developer_uid: rirv938
submission_id: rirv938-simp-grpo-cp624_22822_v1
model_name: rirv938-simp-grpo-cp624_22822_v1
model_group: rirv938/simp_grpo_cp624_
status: torndown
timestamp: 2025-06-11T03:59:28+00:00
num_battles: 8655
num_wins: 4445
celo_rating: 1294.06
family_friendly_score: 0.49019999999999997
family_friendly_standard_error: 0.007069709470692555
submission_type: basic
model_repo: rirv938/simp_grpo_cp624_96ff_b1_r1_merged
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
reward_model: default
display_name: rirv938-simp-grpo-cp624_22822_v1
is_internal_developer: True
language_model: rirv938/simp_grpo_cp624_96ff_b1_r1_merged
model_size: 24B
ranking_group: single
us_pacific_date: 2025-06-10
win_ratio: 0.5135759676487579
generation_params: {'temperature': 0.9, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['</s>', 'You:', '\n', '###'], '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-cp624-22822-v1-mkmlizer
Waiting for job on rirv938-simp-grpo-cp624-22822-v1-mkmlizer to finish
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: ║ ║
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: ║ ║
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: ║ Version: 0.27.1+vampire_v3 ║
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: ║ ║
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: ║ belonging to: ║
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: ║ ║
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: ║ ║
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-cyndonia24b-cpos_11400_v1: ('http://chaiml-cyndonia24b-cpos-11400-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: Downloaded to shared memory in 172.430s
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwrwb3r1z, device:0
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: quantized model in 75.089s
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: Processed model rirv938/simp_grpo_cp624_96ff_b1_r1_merged in 247.556s
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-simp-grpo-cp624-22822-v1
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-simp-grpo-cp624-22822-v1/config.json
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-simp-grpo-cp624-22822-v1/special_tokens_map.json
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-simp-grpo-cp624-22822-v1/tokenizer_config.json
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-simp-grpo-cp624-22822-v1/tokenizer.json
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-simp-grpo-cp624-22822-v1/flywheel_model.1.safetensors
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-simp-grpo-cp624-22822-v1/flywheel_model.0.safetensors
rirv938-simp-grpo-cp624-22822-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 3/363 [00:00<01:18, 4.56it/s] Loading 0: 1%| | 4/363 [00:01<02:07, 2.82it/s] Loading 0: 1%|▏ | 5/363 [00:02<02:52, 2.07it/s] Loading 0: 2%|▏ | 8/363 [00:02<01:19, 4.45it/s] Loading 0: 3%|▎ | 10/363 [00:02<01:02, 5.62it/s] Loading 0: 3%|▎ | 12/363 [00:02<00:55, 6.33it/s] Loading 0: 4%|▍ | 14/363 [00:03<01:51, 3.13it/s] Loading 0: 4%|▍ | 15/363 [00:04<02:18, 2.50it/s] Loading 0: 5%|▍ | 18/363 [00:04<01:21, 4.23it/s] Loading 0: 6%|▌ | 21/363 [00:05<01:23, 4.12it/s] Loading 0: 6%|▋ | 23/363 [00:06<02:04, 2.74it/s] Loading 0: 7%|▋ | 26/363 [00:06<01:22, 4.11it/s] Loading 0: 8%|▊ | 28/363 [00:07<01:08, 4.90it/s] Loading 0: 8%|▊ | 30/363 [00:07<00:54, 6.11it/s] Loading 0: 9%|▉ | 32/363 [00:07<00:47, 6.97it/s] Loading 0: 9%|▉ | 34/363 [00:08<01:10, 4.66it/s] Loading 0: 10%|▉ | 36/363 [00:09<01:55, 2.84it/s] Loading 0: 11%|█ | 39/363 [00:10<01:37, 3.33it/s] Loading 0: 11%|█ | 40/363 [00:10<01:53, 2.85it/s] Loading 0: 11%|█▏ | 41/363 [00:11<02:10, 2.47it/s] Loading 0: 12%|█▏ | 45/363 [00:11<01:09, 4.55it/s] Loading 0: 13%|█▎ | 47/363 [00:11<00:55, 5.65it/s] Loading 0: 13%|█▎ | 49/363 [00:11<00:46, 6.73it/s] Loading 0: 14%|█▍ | 51/363 [00:12<00:43, 7.18it/s] Loading 0: 15%|█▍ | 53/363 [00:12<00:56, 5.48it/s] Loading 0: 15%|█▍ | 54/363 [00:12<00:56, 5.49it/s] Loading 0: 16%|█▌ | 57/363 [00:13<00:37, 8.18it/s] Loading 0: 16%|█▋ | 59/363 [00:13<00:38, 7.86it/s] Loading 0: 18%|█▊ | 64/363 [00:13<00:22, 13.31it/s] Loading 0: 19%|█▊ | 68/363 [00:13<00:17, 17.11it/s] Loading 0: 20%|█▉ | 71/363 [00:13<00:22, 13.03it/s] Loading 0: 20%|██ | 73/363 [00:14<00:22, 12.68it/s] Loading 0: 21%|██ | 75/363 [00:14<00:21, 13.60it/s] Loading 0: 21%|██ | 77/363 [00:14<00:25, 11.05it/s] Loading 0: 23%|██▎ | 82/363 [00:14<00:16, 16.70it/s] Loading 0: 24%|██▎ | 86/363 [00:14<00:13, 19.86it/s] Loading 0: 25%|██▍ | 89/363 [00:15<00:19, 14.30it/s] Loading 0: 25%|██▌ | 91/363 [00:15<00:19, 13.63it/s] Loading 0: 26%|██▌ | 95/363 [00:15<00:15, 17.68it/s] Loading 0: 27%|██▋ | 99/363 [00:15<00:12, 20.88it/s] Loading 0: 28%|██▊ | 102/363 [00:15<00:14, 18.55it/s] Loading 0: 29%|██▉ | 105/363 [00:16<00:18, 13.84it/s] Loading 0: 29%|██▉ | 107/363 [00:16<00:19, 12.96it/s] Loading 0: 30%|███ | 109/363 [00:16<00:20, 12.50it/s] Loading 0: 31%|███ | 111/363 [00:16<00:18, 13.43it/s] Loading 0: 31%|███ | 113/363 [00:16<00:23, 10.81it/s] Loading 0: 33%|███▎ | 118/363 [00:17<00:14, 16.57it/s] Loading 0: 34%|███▎ | 122/363 [00:17<00:12, 20.05it/s] Loading 0: 34%|███▍ | 125/363 [00:17<00:16, 14.21it/s] Loading 0: 35%|███▍ | 127/363 [00:17<00:17, 13.52it/s] Loading 0: 36%|███▌ | 129/363 [00:17<00:16, 14.31it/s] Loading 0: 36%|███▌ | 131/363 [00:18<00:20, 11.59it/s] Loading 0: 37%|███▋ | 136/363 [00:18<00:13, 17.34it/s] Loading 0: 39%|███▊ | 140/363 [00:18<00:10, 20.30it/s] Loading 0: 39%|███▉ | 143/363 [00:18<00:15, 14.31it/s] Loading 0: 40%|███▉ | 145/363 [00:18<00:16, 13.61it/s] Loading 0: 40%|████ | 147/363 [00:19<00:15, 14.39it/s] Loading 0: 41%|████ | 149/363 [00:19<00:18, 11.56it/s] Loading 0: 42%|████▏ | 154/363 [00:19<00:11, 17.65it/s] Loading 0: 44%|████▎ | 158/363 [00:19<00:09, 21.34it/s] Loading 0: 44%|████▍ | 161/363 [00:19<00:13, 15.07it/s] Loading 0: 45%|████▌ | 164/363 [00:20<00:12, 15.68it/s] Loading 0: 46%|████▌ | 167/363 [00:20<00:15, 12.34it/s] Loading 0: 47%|████▋ | 172/363 [00:20<00:11, 17.19it/s] Loading 0: 48%|████▊ | 176/363 [00:20<00:09, 20.50it/s] Loading 0: 49%|████▉ | 179/363 [00:21<00:12, 15.08it/s] Loading 0: 50%|█████ | 182/363 [00:21<00:11, 15.70it/s] Loading 0: 51%|█████ | 185/363 [00:21<00:14, 12.48it/s] Loading 0: 52%|█████▏ | 190/363 [00:21<00:09, 17.55it/s] Loading 0: 53%|█████▎ | 194/363 [00:21<00:08, 21.00it/s] Loading 0: 54%|█████▍ | 197/363 [00:22<00:10, 15.61it/s] Loading 0: 55%|█████▌ | 200/363 [00:22<00:10, 16.19it/s] Loading 0: 56%|█████▌ | 203/363 [00:37<03:55, 1.47s/it] Loading 0: 57%|█████▋ | 207/363 [00:38<02:32, 1.02it/s] Loading 0: 58%|█████▊ | 210/363 [00:38<01:51, 1.37it/s] Loading 0: 59%|█████▊ | 213/363 [00:38<01:23, 1.80it/s] Loading 0: 60%|█████▉ | 216/363 [00:38<01:03, 2.32it/s] Loading 0: 60%|██████ | 219/363 [00:39<00:45, 3.15it/s] Loading 0: 61%|██████ | 222/363 [00:39<00:35, 3.98it/s] Loading 0: 62%|██████▏ | 226/363 [00:39<00:23, 5.83it/s] Loading 0: 63%|██████▎ | 230/363 [00:39<00:16, 8.05it/s] Loading 0: 64%|██████▍ | 233/363 [00:39<00:15, 8.26it/s] Loading 0: 65%|██████▌ | 236/363 [00:40<00:13, 9.58it/s] Loading 0: 66%|██████▌ | 238/363 [00:40<00:13, 9.61it/s] Loading 0: 66%|██████▌ | 240/363 [00:40<00:12, 9.94it/s] Loading 0: 67%|██████▋ | 244/363 [00:40<00:08, 13.54it/s] Loading 0: 68%|██████▊ | 248/363 [00:40<00:06, 17.09it/s] Loading 0: 69%|██████▉ | 251/363 [00:41<00:08, 13.26it/s] Loading 0: 70%|██████▉ | 253/363 [00:41<00:08, 12.76it/s] Loading 0: 70%|███████ | 255/363 [00:41<00:07, 13.55it/s] Loading 0: 71%|███████ | 257/363 [00:41<00:09, 11.00it/s] Loading 0: 72%|███████▏ | 262/363 [00:41<00:06, 16.58it/s] Loading 0: 73%|███████▎ | 266/363 [00:41<00:04, 19.75it/s] Loading 0: 74%|███████▍ | 269/363 [00:42<00:06, 13.82it/s] Loading 0: 75%|███████▍ | 271/363 [00:42<00:06, 13.17it/s] Loading 0: 75%|███████▌ | 273/363 [00:42<00:06, 13.94it/s] Loading 0: 76%|███████▌ | 275/363 [00:42<00:07, 11.06it/s] Loading 0: 77%|███████▋ | 280/363 [00:42<00:05, 16.57it/s] Loading 0: 78%|███████▊ | 284/363 [00:43<00:04, 19.69it/s] Loading 0: 79%|███████▉ | 287/363 [00:43<00:05, 13.60it/s] Loading 0: 80%|███████▉ | 289/363 [00:43<00:05, 12.94it/s] Loading 0: 80%|████████ | 291/363 [00:43<00:05, 13.74it/s] Loading 0: 81%|████████ | 293/363 [00:44<00:06, 11.09it/s] Loading 0: 82%|████████▏ | 298/363 [00:44<00:03, 16.77it/s] Loading 0: 83%|████████▎ | 302/363 [00:44<00:03, 20.19it/s] Loading 0: 84%|████████▍ | 305/363 [00:44<00:04, 14.08it/s] Loading 0: 85%|████████▍ | 307/363 [00:44<00:04, 13.28it/s] Loading 0: 85%|████████▌ | 309/363 [00:45<00:03, 13.97it/s] Loading 0: 86%|████████▌ | 311/363 [00:45<00:04, 11.11it/s] Loading 0: 87%|████████▋ | 316/363 [00:45<00:02, 16.59it/s] Loading 0: 88%|████████▊ | 320/363 [00:45<00:02, 19.64it/s] Loading 0: 89%|████████▉ | 323/363 [00:45<00:02, 13.63it/s] Loading 0: 90%|████████▉ | 325/363 [00:46<00:02, 13.14it/s] Loading 0: 90%|█████████ | 327/363 [00:46<00:02, 14.00it/s] Loading 0: 91%|█████████ | 329/363 [00:46<00:03, 11.33it/s] Loading 0: 92%|█████████▏| 334/363 [00:46<00:01, 17.51it/s] Loading 0: 93%|█████████▎| 338/363 [00:46<00:01, 21.39it/s] Loading 0: 94%|█████████▍| 341/363 [00:47<00:01, 14.74it/s] Loading 0: 95%|█████████▍| 344/363 [00:47<00:01, 15.47it/s] Loading 0: 96%|█████████▌| 347/363 [00:47<00:01, 12.00it/s] Loading 0: 97%|█████████▋| 352/363 [00:47<00:00, 17.02it/s] Loading 0: 98%|█████████▊| 356/363 [00:47<00:00, 20.24it/s] Loading 0: 99%|█████████▉| 359/363 [00:48<00:00, 10.75it/s] Loading 0: 100%|█████████▉| 362/363 [00:48<00:00, 10.78it/s]
Job rirv938-simp-grpo-cp624-22822-v1-mkmlizer completed after 280.61s with status: succeeded
Stopping job with name rirv938-simp-grpo-cp624-22822-v1-mkmlizer
Pipeline stage MKMLizer completed in 281.13s
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-simp-grpo-cp624-22822-v1
Waiting for inference service rirv938-simp-grpo-cp624-22822-v1 to be ready
Failed to get response for submission chaiml-cyndonia24b-cpos_11400_v1: ('http://chaiml-cyndonia24b-cpos-11400-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service rirv938-simp-grpo-cp624-22822-v1 ready after 90.39113807678223s
Pipeline stage MKMLDeployer completed in 90.84s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.396652936935425s
Received healthy response to inference request in 2.0397417545318604s
Received healthy response to inference request in 2.0619089603424072s
Received healthy response to inference request in 1.950765609741211s
Received healthy response to inference request in 1.774730920791626s
5 requests
0 failed requests
5th percentile: 1.8099378585815429
10th percentile: 1.84514479637146
20th percentile: 1.915558671951294
30th percentile: 1.9685608386993407
40th percentile: 2.0041512966156008
50th percentile: 2.0397417545318604
60th percentile: 2.048608636856079
70th percentile: 2.057475519180298
80th percentile: 2.1288577556610107
90th percentile: 2.262755346298218
95th percentile: 2.3297041416168214
99th percentile: 2.383263177871704
mean time: 2.0447600364685057
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 0.94s
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 0.72s
Shutdown handler de-registered
rirv938-simp-grpo-cp624_22822_v1 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 0.19s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-simp-grpo-cp624-22822-v1-profiler
Waiting for inference service rirv938-simp-grpo-cp624-22822-v1-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2800.44s
Shutdown handler de-registered
rirv938-simp-grpo-cp624_22822_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-simp-grpo-cp624_22822_v1 status is now torndown due to DeploymentManager action