developer_uid: rirv938
submission_id: rirv938-rinen-grpo-cp15_48820_v1
model_name: rirv938-rinen-grpo-cp15_48820_v1
model_group: rirv938/rinen_grpo_cp156
status: torndown
timestamp: 2025-05-21T19:57:57+00:00
num_battles: 6608
num_wins: 3380
celo_rating: 1299.44
family_friendly_score: 0.5584
family_friendly_standard_error: 0.007022669577874214
submission_type: basic
model_repo: rirv938/rinen_grpo_cp156_97ff_slerp_rm_b4_merged
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
display_name: rirv938-rinen-grpo-cp15_48820_v1
is_internal_developer: True
language_model: rirv938/rinen_grpo_cp156_97ff_slerp_rm_b4_merged
model_size: 13B
ranking_group: single
us_pacific_date: 2025-05-21
win_ratio: 0.511501210653753
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>', '####', '\n', '<|im_end|>', 'User:', 'Bot:', 'You:', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {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-rinen-grpo-cp15-48820-v1-mkmlizer
Waiting for job on rirv938-rinen-grpo-cp15-48820-v1-mkmlizer to finish
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: ║ _____ __ __ ║
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: ║ /___/ ║
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: ║ ║
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: ║ Version: 0.12.8 ║
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: ║ ║
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: ║ belonging to: ║
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: ║ ║
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: ║ ║
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: Downloaded to shared memory in 82.492s
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwm8ja25i, device:0
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: quantized model in 62.061s
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: Processed model rirv938/rinen_grpo_cp156_97ff_slerp_rm_b4_merged in 144.554s
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-rinen-grpo-cp15-48820-v1
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-rinen-grpo-cp15-48820-v1/config.json
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-rinen-grpo-cp15-48820-v1/special_tokens_map.json
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-rinen-grpo-cp15-48820-v1/tokenizer_config.json
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-rinen-grpo-cp15-48820-v1/tokenizer.json
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-rinen-grpo-cp15-48820-v1/flywheel_model.0.safetensors
rirv938-rinen-grpo-cp15-48820-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:00<01:20, 4.48it/s] Loading 0: 1%|▏ | 5/363 [00:01<01:26, 4.14it/s] Loading 0: 3%|▎ | 10/363 [00:01<00:39, 9.02it/s] Loading 0: 4%|▍ | 14/363 [00:01<00:30, 11.60it/s] Loading 0: 6%|▌ | 20/363 [00:01<00:18, 18.48it/s] Loading 0: 7%|▋ | 24/363 [00:01<00:20, 16.21it/s] Loading 0: 7%|▋ | 27/363 [00:02<00:20, 16.47it/s] Loading 0: 9%|▊ | 31/363 [00:02<00:16, 19.85it/s] Loading 0: 9%|▉ | 34/363 [00:03<00:55, 5.90it/s] Loading 0: 10%|█ | 37/363 [00:03<00:43, 7.47it/s] Loading 0: 11%|█▏ | 41/363 [00:04<00:33, 9.47it/s] Loading 0: 13%|█▎ | 48/363 [00:04<00:21, 14.88it/s] Loading 0: 14%|█▍ | 51/363 [00:04<00:19, 15.69it/s] Loading 0: 15%|█▌ | 56/363 [00:04<00:15, 19.25it/s] Loading 0: 17%|█▋ | 61/363 [00:04<00:15, 19.20it/s] Loading 0: 18%|█▊ | 64/363 [00:06<00:46, 6.41it/s] Loading 0: 19%|█▉ | 69/363 [00:06<00:32, 9.11it/s] Loading 0: 20%|█▉ | 72/363 [00:06<00:28, 10.34it/s] Loading 0: 21%|██ | 77/363 [00:06<00:22, 12.94it/s] Loading 0: 23%|██▎ | 84/363 [00:07<00:15, 18.45it/s] Loading 0: 24%|██▍ | 88/363 [00:07<00:13, 19.72it/s] Loading 0: 26%|██▌ | 93/363 [00:07<00:11, 23.41it/s] Loading 0: 27%|██▋ | 97/363 [00:07<00:10, 24.24it/s] Loading 0: 28%|██▊ | 101/363 [00:07<00:12, 21.74it/s] Loading 0: 29%|██▊ | 104/363 [00:09<00:39, 6.59it/s] Loading 0: 31%|███ | 111/363 [00:09<00:24, 10.47it/s] Loading 0: 31%|███▏ | 114/363 [00:09<00:21, 11.70it/s] Loading 0: 33%|███▎ | 120/363 [00:09<00:15, 16.13it/s] Loading 0: 34%|███▍ | 124/363 [00:09<00:13, 18.01it/s] Loading 0: 36%|███▌ | 129/363 [00:09<00:10, 21.66it/s] Loading 0: 37%|███▋ | 133/363 [00:10<00:10, 22.79it/s] Loading 0: 38%|███▊ | 137/363 [00:11<00:32, 6.90it/s] Loading 0: 39%|███▉ | 141/363 [00:11<00:24, 8.99it/s] Loading 0: 40%|███▉ | 144/363 [00:12<00:24, 8.99it/s] Loading 0: 41%|████ | 149/363 [00:12<00:18, 11.69it/s] Loading 0: 43%|████▎ | 156/363 [00:12<00:12, 17.18it/s] Loading 0: 44%|████▍ | 160/363 [00:12<00:10, 18.47it/s] Loading 0: 45%|████▌ | 165/363 [00:14<00:25, 7.85it/s] Loading 0: 46%|████▋ | 168/363 [00:14<00:22, 8.86it/s] Loading 0: 47%|████▋ | 172/363 [00:14<00:16, 11.26it/s] Loading 0: 48%|████▊ | 176/363 [00:14<00:14, 12.62it/s] Loading 0: 50%|████▉ | 181/363 [00:14<00:10, 16.68it/s] Loading 0: 51%|█████ | 184/363 [00:15<00:11, 15.02it/s] Loading 0: 52%|█████▏ | 187/363 [00:15<00:10, 16.34it/s] Loading 0: 52%|█████▏ | 190/363 [00:16<00:30, 5.69it/s] Loading 0: 53%|█████▎ | 194/363 [00:16<00:22, 7.43it/s] Loading 0: 55%|█████▌ | 201/363 [00:17<00:13, 12.01it/s] Loading 0: 56%|█████▌ | 204/363 [00:17<00:12, 13.04it/s] Loading 0: 57%|█████▋ | 208/363 [00:17<00:09, 16.09it/s] Loading 0: 58%|█████▊ | 212/363 [00:17<00:09, 16.62it/s] Loading 0: 60%|█████▉ | 217/363 [00:17<00:06, 21.49it/s] Loading 0: 61%|██████ | 222/363 [00:17<00:05, 24.25it/s] Loading 0: 62%|██████▏ | 226/363 [00:19<00:18, 7.61it/s] Loading 0: 63%|██████▎ | 230/363 [00:19<00:14, 9.19it/s] Loading 0: 65%|██████▌ | 237/363 [00:19<00:09, 13.84it/s] Loading 0: 66%|██████▋ | 241/363 [00:19<00:07, 15.49it/s] Loading 0: 68%|██████▊ | 246/363 [00:19<00:06, 18.85it/s] Loading 0: 69%|██████▉ | 250/363 [00:20<00:05, 20.24it/s] Loading 0: 70%|███████ | 255/363 [00:20<00:04, 24.00it/s] Loading 0: 71%|███████▏ | 259/363 [00:21<00:12, 8.14it/s] Loading 0: 72%|███████▏ | 263/363 [00:21<00:10, 9.41it/s] Loading 0: 73%|███████▎ | 266/363 [00:21<00:09, 10.40it/s] Loading 0: 75%|███████▌ | 273/363 [00:22<00:05, 15.83it/s] Loading 0: 76%|███████▌ | 276/363 [00:22<00:05, 16.54it/s] Loading 0: 78%|███████▊ | 282/363 [00:22<00:03, 21.38it/s] Loading 0: 79%|███████▉ | 286/363 [00:22<00:03, 22.29it/s] Loading 0: 80%|████████ | 291/363 [00:23<00:08, 8.33it/s] Loading 0: 81%|████████ | 294/363 [00:24<00:07, 9.52it/s] Loading 0: 82%|████████▏ | 299/363 [00:24<00:05, 12.72it/s] Loading 0: 84%|████████▎ | 304/363 [00:24<00:04, 14.65it/s] Loading 0: 85%|████████▍ | 307/363 [00:24<00:03, 15.37it/s] Loading 0: 86%|████████▌ | 311/363 [00:24<00:03, 16.80it/s] Loading 0: 88%|████████▊ | 318/363 [00:24<00:01, 23.52it/s] Loading 0: 89%|████████▊ | 322/363 [00:25<00:03, 12.83it/s] Loading 0: 90%|████████▉ | 325/363 [00:26<00:04, 8.81it/s] Loading 0: 91%|█████████ | 329/363 [00:26<00:03, 10.53it/s] Loading 0: 93%|█████████▎| 336/363 [00:26<00:01, 15.76it/s] Loading 0: 93%|█████████▎| 339/363 [00:26<00:01, 16.54it/s] Loading 0: 95%|█████████▍| 344/363 [00:36<00:13, 1.46it/s] Loading 0: 96%|█████████▌| 348/363 [00:36<00:07, 1.95it/s] Loading 0: 97%|█████████▋| 353/363 [00:37<00:03, 2.81it/s] Loading 0: 98%|█████████▊| 357/363 [00:37<00:01, 3.44it/s] Loading 0: 100%|█████████▉| 362/363 [00:37<00:00, 4.92it/s]
Job rirv938-rinen-grpo-cp15-48820-v1-mkmlizer completed after 166.2s with status: succeeded
Stopping job with name rirv938-rinen-grpo-cp15-48820-v1-mkmlizer
Pipeline stage MKMLizer completed in 166.73s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-rinen-grpo-cp15-48820-v1
Waiting for inference service rirv938-rinen-grpo-cp15-48820-v1 to be ready
Inference service rirv938-rinen-grpo-cp15-48820-v1 ready after 150.740385055542s
Pipeline stage MKMLDeployer completed in 151.30s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.963407278060913s
Received healthy response to inference request in 1.64223051071167s
Received healthy response to inference request in 1.757688283920288s
Received healthy response to inference request in 1.9549586772918701s
Received healthy response to inference request in 1.638486385345459s
5 requests
0 failed requests
5th percentile: 1.6392352104187011
10th percentile: 1.6399840354919433
20th percentile: 1.6414816856384278
30th percentile: 1.6653220653533936
40th percentile: 1.7115051746368408
50th percentile: 1.757688283920288
60th percentile: 1.8365964412689209
70th percentile: 1.9155045986175536
80th percentile: 1.9566483974456788
90th percentile: 1.9600278377532958
95th percentile: 1.9617175579071044
99th percentile: 1.9630693340301513
mean time: 1.79135422706604
Pipeline stage StressChecker completed in 10.24s
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 0.93s
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 0.66s
Shutdown handler de-registered
rirv938-rinen-grpo-cp15_48820_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 5155.36s
Shutdown handler de-registered
rirv938-rinen-grpo-cp15_48820_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-rinen-grpo-cp15_48820_v1 status is now torndown due to DeploymentManager action