rirv938-rinen-grpo-40k-_88641

developer_uid: rirv938

submission_id: rirv938-rinen-grpo-40k-_88641_v1

model_name: rirv938-rinen-grpo-40k-_88641_v1

model_group: rirv938/rinen_grpo_40k_c

status: torndown

timestamp: 2025-04-30T15:03:09+00:00

num_battles: 8773

num_wins: 4691

celo_rating: 1331.33

family_friendly_score: 0.5509999999999999

family_friendly_standard_error: 0.007034187941759872

submission_type: basic

model_repo: rirv938/rinen_grpo_40k_cp1184_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': 0.5979472079780745, 'latency_mean': 1.6723005640506745, 'latency_p50': 1.690940260887146, 'latency_p90': 1.8165634155273438}, {'batch_size': 3, 'throughput': 1.11279866562559, 'latency_mean': 2.693386062383652, 'latency_p50': 2.6963917016983032, 'latency_p90': 2.976641249656677}, {'batch_size': 5, 'throughput': 1.3507845635277556, 'latency_mean': 3.684713064432144, 'latency_p50': 3.683847427368164, 'latency_p90': 4.158677935600281}, {'batch_size': 6, 'throughput': 1.39838360405573, 'latency_mean': 4.267121180295944, 'latency_p50': 4.286787033081055, 'latency_p90': 4.750332045555115}, {'batch_size': 8, 'throughput': 1.4778446899357036, 'latency_mean': 5.380703053474426, 'latency_p50': 5.388363599777222, 'latency_p90': 6.110337018966675}, {'batch_size': 10, 'throughput': 1.5174679550159802, 'latency_mean': 6.534749575853348, 'latency_p50': 6.459657549858093, 'latency_p90': 7.41879780292511}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-rinen-grpo-40k-_88641_v1

is_internal_developer: True

language_model: rirv938/rinen_grpo_40k_cp1184_95ff_run2_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.36

us_pacific_date: 2025-04-30

win_ratio: 0.5347087655306053

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': ['\n', 'Bot:', 'User:', 'You:', '<|im_end|>', '</s>', '<|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-40k-88641-v1-mkmlizer
Waiting for job on rirv938-rinen-grpo-40k-88641-v1-mkmlizer to finish
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: ║       /___/                                                         ║
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: ║                                                                     ║
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: ║                                                                     ║
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: ║                                                                     ║
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: ║                                                                     ║
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: Downloaded to shared memory in 79.573s
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnqzqmqm1, device:0
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: quantized model in 43.605s
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: Processed model rirv938/rinen_grpo_40k_cp1184_95ff_run2_merged in 123.178s
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-rinen-grpo-40k-88641-v1
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-rinen-grpo-40k-88641-v1/config.json
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-rinen-grpo-40k-88641-v1/special_tokens_map.json
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-rinen-grpo-40k-88641-v1/tokenizer_config.json
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-rinen-grpo-40k-88641-v1/tokenizer.json
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-rinen-grpo-40k-88641-v1/flywheel_model.0.safetensors
rirv938-rinen-grpo-40k-88641-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.19it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:13, 25.30it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:15, 22.57it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:12, 28.59it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:16, 20.45it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:18, 18.31it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 23.80it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:14, 23.46it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:13, 24.35it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:14, 22.40it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:11, 27.03it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:13, 23.75it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:10, 28.14it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 29.21it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:15, 19.49it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:12, 23.33it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:13, 21.48it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:13, 21.98it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 26.11it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 23.61it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 27.55it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:11, 24.07it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:09, 27.96it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:13, 18.61it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:11, 22.84it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:11, 21.49it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:09, 25.85it/s]
Loading 0:  34%|███▎      | 122/363 [00:05<00:10, 23.39it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:08, 27.82it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:09, 24.16it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:08, 28.04it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 28.47it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:10, 20.16it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:10, 19.93it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:08, 24.02it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:09, 22.03it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 26.12it/s]
Loading 0:  46%|████▌     | 167/363 [00:07<00:08, 23.39it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:06, 27.35it/s]
Loading 0:  48%|████▊     | 176/363 [00:07<00:07, 23.39it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 27.15it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:09, 18.19it/s]
Loading 0:  52%|█████▏    | 190/363 [00:08<00:07, 22.53it/s]
Loading 0:  53%|█████▎    | 194/363 [00:08<00:07, 21.64it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:06, 26.18it/s]
Loading 0:  56%|█████▌    | 203/363 [00:08<00:07, 22.83it/s]
Loading 0:  57%|█████▋    | 208/363 [00:08<00:05, 26.09it/s]
Loading 0:  58%|█████▊    | 212/363 [00:08<00:06, 23.45it/s]
Loading 0:  60%|█████▉    | 217/363 [00:09<00:05, 27.63it/s]
Loading 0:  61%|██████    | 222/363 [00:09<00:05, 27.85it/s]
Loading 0:  62%|██████▏   | 226/363 [00:09<00:06, 20.21it/s]
Loading 0:  63%|██████▎   | 229/363 [00:09<00:06, 21.71it/s]
Loading 0:  64%|██████▍   | 232/363 [00:09<00:06, 21.68it/s]
Loading 0:  65%|██████▍   | 235/363 [00:09<00:05, 23.05it/s]
Loading 0:  66%|██████▌   | 239/363 [00:10<00:05, 21.29it/s]
Loading 0:  67%|██████▋   | 244/363 [00:10<00:04, 26.82it/s]
Loading 0:  68%|██████▊   | 248/363 [00:10<00:04, 23.80it/s]
Loading 0:  70%|██████▉   | 253/363 [00:10<00:03, 28.41it/s]
Loading 0:  71%|███████   | 257/363 [00:10<00:04, 25.44it/s]
Loading 0:  72%|███████▏  | 262/363 [00:10<00:03, 29.37it/s]
Loading 0:  73%|███████▎  | 266/363 [00:11<00:05, 19.12it/s]
Loading 0:  75%|███████▍  | 271/363 [00:11<00:03, 23.32it/s]
Loading 0:  76%|███████▌  | 275/363 [00:11<00:04, 21.78it/s]
Loading 0:  77%|███████▋  | 280/363 [00:11<00:03, 26.11it/s]
Loading 0:  78%|███████▊  | 284/363 [00:11<00:03, 23.63it/s]
Loading 0:  80%|███████▉  | 289/363 [00:12<00:02, 28.10it/s]
Loading 0:  81%|████████  | 293/363 [00:12<00:02, 24.06it/s]
Loading 0:  82%|████████▏ | 298/363 [00:12<00:02, 27.82it/s]
Loading 0:  83%|████████▎ | 303/363 [00:12<00:02, 29.45it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 21.29it/s]
Loading 0:  86%|████████▌ | 311/363 [00:13<00:02, 20.38it/s]
Loading 0:  87%|████████▋ | 316/363 [00:13<00:01, 24.33it/s]
Loading 0:  88%|████████▊ | 319/363 [00:13<00:01, 24.73it/s]
Loading 0:  89%|████████▊ | 322/363 [00:13<00:01, 24.18it/s]
Loading 0:  90%|████████▉ | 326/363 [00:13<00:01, 27.60it/s]
Loading 0:  91%|█████████ | 330/363 [00:13<00:01, 24.21it/s]
Loading 0:  92%|█████████▏| 334/363 [00:13<00:01, 26.45it/s]
Loading 0:  93%|█████████▎| 337/363 [00:14<00:00, 26.91it/s]
Loading 0:  94%|█████████▎| 340/363 [00:14<00:00, 24.90it/s]
Loading 0:  94%|█████████▍| 343/363 [00:14<00:00, 25.41it/s]
Loading 0:  95%|█████████▌| 346/363 [00:21<00:11,  1.48it/s]
Loading 0:  96%|█████████▌| 348/363 [00:21<00:08,  1.82it/s]
Loading 0:  97%|█████████▋| 353/363 [00:21<00:03,  3.05it/s]
Loading 0:  98%|█████████▊| 357/363 [00:21<00:01,  4.23it/s]
Loading 0: 100%|█████████▉| 362/363 [00:21<00:00,  6.39it/s]
                                                            
Job rirv938-rinen-grpo-40k-88641-v1-mkmlizer completed after 146.86s with status: succeeded
Stopping job with name rirv938-rinen-grpo-40k-88641-v1-mkmlizer
Pipeline stage MKMLizer completed in 147.32s
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-rinen-grpo-40k-88641-v1
Waiting for inference service rirv938-rinen-grpo-40k-88641-v1 to be ready
Inference service rirv938-rinen-grpo-40k-88641-v1 ready after 150.50203371047974s
Pipeline stage MKMLDeployer completed in 150.91s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.264272928237915s
Received healthy response to inference request in 1.7772495746612549s
Received healthy response to inference request in 1.747157096862793s
Received healthy response to inference request in 1.5193545818328857s
Received healthy response to inference request in 1.5082414150238037s
5 requests
0 failed requests
5th percentile: 1.5104640483856202
10th percentile: 1.5126866817474365
20th percentile: 1.5171319484710692
30th percentile: 1.564915084838867
40th percentile: 1.65603609085083
50th percentile: 1.747157096862793
60th percentile: 1.7591940879821777
70th percentile: 1.7712310791015624
80th percentile: 1.874654245376587
90th percentile: 2.069463586807251
95th percentile: 2.166868257522583
99th percentile: 2.2447919940948484
mean time: 1.7632551193237305
Pipeline stage StressChecker completed in 10.04s
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 0.64s
Shutdown handler de-registered
rirv938-rinen-grpo-40k-_88641_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
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 3063.96s
Shutdown handler de-registered
rirv938-rinen-grpo-40k-_88641_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-rinen-grpo-40k-_88641_v1 status is now torndown due to DeploymentManager action