rirv938-anthropic-grpo-_57458

developer_uid: rirv938

submission_id: rirv938-anthropic-grpo-_57458_v1

model_name: rirv938-anthropic-grpo-_57458_v1

model_group: rirv938/anthropic_grpo_4

status: torndown

timestamp: 2025-05-18T15:18:22+00:00

num_battles: 7990

num_wins: 3973

celo_rating: 1285.98

family_friendly_score: 0.5242

family_friendly_standard_error: 0.007062780755481512

submission_type: basic

model_repo: rirv938/anthropic_grpo_40k_cp62_98ff_g4b15_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': 0.6404538460238313, 'latency_mean': 1.5612967360019683, 'latency_p50': 1.577751636505127, 'latency_p90': 1.7137344837188722}, {'batch_size': 3, 'throughput': 1.228290058709049, 'latency_mean': 2.430918802022934, 'latency_p50': 2.4419193267822266, 'latency_p90': 2.6835803031921386}, {'batch_size': 5, 'throughput': 1.5292208753767043, 'latency_mean': 3.2488620567321775, 'latency_p50': 3.240791082382202, 'latency_p90': 3.610530400276184}, {'batch_size': 6, 'throughput': 1.6166140667929887, 'latency_mean': 3.6838276553153992, 'latency_p50': 3.699012041091919, 'latency_p90': 4.12963981628418}, {'batch_size': 8, 'throughput': 1.7088228212823655, 'latency_mean': 4.648852877616882, 'latency_p50': 4.621894955635071, 'latency_p90': 5.343381309509278}, {'batch_size': 10, 'throughput': 1.760913537040449, 'latency_mean': 5.643975363969803, 'latency_p50': 5.668984413146973, 'latency_p90': 6.343898057937622}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-anthropic-grpo-_57458_v1

is_internal_developer: True

language_model: rirv938/anthropic_grpo_40k_cp62_98ff_g4b15_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.63

us_pacific_date: 2025-05-18

win_ratio: 0.49724655819774716

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', '###', 'You:', '</s>'], '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-57458-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-57458-v1-mkmlizer to finish
rirv938-anthropic-grpo-57458-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-57458-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-57458-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-57458-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-57458-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-57458-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-57458-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-57458-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-57458-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-57458-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-57458-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-57458-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-57458-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-57458-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-57458-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-57458-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-57458-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-57458-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-57458-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-57458-v1-mkmlizer: Downloaded to shared memory in 81.522s
rirv938-anthropic-grpo-57458-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7_npt4o0, device:0
rirv938-anthropic-grpo-57458-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-57458-v1-mkmlizer: quantized model in 43.520s
rirv938-anthropic-grpo-57458-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp62_98ff_g4b15_merged in 125.043s
rirv938-anthropic-grpo-57458-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-57458-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-57458-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-57458-v1
rirv938-anthropic-grpo-57458-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-57458-v1/config.json
rirv938-anthropic-grpo-57458-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-57458-v1/special_tokens_map.json
rirv938-anthropic-grpo-57458-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-57458-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-57458-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 19.93it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:14, 24.24it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:16, 21.79it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:12, 27.92it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:16, 20.29it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:18, 18.51it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 24.01it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:13, 24.01it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 25.29it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:14, 22.91it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:11, 28.07it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:12, 24.40it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:10, 28.71it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 30.06it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:15, 19.81it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:12, 24.45it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:11, 24.36it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:12, 22.78it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 27.24it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 24.41it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 28.79it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:10, 25.23it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:08, 29.52it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:13, 19.04it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:11, 22.39it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:11, 21.39it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:09, 25.62it/s]
Loading 0:  34%|███▎      | 122/363 [00:05<00:10, 23.28it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:08, 27.53it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:09, 24.38it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:07, 28.42it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 29.40it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:10, 20.40it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:10, 19.84it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:08, 24.26it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:09, 22.63it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 27.06it/s]
Loading 0:  46%|████▌     | 167/363 [00:06<00:08, 24.23it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:07, 27.00it/s]
Loading 0:  48%|████▊     | 176/363 [00:07<00:07, 23.53it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 27.88it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:09, 19.08it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 23.46it/s]
Loading 0:  53%|█████▎    | 194/363 [00:08<00:07, 22.30it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:06, 26.99it/s]
Loading 0:  56%|█████▌    | 203/363 [00:08<00:06, 24.46it/s]
Loading 0:  57%|█████▋    | 208/363 [00:08<00:05, 28.92it/s]
Loading 0:  58%|█████▊    | 212/363 [00:08<00:05, 25.42it/s]
Loading 0:  60%|█████▉    | 217/363 [00:08<00:04, 29.73it/s]
Loading 0:  61%|██████    | 222/363 [00:09<00:04, 29.63it/s]
Loading 0:  62%|██████▏   | 226/363 [00:09<00:06, 21.13it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 20.50it/s]
Loading 0:  65%|██████▍   | 235/363 [00:09<00:05, 24.96it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:05, 23.08it/s]
Loading 0:  67%|██████▋   | 244/363 [00:09<00:04, 27.62it/s]
Loading 0:  68%|██████▊   | 248/363 [00:10<00:04, 24.43it/s]
Loading 0:  70%|██████▉   | 253/363 [00:10<00:03, 28.99it/s]
Loading 0:  71%|███████   | 257/363 [00:10<00:04, 25.48it/s]
Loading 0:  72%|███████▏  | 262/363 [00:10<00:03, 29.53it/s]
Loading 0:  73%|███████▎  | 266/363 [00:11<00:04, 19.50it/s]
Loading 0:  75%|███████▍  | 271/363 [00:11<00:03, 23.95it/s]
Loading 0:  76%|███████▌  | 275/363 [00:11<00:03, 22.26it/s]
Loading 0:  77%|███████▋  | 280/363 [00:11<00:03, 26.76it/s]
Loading 0:  78%|███████▊  | 284/363 [00:11<00:03, 23.10it/s]
Loading 0:  80%|███████▉  | 289/363 [00:11<00:02, 26.87it/s]
Loading 0:  81%|████████  | 293/363 [00:12<00:02, 24.14it/s]
Loading 0:  82%|████████▏ | 298/363 [00:12<00:02, 28.39it/s]
Loading 0:  83%|████████▎ | 303/363 [00:12<00:02, 29.10it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 20.32it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:02, 19.91it/s]
Loading 0:  87%|████████▋ | 316/363 [00:12<00:01, 24.21it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:01, 22.23it/s]
Loading 0:  90%|████████▉ | 325/363 [00:13<00:01, 26.41it/s]
Loading 0:  91%|█████████ | 329/363 [00:13<00:01, 23.84it/s]
Loading 0:  92%|█████████▏| 334/363 [00:13<00:01, 28.30it/s]
Loading 0:  93%|█████████▎| 338/363 [00:13<00:01, 24.84it/s]
Loading 0:  94%|█████████▍| 343/363 [00:13<00:00, 28.95it/s]
Loading 0:  96%|█████████▌| 347/363 [00:20<00:08,  2.00it/s]
Loading 0:  96%|█████████▋| 350/363 [00:21<00:05,  2.52it/s]
Loading 0:  97%|█████████▋| 353/363 [00:21<00:03,  3.21it/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-57458-v1-mkmlizer completed after 145.82s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-57458-v1-mkmlizer
Pipeline stage MKMLizer completed in 146.39s
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-57458-v1
Waiting for inference service rirv938-anthropic-grpo-57458-v1 to be ready
Inference service rirv938-anthropic-grpo-57458-v1 ready after 150.88351154327393s
Pipeline stage MKMLDeployer completed in 151.45s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1884732246398926s
Received healthy response to inference request in 1.7977790832519531s
Received healthy response to inference request in 1.5676567554473877s
Received healthy response to inference request in 1.496199607849121s
Received healthy response to inference request in 1.755521535873413s
5 requests
0 failed requests
5th percentile: 1.5104910373687743
10th percentile: 1.5247824668884278
20th percentile: 1.5533653259277345
30th percentile: 1.6052297115325929
40th percentile: 1.680375623703003
50th percentile: 1.755521535873413
60th percentile: 1.7724245548248292
70th percentile: 1.789327573776245
80th percentile: 1.875917911529541
90th percentile: 2.032195568084717
95th percentile: 2.1103343963623047
99th percentile: 2.172845458984375
mean time: 1.7611260414123535
Pipeline stage StressChecker completed in 10.18s
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 0.61s
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 0.67s
Shutdown handler de-registered
rirv938-anthropic-grpo-_57458_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-anthropic-grpo-57458-v1-profiler
Waiting for inference service rirv938-anthropic-grpo-57458-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 3089.90s
Shutdown handler de-registered
rirv938-anthropic-grpo-_57458_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_57458_v1 status is now torndown due to DeploymentManager action