rirv938-rinen-grpo-40k-_71220

developer_uid: rirv938

submission_id: rirv938-rinen-grpo-40k-_71220_v1

model_name: rirv938-rinen-grpo-40k-_71220_v1

model_group: rirv938/rinen_grpo_40k_c

status: torndown

timestamp: 2025-04-30T15:03:14+00:00

num_battles: 8869

num_wins: 4816

celo_rating: 1337.11

family_friendly_score: 0.5562

family_friendly_standard_error: 0.007026258748437891

submission_type: basic

model_repo: rirv938/rinen_grpo_40k_cp888_95ff_run2_merged

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6088884923996858, 'latency_mean': 1.642239466905594, 'latency_p50': 1.6447030305862427, 'latency_p90': 1.8040570974349974}, {'batch_size': 3, 'throughput': 1.1077300122335871, 'latency_mean': 2.6978035283088686, 'latency_p50': 2.71378231048584, 'latency_p90': 2.99771671295166}, {'batch_size': 5, 'throughput': 1.3345195654522972, 'latency_mean': 3.7316950953006742, 'latency_p50': 3.7316733598709106, 'latency_p90': 4.21935760974884}, {'batch_size': 6, 'throughput': 1.4025429437286785, 'latency_mean': 4.252830104827881, 'latency_p50': 4.258151054382324, 'latency_p90': 4.722344398498535}, {'batch_size': 8, 'throughput': 1.472199814688258, 'latency_mean': 5.406355322599411, 'latency_p50': 5.331533312797546, 'latency_p90': 6.136609840393066}, {'batch_size': 10, 'throughput': 1.5096119200611455, 'latency_mean': 6.574847903251648, 'latency_p50': 6.5867650508880615, 'latency_p90': 7.411963605880737}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-rinen-grpo-40k-_71220_v1

is_internal_developer: True

language_model: rirv938/rinen_grpo_40k_cp888_95ff_run2_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.33

us_pacific_date: 2025-04-30

win_ratio: 0.5430149960536701

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': ['You:', 'User:', '</s>', '<|eot_id|>', '\n', '<|im_end|>', '####', 'Bot:'], '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-40k-71220-v1-mkmlizer
Waiting for job on rirv938-rinen-grpo-40k-71220-v1-mkmlizer to finish
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: ║       /___/                                                         ║
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: ║                                                                     ║
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: ║                                                                     ║
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: ║                                                                     ║
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: ║                                                                     ║
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: Downloaded to shared memory in 66.671s
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5cofiskg, device:0
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: quantized model in 45.401s
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: Processed model rirv938/rinen_grpo_40k_cp888_95ff_run2_merged in 112.073s
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-rinen-grpo-40k-71220-v1
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-rinen-grpo-40k-71220-v1/config.json
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-rinen-grpo-40k-71220-v1/special_tokens_map.json
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-rinen-grpo-40k-71220-v1/tokenizer_config.json
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-rinen-grpo-40k-71220-v1/tokenizer.json
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-rinen-grpo-40k-71220-v1/flywheel_model.0.safetensors
rirv938-rinen-grpo-40k-71220-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 38.66it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:14, 24.33it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:13, 25.38it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:15, 22.54it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:12, 26.96it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:17, 19.99it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:19, 17.58it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:14, 22.90it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:14, 22.87it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:12, 25.58it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:13, 22.99it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:12, 25.91it/s]
Loading 0:  13%|█▎        | 49/363 [00:02<00:12, 25.93it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:12, 24.24it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:12, 24.62it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:11, 26.16it/s]
Loading 0:  17%|█▋        | 63/363 [00:02<00:16, 17.98it/s]
Loading 0:  18%|█▊        | 66/363 [00:02<00:15, 18.82it/s]
Loading 0:  20%|█▉        | 71/363 [00:03<00:13, 22.41it/s]
Loading 0:  20%|██        | 74/363 [00:03<00:12, 23.05it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:14, 19.36it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 24.73it/s]
Loading 0:  23%|██▎       | 85/363 [00:03<00:10, 25.38it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:11, 24.85it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:09, 27.33it/s]
Loading 0:  26%|██▋       | 96/363 [00:04<00:11, 23.96it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:09, 26.80it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:14, 18.14it/s]
Loading 0:  29%|██▉       | 106/363 [00:04<00:13, 19.04it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:11, 22.83it/s]
Loading 0:  31%|███▏      | 114/363 [00:05<00:11, 21.27it/s]
Loading 0:  33%|███▎      | 118/363 [00:05<00:09, 24.80it/s]
Loading 0:  33%|███▎      | 121/363 [00:05<00:09, 25.74it/s]
Loading 0:  34%|███▍      | 124/363 [00:05<00:09, 25.04it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 27.53it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:09, 24.01it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:08, 26.79it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 27.94it/s]
Loading 0:  40%|███▉      | 144/363 [00:06<00:12, 17.15it/s]
Loading 0:  41%|████      | 148/363 [00:06<00:10, 20.48it/s]
Loading 0:  42%|████▏     | 151/363 [00:06<00:10, 20.84it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:09, 22.61it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:08, 24.06it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 23.85it/s]
Loading 0:  45%|████▍     | 163/363 [00:07<00:08, 24.91it/s]
Loading 0:  46%|████▌     | 166/363 [00:07<00:07, 26.05it/s]
Loading 0:  47%|████▋     | 169/363 [00:07<00:07, 25.25it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:07, 26.31it/s]
Loading 0:  48%|████▊     | 175/363 [00:07<00:06, 26.95it/s]
Loading 0:  49%|████▉     | 178/363 [00:07<00:07, 25.60it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:09, 18.93it/s]
Loading 0:  51%|█████     | 185/363 [00:08<00:10, 17.20it/s]
Loading 0:  52%|█████▏    | 190/363 [00:08<00:07, 22.96it/s]
Loading 0:  53%|█████▎    | 193/363 [00:08<00:07, 24.02it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:07, 23.69it/s]
Loading 0:  55%|█████▌    | 201/363 [00:08<00:06, 26.58it/s]
Loading 0:  56%|█████▌    | 204/363 [00:08<00:06, 23.76it/s]
Loading 0:  57%|█████▋    | 208/363 [00:08<00:05, 26.92it/s]
Loading 0:  58%|█████▊    | 211/363 [00:09<00:05, 27.06it/s]
Loading 0:  59%|█████▉    | 214/363 [00:09<00:05, 26.25it/s]
Loading 0:  60%|██████    | 218/363 [00:09<00:05, 26.15it/s]
Loading 0:  61%|██████    | 222/363 [00:09<00:04, 28.93it/s]
Loading 0:  62%|██████▏   | 225/363 [00:09<00:08, 16.84it/s]
Loading 0:  63%|██████▎   | 229/363 [00:09<00:06, 20.49it/s]
Loading 0:  64%|██████▍   | 232/363 [00:10<00:06, 21.13it/s]
Loading 0:  65%|██████▌   | 237/363 [00:10<00:05, 24.35it/s]
Loading 0:  66%|██████▌   | 240/363 [00:10<00:05, 22.33it/s]
Loading 0:  67%|██████▋   | 244/363 [00:10<00:04, 25.54it/s]
Loading 0:  68%|██████▊   | 247/363 [00:10<00:04, 25.97it/s]
Loading 0:  69%|██████▉   | 250/363 [00:10<00:04, 24.91it/s]
Loading 0:  70%|██████▉   | 254/363 [00:10<00:03, 28.52it/s]
Loading 0:  71%|███████   | 258/363 [00:11<00:04, 23.71it/s]
Loading 0:  72%|███████▏  | 262/363 [00:11<00:03, 26.81it/s]
Loading 0:  73%|███████▎  | 265/363 [00:11<00:05, 18.13it/s]
Loading 0:  74%|███████▍  | 268/363 [00:11<00:04, 19.07it/s]
Loading 0:  75%|███████▍  | 271/363 [00:11<00:04, 20.93it/s]
Loading 0:  75%|███████▌  | 274/363 [00:11<00:03, 22.47it/s]
Loading 0:  76%|███████▋  | 277/363 [00:11<00:03, 22.38it/s]
Loading 0:  77%|███████▋  | 280/363 [00:12<00:03, 23.78it/s]
Loading 0:  78%|███████▊  | 283/363 [00:12<00:03, 24.73it/s]
Loading 0:  79%|███████▉  | 286/363 [00:12<00:03, 24.07it/s]
Loading 0:  80%|███████▉  | 289/363 [00:12<00:02, 25.03it/s]
Loading 0:  80%|████████  | 292/363 [00:12<00:02, 25.64it/s]
Loading 0:  81%|████████▏ | 295/363 [00:12<00:02, 24.80it/s]
Loading 0:  82%|████████▏ | 298/363 [00:12<00:02, 25.89it/s]
Loading 0:  83%|████████▎ | 303/363 [00:12<00:02, 27.52it/s]
Loading 0:  84%|████████▍ | 306/363 [00:13<00:03, 16.19it/s]
Loading 0:  85%|████████▌ | 310/363 [00:13<00:02, 19.92it/s]
Loading 0:  86%|████████▌ | 313/363 [00:13<00:02, 20.53it/s]
Loading 0:  87%|████████▋ | 316/363 [00:13<00:02, 22.29it/s]
Loading 0:  88%|████████▊ | 319/363 [00:13<00:01, 23.38it/s]
Loading 0:  89%|████████▊ | 322/363 [00:13<00:01, 23.16it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:01, 24.67it/s]
Loading 0:  90%|█████████ | 328/363 [00:14<00:01, 25.40it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:01, 23.97it/s]
Loading 0:  92%|█████████▏| 334/363 [00:14<00:01, 25.04it/s]
Loading 0:  93%|█████████▎| 337/363 [00:14<00:01, 25.46it/s]
Loading 0:  94%|█████████▎| 340/363 [00:14<00:00, 24.43it/s]
Loading 0:  94%|█████████▍| 343/363 [00:14<00:00, 25.83it/s]
Loading 0:  95%|█████████▌| 346/363 [00:22<00:13,  1.29it/s]
Loading 0:  96%|█████████▌| 348/363 [00:22<00:09,  1.61it/s]
Loading 0:  97%|█████████▋| 353/363 [00:22<00:03,  2.77it/s]
Loading 0:  98%|█████████▊| 356/363 [00:22<00:01,  3.69it/s]
Loading 0:  99%|█████████▉| 359/363 [00:22<00:00,  4.83it/s]
Loading 0: 100%|█████████▉| 362/363 [00:22<00:00,  6.35it/s]
                                                            
Job rirv938-rinen-grpo-40k-71220-v1-mkmlizer completed after 136.17s with status: succeeded
Stopping job with name rirv938-rinen-grpo-40k-71220-v1-mkmlizer
Pipeline stage MKMLizer completed in 136.66s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.21s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-rinen-grpo-40k-71220-v1
Waiting for inference service rirv938-rinen-grpo-40k-71220-v1 to be ready
Inference service rirv938-rinen-grpo-40k-71220-v1 ready after 140.46639895439148s
Pipeline stage MKMLDeployer completed in 140.94s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1851143836975098s
Received healthy response to inference request in 7.108970642089844s
Received healthy response to inference request in 1.547694206237793s
Received healthy response to inference request in 1.7296392917633057s
Received healthy response to inference request in 1.6562740802764893s
5 requests
0 failed requests
5th percentile: 1.5694101810455323
10th percentile: 1.5911261558532714
20th percentile: 1.63455810546875
30th percentile: 1.6709471225738526
40th percentile: 1.700293207168579
50th percentile: 1.7296392917633057
60th percentile: 1.9118293285369872
70th percentile: 2.0940193653106687
80th percentile: 3.1698856353759775
90th percentile: 5.13942813873291
95th percentile: 6.124199390411376
99th percentile: 6.91201639175415
mean time: 2.845538520812988
Pipeline stage StressChecker completed in 15.43s
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 0.59s
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 0.79s
Shutdown handler de-registered
rirv938-rinen-grpo-40k-_71220_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-rinen-grpo-40k-71220-v1-profiler
Waiting for inference service rirv938-rinen-grpo-40k-71220-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 3038.16s
Shutdown handler de-registered
rirv938-rinen-grpo-40k-_71220_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-rinen-grpo-40k-_71220_v1 status is now torndown due to DeploymentManager action