rirv938-anthropic-grpo-_65100

developer_uid: rirv938

submission_id: rirv938-anthropic-grpo-_65100_v1

model_name: rirv938-anthropic-grpo-_65100_v1

model_group: rirv938/anthropic_grpo_4

status: torndown

timestamp: 2025-05-17T17:37:27+00:00

num_battles: 9127

num_wins: 4863

celo_rating: 1306.78

family_friendly_score: 0.542

family_friendly_standard_error: 0.007046076922657033

submission_type: basic

model_repo: rirv938/anthropic_grpo_40k_cp2368_95ff_beta6_3_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': 0.6508950026649999, 'latency_mean': 1.5362601268291474, 'latency_p50': 1.51755952835083, 'latency_p90': 1.7182019233703614}, {'batch_size': 3, 'throughput': 1.2347791218641562, 'latency_mean': 2.4257741379737854, 'latency_p50': 2.4332207441329956, 'latency_p90': 2.706336259841919}, {'batch_size': 5, 'throughput': 1.52368867548089, 'latency_mean': 3.2680872929096223, 'latency_p50': 3.3071773052215576, 'latency_p90': 3.607191061973572}, {'batch_size': 6, 'throughput': 1.634075546727737, 'latency_mean': 3.6511391687393187, 'latency_p50': 3.671318769454956, 'latency_p90': 4.06133337020874}, {'batch_size': 8, 'throughput': 1.6983182604002913, 'latency_mean': 4.678509047031403, 'latency_p50': 4.740750551223755, 'latency_p90': 5.226226568222046}, {'batch_size': 10, 'throughput': 1.7723435220353552, 'latency_mean': 5.593967070579529, 'latency_p50': 5.592658996582031, 'latency_p90': 6.27595705986023}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-anthropic-grpo-_65100_v1

is_internal_developer: True

language_model: rirv938/anthropic_grpo_40k_cp2368_95ff_beta6_3_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.65

us_pacific_date: 2025-05-17

win_ratio: 0.5328147255396077

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-65100-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-65100-v1-mkmlizer to finish
rirv938-anthropic-grpo-65100-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-65100-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-65100-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-65100-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-65100-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-65100-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-65100-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-65100-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-65100-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-65100-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-65100-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-65100-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-65100-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-65100-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-65100-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-65100-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-65100-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-65100-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-65100-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-65100-v1-mkmlizer: Downloaded to shared memory in 76.049s
rirv938-anthropic-grpo-65100-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzqwruyfn, device:0
rirv938-anthropic-grpo-65100-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-65100-v1-mkmlizer: quantized model in 42.902s
rirv938-anthropic-grpo-65100-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp2368_95ff_beta6_3_merged in 118.952s
rirv938-anthropic-grpo-65100-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-65100-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-65100-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-65100-v1
rirv938-anthropic-grpo-65100-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-65100-v1/config.json
rirv938-anthropic-grpo-65100-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-65100-v1/special_tokens_map.json
rirv938-anthropic-grpo-65100-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-65100-v1/tokenizer_config.json
rirv938-anthropic-grpo-65100-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-65100-v1/tokenizer.json
rirv938-anthropic-grpo-65100-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-65100-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-65100-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 21.00it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:13, 26.00it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:15, 22.63it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:11, 28.81it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:15, 22.06it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:17, 19.34it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 24.95it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:12, 25.84it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:12, 26.90it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:13, 24.21it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:11, 27.48it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:13, 23.42it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:10, 28.54it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 29.64it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:15, 19.65it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:12, 24.28it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:12, 23.45it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:13, 21.54it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 26.21it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 23.66it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 27.74it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:11, 24.20it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:09, 28.33it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:13, 19.13it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:10, 23.51it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:11, 21.68it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:09, 26.15it/s]
Loading 0:  34%|███▎      | 122/363 [00:05<00:10, 23.71it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:08, 27.87it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:09, 24.59it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:07, 29.21it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 28.47it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:10, 20.31it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:10, 20.18it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:08, 25.07it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:08, 23.05it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 27.56it/s]
Loading 0:  46%|████▌     | 167/363 [00:06<00:08, 24.44it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:06, 29.29it/s]
Loading 0:  48%|████▊     | 176/363 [00:07<00:07, 25.53it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 30.33it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:08, 20.36it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:06, 25.22it/s]
Loading 0:  53%|█████▎    | 194/363 [00:07<00:07, 23.13it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:05, 27.99it/s]
Loading 0:  56%|█████▌    | 203/363 [00:08<00:06, 24.59it/s]
Loading 0:  58%|█████▊    | 209/363 [00:08<00:04, 31.41it/s]
Loading 0:  59%|█████▊    | 213/363 [00:08<00:05, 26.99it/s]
Loading 0:  60%|█████▉    | 217/363 [00:08<00:04, 29.33it/s]
Loading 0:  61%|██████    | 222/363 [00:08<00:04, 30.65it/s]
Loading 0:  62%|██████▏   | 226/363 [00:09<00:06, 21.51it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 20.98it/s]
Loading 0:  65%|██████▍   | 235/363 [00:09<00:04, 25.81it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:05, 23.24it/s]
Loading 0:  67%|██████▋   | 244/363 [00:09<00:04, 28.09it/s]
Loading 0:  68%|██████▊   | 248/363 [00:10<00:04, 24.68it/s]
Loading 0:  70%|██████▉   | 253/363 [00:10<00:03, 29.48it/s]
Loading 0:  71%|███████   | 257/363 [00:10<00:04, 24.41it/s]
Loading 0:  72%|███████▏  | 262/363 [00:10<00:03, 28.88it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 19.41it/s]
Loading 0:  75%|███████▍  | 272/363 [00:10<00:03, 25.86it/s]
Loading 0:  76%|███████▌  | 276/363 [00:11<00:03, 24.33it/s]
Loading 0:  77%|███████▋  | 280/363 [00:11<00:03, 27.13it/s]
Loading 0:  78%|███████▊  | 284/363 [00:11<00:03, 24.64it/s]
Loading 0:  80%|███████▉  | 289/363 [00:11<00:02, 28.37it/s]
Loading 0:  81%|████████  | 293/363 [00:11<00:02, 24.23it/s]
Loading 0:  82%|████████▏ | 298/363 [00:11<00:02, 29.08it/s]
Loading 0:  83%|████████▎ | 303/363 [00:12<00:01, 30.29it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 22.04it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:02, 21.62it/s]
Loading 0:  88%|████████▊ | 318/363 [00:12<00:01, 28.07it/s]
Loading 0:  89%|████████▊ | 322/363 [00:12<00:01, 27.60it/s]
Loading 0:  90%|█████████ | 327/363 [00:12<00:01, 30.18it/s]
Loading 0:  91%|█████████ | 331/363 [00:13<00:01, 28.44it/s]
Loading 0:  93%|█████████▎| 336/363 [00:13<00:00, 30.34it/s]
Loading 0:  94%|█████████▎| 340/363 [00:13<00:00, 28.55it/s]
Loading 0:  95%|█████████▍| 344/363 [00:20<00:09,  1.97it/s]
Loading 0:  96%|█████████▌| 348/363 [00:20<00:05,  2.64it/s]
Loading 0:  97%|█████████▋| 353/363 [00:20<00:02,  3.83it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  4.94it/s]
                                                            
Job rirv938-anthropic-grpo-65100-v1-mkmlizer completed after 147.71s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-65100-v1-mkmlizer
Pipeline stage MKMLizer completed in 148.17s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-grpo-65100-v1
Waiting for inference service rirv938-anthropic-grpo-65100-v1 to be ready
Inference service rirv938-anthropic-grpo-65100-v1 ready after 140.76896572113037s
Pipeline stage MKMLDeployer completed in 141.30s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0895273685455322s
Received healthy response to inference request in 1.7723572254180908s
Received healthy response to inference request in 1.565202236175537s
Received healthy response to inference request in 2.0496740341186523s
Received healthy response to inference request in 1.8631587028503418s
5 requests
0 failed requests
5th percentile: 1.606633234024048
10th percentile: 1.6480642318725587
20th percentile: 1.73092622756958
30th percentile: 1.790517520904541
40th percentile: 1.8268381118774415
50th percentile: 1.8631587028503418
60th percentile: 1.937764835357666
70th percentile: 2.01237096786499
80th percentile: 2.0576447010040284
90th percentile: 2.07358603477478
95th percentile: 2.081556701660156
99th percentile: 2.087933235168457
mean time: 1.867983913421631
Pipeline stage StressChecker completed in 10.47s
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 0.66s
Shutdown handler de-registered
rirv938-anthropic-grpo-_65100_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-anthropic-grpo-65100-v1-profiler
Waiting for inference service rirv938-anthropic-grpo-65100-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 2655.76s
Shutdown handler de-registered
rirv938-anthropic-grpo-_65100_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_65100_v1 status is now torndown due to DeploymentManager action