developer_uid: rirv938
submission_id: rirv938-groksyn-grpo-cp_55837_v2
model_name: rirv938-groksyn-grpo-cp_55837_v2
model_group: rirv938/groksyn_grpo_cp6
status: torndown
timestamp: 2025-07-07T15:53:03+00:00
num_battles: 8382
num_wins: 4246
celo_rating: 1293.76
family_friendly_score: 0.5394
family_friendly_standard_error: 0.007049079939963797
submission_type: basic
model_repo: rirv938/groksyn_grpo_cp624_98ff_b35_r1_merged
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 6
max_input_tokens: 1536
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.4854702980375165, 'latency_mean': 2.0597042739391327, 'latency_p50': 2.0448755025863647, 'latency_p90': 2.266366648674011}, {'batch_size': 3, 'throughput': 0.9355041664918811, 'latency_mean': 3.197147786617279, 'latency_p50': 3.2237355709075928, 'latency_p90': 3.53262825012207}, {'batch_size': 5, 'throughput': 1.1811042369324998, 'latency_mean': 4.2075125074386595, 'latency_p50': 4.232767939567566, 'latency_p90': 4.638977026939392}, {'batch_size': 6, 'throughput': 1.2672088726084123, 'latency_mean': 4.717433354854584, 'latency_p50': 4.674109101295471, 'latency_p90': 5.295678830146789}, {'batch_size': 8, 'throughput': 1.3727907105266057, 'latency_mean': 5.79307343840599, 'latency_p50': 5.777111887931824, 'latency_p90': 6.4910829067230225}, {'batch_size': 10, 'throughput': 1.4382526144784706, 'latency_mean': 6.894899425506591, 'latency_p50': 6.95840847492218, 'latency_p90': 7.82077808380127}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: rirv938-groksyn-grpo-cp_55837_v2
is_internal_developer: True
language_model: rirv938/groksyn_grpo_cp624_98ff_b35_r1_merged
model_size: 24B
ranking_group: single
throughput_3p7s: 1.08
us_pacific_date: 2025-07-07
win_ratio: 0.5065616797900262
generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n', '<|im_end|>', '<|im_start|>'], 'max_input_tokens': 1536, 'best_of': 6, 'max_output_tokens': 64}
formatter: {'memory_template': '<|system|>{bot_name}memory:{memory}\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', '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-groksyn-grpo-cp-55837-v2-mkmlizer
Waiting for job on rirv938-groksyn-grpo-cp-55837-v2-mkmlizer to finish
Failed to get response for submission rirv938-harry-potter-rp_79878_v2: HTTPConnectionPool(host='rirv938-harry-potter-rp-79878-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: ║ ║
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: ║ ║
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: ║ Version: 0.29.15 ║
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: ║ https://mk1.ai ║
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: ║ ║
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: ║ belonging to: ║
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: ║ ║
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: ║ Chai Research Corp. ║
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: ║ ║
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: Downloaded to shared memory in 206.155s
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: Checking if rirv938/groksyn_grpo_cp624_98ff_b35_r1_merged already exists in ChaiML
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpm8txinjf, device:0
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Retrying (%r) after connection broken by '%r': %s
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: quantized model in 100.357s
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: Processed model rirv938/groksyn_grpo_cp624_98ff_b35_r1_merged in 306.601s
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: creating bucket guanaco-mkml-models
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-groksyn-grpo-cp-55837-v2/nvidia
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-groksyn-grpo-cp-55837-v2/nvidia/config.json
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-groksyn-grpo-cp-55837-v2/nvidia/special_tokens_map.json
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-groksyn-grpo-cp-55837-v2/nvidia/tokenizer_config.json
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-groksyn-grpo-cp-55837-v2/nvidia/tokenizer.json
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-groksyn-grpo-cp-55837-v2/nvidia/flywheel_model.1.safetensors
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-groksyn-grpo-cp-55837-v2/nvidia/flywheel_model.0.safetensors
rirv938-groksyn-grpo-cp-55837-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 3/363 [00:00<00:19, 18.79it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:46, 7.71it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:23, 15.15it/s] Loading 0: 4%|▎ | 13/363 [00:01<00:35, 9.86it/s] Loading 0: 4%|▍ | 15/363 [00:01<00:45, 7.61it/s] Loading 0: 5%|▌ | 19/363 [00:01<00:30, 11.29it/s] Loading 0: 6%|▌ | 21/363 [00:01<00:29, 11.79it/s] Loading 0: 6%|▋ | 23/363 [00:02<00:35, 9.50it/s] Loading 0: 8%|▊ | 28/363 [00:02<00:23, 14.40it/s] Loading 0: 9%|▉ | 32/363 [00:02<00:19, 17.18it/s] Loading 0: 10%|▉ | 35/363 [00:03<00:30, 10.65it/s] Loading 0: 10%|█ | 37/363 [00:03<00:32, 10.01it/s] Loading 0: 11%|█ | 39/363 [00:03<00:30, 10.54it/s] Loading 0: 11%|█▏ | 41/363 [00:03<00:39, 8.18it/s] Loading 0: 13%|█▎ | 46/363 [00:04<00:25, 12.30it/s] Loading 0: 14%|█▍ | 50/363 [00:04<00:21, 14.82it/s] Loading 0: 14%|█▍ | 52/363 [00:04<00:29, 10.60it/s] Loading 0: 15%|█▍ | 54/363 [00:05<00:38, 8.11it/s] Loading 0: 16%|█▌ | 57/363 [00:05<00:31, 9.57it/s] Loading 0: 16%|█▋ | 59/363 [00:05<00:39, 7.77it/s] Loading 0: 18%|█▊ | 64/363 [00:05<00:25, 11.88it/s] Loading 0: 19%|█▊ | 68/363 [00:06<00:20, 14.60it/s] Loading 0: 19%|█▉ | 70/363 [00:06<00:28, 10.39it/s] Loading 0: 20%|█▉ | 72/363 [00:06<00:36, 7.93it/s] Loading 0: 21%|██ | 75/363 [00:07<00:30, 9.48it/s] Loading 0: 21%|██ | 77/363 [00:07<00:36, 7.87it/s] Loading 0: 23%|██▎ | 82/363 [00:07<00:23, 11.92it/s] Loading 0: 24%|██▎ | 86/363 [00:07<00:18, 14.74it/s] Loading 0: 24%|██▍ | 88/363 [00:08<00:28, 9.81it/s] Loading 0: 25%|██▍ | 90/363 [00:08<00:34, 7.89it/s] Loading 0: 26%|██▌ | 95/363 [00:08<00:22, 11.70it/s] Loading 0: 27%|██▋ | 99/363 [00:09<00:18, 14.40it/s] Loading 0: 28%|██▊ | 102/363 [00:09<00:20, 12.65it/s] Loading 0: 29%|██▊ | 104/363 [00:09<00:23, 11.08it/s] Loading 0: 29%|██▉ | 106/363 [00:10<00:29, 8.77it/s] Loading 0: 30%|██▉ | 108/363 [00:10<00:33, 7.59it/s] Loading 0: 31%|███ | 111/363 [00:10<00:26, 9.44it/s] Loading 0: 31%|███ | 113/363 [00:10<00:32, 7.69it/s] Loading 0: 33%|███▎ | 118/363 [00:11<00:20, 12.14it/s] Loading 0: 34%|███▎ | 122/363 [00:11<00:15, 15.10it/s] Loading 0: 34%|███▍ | 125/363 [00:11<00:23, 10.12it/s] Loading 0: 35%|███▍ | 127/363 [00:12<00:24, 9.83it/s] Loading 0: 36%|███▌ | 129/363 [00:12<00:22, 10.36it/s] Loading 0: 36%|███▌ | 131/363 [00:12<00:27, 8.33it/s] Loading 0: 37%|███▋ | 136/363 [00:12<00:17, 12.72it/s] Loading 0: 39%|███▊ | 140/363 [00:12<00:14, 15.57it/s] Loading 0: 39%|███▉ | 143/363 [00:13<00:20, 10.69it/s] Loading 0: 40%|███▉ | 145/363 [00:13<00:21, 9.99it/s] Loading 0: 40%|████ | 147/363 [00:13<00:20, 10.65it/s] Loading 0: 41%|████ | 149/363 [00:14<00:25, 8.56it/s] Loading 0: 42%|████▏ | 154/363 [00:14<00:16, 12.74it/s] Loading 0: 44%|████▎ | 158/363 [00:14<00:12, 16.01it/s] Loading 0: 44%|████▍ | 161/363 [00:15<00:18, 10.71it/s] Loading 0: 45%|████▍ | 163/363 [00:15<00:19, 10.05it/s] Loading 0: 45%|████▌ | 165/363 [00:15<00:18, 10.61it/s] Loading 0: 46%|████▌ | 167/363 [00:15<00:23, 8.41it/s] Loading 0: 47%|████▋ | 172/363 [00:15<00:14, 13.11it/s] Loading 0: 48%|████▊ | 176/363 [00:16<00:11, 16.01it/s] Loading 0: 49%|████▉ | 179/363 [00:16<00:18, 10.17it/s] Loading 0: 50%|████▉ | 181/363 [00:16<00:19, 9.46it/s] Loading 0: 50%|█████ | 183/363 [00:17<00:18, 9.79it/s] Loading 0: 51%|█████ | 185/363 [00:17<00:22, 7.87it/s] Loading 0: 52%|█████▏ | 190/363 [00:17<00:14, 11.55it/s] Loading 0: 53%|█████▎ | 194/363 [00:17<00:12, 13.41it/s] Loading 0: 54%|█████▍ | 196/363 [00:18<00:17, 9.60it/s] Loading 0: 55%|█████▍ | 198/363 [00:18<00:21, 7.79it/s] Loading 0: 55%|█████▌ | 200/363 [00:30<00:20, 7.79it/s] Loading 0: 55%|█████▌ | 201/363 [00:45<08:01, 2.97s/it] Loading 0: 56%|█████▌ | 202/363 [00:45<06:58, 2.60s/it] Loading 0: 56%|█████▌ | 203/363 [00:46<05:56, 2.23s/it] Loading 0: 57%|█████▋ | 207/363 [00:46<03:04, 1.18s/it] Loading 0: 58%|█████▊ | 209/363 [00:46<02:18, 1.11it/s] Loading 0: 58%|█████▊ | 212/363 [00:46<01:31, 1.66it/s] Loading 0: 59%|█████▉ | 214/363 [00:47<01:15, 1.99it/s] Loading 0: 60%|█████▉ | 216/363 [00:47<01:02, 2.35it/s] Loading 0: 60%|██████ | 219/363 [00:47<00:41, 3.46it/s] Loading 0: 61%|██████ | 221/363 [00:47<00:37, 3.77it/s] Loading 0: 62%|██████▏ | 226/363 [00:48<00:20, 6.57it/s] Loading 0: 63%|██████▎ | 230/363 [00:48<00:14, 8.92it/s] Loading 0: 64%|██████▍ | 233/363 [00:48<00:17, 7.27it/s] Loading 0: 65%|██████▍ | 235/363 [00:49<00:17, 7.41it/s] Loading 0: 65%|██████▌ | 237/363 [00:49<00:15, 8.14it/s] Loading 0: 66%|██████▌ | 239/363 [00:49<00:16, 7.35it/s] Loading 0: 67%|██████▋ | 244/363 [00:49<00:10, 11.69it/s] Loading 0: 68%|██████▊ | 248/363 [00:49<00:07, 14.42it/s] Loading 0: 69%|██████▉ | 251/363 [00:50<00:11, 10.12it/s] Loading 0: 70%|██████▉ | 253/363 [00:50<00:12, 9.15it/s] Loading 0: 70%|███████ | 255/363 [00:50<00:11, 9.62it/s] Loading 0: 71%|███████ | 257/363 [00:51<00:15, 7.03it/s] Loading 0: 72%|███████▏ | 262/363 [00:51<00:09, 10.47it/s] Loading 0: 73%|███████▎ | 266/363 [00:51<00:07, 12.71it/s] Loading 0: 74%|███████▍ | 268/363 [00:52<00:09, 10.12it/s] Loading 0: 74%|███████▍ | 270/363 [00:52<00:11, 8.21it/s] Loading 0: 75%|███████▌ | 273/363 [00:52<00:08, 10.03it/s] Loading 0: 76%|███████▌ | 275/363 [00:53<00:10, 8.28it/s] Loading 0: 77%|███████▋ | 280/363 [00:53<00:06, 12.55it/s] Loading 0: 78%|███████▊ | 284/363 [00:53<00:05, 14.83it/s] Loading 0: 79%|███████▉ | 286/363 [00:53<00:07, 10.84it/s] Loading 0: 79%|███████▉ | 288/363 [00:54<00:08, 8.66it/s] Loading 0: 80%|████████ | 291/363 [00:54<00:06, 10.61it/s] Loading 0: 81%|████████ | 293/363 [00:54<00:08, 8.65it/s] Loading 0: 82%|████████▏ | 298/363 [00:54<00:04, 13.15it/s] Loading 0: 83%|████████▎ | 302/363 [00:55<00:04, 15.11it/s] Loading 0: 84%|████████▎ | 304/363 [00:55<00:05, 10.73it/s] Loading 0: 84%|████████▍ | 306/363 [00:55<00:06, 9.07it/s] Loading 0: 85%|████████▌ | 309/363 [00:56<00:04, 11.13it/s] Loading 0: 86%|████████▌ | 311/363 [00:56<00:06, 8.61it/s] Loading 0: 87%|████████▋ | 316/363 [00:56<00:03, 12.91it/s] Loading 0: 88%|████████▊ | 320/363 [00:56<00:02, 15.94it/s] Loading 0: 89%|████████▉ | 323/363 [00:57<00:03, 10.86it/s] Loading 0: 90%|████████▉ | 325/363 [00:57<00:03, 10.01it/s] Loading 0: 90%|█████████ | 327/363 [00:57<00:03, 10.55it/s] Loading 0: 91%|█████████ | 329/363 [00:58<00:04, 8.35it/s] Loading 0: 92%|█████████▏| 334/363 [00:58<00:02, 12.49it/s] Loading 0: 93%|█████████▎| 338/363 [00:58<00:01, 14.36it/s] Loading 0: 94%|█████████▎| 340/363 [00:58<00:02, 9.68it/s] Loading 0: 94%|█████████▍| 342/363 [00:59<00:02, 7.71it/s] Loading 0: 95%|█████████▌| 345/363 [00:59<00:02, 8.99it/s] Loading 0: 96%|█████████▌| 347/363 [01:00<00:02, 6.99it/s] Loading 0: 97%|█████████▋| 352/363 [01:00<00:01, 10.44it/s] Loading 0: 98%|█████████▊| 356/363 [01:00<00:00, 12.42it/s] Loading 0: 99%|█████████▊| 358/363 [01:01<00:00, 6.76it/s] Loading 0: 99%|█████████▉| 360/363 [01:01<00:00, 6.90it/s] Loading 0: 100%|█████████▉| 362/363 [01:01<00:00, 7.23it/s]
Job rirv938-groksyn-grpo-cp-55837-v2-mkmlizer completed after 354.83s with status: succeeded
Stopping job with name rirv938-groksyn-grpo-cp-55837-v2-mkmlizer
Pipeline stage MKMLizer completed in 355.37s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-groksyn-grpo-cp-55837-v2
Waiting for inference service rirv938-groksyn-grpo-cp-55837-v2 to be ready
Inference service rirv938-groksyn-grpo-cp-55837-v2 ready after 191.17695689201355s
Pipeline stage MKMLDeployer completed in 191.99s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0083906650543213s
Received healthy response to inference request in 1.661710262298584s
Received healthy response to inference request in 1.5772335529327393s
Received healthy response to inference request in 1.5356454849243164s
Received healthy response to inference request in 2.1766324043273926s
5 requests
0 failed requests
5th percentile: 1.5439630985260009
10th percentile: 1.5522807121276856
20th percentile: 1.5689159393310548
30th percentile: 1.5941288948059082
40th percentile: 1.627919578552246
50th percentile: 1.661710262298584
60th percentile: 1.8676791191101074
70th percentile: 2.073647975921631
80th percentile: 2.3429840564727784
90th percentile: 2.67568736076355
95th percentile: 2.8420390129089355
99th percentile: 2.975120334625244
mean time: 1.9919224739074708
Pipeline stage StressChecker completed in 11.59s
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 0.77s
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-groksyn-grpo-cp_55837_v2 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-groksyn-grpo-cp-55837-v2-profiler
Waiting for inference service rirv938-groksyn-grpo-cp-55837-v2-profiler to be ready
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 5959.46s
Shutdown handler de-registered
rirv938-groksyn-grpo-cp_55837_v2 status is now inactive due to auto deactivation removed underperforming models
rirv938-groksyn-grpo-cp_55837_v2 status is now torndown due to DeploymentManager action