jellywibble-art-appreci_78611

developer_uid: chai_backend_admin

submission_id: jellywibble-art-appreci_78611_v1

model_name: jellywibble-art-appreci_78611_v1

model_group: Jellywibble/Art-Apprecia

status: torndown

timestamp: 2025-03-16T01:16:26+00:00

num_battles: 7843

num_wins: 4050

celo_rating: 1291.79

family_friendly_score: 0.6402

family_friendly_standard_error: 0.006787399502018428

submission_type: basic

model_repo: Jellywibble/Art-Appreciation_Alex-the-Gym-Coach_Da250316005700

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 2

max_input_tokens: 1024

max_output_tokens: 96

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.278818611762286, 'latency_mean': 3.5864589726924896, 'latency_p50': 3.60611093044281, 'latency_p90': 3.848149633407593}, {'batch_size': 2, 'throughput': 0.4784069075891961, 'latency_mean': 4.179630167484284, 'latency_p50': 4.173443675041199, 'latency_p90': 4.474291086196899}, {'batch_size': 3, 'throughput': 0.6451697822045147, 'latency_mean': 4.637531160116196, 'latency_p50': 4.644403100013733, 'latency_p90': 4.959986305236816}, {'batch_size': 4, 'throughput': 0.7955558260240886, 'latency_mean': 4.993350305557251, 'latency_p50': 4.971478581428528, 'latency_p90': 5.357887220382691}, {'batch_size': 5, 'throughput': 0.9092519489700363, 'latency_mean': 5.464710292816162, 'latency_p50': 5.462120175361633, 'latency_p90': 5.966911005973816}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: jellywibble-art-appreci_78611_v1

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: Jellywibble/Art-Appreciation_Alex-the-Gym-Coach_Da250316005700

model_size: 22B

ranking_group: single

throughput_3p7s: 0.32

us_pacific_date: 2025-03-15

win_ratio: 0.5163840367206426

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': ['You:', '####\n', '</s>', '####', '\n'], 'max_input_tokens': 1024, 'best_of': 2, 'max_output_tokens': 96}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': 'You: {message}\n', 'response_template': '####\n{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-art-appreci-78611-v1-mkmlizer
Waiting for job on jellywibble-art-appreci-78611-v1-mkmlizer to finish
jellywibble-art-appreci-78611-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jellywibble-art-appreci-78611-v1-mkmlizer: ║     _____            __           __                                ║
jellywibble-art-appreci-78611-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jellywibble-art-appreci-78611-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jellywibble-art-appreci-78611-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jellywibble-art-appreci-78611-v1-mkmlizer: ║       /___/                                                         ║
jellywibble-art-appreci-78611-v1-mkmlizer: ║                                                                     ║
jellywibble-art-appreci-78611-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
jellywibble-art-appreci-78611-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jellywibble-art-appreci-78611-v1-mkmlizer: ║  https://mk1.ai                                                     ║
jellywibble-art-appreci-78611-v1-mkmlizer: ║                                                                     ║
jellywibble-art-appreci-78611-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
jellywibble-art-appreci-78611-v1-mkmlizer: ║  belonging to:                                                      ║
jellywibble-art-appreci-78611-v1-mkmlizer: ║                                                                     ║
jellywibble-art-appreci-78611-v1-mkmlizer: ║  Chai Research Corp.                                                ║
jellywibble-art-appreci-78611-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jellywibble-art-appreci-78611-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
jellywibble-art-appreci-78611-v1-mkmlizer: ║                                                                     ║
jellywibble-art-appreci-78611-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jellywibble-art-appreci-78611-v1-mkmlizer: Downloaded to shared memory in 85.597s
jellywibble-art-appreci-78611-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpohnzqbur, device:0
jellywibble-art-appreci-78611-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jellywibble-art-appreci-78611-v1-mkmlizer: quantized model in 46.178s
jellywibble-art-appreci-78611-v1-mkmlizer: Processed model Jellywibble/Art-Appreciation_Alex-the-Gym-Coach_Da250316005700 in 131.775s
jellywibble-art-appreci-78611-v1-mkmlizer: creating bucket guanaco-mkml-models
jellywibble-art-appreci-78611-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jellywibble-art-appreci-78611-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jellywibble-art-appreci-78611-v1
jellywibble-art-appreci-78611-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jellywibble-art-appreci-78611-v1/config.json
jellywibble-art-appreci-78611-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jellywibble-art-appreci-78611-v1/special_tokens_map.json
jellywibble-art-appreci-78611-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jellywibble-art-appreci-78611-v1/tokenizer_config.json
jellywibble-art-appreci-78611-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jellywibble-art-appreci-78611-v1/tokenizer.json
jellywibble-art-appreci-78611-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jellywibble-art-appreci-78611-v1/flywheel_model.0.safetensors
jellywibble-art-appreci-78611-v1-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:21, 22.89it/s]
Loading 0:   2%|▏         | 10/507 [00:00<00:14, 33.17it/s]
Loading 0:   3%|▎         | 14/507 [00:00<00:17, 28.91it/s]
Loading 0:   4%|▍         | 20/507 [00:00<00:12, 38.02it/s]
Loading 0:   5%|▍         | 25/507 [00:00<00:13, 34.74it/s]
Loading 0:   6%|▌         | 29/507 [00:00<00:13, 36.02it/s]
Loading 0:   7%|▋         | 33/507 [00:01<00:15, 31.49it/s]
Loading 0:   7%|▋         | 38/507 [00:01<00:13, 36.04it/s]
Loading 0:   8%|▊         | 42/507 [00:01<00:14, 31.45it/s]
Loading 0:   9%|▉         | 47/507 [00:01<00:13, 33.76it/s]
Loading 0:  10%|█         | 51/507 [00:01<00:13, 32.88it/s]
Loading 0:  11%|█         | 55/507 [00:01<00:20, 21.95it/s]
Loading 0:  11%|█▏        | 58/507 [00:01<00:19, 22.93it/s]
Loading 0:  12%|█▏        | 63/507 [00:02<00:16, 26.67it/s]
Loading 0:  13%|█▎        | 67/507 [00:02<00:15, 27.52it/s]
Loading 0:  14%|█▍        | 71/507 [00:02<00:14, 30.24it/s]
Loading 0:  15%|█▍        | 75/507 [00:02<00:13, 31.65it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:13, 31.39it/s]
Loading 0:  17%|█▋        | 85/507 [00:02<00:11, 35.20it/s]
Loading 0:  18%|█▊        | 89/507 [00:02<00:13, 30.68it/s]
Loading 0:  19%|█▊        | 94/507 [00:03<00:11, 35.00it/s]
Loading 0:  19%|█▉        | 98/507 [00:03<00:13, 31.02it/s]
Loading 0:  21%|██        | 105/507 [00:03<00:10, 37.28it/s]
Loading 0:  21%|██▏       | 109/507 [00:03<00:11, 34.84it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:16, 24.36it/s]
Loading 0:  23%|██▎       | 116/507 [00:03<00:17, 22.37it/s]
Loading 0:  24%|██▍       | 122/507 [00:04<00:14, 25.82it/s]
Loading 0:  25%|██▌       | 129/507 [00:04<00:11, 32.10it/s]
Loading 0:  26%|██▌       | 133/507 [00:04<00:11, 31.78it/s]
Loading 0:  27%|██▋       | 138/507 [00:04<00:10, 34.14it/s]
Loading 0:  28%|██▊       | 142/507 [00:04<00:11, 32.80it/s]
Loading 0:  29%|██▉       | 147/507 [00:04<00:10, 34.90it/s]
Loading 0:  30%|██▉       | 151/507 [00:04<00:10, 33.19it/s]
Loading 0:  31%|███       | 156/507 [00:05<00:09, 35.22it/s]
Loading 0:  32%|███▏      | 160/507 [00:05<00:10, 34.06it/s]
Loading 0:  32%|███▏      | 164/507 [00:05<00:10, 33.88it/s]
Loading 0:  33%|███▎      | 169/507 [00:05<00:12, 26.56it/s]
Loading 0:  34%|███▍      | 172/507 [00:05<00:13, 25.43it/s]
Loading 0:  35%|███▍      | 176/507 [00:05<00:13, 25.02it/s]
Loading 0:  36%|███▌      | 181/507 [00:05<00:10, 30.00it/s]
Loading 0:  36%|███▋      | 185/507 [00:06<00:11, 28.59it/s]
Loading 0:  37%|███▋      | 190/507 [00:06<00:09, 33.29it/s]
Loading 0:  38%|███▊      | 194/507 [00:06<00:10, 30.43it/s]
Loading 0:  39%|███▉      | 199/507 [00:06<00:08, 34.82it/s]
Loading 0:  40%|████      | 203/507 [00:06<00:09, 31.82it/s]
Loading 0:  41%|████▏     | 210/507 [00:06<00:07, 38.82it/s]
Loading 0:  42%|████▏     | 215/507 [00:06<00:07, 38.17it/s]
Loading 0:  43%|████▎     | 219/507 [00:07<00:09, 31.00it/s]
Loading 0:  44%|████▍     | 224/507 [00:07<00:11, 25.43it/s]
Loading 0:  45%|████▌     | 230/507 [00:07<00:10, 27.09it/s]
Loading 0:  46%|████▋     | 235/507 [00:07<00:08, 31.05it/s]
Loading 0:  47%|████▋     | 239/507 [00:07<00:09, 28.87it/s]
Loading 0:  48%|████▊     | 244/507 [00:07<00:07, 33.02it/s]
Loading 0:  49%|████▉     | 248/507 [00:08<00:08, 30.10it/s]
Loading 0:  50%|████▉     | 253/507 [00:08<00:07, 34.36it/s]
Loading 0:  51%|█████     | 257/507 [00:08<00:08, 30.77it/s]
Loading 0:  52%|█████▏    | 262/507 [00:08<00:06, 35.00it/s]
Loading 0:  52%|█████▏    | 266/507 [00:08<00:07, 30.99it/s]
Loading 0:  53%|█████▎    | 271/507 [00:08<00:06, 35.04it/s]
Loading 0:  54%|█████▍    | 275/507 [00:08<00:07, 31.87it/s]
Loading 0:  55%|█████▌    | 281/507 [00:08<00:05, 38.40it/s]
Loading 0:  56%|█████▋    | 286/507 [00:09<00:08, 27.33it/s]
Loading 0:  57%|█████▋    | 290/507 [00:09<00:07, 28.47it/s]
Loading 0:  58%|█████▊    | 294/507 [00:09<00:07, 27.42it/s]
Loading 0:  59%|█████▉    | 298/507 [00:09<00:06, 30.03it/s]
Loading 0:  59%|█████▉    | 299/507 [00:20<00:06, 30.03it/s]
Loading 0:  59%|█████▉    | 300/507 [00:24<04:17,  1.24s/it]
Loading 0:  60%|█████▉    | 302/507 [00:24<03:29,  1.02s/it]
Loading 0:  61%|██████    | 307/507 [00:24<02:03,  1.61it/s]
Loading 0:  61%|██████    | 310/507 [00:24<01:33,  2.12it/s]
Loading 0:  62%|██████▏   | 313/507 [00:24<01:08,  2.82it/s]
Loading 0:  63%|██████▎   | 318/507 [00:25<00:42,  4.43it/s]
Loading 0:  64%|██████▎   | 322/507 [00:25<00:30,  6.02it/s]
Loading 0:  64%|██████▍   | 327/507 [00:25<00:20,  8.65it/s]
Loading 0:  65%|██████▌   | 331/507 [00:25<00:16, 10.81it/s]
Loading 0:  66%|██████▌   | 335/507 [00:25<00:12, 13.31it/s]
Loading 0:  67%|██████▋   | 339/507 [00:25<00:10, 16.49it/s]
Loading 0:  68%|██████▊   | 343/507 [00:25<00:10, 15.09it/s]
Loading 0:  68%|██████▊   | 347/507 [00:26<00:09, 16.72it/s]
Loading 0:  69%|██████▉   | 352/507 [00:26<00:07, 21.43it/s]
Loading 0:  70%|███████   | 356/507 [00:26<00:06, 22.12it/s]
Loading 0:  71%|███████   | 361/507 [00:26<00:05, 26.92it/s]
Loading 0:  72%|███████▏  | 365/507 [00:26<00:05, 26.04it/s]
Loading 0:  73%|███████▎  | 370/507 [00:26<00:04, 30.64it/s]
Loading 0:  74%|███████▍  | 374/507 [00:26<00:04, 28.57it/s]
Loading 0:  75%|███████▌  | 381/507 [00:27<00:03, 35.56it/s]
Loading 0:  76%|███████▌  | 385/507 [00:27<00:03, 33.76it/s]
Loading 0:  77%|███████▋  | 389/507 [00:27<00:03, 32.67it/s]
Loading 0:  78%|███████▊  | 393/507 [00:27<00:03, 31.26it/s]
Loading 0:  78%|███████▊  | 397/507 [00:27<00:04, 23.46it/s]
Loading 0:  79%|███████▉  | 401/507 [00:28<00:04, 22.31it/s]
Loading 0:  80%|████████  | 406/507 [00:28<00:03, 26.89it/s]
Loading 0:  81%|████████  | 410/507 [00:28<00:03, 25.24it/s]
Loading 0:  82%|████████▏ | 415/507 [00:28<00:03, 29.63it/s]
Loading 0:  83%|████████▎ | 419/507 [00:28<00:03, 27.41it/s]
Loading 0:  84%|████████▎ | 424/507 [00:28<00:02, 31.46it/s]
Loading 0:  84%|████████▍ | 428/507 [00:28<00:02, 28.94it/s]
Loading 0:  85%|████████▌ | 433/507 [00:28<00:02, 32.94it/s]
Loading 0:  86%|████████▌ | 437/507 [00:29<00:02, 29.88it/s]
Loading 0:  87%|████████▋ | 442/507 [00:29<00:01, 34.31it/s]
Loading 0:  88%|████████▊ | 446/507 [00:29<00:01, 30.62it/s]
Loading 0:  89%|████████▉ | 451/507 [00:29<00:01, 34.58it/s]
Loading 0:  90%|████████▉ | 455/507 [00:31<00:09,  5.63it/s]
Loading 0:  91%|█████████ | 459/507 [00:31<00:06,  7.12it/s]
Loading 0:  92%|█████████▏| 465/507 [00:32<00:04, 10.05it/s]
Loading 0:  93%|█████████▎| 470/507 [00:32<00:02, 13.29it/s]
Loading 0:  93%|█████████▎| 474/507 [00:32<00:02, 14.97it/s]
Loading 0:  94%|█████████▍| 479/507 [00:32<00:01, 19.16it/s]
Loading 0:  95%|█████████▌| 483/507 [00:32<00:01, 20.50it/s]
Loading 0:  96%|█████████▋| 488/507 [00:32<00:00, 25.18it/s]
Loading 0:  97%|█████████▋| 492/507 [00:33<00:00, 24.39it/s]
Loading 0:  98%|█████████▊| 497/507 [00:33<00:00, 28.86it/s]
Loading 0:  99%|█████████▉| 501/507 [00:33<00:00, 27.52it/s]
Loading 0: 100%|█████████▉| 506/507 [00:33<00:00, 31.89it/s]
                                                            
Job jellywibble-art-appreci-78611-v1-mkmlizer completed after 165.41s with status: succeeded
Stopping job with name jellywibble-art-appreci-78611-v1-mkmlizer
Pipeline stage MKMLizer completed in 165.90s
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 jellywibble-art-appreci-78611-v1
Waiting for inference service jellywibble-art-appreci-78611-v1 to be ready
Inference service jellywibble-art-appreci-78611-v1 ready after 80.3059024810791s
Pipeline stage MKMLDeployer completed in 81.01s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.102447032928467s
Received healthy response to inference request in 3.3646152019500732s
Received healthy response to inference request in 3.3113763332366943s
Received healthy response to inference request in 3.2189412117004395s
Received healthy response to inference request in 3.2034313678741455s
5 requests
0 failed requests
5th percentile: 3.206533336639404
10th percentile: 3.209635305404663
20th percentile: 3.2158392429351808
30th percentile: 3.2374282360076903
40th percentile: 3.2744022846221923
50th percentile: 3.3113763332366943
60th percentile: 3.332671880722046
70th percentile: 3.3539674282073975
80th percentile: 3.512181568145752
90th percentile: 3.8073143005371093
95th percentile: 3.954880666732788
99th percentile: 4.072933759689331
mean time: 3.4401622295379637
Pipeline stage StressChecker completed in 18.56s
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 0.74s
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
jellywibble-art-appreci_78611_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 jellywibble-art-appreci-78611-v1-profiler
Waiting for inference service jellywibble-art-appreci-78611-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 3054.27s
Shutdown handler de-registered
jellywibble-art-appreci_78611_v1 status is now inactive due to auto deactivation removed underperforming models
jellywibble-art-appreci_78611_v1 status is now torndown due to DeploymentManager action