developer_uid: rirv938
submission_id: rirv938-simp-grpo-cp624_97924_v1
model_name: rirv938-simp-grpo-cp624_97924_v1
model_group: rirv938/simp_grpo_cp624_
status: torndown
timestamp: 2025-07-02T17:21:01+00:00
num_battles: 6668
num_wins: 3423
celo_rating: 1293.34
family_friendly_score: 0.48960000000000004
family_friendly_standard_error: 0.00706953803299763
submission_type: basic
model_repo: rirv938/simp_grpo_cp624_2ff_b35_r1_ava_rm_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': 0.5431427279453789, 'latency_mean': 1.8410147297382355, 'latency_p50': 1.8526784181594849, 'latency_p90': 2.0499468564987184}, {'batch_size': 3, 'throughput': 1.1438985550939758, 'latency_mean': 2.619631918668747, 'latency_p50': 2.6341437101364136, 'latency_p90': 2.8668268442153932}, {'batch_size': 5, 'throughput': 1.4890518695545298, 'latency_mean': 3.337046625614166, 'latency_p50': 3.3419957160949707, 'latency_p90': 3.7058005809783934}, {'batch_size': 6, 'throughput': 1.6098263803731818, 'latency_mean': 3.706842256784439, 'latency_p50': 3.7093359231948853, 'latency_p90': 4.168351840972901}, {'batch_size': 8, 'throughput': 1.7758444990866336, 'latency_mean': 4.467865998744965, 'latency_p50': 4.472991466522217, 'latency_p90': 5.006855630874634}, {'batch_size': 10, 'throughput': 1.8772048369206986, 'latency_mean': 5.263312658071518, 'latency_p50': 5.33134913444519, 'latency_p90': 5.973056674003601}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: rirv938-simp-grpo-cp624_97924_v1
ineligible_reason: num_battles<10000
is_internal_developer: True
language_model: rirv938/simp_grpo_cp624_2ff_b35_r1_ava_rm_merged
model_size: 24B
ranking_group: single
throughput_3p7s: 1.62
us_pacific_date: 2025-07-02
win_ratio: 0.5133473305338933
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-simp-grpo-cp624-97924-v1-mkmlizer
Waiting for job on rirv938-simp-grpo-cp624-97924-v1-mkmlizer to finish
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: ║ ║
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: ║ ║
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: ║ Version: 0.29.8 ║
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: ║ ║
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: ║ belonging to: ║
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: ║ ║
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: ║ ║
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: Downloaded to shared memory in 324.235s
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: Checking if rirv938/simp_grpo_cp624_2ff_b35_r1_ava_rm_merged already exists in ChaiML
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: Creating repo ChaiML/simp_grpo_cp624_2ff_b35_r1_ava_rm_merged and uploading /tmp/tmplleal156 to it
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: 0%| | 0/22 [00:00<?, ?it/s] 5%|▍ | 1/22 [00:04<01:24, 4.01s/it] 9%|▉ | 2/22 [00:11<01:57, 5.86s/it] 14%|█▎ | 3/22 [00:18<02:00, 6.32s/it] 18%|█▊ | 4/22 [00:23<01:46, 5.93s/it] 23%|██▎ | 5/22 [00:27<01:26, 5.12s/it] 27%|██▋ | 6/22 [00:34<01:36, 6.01s/it] 32%|███▏ | 7/22 [00:43<01:41, 6.74s/it] 36%|███▋ | 8/22 [00:47<01:24, 6.07s/it] 41%|████ | 9/22 [00:56<01:28, 6.81s/it] 45%|████▌ | 10/22 [01:03<01:22, 6.87s/it] 50%|█████ | 11/22 [01:06<01:04, 5.86s/it] 55%|█████▍ | 12/22 [01:11<00:54, 5.41s/it] 59%|█████▉ | 13/22 [01:14<00:43, 4.80s/it] 64%|██████▎ | 14/22 [01:21<00:42, 5.36s/it] 68%|██████▊ | 15/22 [01:24<00:33, 4.84s/it] 73%|███████▎ | 16/22 [01:32<00:34, 5.82s/it] 77%|███████▋ | 17/22 [01:36<00:25, 5.20s/it] 82%|████████▏ | 18/22 [01:42<00:21, 5.46s/it] 86%|████████▋ | 19/22 [01:46<00:14, 4.85s/it] 91%|█████████ | 20/22 [01:49<00:09, 4.52s/it] 95%|█████████▌| 21/22 [01:53<00:04, 4.24s/it] 100%|██████████| 22/22 [01:54<00:00, 3.42s/it] 100%|██████████| 22/22 [01:54<00:00, 5.23s/it]
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplleal156, device:0
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: quantized model in 58.058s
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: Processed model rirv938/simp_grpo_cp624_2ff_b35_r1_ava_rm_merged in 589.711s
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-simp-grpo-cp624-97924-v1/nvidia
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-simp-grpo-cp624-97924-v1/nvidia/config.json
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-simp-grpo-cp624-97924-v1/nvidia/special_tokens_map.json
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-simp-grpo-cp624-97924-v1/nvidia/tokenizer.json
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-simp-grpo-cp624-97924-v1/nvidia/flywheel_model.1.safetensors
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-simp-grpo-cp624-97924-v1/nvidia/flywheel_model.0.safetensors
rirv938-simp-grpo-cp624-97924-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 3/363 [00:00<00:12, 29.52it/s] Loading 0: 2%|▏ | 6/363 [00:00<00:25, 14.17it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:16, 20.82it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:25, 13.95it/s] Loading 0: 4%|▍ | 15/363 [00:01<00:30, 11.34it/s] Loading 0: 6%|▌ | 21/363 [00:01<00:20, 16.53it/s] Loading 0: 6%|▋ | 23/363 [00:01<00:25, 13.32it/s] Loading 0: 8%|▊ | 28/363 [00:01<00:17, 18.88it/s] Loading 0: 9%|▉ | 32/363 [00:01<00:14, 22.19it/s] Loading 0: 10%|▉ | 35/363 [00:02<00:21, 15.43it/s] Loading 0: 10%|█ | 38/363 [00:02<00:20, 16.13it/s] Loading 0: 11%|█▏ | 41/363 [00:02<00:25, 12.59it/s] Loading 0: 13%|█▎ | 46/363 [00:02<00:17, 17.76it/s] Loading 0: 14%|█▍ | 50/363 [00:02<00:14, 21.42it/s] Loading 0: 15%|█▍ | 54/363 [00:03<00:22, 13.61it/s] Loading 0: 16%|█▌ | 57/363 [00:03<00:20, 15.29it/s] Loading 0: 17%|█▋ | 60/363 [00:03<00:21, 13.88it/s] Loading 0: 18%|█▊ | 64/363 [00:03<00:17, 17.01it/s] Loading 0: 19%|█▊ | 68/363 [00:04<00:14, 20.08it/s] Loading 0: 20%|█▉ | 71/363 [00:04<00:19, 14.63it/s] Loading 0: 20%|██ | 74/363 [00:04<00:18, 15.29it/s] Loading 0: 21%|██ | 76/363 [00:04<00:20, 13.67it/s] Loading 0: 21%|██▏ | 78/363 [00:05<00:21, 13.25it/s] Loading 0: 23%|██▎ | 82/363 [00:05<00:15, 17.80it/s] Loading 0: 24%|██▎ | 86/363 [00:05<00:12, 21.87it/s] Loading 0: 25%|██▍ | 89/363 [00:05<00:17, 15.37it/s] Loading 0: 25%|██▌ | 92/363 [00:05<00:17, 15.56it/s] Loading 0: 26%|██▌ | 95/363 [00:05<00:14, 17.93it/s] Loading 0: 27%|██▋ | 99/363 [00:05<00:11, 22.09it/s] Loading 0: 28%|██▊ | 102/363 [00:06<00:13, 19.62it/s] Loading 0: 29%|██▉ | 105/363 [00:06<00:17, 15.00it/s] Loading 0: 29%|██▉ | 107/363 [00:06<00:18, 13.65it/s] Loading 0: 30%|███ | 109/363 [00:06<00:19, 13.22it/s] Loading 0: 31%|███ | 111/363 [00:06<00:17, 14.10it/s] Loading 0: 31%|███ | 113/363 [00:07<00:21, 11.48it/s] Loading 0: 33%|███▎ | 118/363 [00:07<00:13, 17.53it/s] Loading 0: 34%|███▎ | 122/363 [00:07<00:11, 21.85it/s] Loading 0: 34%|███▍ | 125/363 [00:07<00:15, 15.28it/s] Loading 0: 35%|███▌ | 128/363 [00:07<00:14, 16.03it/s] Loading 0: 36%|███▌ | 131/363 [00:08<00:18, 12.42it/s] Loading 0: 38%|███▊ | 137/363 [00:08<00:11, 19.08it/s] Loading 0: 39%|███▉ | 141/363 [00:08<00:12, 18.03it/s] Loading 0: 40%|███▉ | 144/363 [00:09<00:15, 13.76it/s] Loading 0: 40%|████ | 147/363 [00:09<00:13, 15.79it/s] Loading 0: 41%|████▏ | 150/363 [00:09<00:14, 14.34it/s] Loading 0: 42%|████▏ | 154/363 [00:09<00:11, 18.32it/s] Loading 0: 44%|████▎ | 158/363 [00:09<00:09, 22.08it/s] Loading 0: 44%|████▍ | 161/363 [00:10<00:12, 15.79it/s] Loading 0: 45%|████▌ | 164/363 [00:10<00:12, 16.31it/s] Loading 0: 46%|████▌ | 167/363 [00:10<00:15, 12.82it/s] Loading 0: 47%|████▋ | 172/363 [00:10<00:10, 18.13it/s] Loading 0: 48%|████▊ | 176/363 [00:10<00:08, 21.63it/s] Loading 0: 49%|████▉ | 179/363 [00:11<00:11, 15.75it/s] Loading 0: 50%|█████ | 182/363 [00:11<00:11, 16.31it/s] Loading 0: 51%|█████ | 185/363 [00:11<00:14, 12.42it/s] Loading 0: 52%|█████▏ | 190/363 [00:11<00:10, 17.06it/s] Loading 0: 53%|█████▎ | 194/363 [00:11<00:08, 20.19it/s] Loading 0: 54%|█████▍ | 197/363 [00:12<00:11, 15.07it/s] Loading 0: 55%|█████▌ | 200/363 [00:12<00:10, 15.80it/s] Loading 0: 56%|█████▌ | 203/363 [00:28<03:56, 1.48s/it] Loading 0: 57%|█████▋ | 207/363 [00:28<02:32, 1.02it/s] Loading 0: 58%|█████▊ | 210/363 [00:28<01:51, 1.37it/s] Loading 0: 59%|█████▊ | 213/363 [00:28<01:22, 1.81it/s] Loading 0: 60%|█████▉ | 216/363 [00:28<01:02, 2.34it/s] Loading 0: 60%|██████ | 219/363 [00:29<00:45, 3.18it/s] Loading 0: 61%|██████ | 222/363 [00:29<00:34, 4.04it/s] Loading 0: 62%|██████▏ | 226/363 [00:29<00:23, 5.95it/s] Loading 0: 64%|██████▎ | 231/363 [00:29<00:16, 8.20it/s] Loading 0: 64%|██████▍ | 234/363 [00:30<00:15, 8.27it/s] Loading 0: 65%|██████▌ | 237/363 [00:30<00:12, 10.19it/s] Loading 0: 66%|██████▌ | 240/363 [00:30<00:11, 10.57it/s] Loading 0: 67%|██████▋ | 244/363 [00:30<00:08, 14.11it/s] Loading 0: 69%|██████▊ | 249/363 [00:30<00:07, 16.03it/s] Loading 0: 69%|██████▉ | 252/363 [00:31<00:08, 13.24it/s] Loading 0: 70%|███████ | 255/363 [00:31<00:07, 15.39it/s] Loading 0: 71%|███████ | 258/363 [00:31<00:07, 14.26it/s] Loading 0: 72%|███████▏ | 263/363 [00:31<00:05, 19.50it/s] Loading 0: 74%|███████▎ | 267/363 [00:31<00:05, 18.58it/s] Loading 0: 74%|███████▍ | 270/363 [00:32<00:06, 14.53it/s] Loading 0: 75%|███████▌ | 273/363 [00:32<00:05, 16.69it/s] Loading 0: 76%|███████▌ | 276/363 [00:32<00:05, 15.03it/s] Loading 0: 77%|███████▋ | 281/363 [00:32<00:04, 20.41it/s] Loading 0: 79%|███████▊ | 285/363 [00:32<00:04, 19.20it/s] Loading 0: 79%|███████▉ | 288/363 [00:33<00:05, 14.76it/s] Loading 0: 80%|████████ | 291/363 [00:33<00:04, 16.94it/s] Loading 0: 81%|████████ | 294/363 [00:33<00:04, 15.20it/s] Loading 0: 82%|████████▏ | 298/363 [00:33<00:03, 19.08it/s] Loading 0: 83%|████████▎ | 302/363 [00:33<00:02, 22.88it/s] Loading 0: 84%|████████▍ | 305/363 [00:34<00:03, 16.42it/s] Loading 0: 85%|████████▍ | 308/363 [00:34<00:03, 17.12it/s] Loading 0: 86%|████████▌ | 311/363 [00:34<00:03, 13.30it/s] Loading 0: 87%|████████▋ | 316/363 [00:34<00:02, 18.64it/s] Loading 0: 88%|████████▊ | 320/363 [00:34<00:01, 21.74it/s] Loading 0: 89%|████████▉ | 323/363 [00:35<00:02, 15.82it/s] Loading 0: 90%|████████▉ | 326/363 [00:35<00:02, 16.47it/s] Loading 0: 91%|█████████ | 329/363 [00:35<00:02, 13.01it/s] Loading 0: 92%|█████████▏| 334/363 [00:35<00:01, 17.54it/s] Loading 0: 93%|█████████▎| 338/363 [00:35<00:01, 20.47it/s] Loading 0: 94%|█████████▍| 341/363 [00:36<00:01, 15.25it/s] Loading 0: 95%|█████████▍| 344/363 [00:36<00:01, 15.98it/s] Loading 0: 96%|█████████▌| 347/363 [00:36<00:01, 12.71it/s] Loading 0: 97%|█████████▋| 352/363 [00:36<00:00, 17.96it/s] Loading 0: 98%|█████████▊| 356/363 [00:37<00:00, 21.56it/s] Loading 0: 99%|█████████▉| 360/363 [00:37<00:00, 11.86it/s] Loading 0: 100%|██████████| 363/363 [00:37<00:00, 13.09it/s]
Job rirv938-simp-grpo-cp624-97924-v1-mkmlizer completed after 677.77s with status: succeeded
Stopping job with name rirv938-simp-grpo-cp624-97924-v1-mkmlizer
Pipeline stage MKMLizer completed in 678.37s
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-simp-grpo-cp624-97924-v1
Waiting for inference service rirv938-simp-grpo-cp624-97924-v1 to be ready
Inference service rirv938-simp-grpo-cp624-97924-v1 ready after 210.91898560523987s
Pipeline stage MKMLDeployer completed in 211.58s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0587048530578613s
Received healthy response to inference request in 1.8169150352478027s
Received healthy response to inference request in 2.135964870452881s
Received healthy response to inference request in 1.8922767639160156s
Received healthy response to inference request in 1.9291110038757324s
5 requests
0 failed requests
5th percentile: 1.8319873809814453
10th percentile: 1.847059726715088
20th percentile: 1.877204418182373
30th percentile: 1.899643611907959
40th percentile: 1.9143773078918458
50th percentile: 1.9291110038757324
60th percentile: 2.0118525505065916
70th percentile: 2.0945940971374513
80th percentile: 2.320512866973877
90th percentile: 2.6896088600158694
95th percentile: 2.874156856536865
99th percentile: 3.021795253753662
mean time: 2.1665945053100586
Pipeline stage StressChecker completed in 12.11s
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 0.65s
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-simp-grpo-cp624_97924_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 5700.45s
Shutdown handler de-registered
rirv938-simp-grpo-cp624_97924_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-simp-grpo-cp624_97924_v1 status is now torndown due to DeploymentManager action