jellywibble-kang-dae-ho2_3034

developer_uid: chai_backend_admin

submission_id: jellywibble-kang-dae-ho2_3034_v2

model_name: jellywibble-kang-dae-ho2_3034_v2

model_group: Jellywibble/Kang-Dae-Ho2

status: torndown

timestamp: 2025-04-10T00:34:26+00:00

num_battles: 7655

num_wins: 3830

celo_rating: 1279.73

family_friendly_score: 0.5349999999999999

family_friendly_standard_error: 0.007053722421530351

submission_type: basic

model_repo: Jellywibble/Kang-Dae-Ho250410011602

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.3680926468272859, 'latency_mean': 2.716620796918869, 'latency_p50': 2.723822236061096, 'latency_p90': 2.997897982597351}, {'batch_size': 2, 'throughput': 0.5744667531795998, 'latency_mean': 3.4724359941482543, 'latency_p50': 3.480793833732605, 'latency_p90': 3.8206993103027345}, {'batch_size': 3, 'throughput': 0.7243722573130111, 'latency_mean': 4.134679610729218, 'latency_p50': 4.140785336494446, 'latency_p90': 4.542954826354981}, {'batch_size': 4, 'throughput': 0.8437829182124027, 'latency_mean': 4.724084243774414, 'latency_p50': 4.715371131896973, 'latency_p90': 5.27500319480896}, {'batch_size': 5, 'throughput': 0.9288526314686857, 'latency_mean': 5.3599089181423185, 'latency_p50': 5.381052494049072, 'latency_p90': 5.969505143165589}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: jellywibble-kang-dae-ho2_3034_v2

is_internal_developer: True

language_model: Jellywibble/Kang-Dae-Ho250410011602

model_size: 24B

ranking_group: single

throughput_3p7s: 0.63

us_pacific_date: 2025-04-09

win_ratio: 0.5003265839320705

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>', '\n', '####', 'You:', '####\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}</s>\n', 'user_template': 'You: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}

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 jellywibble-kang-dae-ho2-3034-v2-mkmlizer
Waiting for job on jellywibble-kang-dae-ho2-3034-v2-mkmlizer to finish
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: ║     _____            __           __                                ║
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: ║       /___/                                                         ║
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: ║                                                                     ║
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: ║  https://mk1.ai                                                     ║
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: ║                                                                     ║
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: ║  belonging to:                                                      ║
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: ║                                                                     ║
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: ║  Chai Research Corp.                                                ║
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: ║                                                                     ║
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: Downloaded to shared memory in 67.790s
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpoybaqs8v, device:0
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: quantized model in 52.775s
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: Processed model Jellywibble/Kang-Dae-Ho250410011602 in 120.565s
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: creating bucket guanaco-mkml-models
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jellywibble-kang-dae-ho2-3034-v2
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jellywibble-kang-dae-ho2-3034-v2/config.json
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jellywibble-kang-dae-ho2-3034-v2/special_tokens_map.json
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jellywibble-kang-dae-ho2-3034-v2/tokenizer_config.json
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jellywibble-kang-dae-ho2-3034-v2/tokenizer.json
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/jellywibble-kang-dae-ho2-3034-v2/flywheel_model.1.safetensors
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jellywibble-kang-dae-ho2-3034-v2/flywheel_model.0.safetensors
jellywibble-kang-dae-ho2-3034-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:10, 33.98it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 27.50it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 31.41it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:11, 29.14it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 32.29it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 29.73it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 35.81it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:15, 21.39it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 24.01it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 25.37it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.56it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 26.37it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 29.02it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 27.51it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.56it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 25.00it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 20.37it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 26.08it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 26.04it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:09, 28.94it/s]
Loading 0:  25%|██▍       | 90/363 [00:03<00:10, 26.87it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:11, 24.14it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 29.98it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 27.67it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 23.24it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 25.98it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 25.69it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 29.57it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 28.49it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 32.61it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 30.08it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 31.95it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 29.86it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 34.28it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:08, 25.22it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:08, 23.23it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:08, 24.04it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:08, 24.65it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 29.01it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 28.22it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 30.99it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 29.30it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:05, 30.17it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 26.94it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 23.60it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:06, 24.48it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 25.50it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 25.50it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<02:58,  1.10s/it]
Loading 0:  56%|█████▌    | 203/363 [00:21<02:28,  1.08it/s]
Loading 0:  57%|█████▋    | 208/363 [00:21<01:29,  1.74it/s]
Loading 0:  58%|█████▊    | 211/363 [00:21<01:08,  2.22it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:50,  2.94it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:34,  4.23it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.43it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21,  6.54it/s]
Loading 0:  63%|██████▎   | 228/363 [00:22<00:14,  9.16it/s]
Loading 0:  64%|██████▎   | 231/363 [00:22<00:12, 10.44it/s]
Loading 0:  65%|██████▌   | 237/363 [00:22<00:07, 15.78it/s]
Loading 0:  66%|██████▋   | 241/363 [00:23<00:06, 17.97it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 22.52it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:04, 22.87it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:03, 27.08it/s]
Loading 0:  71%|███████▏  | 259/363 [00:23<00:03, 26.84it/s]
Loading 0:  73%|███████▎  | 266/363 [00:23<00:02, 32.78it/s]
Loading 0:  74%|███████▍  | 270/363 [00:24<00:04, 21.69it/s]
Loading 0:  75%|███████▌  | 274/363 [00:24<00:03, 24.18it/s]
Loading 0:  77%|███████▋  | 278/363 [00:24<00:03, 26.08it/s]
Loading 0:  78%|███████▊  | 282/363 [00:24<00:02, 28.05it/s]
Loading 0:  79%|███████▉  | 286/363 [00:24<00:02, 26.77it/s]
Loading 0:  80%|████████  | 291/363 [00:24<00:02, 29.02it/s]
Loading 0:  81%|████████▏ | 295/363 [00:24<00:02, 27.17it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 28.07it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 25.53it/s]
Loading 0:  85%|████████▍ | 307/363 [00:25<00:02, 23.41it/s]
Loading 0:  85%|████████▌ | 310/363 [00:25<00:02, 24.15it/s]
Loading 0:  86%|████████▌ | 313/363 [00:25<00:02, 24.32it/s]
Loading 0:  88%|████████▊ | 318/363 [00:25<00:01, 28.79it/s]
Loading 0:  88%|████████▊ | 321/363 [00:25<00:01, 25.51it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 31.83it/s]
Loading 0:  91%|█████████ | 331/363 [00:26<00:01, 30.57it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:00, 32.23it/s]
Loading 0:  93%|█████████▎| 339/363 [00:26<00:00, 32.27it/s]
Loading 0:  94%|█████████▍| 343/363 [00:33<00:10,  1.91it/s]
Loading 0:  96%|█████████▌| 348/363 [00:33<00:05,  2.80it/s]
Loading 0:  98%|█████████▊| 355/363 [00:33<00:01,  4.59it/s]
Loading 0:  99%|█████████▉| 359/363 [00:33<00:00,  5.79it/s]
                                                            
Job jellywibble-kang-dae-ho2-3034-v2-mkmlizer completed after 156.0s with status: succeeded
Stopping job with name jellywibble-kang-dae-ho2-3034-v2-mkmlizer
Pipeline stage MKMLizer completed in 156.44s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service jellywibble-kang-dae-ho2-3034-v2
Waiting for inference service jellywibble-kang-dae-ho2-3034-v2 to be ready
Inference service jellywibble-kang-dae-ho2-3034-v2 ready after 110.56992983818054s
Pipeline stage MKMLDeployer completed in 111.06s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.870002269744873s
Received healthy response to inference request in 2.236248731613159s
Received healthy response to inference request in 1.3701586723327637s
Received healthy response to inference request in 2.241570472717285s
Received healthy response to inference request in 1.2065584659576416s
5 requests
0 failed requests
5th percentile: 1.239278507232666
10th percentile: 1.2719985485076903
20th percentile: 1.3374386310577393
30th percentile: 1.4701273918151856
40th percentile: 1.6700648307800294
50th percentile: 1.870002269744873
60th percentile: 2.0165008544921874
70th percentile: 2.1629994392395018
80th percentile: 2.237313079833984
90th percentile: 2.2394417762756347
95th percentile: 2.24050612449646
99th percentile: 2.24135760307312
mean time: 1.7849077224731444
Pipeline stage StressChecker completed in 10.19s
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 0.61s
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
jellywibble-kang-dae-ho2_3034_v2 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 4896.90s
Shutdown handler de-registered
jellywibble-kang-dae-ho2_3034_v2 status is now inactive due to auto deactivation removed underperforming models
jellywibble-kang-dae-ho2_3034_v2 status is now torndown due to DeploymentManager action
jellywibble-kang-dae-ho2_3034_v2 status is now torndown due to DeploymentManager action
jellywibble-kang-dae-ho2_3034_v2 status is now torndown due to DeploymentManager action
jellywibble-kang-dae-ho2_3034_v2 status is now torndown due to DeploymentManager action