rirv938-harry-potter-rp_79878

developer_uid: rirv938

submission_id: rirv938-harry-potter-rp_79878_v1

model_name: rirv938-harry-potter-rp_79878_v1

model_group: rirv938/harry_potter_rp_

status: torndown

timestamp: 2025-07-03T20:16:30+00:00

num_battles: 10033

num_wins: 5298

celo_rating: 1284.93

family_friendly_score: 0.5664

family_friendly_standard_error: 0.007008438342455472

submission_type: basic

model_repo: rirv938/harry_potter_rp_grpo_cp312_98ff_b35_r1_merged

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 768

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5511948251498449, 'latency_mean': 1.8141304242610932, 'latency_p50': 1.8178305625915527, 'latency_p90': 2.0253156185150147}, {'batch_size': 3, 'throughput': 1.1389542321645454, 'latency_mean': 2.622654504776001, 'latency_p50': 2.619627833366394, 'latency_p90': 2.9118569612503054}, {'batch_size': 5, 'throughput': 1.4803288255311249, 'latency_mean': 3.3548515808582304, 'latency_p50': 3.3359475135803223, 'latency_p90': 3.7343956232070923}, {'batch_size': 6, 'throughput': 1.5814938183702592, 'latency_mean': 3.7677773892879487, 'latency_p50': 3.791856050491333, 'latency_p90': 4.190367269515991}, {'batch_size': 8, 'throughput': 1.7494281658329272, 'latency_mean': 4.5208066463470455, 'latency_p50': 4.556007146835327, 'latency_p90': 5.087809491157532}, {'batch_size': 10, 'throughput': 1.8789046208394877, 'latency_mean': 5.260820415019989, 'latency_p50': 5.275143504142761, 'latency_p90': 5.925748443603515}]

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

display_name: rirv938-harry-potter-rp_79878_v1

is_internal_developer: True

language_model: rirv938/harry_potter_rp_grpo_cp312_98ff_b35_r1_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.58

us_pacific_date: 2025-07-03

win_ratio: 0.5280574105452008

generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['###', '</s>', 'You:', '\n'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', '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 rirv938-harry-potter-rp-79878-v1-mkmlizer
Waiting for job on rirv938-harry-potter-rp-79878-v1-mkmlizer to finish
rirv938-harry-potter-rp-79878-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-harry-potter-rp-79878-v1-mkmlizer: ║                                                                     ║
rirv938-harry-potter-rp-79878-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rirv938-harry-potter-rp-79878-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rirv938-harry-potter-rp-79878-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rirv938-harry-potter-rp-79878-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rirv938-harry-potter-rp-79878-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rirv938-harry-potter-rp-79878-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rirv938-harry-potter-rp-79878-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rirv938-harry-potter-rp-79878-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rirv938-harry-potter-rp-79878-v1-mkmlizer: ║                                                                     ║
rirv938-harry-potter-rp-79878-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
rirv938-harry-potter-rp-79878-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rirv938-harry-potter-rp-79878-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rirv938-harry-potter-rp-79878-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-harry-potter-rp-79878-v1-mkmlizer: ║                                                                     ║
rirv938-harry-potter-rp-79878-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-harry-potter-rp-79878-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-harry-potter-rp-79878-v1-mkmlizer: ║                                                                     ║
rirv938-harry-potter-rp-79878-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-harry-potter-rp-79878-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-harry-potter-rp-79878-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-harry-potter-rp-79878-v1-mkmlizer: ║                                                                     ║
rirv938-harry-potter-rp-79878-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-qwen3-8brerank-ex_2225_v1: HTTPConnectionPool(host='chaiml-qwen3-8brerank-ex-2225-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rirv938-harry-potter-rp-79878-v1-mkmlizer: Downloaded to shared memory in 161.264s
rirv938-harry-potter-rp-79878-v1-mkmlizer: Checking if rirv938/harry_potter_rp_grpo_cp312_98ff_b35_r1_merged already exists in ChaiML
rirv938-harry-potter-rp-79878-v1-mkmlizer: Creating repo ChaiML/harry_potter_rp_grpo_cp312_98ff_b35_r1_merged and uploading /tmp/tmplkpzawaq to it
Failed to get response for submission chaiml-qwen3-8brerank-ex_2225_v1: HTTPConnectionPool(host='chaiml-qwen3-8brerank-ex-2225-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rirv938-harry-potter-rp-79878-v1-mkmlizer: 
  0%|          | 0/22 [00:00<?, ?it/s]
  5%|▍         | 1/22 [00:04<01:42,  4.86s/it]
  9%|▉         | 2/22 [00:08<01:19,  3.96s/it]
 14%|█▎        | 3/22 [00:16<01:50,  5.84s/it]
 18%|█▊        | 4/22 [00:24<02:00,  6.70s/it]
 23%|██▎       | 5/22 [00:27<01:32,  5.46s/it]
 27%|██▋       | 6/22 [00:34<01:34,  5.94s/it]
 32%|███▏      | 7/22 [00:38<01:19,  5.28s/it]
 36%|███▋      | 8/22 [00:42<01:10,  5.01s/it]
 41%|████      | 9/22 [00:46<00:58,  4.52s/it]
 45%|████▌     | 10/22 [00:49<00:50,  4.19s/it]
 50%|█████     | 11/22 [00:53<00:45,  4.09s/it]
 55%|█████▍    | 12/22 [00:56<00:38,  3.83s/it]
 59%|█████▉    | 13/22 [01:01<00:37,  4.14s/it]
 64%|██████▎   | 14/22 [01:04<00:30,  3.87s/it]
 68%|██████▊   | 15/22 [01:11<00:32,  4.59s/it]
 73%|███████▎  | 16/22 [01:17<00:31,  5.27s/it]
 77%|███████▋  | 17/22 [01:22<00:25,  5.07s/it]
 82%|████████▏ | 18/22 [01:29<00:22,  5.59s/it]
 86%|████████▋ | 19/22 [01:32<00:14,  4.91s/it]
 91%|█████████ | 20/22 [01:36<00:09,  4.64s/it]
 95%|█████████▌| 21/22 [01:43<00:05,  5.31s/it]
100%|██████████| 22/22 [01:44<00:00,  4.09s/it]
100%|██████████| 22/22 [01:44<00:00,  4.76s/it]
rirv938-harry-potter-rp-79878-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplkpzawaq, device:0
rirv938-harry-potter-rp-79878-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-harry-potter-rp-79878-v1-mkmlizer: quantized model in 54.675s
rirv938-harry-potter-rp-79878-v1-mkmlizer: Processed model rirv938/harry_potter_rp_grpo_cp312_98ff_b35_r1_merged in 412.447s
rirv938-harry-potter-rp-79878-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-harry-potter-rp-79878-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-harry-potter-rp-79878-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-harry-potter-rp-79878-v1/nvidia
rirv938-harry-potter-rp-79878-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-harry-potter-rp-79878-v1/nvidia/config.json
rirv938-harry-potter-rp-79878-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-harry-potter-rp-79878-v1/nvidia/tokenizer.json
rirv938-harry-potter-rp-79878-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-harry-potter-rp-79878-v1/nvidia/flywheel_model.1.safetensors
rirv938-harry-potter-rp-79878-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-harry-potter-rp-79878-v1/nvidia/flywheel_model.0.safetensors
rirv938-harry-potter-rp-79878-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:16, 21.99it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:18, 18.74it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:15, 23.01it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:24, 14.12it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:25, 13.86it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:19, 17.49it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:23, 14.20it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:16, 20.45it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:13, 23.83it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:19, 16.64it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:19, 16.85it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:24, 13.36it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:16, 18.68it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 21.94it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:19, 16.11it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:18, 16.92it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:22, 13.45it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:16, 18.47it/s]
Loading 0:  19%|█▊        | 68/363 [00:03<00:13, 21.70it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:18, 15.96it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:17, 16.61it/s]
Loading 0:  21%|██        | 77/363 [00:04<00:21, 13.39it/s]
Loading 0:  23%|██▎       | 82/363 [00:04<00:15, 18.47it/s]
Loading 0:  24%|██▎       | 86/363 [00:04<00:12, 21.63it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:17, 15.89it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:16, 16.49it/s]
Loading 0:  26%|██▋       | 96/363 [00:05<00:13, 20.34it/s]
Loading 0:  27%|██▋       | 99/363 [00:05<00:12, 21.94it/s]
Loading 0:  28%|██▊       | 102/363 [00:05<00:12, 20.30it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:16, 15.55it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:17, 14.34it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:18, 14.01it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:16, 15.03it/s]
Loading 0:  31%|███       | 113/363 [00:06<00:20, 12.36it/s]
Loading 0:  33%|███▎      | 118/363 [00:06<00:12, 19.11it/s]
Loading 0:  34%|███▎      | 122/363 [00:06<00:10, 23.03it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:14, 16.30it/s]
Loading 0:  35%|███▌      | 128/363 [00:07<00:13, 16.87it/s]
Loading 0:  36%|███▌      | 131/363 [00:07<00:17, 13.27it/s]
Loading 0:  37%|███▋      | 136/363 [00:07<00:12, 18.68it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 22.13it/s]
Loading 0:  39%|███▉      | 143/363 [00:08<00:13, 16.02it/s]
Loading 0:  40%|████      | 146/363 [00:08<00:13, 16.57it/s]
Loading 0:  41%|████      | 149/363 [00:08<00:16, 12.98it/s]
Loading 0:  42%|████▏     | 154/363 [00:08<00:11, 18.03it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 21.18it/s]
Loading 0:  44%|████▍     | 161/363 [00:09<00:12, 15.70it/s]
Loading 0:  45%|████▌     | 164/363 [00:09<00:12, 16.32it/s]
Loading 0:  46%|████▌     | 167/363 [00:09<00:15, 13.01it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 17.89it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:08, 21.33it/s]
Loading 0:  49%|████▉     | 179/363 [00:10<00:11, 15.67it/s]
Loading 0:  50%|█████     | 182/363 [00:10<00:10, 16.59it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:13, 13.40it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:09, 18.56it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:07, 21.97it/s]
Loading 0:  54%|█████▍    | 197/363 [00:11<00:10, 16.42it/s]
Loading 0:  55%|█████▌    | 200/363 [00:11<00:09, 16.98it/s]
Loading 0:  56%|█████▌    | 203/363 [00:26<03:38,  1.36s/it]
Loading 0:  57%|█████▋    | 207/363 [00:26<02:21,  1.10it/s]
Loading 0:  58%|█████▊    | 210/363 [00:26<01:43,  1.48it/s]
Loading 0:  59%|█████▊    | 213/363 [00:26<01:16,  1.95it/s]
Loading 0:  60%|█████▉    | 216/363 [00:27<00:58,  2.51it/s]
Loading 0:  60%|██████    | 219/363 [00:27<00:42,  3.41it/s]
Loading 0:  61%|██████    | 222/363 [00:27<00:32,  4.31it/s]
Loading 0:  62%|██████▏   | 226/363 [00:27<00:21,  6.29it/s]
Loading 0:  63%|██████▎   | 230/363 [00:27<00:15,  8.74it/s]
Loading 0:  64%|██████▍   | 233/363 [00:27<00:14,  8.78it/s]
Loading 0:  65%|██████▌   | 236/363 [00:28<00:12, 10.36it/s]
Loading 0:  66%|██████▌   | 239/363 [00:28<00:12,  9.96it/s]
Loading 0:  67%|██████▋   | 244/363 [00:28<00:08, 14.53it/s]
Loading 0:  68%|██████▊   | 248/363 [00:28<00:06, 17.96it/s]
Loading 0:  69%|██████▉   | 251/363 [00:29<00:07, 14.56it/s]
Loading 0:  70%|██████▉   | 254/363 [00:29<00:07, 15.41it/s]
Loading 0:  71%|███████   | 257/363 [00:29<00:08, 12.61it/s]
Loading 0:  72%|███████▏  | 262/363 [00:29<00:05, 17.66it/s]
Loading 0:  73%|███████▎  | 266/363 [00:29<00:04, 20.96it/s]
Loading 0:  74%|███████▍  | 269/363 [00:30<00:05, 15.78it/s]
Loading 0:  75%|███████▍  | 272/363 [00:30<00:05, 16.46it/s]
Loading 0:  76%|███████▌  | 275/363 [00:30<00:06, 13.22it/s]
Loading 0:  77%|███████▋  | 280/363 [00:30<00:04, 18.38it/s]
Loading 0:  78%|███████▊  | 284/363 [00:30<00:03, 21.84it/s]
Loading 0:  79%|███████▉  | 287/363 [00:31<00:04, 16.23it/s]
Loading 0:  80%|███████▉  | 290/363 [00:31<00:04, 16.94it/s]
Loading 0:  81%|████████  | 293/363 [00:31<00:05, 13.50it/s]
Loading 0:  82%|████████▏ | 298/363 [00:31<00:03, 18.63it/s]
Loading 0:  83%|████████▎ | 302/363 [00:31<00:02, 21.99it/s]
Loading 0:  84%|████████▍ | 305/363 [00:32<00:03, 16.31it/s]
Loading 0:  85%|████████▍ | 308/363 [00:32<00:03, 17.11it/s]
Loading 0:  86%|████████▌ | 311/363 [00:32<00:03, 13.64it/s]
Loading 0:  87%|████████▋ | 316/363 [00:32<00:02, 18.92it/s]
Loading 0:  88%|████████▊ | 320/363 [00:32<00:01, 22.37it/s]
Loading 0:  89%|████████▉ | 324/363 [00:33<00:02, 14.93it/s]
Loading 0:  90%|█████████ | 327/363 [00:33<00:02, 16.97it/s]
Loading 0:  91%|█████████ | 330/363 [00:33<00:02, 15.57it/s]
Loading 0:  92%|█████████▏| 334/363 [00:33<00:01, 19.29it/s]
Loading 0:  93%|█████████▎| 338/363 [00:33<00:01, 22.69it/s]
Loading 0:  94%|█████████▍| 341/363 [00:34<00:01, 16.39it/s]
Loading 0:  95%|█████████▍| 344/363 [00:34<00:01, 17.08it/s]
Loading 0:  96%|█████████▌| 347/363 [00:34<00:01, 13.41it/s]
Loading 0:  97%|█████████▋| 352/363 [00:34<00:00, 18.69it/s]
Loading 0:  98%|█████████▊| 356/363 [00:34<00:00, 22.16it/s]
Loading 0:  99%|█████████▉| 359/363 [00:35<00:00, 12.02it/s]
Loading 0: 100%|█████████▉| 362/363 [00:35<00:00, 12.18it/s]
                                                            
Job rirv938-harry-potter-rp-79878-v1-mkmlizer completed after 442.98s with status: succeeded
Stopping job with name rirv938-harry-potter-rp-79878-v1-mkmlizer
Pipeline stage MKMLizer completed in 443.53s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-harry-potter-rp-79878-v1
Waiting for inference service rirv938-harry-potter-rp-79878-v1 to be ready
Inference service rirv938-harry-potter-rp-79878-v1 ready after 210.82687187194824s
Pipeline stage MKMLDeployer completed in 211.61s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.921008825302124s
Received healthy response to inference request in 2.071545362472534s
Received healthy response to inference request in 1.8336122035980225s
Received healthy response to inference request in 1.8811380863189697s
Received healthy response to inference request in 2.0759389400482178s
5 requests
0 failed requests
5th percentile: 1.8431173801422118
10th percentile: 1.8526225566864014
20th percentile: 1.8716329097747804
30th percentile: 1.8891122341156006
40th percentile: 1.9050605297088623
50th percentile: 1.921008825302124
60th percentile: 1.9812234401702882
70th percentile: 2.0414380550384523
80th percentile: 2.072424077987671
90th percentile: 2.0741815090179445
95th percentile: 2.075060224533081
99th percentile: 2.0757631969451906
mean time: 1.9566486835479737
Pipeline stage StressChecker completed in 11.34s
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 0.78s
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 0.85s
Shutdown handler de-registered
rirv938-harry-potter-rp_79878_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5274.04s
Shutdown handler de-registered
rirv938-harry-potter-rp_79878_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-harry-potter-rp_79878_v1 status is now torndown due to DeploymentManager action