rirv938-anthropic-grpo-_76361

developer_uid: rirv938

submission_id: rirv938-anthropic-grpo-_76361_v1

model_name: rirv938-anthropic-grpo-_76361_v1

model_group: rirv938/anthropic_grpo_4

status: torndown

timestamp: 2025-05-18T15:18:18+00:00

num_battles: 8318

num_wins: 4233

celo_rating: 1291.1

family_friendly_score: 0.5446

family_friendly_standard_error: 0.0070428806606387985

submission_type: basic

model_repo: rirv938/anthropic_grpo_40k_cp120_98ff_g2b15_merged

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 768

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6506357273755073, 'latency_mean': 1.536892899274826, 'latency_p50': 1.5257651805877686, 'latency_p90': 1.7162243366241454}, {'batch_size': 3, 'throughput': 1.239510708261633, 'latency_mean': 2.413979914188385, 'latency_p50': 2.4305115938186646, 'latency_p90': 2.6456711053848267}, {'batch_size': 5, 'throughput': 1.539470238783304, 'latency_mean': 3.2287391519546507, 'latency_p50': 3.224122405052185, 'latency_p90': 3.565504050254822}, {'batch_size': 6, 'throughput': 1.617438583542401, 'latency_mean': 3.681192560195923, 'latency_p50': 3.67561936378479, 'latency_p90': 4.112981390953064}, {'batch_size': 8, 'throughput': 1.7100150878731877, 'latency_mean': 4.643979198932648, 'latency_p50': 4.678887605667114, 'latency_p90': 5.200026965141296}, {'batch_size': 10, 'throughput': 1.7652479007866897, 'latency_mean': 5.624407470226288, 'latency_p50': 5.629634857177734, 'latency_p90': 6.410972809791565}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-anthropic-grpo-_76361_v1

is_internal_developer: True

language_model: rirv938/anthropic_grpo_40k_cp120_98ff_g2b15_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.63

us_pacific_date: 2025-05-18

win_ratio: 0.508896369319548

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['###', '\n', '</s>', 'You:'], '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-anthropic-grpo-76361-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-76361-v1-mkmlizer to finish
rirv938-anthropic-grpo-76361-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-76361-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-76361-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-76361-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-76361-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-76361-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-76361-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-76361-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-76361-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-76361-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-76361-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-76361-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-76361-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-76361-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-76361-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-76361-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-76361-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-76361-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-76361-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-76361-v1-mkmlizer: Downloaded to shared memory in 88.987s
rirv938-anthropic-grpo-76361-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7ysc1nd7, device:0
rirv938-anthropic-grpo-76361-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-76361-v1-mkmlizer: quantized model in 43.897s
rirv938-anthropic-grpo-76361-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp120_98ff_g2b15_merged in 132.885s
rirv938-anthropic-grpo-76361-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-76361-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-76361-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-76361-v1
rirv938-anthropic-grpo-76361-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-76361-v1/tokenizer.json
rirv938-anthropic-grpo-76361-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-76361-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-76361-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.40it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:13, 25.89it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:15, 22.81it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:12, 28.53it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:16, 20.48it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:18, 18.34it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 23.79it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:13, 23.72it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:13, 24.82it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:14, 22.63it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:11, 27.58it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:13, 23.13it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:11, 26.21it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 28.09it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:15, 18.99it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:12, 23.60it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:12, 23.70it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:12, 22.18it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 26.45it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 23.96it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 28.33it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:10, 25.49it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:08, 29.94it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:13, 19.77it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:10, 24.22it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:11, 22.56it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:09, 26.85it/s]
Loading 0:  34%|███▎      | 122/363 [00:05<00:09, 24.10it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:08, 27.55it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:09, 24.69it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:07, 28.90it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 29.51it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:10, 20.67it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:10, 20.00it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:08, 24.40it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:08, 22.90it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 27.32it/s]
Loading 0:  46%|████▌     | 167/363 [00:06<00:08, 23.13it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:06, 27.36it/s]
Loading 0:  48%|████▊     | 176/363 [00:07<00:07, 24.05it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 28.38it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:09, 18.76it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.90it/s]
Loading 0:  53%|█████▎    | 194/363 [00:08<00:07, 21.96it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:06, 26.24it/s]
Loading 0:  56%|█████▌    | 203/363 [00:08<00:06, 23.57it/s]
Loading 0:  57%|█████▋    | 208/363 [00:08<00:05, 27.64it/s]
Loading 0:  58%|█████▊    | 212/363 [00:08<00:06, 24.86it/s]
Loading 0:  60%|█████▉    | 217/363 [00:08<00:04, 29.21it/s]
Loading 0:  61%|██████    | 222/363 [00:09<00:04, 30.18it/s]
Loading 0:  62%|██████▏   | 226/363 [00:09<00:06, 21.11it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 20.52it/s]
Loading 0:  65%|██████▍   | 235/363 [00:09<00:05, 25.22it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:05, 23.26it/s]
Loading 0:  67%|██████▋   | 244/363 [00:09<00:04, 27.97it/s]
Loading 0:  68%|██████▊   | 248/363 [00:10<00:04, 25.39it/s]
Loading 0:  70%|██████▉   | 253/363 [00:10<00:03, 30.08it/s]
Loading 0:  71%|███████   | 257/363 [00:10<00:04, 24.55it/s]
Loading 0:  72%|███████▏  | 262/363 [00:10<00:03, 29.31it/s]
Loading 0:  73%|███████▎  | 266/363 [00:11<00:04, 19.95it/s]
Loading 0:  75%|███████▍  | 271/363 [00:11<00:03, 24.58it/s]
Loading 0:  76%|███████▌  | 275/363 [00:11<00:03, 23.16it/s]
Loading 0:  78%|███████▊  | 282/363 [00:11<00:02, 29.25it/s]
Loading 0:  79%|███████▉  | 286/363 [00:11<00:02, 28.07it/s]
Loading 0:  80%|████████  | 291/363 [00:11<00:02, 30.17it/s]
Loading 0:  81%|████████▏ | 295/363 [00:11<00:02, 28.59it/s]
Loading 0:  82%|████████▏ | 299/363 [00:12<00:02, 28.58it/s]
Loading 0:  84%|████████▎ | 304/363 [00:12<00:02, 24.36it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 23.24it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:02, 22.19it/s]
Loading 0:  88%|████████▊ | 318/363 [00:12<00:01, 28.61it/s]
Loading 0:  89%|████████▊ | 322/363 [00:12<00:01, 27.76it/s]
Loading 0:  90%|█████████ | 327/363 [00:13<00:01, 29.99it/s]
Loading 0:  91%|█████████ | 331/363 [00:13<00:01, 28.67it/s]
Loading 0:  93%|█████████▎| 336/363 [00:13<00:00, 30.57it/s]
Loading 0:  94%|█████████▎| 340/363 [00:13<00:00, 29.07it/s]
Loading 0:  94%|█████████▍| 343/363 [00:13<00:00, 29.13it/s]
Loading 0:  95%|█████████▌| 346/363 [00:20<00:09,  1.72it/s]
Loading 0:  96%|█████████▌| 349/363 [00:20<00:06,  2.24it/s]
Loading 0:  97%|█████████▋| 353/363 [00:20<00:03,  3.20it/s]
Loading 0:  98%|█████████▊| 357/363 [00:21<00:01,  4.38it/s]
Loading 0: 100%|█████████▉| 362/363 [00:21<00:00,  6.53it/s]
                                                            
Job rirv938-anthropic-grpo-76361-v1-mkmlizer completed after 165.94s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-76361-v1-mkmlizer
Pipeline stage MKMLizer completed in 166.41s
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-anthropic-grpo-76361-v1
Waiting for inference service rirv938-anthropic-grpo-76361-v1 to be ready
Inference service rirv938-anthropic-grpo-76361-v1 ready after 150.69531273841858s
Pipeline stage MKMLDeployer completed in 151.13s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4114181995391846s
Received healthy response to inference request in 1.724456787109375s
Received healthy response to inference request in 1.714296579360962s
Received healthy response to inference request in 1.663313388824463s
Received healthy response to inference request in 1.4837641716003418s
5 requests
0 failed requests
5th percentile: 1.519674015045166
10th percentile: 1.5555838584899901
20th percentile: 1.6274035453796387
30th percentile: 1.6735100269317627
40th percentile: 1.6939033031463624
50th percentile: 1.714296579360962
60th percentile: 1.7183606624603271
70th percentile: 1.7224247455596924
80th percentile: 1.861849069595337
90th percentile: 2.1366336345672607
95th percentile: 2.2740259170532227
99th percentile: 2.383939743041992
mean time: 1.7994498252868651
Pipeline stage StressChecker completed in 10.59s
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 0.74s
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-anthropic-grpo-_76361_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-anthropic-grpo-76361-v1-profiler
Waiting for inference service rirv938-anthropic-grpo-76361-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4677.25s
Shutdown handler de-registered
rirv938-anthropic-grpo-_76361_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_76361_v1 status is now torndown due to DeploymentManager action