rirv938-gy-rerank-grpo-_99051

developer_uid: rirv938

submission_id: rirv938-gy-rerank-grpo-_99051_v1

model_name: rirv938-gy-rerank-grpo-_99051_v1

model_group: rirv938/gy_rerank_grpo_c

status: torndown

timestamp: 2025-07-04T02:09:39+00:00

num_battles: 7463

num_wins: 3854

celo_rating: 1298.93

family_friendly_score: 0.5292

family_friendly_standard_error: 0.007058999362515909

submission_type: basic

model_repo: rirv938/gy_rerank_grpo_cp624_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': 0.5402569389119208, 'latency_mean': 1.850863801240921, 'latency_p50': 1.8602111339569092, 'latency_p90': 2.0702079057693483}, {'batch_size': 3, 'throughput': 1.120585993325906, 'latency_mean': 2.6672358989715574, 'latency_p50': 2.67147958278656, 'latency_p90': 2.92548406124115}, {'batch_size': 5, 'throughput': 1.458922192283692, 'latency_mean': 3.4123433196544646, 'latency_p50': 3.4048798084259033, 'latency_p90': 3.771431493759155}, {'batch_size': 6, 'throughput': 1.5745485061169489, 'latency_mean': 3.7783367347717287, 'latency_p50': 3.745958089828491, 'latency_p90': 4.235105848312378}, {'batch_size': 8, 'throughput': 1.7423258399401513, 'latency_mean': 4.54756561756134, 'latency_p50': 4.53454065322876, 'latency_p90': 5.141022253036499}, {'batch_size': 10, 'throughput': 1.8434660590490892, 'latency_mean': 5.379423916339874, 'latency_p50': 5.392725825309753, 'latency_p90': 6.065167355537414}]

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

display_name: rirv938-gy-rerank-grpo-_99051_v1

is_internal_developer: True

language_model: rirv938/gy_rerank_grpo_cp624_98ff_b35_r1_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.56

us_pacific_date: 2025-07-03

win_ratio: 0.5164143105989548

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': ['###', 'You:', '\n', '</s>'], '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-gy-rerank-grpo-99051-v1-mkmlizer
Waiting for job on rirv938-gy-rerank-grpo-99051-v1-mkmlizer to finish
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: ║                                                                     ║
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: ║                                                                     ║
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: ║                                                                     ║
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: ║                                                                     ║
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: ║                                                                     ║
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: Downloaded to shared memory in 162.631s
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: Checking if rirv938/gy_rerank_grpo_cp624_98ff_b35_r1_merged already exists in ChaiML
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: Creating repo ChaiML/gy_rerank_grpo_cp624_98ff_b35_r1_merged and uploading /tmp/tmptlmkkkqp to it
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: 
  0%|          | 0/22 [00:00<?, ?it/s]
  5%|▍         | 1/22 [00:03<01:16,  3.63s/it]
  9%|▉         | 2/22 [00:07<01:10,  3.51s/it]
 14%|█▎        | 3/22 [00:11<01:13,  3.88s/it]
 18%|█▊        | 4/22 [00:14<01:06,  3.69s/it]
 23%|██▎       | 5/22 [00:18<01:00,  3.59s/it]
 27%|██▋       | 6/22 [00:21<00:55,  3.48s/it]
 32%|███▏      | 7/22 [00:24<00:51,  3.43s/it]
 36%|███▋      | 8/22 [00:28<00:47,  3.41s/it]
 41%|████      | 9/22 [00:31<00:45,  3.47s/it]
 45%|████▌     | 10/22 [00:38<00:54,  4.52s/it]
 50%|█████     | 11/22 [00:41<00:45,  4.15s/it]
 55%|█████▍    | 12/22 [00:45<00:38,  3.89s/it]
 59%|█████▉    | 13/22 [00:52<00:43,  4.81s/it]
 64%|██████▎   | 14/22 [01:26<01:50, 13.78s/it]
 68%|██████▊   | 15/22 [01:33<01:21, 11.67s/it]
 73%|███████▎  | 16/22 [01:41<01:03, 10.64s/it]
 77%|███████▋  | 17/22 [01:49<00:48,  9.71s/it]
 82%|████████▏ | 18/22 [01:55<00:35,  8.76s/it]
 86%|████████▋ | 19/22 [01:59<00:21,  7.19s/it]
 91%|█████████ | 20/22 [02:03<00:12,  6.19s/it]
 95%|█████████▌| 21/22 [02:07<00:05,  5.72s/it]
100%|██████████| 22/22 [02:08<00:00,  4.35s/it]
100%|██████████| 22/22 [02:08<00:00,  5.86s/it]
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmptlmkkkqp, device:0
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: quantized model in 58.408s
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: Processed model rirv938/gy_rerank_grpo_cp624_98ff_b35_r1_merged in 441.864s
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-gy-rerank-grpo-99051-v1/nvidia
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-gy-rerank-grpo-99051-v1/nvidia/config.json
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-gy-rerank-grpo-99051-v1/nvidia/special_tokens_map.json
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-gy-rerank-grpo-99051-v1/nvidia/tokenizer_config.json
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-gy-rerank-grpo-99051-v1/nvidia/tokenizer.json
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-gy-rerank-grpo-99051-v1/nvidia/flywheel_model.1.safetensors
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-gy-rerank-grpo-99051-v1/nvidia/flywheel_model.0.safetensors
rirv938-gy-rerank-grpo-99051-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:13, 25.87it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:28, 12.37it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:18, 18.66it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:28, 12.14it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:33, 10.34it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:21, 15.67it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:26, 12.79it/s]
Loading 0:   8%|▊         | 29/363 [00:01<00:16, 19.78it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.00it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:22, 14.66it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:21, 15.32it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:26, 12.10it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:18, 17.00it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:15, 20.20it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:21, 14.56it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:20, 15.10it/s]
Loading 0:  16%|█▋        | 59/363 [00:04<00:25, 12.08it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:17, 16.73it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:15, 19.54it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:20, 14.31it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:19, 14.93it/s]
Loading 0:  21%|██        | 76/363 [00:05<00:21, 13.49it/s]
Loading 0:  21%|██▏       | 78/363 [00:05<00:21, 13.12it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:16, 17.52it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:12, 21.56it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:19, 14.41it/s]
Loading 0:  25%|██▌       | 92/363 [00:06<00:18, 15.04it/s]
Loading 0:  26%|██▋       | 96/363 [00:06<00:13, 19.10it/s]
Loading 0:  28%|██▊       | 101/363 [00:06<00:12, 21.28it/s]
Loading 0:  29%|██▊       | 104/363 [00:06<00:14, 17.45it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:18, 13.50it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:19, 12.91it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:18, 13.80it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:21, 11.52it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:14, 17.47it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 21.55it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:15, 15.31it/s]
Loading 0:  35%|███▌      | 128/363 [00:08<00:14, 15.83it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:18, 12.41it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 17.59it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 21.13it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:14, 15.32it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:13, 15.59it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:17, 12.32it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:12, 16.98it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:10, 20.12it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:13, 14.78it/s]
Loading 0:  45%|████▌     | 164/363 [00:10<00:13, 15.02it/s]
Loading 0:  46%|████▌     | 166/363 [00:10<00:14, 13.44it/s]
Loading 0:  46%|████▋     | 168/363 [00:10<00:15, 12.93it/s]
Loading 0:  47%|████▋     | 172/363 [00:11<00:11, 17.05it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:08, 20.89it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:12, 14.66it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:11, 15.26it/s]
Loading 0:  51%|█████     | 184/363 [00:11<00:13, 13.58it/s]
Loading 0:  51%|█████     | 186/363 [00:12<00:13, 13.00it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:10, 17.29it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:08, 20.74it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:11, 14.56it/s]
Loading 0:  55%|█████▍    | 199/363 [00:12<00:11, 13.70it/s]
Loading 0:  55%|█████▌    | 201/363 [00:27<04:46,  1.77s/it]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:38,  1.36s/it]
Loading 0:  57%|█████▋    | 207/363 [00:28<02:06,  1.24it/s]
Loading 0:  58%|█████▊    | 210/363 [00:28<01:27,  1.74it/s]
Loading 0:  59%|█████▊    | 213/363 [00:28<01:04,  2.34it/s]
Loading 0:  59%|█████▉    | 215/363 [00:28<00:52,  2.83it/s]
Loading 0:  60%|█████▉    | 217/363 [00:28<00:42,  3.46it/s]
Loading 0:  60%|██████    | 219/363 [00:28<00:32,  4.37it/s]
Loading 0:  61%|██████    | 221/363 [00:29<00:28,  4.92it/s]
Loading 0:  62%|██████▏   | 226/363 [00:29<00:15,  8.69it/s]
Loading 0:  63%|██████▎   | 230/363 [00:29<00:11, 11.83it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:12, 10.62it/s]
Loading 0:  65%|██████▌   | 236/363 [00:30<00:10, 11.77it/s]
Loading 0:  66%|██████▌   | 238/363 [00:30<00:11, 11.26it/s]
Loading 0:  66%|██████▌   | 240/363 [00:30<00:10, 11.25it/s]
Loading 0:  67%|██████▋   | 244/363 [00:30<00:07, 15.11it/s]
Loading 0:  68%|██████▊   | 248/363 [00:30<00:06, 18.91it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:07, 14.06it/s]
Loading 0:  70%|██████▉   | 253/363 [00:31<00:08, 13.57it/s]
Loading 0:  70%|███████   | 255/363 [00:31<00:07, 14.39it/s]
Loading 0:  71%|███████   | 257/363 [00:31<00:08, 11.78it/s]
Loading 0:  72%|███████▏  | 262/363 [00:31<00:05, 17.87it/s]
Loading 0:  73%|███████▎  | 266/363 [00:31<00:04, 21.54it/s]
Loading 0:  74%|███████▍  | 269/363 [00:32<00:06, 15.29it/s]
Loading 0:  75%|███████▍  | 272/363 [00:32<00:05, 15.94it/s]
Loading 0:  76%|███████▌  | 275/363 [00:32<00:07, 12.31it/s]
Loading 0:  77%|███████▋  | 280/363 [00:32<00:04, 17.01it/s]
Loading 0:  78%|███████▊  | 284/363 [00:32<00:03, 20.25it/s]
Loading 0:  79%|███████▉  | 287/363 [00:33<00:05, 14.87it/s]
Loading 0:  80%|███████▉  | 290/363 [00:33<00:04, 15.31it/s]
Loading 0:  80%|████████  | 292/363 [00:33<00:05, 13.64it/s]
Loading 0:  81%|████████  | 294/363 [00:33<00:05, 13.16it/s]
Loading 0:  82%|████████▏ | 298/363 [00:33<00:03, 17.08it/s]
Loading 0:  83%|████████▎ | 302/363 [00:34<00:02, 20.50it/s]
Loading 0:  84%|████████▍ | 305/363 [00:34<00:04, 14.42it/s]
Loading 0:  85%|████████▍ | 307/363 [00:34<00:04, 13.59it/s]
Loading 0:  85%|████████▌ | 309/363 [00:34<00:03, 14.47it/s]
Loading 0:  86%|████████▌ | 311/363 [00:35<00:04, 11.60it/s]
Loading 0:  87%|████████▋ | 316/363 [00:35<00:02, 17.36it/s]
Loading 0:  88%|████████▊ | 320/363 [00:35<00:02, 20.59it/s]
Loading 0:  89%|████████▉ | 323/363 [00:35<00:02, 14.68it/s]
Loading 0:  90%|████████▉ | 325/363 [00:35<00:02, 13.85it/s]
Loading 0:  90%|█████████ | 327/363 [00:35<00:02, 14.52it/s]
Loading 0:  91%|█████████ | 329/363 [00:36<00:02, 11.82it/s]
Loading 0:  92%|█████████▏| 334/363 [00:36<00:01, 17.81it/s]
Loading 0:  93%|█████████▎| 338/363 [00:36<00:01, 21.33it/s]
Loading 0:  94%|█████████▍| 341/363 [00:36<00:01, 14.85it/s]
Loading 0:  95%|█████████▍| 344/363 [00:36<00:01, 15.41it/s]
Loading 0:  95%|█████████▌| 346/363 [00:37<00:01, 13.82it/s]
Loading 0:  96%|█████████▌| 348/363 [00:37<00:01, 13.23it/s]
Loading 0:  97%|█████████▋| 352/363 [00:37<00:00, 17.45it/s]
Loading 0:  98%|█████████▊| 356/363 [00:37<00:00, 21.13it/s]
Loading 0:  99%|█████████▉| 359/363 [00:38<00:00, 10.80it/s]
Loading 0:  99%|█████████▉| 361/363 [00:38<00:00,  9.82it/s]
                                                            
Job rirv938-gy-rerank-grpo-99051-v1-mkmlizer completed after 476.26s with status: succeeded
Stopping job with name rirv938-gy-rerank-grpo-99051-v1-mkmlizer
Pipeline stage MKMLizer completed in 477.11s
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-gy-rerank-grpo-99051-v1
Waiting for inference service rirv938-gy-rerank-grpo-99051-v1 to be ready
Inference service rirv938-gy-rerank-grpo-99051-v1 ready after 221.0094895362854s
Pipeline stage MKMLDeployer completed in 221.52s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.938856840133667s
Received healthy response to inference request in 1.2980194091796875s
Received healthy response to inference request in 2.4843661785125732s
Received healthy response to inference request in 2.4906952381134033s
Received healthy response to inference request in 2.3509624004364014s
5 requests
0 failed requests
5th percentile: 1.5086080074310302
10th percentile: 1.719196605682373
20th percentile: 2.1403738021850587
30th percentile: 2.3776431560516356
40th percentile: 2.4310046672821044
50th percentile: 2.4843661785125732
60th percentile: 2.4868978023529054
70th percentile: 2.4894294261932375
80th percentile: 2.5803275585174563
90th percentile: 2.7595921993255614
95th percentile: 2.849224519729614
99th percentile: 2.920930376052856
mean time: 2.3125800132751464
Pipeline stage StressChecker completed in 12.89s
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 0.67s
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 0.71s
Shutdown handler de-registered
rirv938-gy-rerank-grpo-_99051_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3308.19s
Shutdown handler de-registered
rirv938-gy-rerank-grpo-_99051_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-gy-rerank-grpo-_99051_v1 status is now torndown due to DeploymentManager action