jellywibble-starwars-rpg

developer_uid: chai_backend_admin

submission_id: jellywibble-starwars-rpg_v3

model_name: jellywibble-starwars-rpg_v3

model_group: Jellywibble/Starwars-RPG

status: torndown

timestamp: 2025-03-12T17:17:54+00:00

num_battles: 11256

num_wins: 5765

celo_rating: 1289.01

family_friendly_score: 0.6152

family_friendly_standard_error: 0.006880827857169513

submission_type: basic

model_repo: Jellywibble/Starwars-RPG

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': 0.2786460306054123, 'latency_mean': 3.5887155079841615, 'latency_p50': 3.5785279273986816, 'latency_p90': 3.873336672782898}, {'batch_size': 2, 'throughput': 0.47281221090101605, 'latency_mean': 4.212011632919311, 'latency_p50': 4.2244263887405396, 'latency_p90': 4.532303142547607}, {'batch_size': 3, 'throughput': 0.640629512142389, 'latency_mean': 4.668573229312897, 'latency_p50': 4.681208610534668, 'latency_p90': 4.987969899177552}, {'batch_size': 4, 'throughput': 0.7820841607471648, 'latency_mean': 5.098799788951874, 'latency_p50': 5.114730358123779, 'latency_p90': 5.567921447753906}, {'batch_size': 5, 'throughput': 0.8995901086555417, 'latency_mean': 5.5269776117801666, 'latency_p50': 5.491160988807678, 'latency_p90': 6.111462664604187}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: jellywibble-starwars-rpg_v3

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: Jellywibble/Starwars-RPG

model_size: 22B

ranking_group: single

throughput_3p7s: 0.32

us_pacific_date: 2025-03-12

win_ratio: 0.5121712864250177

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:', '</s>', '\n', '####', '####\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-starwars-rpg-v3-mkmlizer
Waiting for job on jellywibble-starwars-rpg-v3-mkmlizer to finish
jellywibble-starwars-rpg-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jellywibble-starwars-rpg-v3-mkmlizer: ║     _____            __           __                                ║
jellywibble-starwars-rpg-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jellywibble-starwars-rpg-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jellywibble-starwars-rpg-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jellywibble-starwars-rpg-v3-mkmlizer: ║       /___/                                                         ║
jellywibble-starwars-rpg-v3-mkmlizer: ║                                                                     ║
jellywibble-starwars-rpg-v3-mkmlizer: ║  Version: 0.12.8                                                    ║
jellywibble-starwars-rpg-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jellywibble-starwars-rpg-v3-mkmlizer: ║  https://mk1.ai                                                     ║
jellywibble-starwars-rpg-v3-mkmlizer: ║                                                                     ║
jellywibble-starwars-rpg-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
jellywibble-starwars-rpg-v3-mkmlizer: ║  belonging to:                                                      ║
jellywibble-starwars-rpg-v3-mkmlizer: ║                                                                     ║
jellywibble-starwars-rpg-v3-mkmlizer: ║  Chai Research Corp.                                                ║
jellywibble-starwars-rpg-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jellywibble-starwars-rpg-v3-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
jellywibble-starwars-rpg-v3-mkmlizer: ║                                                                     ║
jellywibble-starwars-rpg-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jellywibble-starwars-rpg-v3-mkmlizer: Downloaded to shared memory in 51.956s
jellywibble-starwars-rpg-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7fo3xu1_, device:0
jellywibble-starwars-rpg-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jellywibble-starwars-rpg-v3-mkmlizer: quantized model in 44.756s
jellywibble-starwars-rpg-v3-mkmlizer: Processed model Jellywibble/Starwars-RPG in 96.713s
jellywibble-starwars-rpg-v3-mkmlizer: creating bucket guanaco-mkml-models
jellywibble-starwars-rpg-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jellywibble-starwars-rpg-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jellywibble-starwars-rpg-v3
jellywibble-starwars-rpg-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jellywibble-starwars-rpg-v3/config.json
jellywibble-starwars-rpg-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jellywibble-starwars-rpg-v3/special_tokens_map.json
jellywibble-starwars-rpg-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jellywibble-starwars-rpg-v3/tokenizer_config.json
jellywibble-starwars-rpg-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jellywibble-starwars-rpg-v3/tokenizer.json
jellywibble-starwars-rpg-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/jellywibble-starwars-rpg-v3/flywheel_model.1.safetensors
jellywibble-starwars-rpg-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jellywibble-starwars-rpg-v3/flywheel_model.0.safetensors
jellywibble-starwars-rpg-v3-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:20, 24.02it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:12, 38.53it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:13, 36.60it/s]
Loading 0:   4%|▍         | 21/507 [00:00<00:12, 37.39it/s]
Loading 0:   5%|▍         | 25/507 [00:00<00:13, 35.04it/s]
Loading 0:   6%|▌         | 30/507 [00:00<00:13, 36.62it/s]
Loading 0:   7%|▋         | 34/507 [00:00<00:13, 34.62it/s]
Loading 0:   8%|▊         | 39/507 [00:01<00:12, 36.18it/s]
Loading 0:   8%|▊         | 43/507 [00:01<00:13, 35.01it/s]
Loading 0:   9%|▉         | 47/507 [00:01<00:13, 35.22it/s]
Loading 0:  10%|█         | 51/507 [00:01<00:13, 34.62it/s]
Loading 0:  11%|█         | 55/507 [00:01<00:19, 23.75it/s]
Loading 0:  11%|█▏        | 58/507 [00:01<00:18, 24.58it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:15, 28.34it/s]
Loading 0:  13%|█▎        | 67/507 [00:02<00:15, 28.67it/s]
Loading 0:  14%|█▍        | 71/507 [00:02<00:14, 31.10it/s]
Loading 0:  15%|█▍        | 75/507 [00:02<00:12, 33.28it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:13, 32.15it/s]
Loading 0:  17%|█▋        | 85/507 [00:02<00:11, 35.55it/s]
Loading 0:  18%|█▊        | 89/507 [00:02<00:13, 30.53it/s]
Loading 0:  19%|█▊        | 94/507 [00:02<00:12, 33.77it/s]
Loading 0:  19%|█▉        | 98/507 [00:03<00:14, 29.19it/s]
Loading 0:  20%|██        | 103/507 [00:03<00:12, 33.49it/s]
Loading 0:  21%|██        | 107/507 [00:03<00:13, 30.50it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:14, 26.50it/s]
Loading 0:  23%|██▎       | 116/507 [00:03<00:16, 23.82it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:14, 26.44it/s]
Loading 0:  25%|██▌       | 129/507 [00:04<00:11, 32.76it/s]
Loading 0:  26%|██▌       | 133/507 [00:04<00:11, 31.65it/s]
Loading 0:  27%|██▋       | 138/507 [00:04<00:10, 33.73it/s]
Loading 0:  28%|██▊       | 142/507 [00:04<00:11, 32.70it/s]
Loading 0:  29%|██▉       | 147/507 [00:04<00:10, 35.04it/s]
Loading 0:  30%|██▉       | 151/507 [00:04<00:10, 33.01it/s]
Loading 0:  31%|███       | 156/507 [00:04<00:09, 35.79it/s]
Loading 0:  32%|███▏      | 160/507 [00:05<00:10, 34.26it/s]
Loading 0:  32%|███▏      | 164/507 [00:05<00:09, 34.55it/s]
Loading 0:  33%|███▎      | 169/507 [00:05<00:12, 27.89it/s]
Loading 0:  34%|███▍      | 173/507 [00:05<00:11, 28.90it/s]
Loading 0:  35%|███▍      | 177/507 [00:05<00:11, 27.71it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:09, 33.59it/s]
Loading 0:  37%|███▋      | 187/507 [00:05<00:09, 32.72it/s]
Loading 0:  38%|███▊      | 192/507 [00:06<00:08, 35.88it/s]
Loading 0:  39%|███▊      | 196/507 [00:06<00:08, 34.64it/s]
Loading 0:  40%|███▉      | 201/507 [00:06<00:08, 37.72it/s]
Loading 0:  40%|████      | 205/507 [00:06<00:08, 35.75it/s]
Loading 0:  41%|████▏     | 210/507 [00:06<00:07, 37.42it/s]
Loading 0:  42%|████▏     | 214/507 [00:06<00:08, 36.36it/s]
Loading 0:  43%|████▎     | 218/507 [00:06<00:07, 36.59it/s]
Loading 0:  44%|████▍     | 222/507 [00:06<00:08, 35.23it/s]
Loading 0:  45%|████▍     | 226/507 [00:07<00:10, 26.17it/s]
Loading 0:  45%|████▌     | 230/507 [00:07<00:10, 25.56it/s]
Loading 0:  47%|████▋     | 237/507 [00:07<00:08, 33.00it/s]
Loading 0:  48%|████▊     | 241/507 [00:07<00:08, 32.77it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:07, 34.96it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 34.02it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:06, 36.25it/s]
Loading 0:  51%|█████     | 259/507 [00:08<00:07, 34.79it/s]
Loading 0:  52%|█████▏    | 264/507 [00:08<00:06, 36.17it/s]
Loading 0:  53%|█████▎    | 268/507 [00:08<00:07, 33.56it/s]
Loading 0:  54%|█████▍    | 273/507 [00:08<00:06, 35.80it/s]
Loading 0:  55%|█████▍    | 277/507 [00:08<00:06, 33.78it/s]
Loading 0:  56%|█████▌    | 282/507 [00:08<00:06, 37.39it/s]
Loading 0:  56%|█████▋    | 286/507 [00:08<00:08, 25.10it/s]
Loading 0:  57%|█████▋    | 290/507 [00:09<00:08, 26.87it/s]
Loading 0:  58%|█████▊    | 294/507 [00:09<00:08, 25.53it/s]
Loading 0:  59%|█████▉    | 299/507 [00:20<00:08, 25.53it/s]
Loading 0:  59%|█████▉    | 300/507 [00:24<03:19,  1.04it/s]
Loading 0:  60%|█████▉    | 302/507 [00:24<02:50,  1.20it/s]
Loading 0:  61%|██████    | 307/507 [00:24<01:50,  1.82it/s]
Loading 0:  61%|██████    | 310/507 [00:24<01:24,  2.32it/s]
Loading 0:  62%|██████▏   | 313/507 [00:24<01:04,  3.00it/s]
Loading 0:  63%|██████▎   | 318/507 [00:24<00:41,  4.58it/s]
Loading 0:  63%|██████▎   | 321/507 [00:24<00:32,  5.68it/s]
Loading 0:  64%|██████▍   | 327/507 [00:25<00:20,  8.89it/s]
Loading 0:  65%|██████▌   | 331/507 [00:25<00:16, 11.00it/s]
Loading 0:  66%|██████▌   | 335/507 [00:25<00:12, 13.50it/s]
Loading 0:  67%|██████▋   | 339/507 [00:25<00:10, 16.71it/s]
Loading 0:  68%|██████▊   | 343/507 [00:25<00:10, 15.13it/s]
Loading 0:  68%|██████▊   | 347/507 [00:25<00:09, 17.13it/s]
Loading 0:  70%|██████▉   | 354/507 [00:26<00:06, 24.46it/s]
Loading 0:  71%|███████   | 358/507 [00:26<00:05, 25.85it/s]
Loading 0:  72%|███████▏  | 363/507 [00:26<00:04, 29.98it/s]
Loading 0:  72%|███████▏  | 367/507 [00:26<00:04, 29.57it/s]
Loading 0:  73%|███████▎  | 372/507 [00:26<00:04, 33.19it/s]
Loading 0:  74%|███████▍  | 376/507 [00:26<00:04, 32.59it/s]
Loading 0:  75%|███████▌  | 381/507 [00:26<00:03, 36.22it/s]
Loading 0:  76%|███████▌  | 385/507 [00:26<00:03, 35.36it/s]
Loading 0:  77%|███████▋  | 389/507 [00:27<00:03, 35.90it/s]
Loading 0:  78%|███████▊  | 393/507 [00:27<00:03, 35.54it/s]
Loading 0:  78%|███████▊  | 397/507 [00:27<00:04, 25.73it/s]
Loading 0:  79%|███████▉  | 401/507 [00:27<00:04, 25.66it/s]
Loading 0:  80%|████████  | 408/507 [00:27<00:02, 33.33it/s]
Loading 0:  81%|████████▏ | 412/507 [00:27<00:02, 32.97it/s]
Loading 0:  82%|████████▏ | 417/507 [00:27<00:02, 35.01it/s]
Loading 0:  83%|████████▎ | 421/507 [00:28<00:02, 34.21it/s]
Loading 0:  84%|████████▍ | 426/507 [00:28<00:02, 37.31it/s]
Loading 0:  85%|████████▍ | 430/507 [00:28<00:02, 33.65it/s]
Loading 0:  86%|████████▌ | 435/507 [00:28<00:01, 36.29it/s]
Loading 0:  87%|████████▋ | 439/507 [00:28<00:01, 35.14it/s]
Loading 0:  88%|████████▊ | 444/507 [00:28<00:01, 38.28it/s]
Loading 0:  88%|████████▊ | 448/507 [00:28<00:01, 36.88it/s]
Loading 0:  90%|████████▉ | 454/507 [00:28<00:01, 38.65it/s]
Loading 0:  90%|█████████ | 458/507 [00:31<00:07,  6.13it/s]
Loading 0:  91%|█████████ | 461/507 [00:31<00:06,  7.35it/s]
Loading 0:  92%|█████████▏| 465/507 [00:31<00:04,  9.35it/s]
Loading 0:  93%|█████████▎| 472/507 [00:31<00:02, 14.43it/s]
Loading 0:  94%|█████████▍| 476/507 [00:31<00:01, 16.67it/s]
Loading 0:  95%|█████████▍| 481/507 [00:31<00:01, 20.36it/s]
Loading 0:  96%|█████████▌| 485/507 [00:31<00:00, 22.42it/s]
Loading 0:  97%|█████████▋| 490/507 [00:32<00:00, 26.03it/s]
Loading 0:  97%|█████████▋| 494/507 [00:32<00:00, 27.15it/s]
Loading 0:  98%|█████████▊| 499/507 [00:32<00:00, 30.49it/s]
Loading 0:  99%|█████████▉| 503/507 [00:32<00:00, 29.69it/s]
                                                            
Job jellywibble-starwars-rpg-v3-mkmlizer completed after 124.9s with status: succeeded
Stopping job with name jellywibble-starwars-rpg-v3-mkmlizer
Pipeline stage MKMLizer completed in 125.42s
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 jellywibble-starwars-rpg-v3
Waiting for inference service jellywibble-starwars-rpg-v3 to be ready
Inference service jellywibble-starwars-rpg-v3 ready after 90.34128975868225s
Pipeline stage MKMLDeployer completed in 90.95s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.720766544342041s
Received healthy response to inference request in 3.3402891159057617s
Received healthy response to inference request in 3.248108386993408s
Received healthy response to inference request in 3.309389352798462s
Received healthy response to inference request in 3.2382168769836426s
5 requests
0 failed requests
5th percentile: 3.2401951789855956
10th percentile: 3.2421734809875487
20th percentile: 3.246130084991455
30th percentile: 3.2603645801544188
40th percentile: 3.2848769664764403
50th percentile: 3.309389352798462
60th percentile: 3.3217492580413817
70th percentile: 3.334109163284302
80th percentile: 3.4163846015930175
90th percentile: 3.5685755729675295
95th percentile: 3.6446710586547852
99th percentile: 3.70554744720459
mean time: 3.3713540554046633
Pipeline stage StressChecker completed in 18.20s
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 0.71s
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 0.72s
Shutdown handler de-registered
jellywibble-starwars-rpg_v3 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 3027.01s
Shutdown handler de-registered
jellywibble-starwars-rpg_v3 status is now inactive due to auto deactivation removed underperforming models
jellywibble-starwars-rpg_v3 status is now torndown due to DeploymentManager action