developer_uid: rirv938
submission_id: rirv938-harry-potter-rp_65094_v2
model_name: rirv938-harry-potter-rp_65094_v2
model_group: rirv938/harry_potter_rp_
status: torndown
timestamp: 2025-07-07T15:39:58+00:00
num_battles: 6902
num_wins: 3440
celo_rating: 1288.23
family_friendly_score: 0.5642
family_friendly_standard_error: 0.0070125367735221185
submission_type: basic
model_repo: rirv938/harry_potter_rp_grpo_cp624_98ff_b35_r1_merged
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': 0.5174415554959068, 'latency_mean': 1.9324631106853485, 'latency_p50': 1.9208192825317383, 'latency_p90': 2.1547218561172485}, {'batch_size': 3, 'throughput': 1.048748680403036, 'latency_mean': 2.8553467166423796, 'latency_p50': 2.889013648033142, 'latency_p90': 3.1636968851089478}, {'batch_size': 5, 'throughput': 1.3294803364972603, 'latency_mean': 3.7439506328105927, 'latency_p50': 3.7464451789855957, 'latency_p90': 4.093713545799256}, {'batch_size': 6, 'throughput': 1.4211602192489339, 'latency_mean': 4.184034525156021, 'latency_p50': 4.203451991081238, 'latency_p90': 4.7137442350387575}, {'batch_size': 8, 'throughput': 1.5593006725876044, 'latency_mean': 5.1029254865646365, 'latency_p50': 5.082183480262756, 'latency_p90': 5.707992196083069}, {'batch_size': 10, 'throughput': 1.6234530548020358, 'latency_mean': 6.100385248661041, 'latency_p50': 6.102127194404602, 'latency_p90': 6.969566535949707}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: rirv938-harry-potter-rp_65094_v2
is_internal_developer: True
language_model: rirv938/harry_potter_rp_grpo_cp624_98ff_b35_r1_merged
model_size: 24B
ranking_group: single
throughput_3p7s: 1.32
us_pacific_date: 2025-07-07
win_ratio: 0.4984062590553463
generation_params: {'temperature': 0.5, 'top_p': 0.95, 'min_p': 0.02, 'top_k': 60, 'presence_penalty': 0.2, 'frequency_penalty': 0.2, 'stopping_words': ['####\n', '####', '</s>', '\n', 'You:'], '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 rirv938-harry-potter-rp-65094-v2-mkmlizer
Waiting for job on rirv938-harry-potter-rp-65094-v2-mkmlizer to finish
rirv938-harry-potter-rp-65094-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-harry-potter-rp-65094-v2-mkmlizer: ║                                                                     ║
rirv938-harry-potter-rp-65094-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rirv938-harry-potter-rp-65094-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rirv938-harry-potter-rp-65094-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rirv938-harry-potter-rp-65094-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rirv938-harry-potter-rp-65094-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rirv938-harry-potter-rp-65094-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rirv938-harry-potter-rp-65094-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rirv938-harry-potter-rp-65094-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rirv938-harry-potter-rp-65094-v2-mkmlizer: ║                                                                     ║
rirv938-harry-potter-rp-65094-v2-mkmlizer: ║  Version: 0.29.15                                                   ║
rirv938-harry-potter-rp-65094-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rirv938-harry-potter-rp-65094-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rirv938-harry-potter-rp-65094-v2-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-harry-potter-rp-65094-v2-mkmlizer: ║                                                                     ║
rirv938-harry-potter-rp-65094-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-harry-potter-rp-65094-v2-mkmlizer: ║  belonging to:                                                      ║
rirv938-harry-potter-rp-65094-v2-mkmlizer: ║                                                                     ║
rirv938-harry-potter-rp-65094-v2-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-harry-potter-rp-65094-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-harry-potter-rp-65094-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-harry-potter-rp-65094-v2-mkmlizer: ║                                                                     ║
rirv938-harry-potter-rp-65094-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
admin requested tearing down of jreisler-mistral-dpo-step-200_v5
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLDeleter
Checking if service jreisler-mistral-dpo-step-200-v5 is running
Tearing down inference service jreisler-mistral-dpo-step-200-v5
Service jreisler-mistral-dpo-step-200-v5 has been torndown
Pipeline stage MKMLDeleter completed in 2.41s
run pipeline stage %s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key jreisler-mistral-dpo-step-200-v5/config.json from bucket guanaco-mkml-models
Deleting key jreisler-mistral-dpo-step-200-v5/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key jreisler-mistral-dpo-step-200-v5/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key jreisler-mistral-dpo-step-200-v5/tokenizer.json from bucket guanaco-mkml-models
Deleting key jreisler-mistral-dpo-step-200-v5/tokenizer_config.json from bucket guanaco-mkml-models
Pipeline stage MKMLModelDeleter completed in 2.31s
Shutdown handler de-registered
jreisler-mistral-dpo-step-200_v5 status is now torndown due to DeploymentManager action
Failed to get response for submission chaiml-qwen-8bskywork-v_35275_v1: HTTPConnectionPool(host='chaiml-qwen-8bskywork-v-35275-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-qwen-8bskywork-v_35275_v1: HTTPConnectionPool(host='chaiml-qwen-8bskywork-v-35275-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rirv938-harry-potter-rp-65094-v2-mkmlizer: Downloaded to shared memory in 154.151s
rirv938-harry-potter-rp-65094-v2-mkmlizer: Checking if rirv938/harry_potter_rp_grpo_cp624_98ff_b35_r1_merged already exists in ChaiML
rirv938-harry-potter-rp-65094-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2mfsbhv5, device:0
rirv938-harry-potter-rp-65094-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission chaiml-qwen-8bskywork-v_35275_v1: HTTPConnectionPool(host='chaiml-qwen-8bskywork-v-35275-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rirv938-harry-potter-rp-65094-v2-mkmlizer: quantized model in 56.352s
rirv938-harry-potter-rp-65094-v2-mkmlizer: Processed model rirv938/harry_potter_rp_grpo_cp624_98ff_b35_r1_merged in 210.601s
rirv938-harry-potter-rp-65094-v2-mkmlizer: creating bucket guanaco-mkml-models
rirv938-harry-potter-rp-65094-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-harry-potter-rp-65094-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-harry-potter-rp-65094-v2/nvidia
rirv938-harry-potter-rp-65094-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-harry-potter-rp-65094-v2/nvidia/config.json
rirv938-harry-potter-rp-65094-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-harry-potter-rp-65094-v2/nvidia/special_tokens_map.json
rirv938-harry-potter-rp-65094-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-harry-potter-rp-65094-v2/nvidia/tokenizer_config.json
rirv938-harry-potter-rp-65094-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-harry-potter-rp-65094-v2/nvidia/tokenizer.json
rirv938-harry-potter-rp-65094-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-harry-potter-rp-65094-v2/nvidia/flywheel_model.0.safetensors
rirv938-harry-potter-rp-65094-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-harry-potter-rp-65094-v2/nvidia/flywheel_model.1.safetensors
rirv938-harry-potter-rp-65094-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:16, 21.58it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:19, 18.48it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:15, 22.19it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:25, 13.81it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:25, 13.46it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:20, 16.61it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:21, 16.00it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:22, 14.95it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 19.70it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 23.41it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:20, 15.79it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:19, 16.36it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:24, 12.95it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:17, 18.41it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 21.86it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:19, 15.76it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:18, 16.66it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:23, 13.15it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:16, 18.30it/s]
Loading 0:  19%|█▊        | 68/363 [00:03<00:13, 21.69it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:17, 16.22it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:17, 16.97it/s]
Loading 0:  21%|██        | 77/363 [00:04<00:21, 13.42it/s]
Loading 0:  23%|██▎       | 82/363 [00:04<00:15, 18.73it/s]
Loading 0:  24%|██▎       | 86/363 [00:04<00:12, 22.17it/s]
Loading 0:  25%|██▍       | 90/363 [00:05<00:18, 14.51it/s]
Loading 0:  26%|██▌       | 95/363 [00:05<00:13, 19.32it/s]
Loading 0:  27%|██▋       | 99/363 [00:05<00:12, 21.99it/s]
Loading 0:  28%|██▊       | 103/363 [00:05<00:15, 17.28it/s]
Loading 0:  29%|██▉       | 106/363 [00:06<00:17, 15.08it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:18, 14.01it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:17, 14.60it/s]
Loading 0:  31%|███       | 113/363 [00:06<00:20, 12.35it/s]
Loading 0:  33%|███▎      | 118/363 [00:06<00:13, 18.20it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 21.69it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:15, 15.51it/s]
Loading 0:  35%|███▌      | 128/363 [00:07<00:14, 16.32it/s]
Loading 0:  36%|███▌      | 131/363 [00:07<00:17, 12.93it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 17.93it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 21.23it/s]
Loading 0:  39%|███▉      | 143/363 [00:08<00:14, 15.37it/s]
Loading 0:  40%|████      | 146/363 [00:08<00:13, 16.19it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:16, 12.97it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 17.99it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 21.32it/s]
Loading 0:  44%|████▍     | 161/363 [00:09<00:12, 15.73it/s]
Loading 0:  45%|████▌     | 164/363 [00:09<00:12, 16.36it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:15, 13.05it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 17.92it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:08, 21.02it/s]
Loading 0:  49%|████▉     | 179/363 [00:10<00:11, 15.70it/s]
Loading 0:  50%|█████     | 182/363 [00:10<00:11, 16.45it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:13, 13.22it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:09, 18.33it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:07, 21.23it/s]
Loading 0:  54%|█████▍    | 197/363 [00:11<00:10, 15.67it/s]
Loading 0:  55%|█████▌    | 200/363 [00:11<00:10, 16.21it/s]
Loading 0:  55%|█████▌    | 200/363 [00:26<00:10, 16.21it/s]
Loading 0:  55%|█████▌    | 201/363 [00:26<04:32,  1.68s/it]
Loading 0:  56%|█████▌    | 203/363 [00:26<03:29,  1.31s/it]
Loading 0:  57%|█████▋    | 207/363 [00:26<02:02,  1.27it/s]
Loading 0:  58%|█████▊    | 210/363 [00:27<01:25,  1.78it/s]
Loading 0:  59%|█████▊    | 213/363 [00:27<01:03,  2.38it/s]
Loading 0:  59%|█████▉    | 215/363 [00:27<00:51,  2.88it/s]
Loading 0:  60%|█████▉    | 217/363 [00:27<00:41,  3.53it/s]
Loading 0:  60%|██████    | 219/363 [00:27<00:32,  4.47it/s]
Loading 0:  61%|██████    | 221/363 [00:28<00:27,  5.09it/s]
Loading 0:  62%|██████▏   | 226/363 [00:28<00:15,  8.98it/s]
Loading 0:  63%|██████▎   | 230/363 [00:28<00:10, 12.23it/s]
Loading 0:  64%|██████▍   | 233/363 [00:28<00:11, 10.99it/s]
Loading 0:  65%|██████▌   | 236/363 [00:28<00:10, 12.45it/s]
Loading 0:  66%|██████▌   | 239/363 [00:29<00:11, 10.94it/s]
Loading 0:  67%|██████▋   | 244/363 [00:29<00:07, 15.80it/s]
Loading 0:  68%|██████▊   | 248/363 [00:29<00:06, 18.98it/s]
Loading 0:  69%|██████▉   | 251/363 [00:29<00:07, 14.63it/s]
Loading 0:  70%|██████▉   | 254/363 [00:29<00:07, 15.54it/s]
Loading 0:  71%|███████   | 257/363 [00:30<00:08, 12.69it/s]
Loading 0:  72%|███████▏  | 262/363 [00:30<00:05, 17.63it/s]
Loading 0:  73%|███████▎  | 266/363 [00:30<00:04, 20.88it/s]
Loading 0:  74%|███████▍  | 269/363 [00:30<00:06, 15.49it/s]
Loading 0:  75%|███████▍  | 272/363 [00:31<00:05, 16.12it/s]
Loading 0:  76%|███████▌  | 275/363 [00:31<00:06, 13.05it/s]
Loading 0:  77%|███████▋  | 280/363 [00:31<00:04, 18.15it/s]
Loading 0:  78%|███████▊  | 284/363 [00:31<00:03, 21.35it/s]
Loading 0:  79%|███████▉  | 287/363 [00:31<00:04, 15.83it/s]
Loading 0:  80%|███████▉  | 290/363 [00:32<00:04, 16.56it/s]
Loading 0:  81%|████████  | 293/363 [00:32<00:05, 13.21it/s]
Loading 0:  82%|████████▏ | 298/363 [00:32<00:03, 18.35it/s]
Loading 0:  83%|████████▎ | 302/363 [00:32<00:02, 21.76it/s]
Loading 0:  84%|████████▍ | 305/363 [00:32<00:03, 16.44it/s]
Loading 0:  85%|████████▍ | 308/363 [00:33<00:03, 17.12it/s]
Loading 0:  86%|████████▌ | 311/363 [00:33<00:03, 13.44it/s]
Loading 0:  87%|████████▋ | 316/363 [00:33<00:02, 18.70it/s]
Loading 0:  88%|████████▊ | 320/363 [00:33<00:01, 22.07it/s]
Loading 0:  89%|████████▉ | 323/363 [00:34<00:02, 16.22it/s]
Loading 0:  90%|████████▉ | 326/363 [00:34<00:02, 16.97it/s]
Loading 0:  91%|█████████ | 329/363 [00:34<00:02, 13.55it/s]
Loading 0:  92%|█████████▏| 334/363 [00:34<00:01, 18.82it/s]
Loading 0:  93%|█████████▎| 338/363 [00:34<00:01, 22.09it/s]
Loading 0:  94%|█████████▍| 341/363 [00:35<00:01, 16.39it/s]
Loading 0:  95%|█████████▍| 344/363 [00:35<00:01, 17.07it/s]
Loading 0:  96%|█████████▌| 347/363 [00:35<00:01, 13.56it/s]
Loading 0:  97%|█████████▋| 352/363 [00:35<00:00, 18.62it/s]
Loading 0:  98%|█████████▊| 356/363 [00:35<00:00, 22.09it/s]
Loading 0:  99%|█████████▉| 359/363 [00:36<00:00, 12.06it/s]
Loading 0: 100%|█████████▉| 362/363 [00:36<00:00, 12.15it/s]
                                                            

Job rirv938-harry-potter-rp-65094-v2-mkmlizer completed after 238.23s with status: succeeded
Stopping job with name rirv938-harry-potter-rp-65094-v2-mkmlizer
Pipeline stage MKMLizer completed in 238.84s
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 rirv938-harry-potter-rp-65094-v2
Waiting for inference service rirv938-harry-potter-rp-65094-v2 to be ready
Inference service rirv938-harry-potter-rp-65094-v2 ready after 181.50124788284302s
Pipeline stage MKMLDeployer completed in 181.98s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6476426124572754s
Received healthy response to inference request in 1.616806983947754s
Received healthy response to inference request in 1.9442470073699951s
Received healthy response to inference request in 2.184828519821167s
Received healthy response to inference request in 1.894254446029663s
5 requests
0 failed requests
5th percentile: 1.6722964763641357
10th percentile: 1.7277859687805175
20th percentile: 1.8387649536132813
30th percentile: 1.9042529582977294
40th percentile: 1.9242499828338624
50th percentile: 1.9442470073699951
60th percentile: 2.040479612350464
70th percentile: 2.1367122173309325
80th percentile: 2.2773913383483886
90th percentile: 2.462516975402832
95th percentile: 2.555079793930054
99th percentile: 2.629130048751831
mean time: 2.057555913925171
Pipeline stage StressChecker completed in 11.64s
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 0.68s
Shutdown handler de-registered
rirv938-harry-potter-rp_65094_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3631.69s
Shutdown handler de-registered
rirv938-harry-potter-rp_65094_v2 status is now inactive due to auto deactivation removed underperforming models
rirv938-harry-potter-rp_65094_v2 status is now torndown due to DeploymentManager action