rirv938-anthropic-grpo-_49016

developer_uid: rirv938

submission_id: rirv938-anthropic-grpo-_49016_v2

model_name: rirv938-anthropic-grpo-_49016_v2

model_group: rirv938/anthropic_grpo_4

status: torndown

timestamp: 2025-05-14T23:11:51+00:00

num_battles: 6470

num_wins: 3351

celo_rating: 1292.72

family_friendly_score: 0.5438000000000001

family_friendly_standard_error: 0.0070438847236450434

submission_type: basic

model_repo: rirv938/anthropic_grpo_40k_cp148_95ff_20ww2_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': 0.6384294796512149, 'latency_mean': 1.5662782084941864, 'latency_p50': 1.572187900543213, 'latency_p90': 1.7253746271133423}, {'batch_size': 3, 'throughput': 1.2037263524538078, 'latency_mean': 2.4854067385196688, 'latency_p50': 2.496456027030945, 'latency_p90': 2.7479525089263914}, {'batch_size': 5, 'throughput': 1.5038298720175418, 'latency_mean': 3.306262048482895, 'latency_p50': 3.3072186708450317, 'latency_p90': 3.687438464164734}, {'batch_size': 6, 'throughput': 1.5831988619323816, 'latency_mean': 3.778114207983017, 'latency_p50': 3.7772125005722046, 'latency_p90': 4.26121711730957}, {'batch_size': 8, 'throughput': 1.66464354109377, 'latency_mean': 4.776165750026703, 'latency_p50': 4.753379583358765, 'latency_p90': 5.274718999862671}, {'batch_size': 10, 'throughput': 1.71940474758792, 'latency_mean': 5.768234812021255, 'latency_p50': 5.728957653045654, 'latency_p90': 6.557492518424987}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-anthropic-grpo-_49016_v2

is_internal_developer: True

language_model: rirv938/anthropic_grpo_40k_cp148_95ff_20ww2_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.58

us_pacific_date: 2025-05-14

win_ratio: 0.5179289026275116

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': ['You:', '\n', '</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-49016-v2-mkmlizer
Waiting for job on rirv938-anthropic-grpo-49016-v2-mkmlizer to finish
rirv938-anthropic-grpo-49016-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-49016-v2-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-49016-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-49016-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-49016-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-49016-v2-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-49016-v2-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-49016-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-49016-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-49016-v2-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-49016-v2-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-49016-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-49016-v2-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-49016-v2-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-49016-v2-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-49016-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-49016-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-49016-v2-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-49016-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-49016-v2-mkmlizer: Downloaded to shared memory in 77.071s
rirv938-anthropic-grpo-49016-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwuh6mrj5, device:0
rirv938-anthropic-grpo-49016-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-49016-v2-mkmlizer: quantized model in 40.950s
rirv938-anthropic-grpo-49016-v2-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp148_95ff_20ww2_merged in 118.021s
rirv938-anthropic-grpo-49016-v2-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-49016-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-49016-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-49016-v2
rirv938-anthropic-grpo-49016-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-49016-v2/config.json
rirv938-anthropic-grpo-49016-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-49016-v2/special_tokens_map.json
rirv938-anthropic-grpo-49016-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-49016-v2/tokenizer_config.json
rirv938-anthropic-grpo-49016-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-49016-v2/tokenizer.json
rirv938-anthropic-grpo-49016-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-49016-v2/flywheel_model.0.safetensors
rirv938-anthropic-grpo-49016-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.51it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 27.61it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 24.37it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:10, 33.14it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:15, 22.46it/s]
Loading 0:   7%|▋         | 27/363 [00:01<00:15, 21.81it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 25.08it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:12, 25.33it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 28.57it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 27.54it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 29.72it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 28.42it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 28.58it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 24.21it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 21.61it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 28.23it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:10, 27.39it/s]
Loading 0:  21%|██▏       | 78/363 [00:03<00:11, 25.44it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:09, 28.36it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 25.17it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 31.73it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 30.02it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:11, 23.54it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:12, 21.24it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:08, 28.01it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 27.46it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 29.70it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 28.20it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 29.97it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 28.75it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 29.02it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 24.75it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 23.50it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 22.88it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:07, 27.48it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:08, 24.86it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 30.97it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 29.74it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 31.07it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 29.84it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 23.89it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:08, 21.26it/s]
Loading 0:  53%|█████▎    | 192/363 [00:07<00:06, 27.82it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 26.95it/s]
Loading 0:  55%|█████▍    | 199/363 [00:07<00:06, 27.27it/s]
Loading 0:  56%|█████▌    | 203/363 [00:07<00:06, 24.36it/s]
Loading 0:  57%|█████▋    | 208/363 [00:07<00:05, 29.27it/s]
Loading 0:  58%|█████▊    | 212/363 [00:07<00:05, 25.77it/s]
Loading 0:  60%|█████▉    | 217/363 [00:08<00:04, 30.52it/s]
Loading 0:  61%|██████    | 222/363 [00:08<00:04, 32.17it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 23.09it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:06, 22.13it/s]
Loading 0:  65%|██████▍   | 235/363 [00:08<00:04, 27.00it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:05, 24.05it/s]
Loading 0:  67%|██████▋   | 244/363 [00:09<00:04, 28.97it/s]
Loading 0:  68%|██████▊   | 248/363 [00:09<00:04, 25.91it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 32.00it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 30.11it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 23.97it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 21.29it/s]
Loading 0:  75%|███████▌  | 273/363 [00:10<00:03, 27.86it/s]
Loading 0:  76%|███████▋  | 277/363 [00:10<00:03, 27.49it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 30.04it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 29.06it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 31.50it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 30.34it/s]
Loading 0:  82%|████████▏ | 299/363 [00:11<00:02, 29.67it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 25.98it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 24.61it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 23.02it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 29.58it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 28.64it/s]
Loading 0:  90%|█████████ | 327/363 [00:12<00:01, 30.58it/s]
Loading 0:  91%|█████████ | 331/363 [00:12<00:01, 29.00it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 30.91it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 29.32it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  1.98it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.67it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.88it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  5.03it/s]
                                                            
Job rirv938-anthropic-grpo-49016-v2-mkmlizer completed after 144.79s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-49016-v2-mkmlizer
Pipeline stage MKMLizer completed in 145.33s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-grpo-49016-v2
Waiting for inference service rirv938-anthropic-grpo-49016-v2 to be ready
Inference service rirv938-anthropic-grpo-49016-v2 ready after 130.746764421463s
Pipeline stage MKMLDeployer completed in 131.30s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2881810665130615s
Received healthy response to inference request in 1.850287675857544s
Received healthy response to inference request in 1.69734787940979s
Received healthy response to inference request in 1.6802806854248047s
Received healthy response to inference request in 1.550811529159546s
5 requests
0 failed requests
5th percentile: 1.5767053604125976
10th percentile: 1.6025991916656495
20th percentile: 1.654386854171753
30th percentile: 1.6836941242218018
40th percentile: 1.690521001815796
50th percentile: 1.69734787940979
60th percentile: 1.7585237979888917
70th percentile: 1.8196997165679931
80th percentile: 1.9378663539886476
90th percentile: 2.1130237102508547
95th percentile: 2.200602388381958
99th percentile: 2.2706653308868407
mean time: 1.8133817672729493
Pipeline stage StressChecker completed in 10.56s
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 0.79s
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 0.76s
Shutdown handler de-registered
rirv938-anthropic-grpo-_49016_v2 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
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-anthropic-grpo-49016-v2-profiler
Waiting for inference service rirv938-anthropic-grpo-49016-v2-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 2923.92s
Shutdown handler de-registered
rirv938-anthropic-grpo-_49016_v2 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_49016_v2 status is now torndown due to DeploymentManager action