████████▏ | 627/771 [00:38<01:00,  2.36it/s]
Loading 0:  83%|████████▎ | 637/771 [00:38<00:40,  3.29it/s]
Loading 0:  84%|████████▍ | 646/771 [00:39<00:28,  4.36it/s]
Loading 0:  85%|████████▍ | 653/771 [00:39<00:22,  5.34it/s]
Loading 0:  86%|████████▌ | 664/771 [00:39<00:13,  7.91it/s]
Loading 0:  88%|████████▊ | 675/771 [00:39<00:08, 11.37it/s]
Loading 0:  89%|████████▉ | 685/771 [00:39<00:05, 15.46it/s]
Loading 0:  90%|█████████ | 694/771 [00:39<00:03, 19.70it/s]
Loading 0:  92%|█████████▏| 706/771 [00:40<00:02, 24.67it/s]
Loading 0:  93%|█████████▎| 714/771 [00:40<00:02, 27.17it/s]
Loading 0:  94%|█████████▍| 725/771 [00:40<00:01, 34.76it/s]
Loading 0:  96%|█████████▌| 737/771 [00:40<00:00, 43.60it/s]
Loading 0:  97%|█████████▋| 749/771 [00:40<00:00, 52.11it/s]
Loading 0:  99%|█████████▉| 766/771 [00:48<00:00,  5.17it/s]
                                                            
Job chaiml-arliqwq32b-sftex-44089-v1-mkmlizer completed after 207.26s with status: succeeded
Stopping job with name chaiml-arliqwq32b-sftex-44089-v1-mkmlizer
Pipeline stage MKMLizer completed in 207.73s
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-arliqwq32b-sftex-44089-v1
Waiting for inference service chaiml-arliqwq32b-sftex-44089-v1 to be ready
Failed to get response for submission bbchicago-tang82mv-dpo-_85183_v2: HTTPConnectionPool(host='bbchicago-tang82mv-dpo-85183-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-arliqwq32b-sftex-44089-v1 ready after 150.51722478866577s
Pipeline stage MKMLDeployer completed in 151.07s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.4333927631378174s
Received healthy response to inference request in 2.610684394836426s
Received healthy response to inference request in 2.7535603046417236s
Received healthy response to inference request in 2.539360523223877s
Received healthy response to inference request in 2.539862871170044s
5 requests
0 failed requests
5th percentile: 2.5394609928131104
10th percentile: 2.539561462402344
20th percentile: 2.5397624015808105
30th percentile: 2.5540271759033204
40th percentile: 2.582355785369873
50th percentile: 2.610684394836426
60th percentile: 2.667834758758545
70th percentile: 2.724985122680664
80th percentile: 2.8895267963409426
90th percentile: 3.16145977973938
95th percentile: 3.2974262714385985
99th percentile: 3.4061994647979734
mean time: 2.7753721714019775
Pipeline stage StressChecker completed in 15.24s
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 0.64s
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 0.64s
Shutdown handler de-registered
chaiml-arliqwq32b-sftex_44089_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 3314.20s
Shutdown handler de-registered
chaiml-arliqwq32b-sftex_44089_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-arliqwq32b-sftex_44089_v1 status is now torndown due to DeploymentManager action