rirv938-anthropic-grpo-_19396

developer_uid: rirv938

submission_id: rirv938-anthropic-grpo-_19396_v1

model_name: rirv938-anthropic-grpo-_19396_v1

model_group: rirv938/anthropic_grpo_4

status: torndown

timestamp: 2025-05-15T19:11:53+00:00

num_battles: 8024

num_wins: 4014

celo_rating: 1291.03

family_friendly_score: 0.5398000000000001

family_friendly_standard_error: 0.0070486305052825686

submission_type: basic

model_repo: rirv938/anthropic_grpo_40k_cp78_95ff_baseline_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': 0.6475889568029505, 'latency_mean': 1.5441244053840637, 'latency_p50': 1.5426552295684814, 'latency_p90': 1.7176831245422364}, {'batch_size': 3, 'throughput': 1.2486675202588953, 'latency_mean': 2.398809801340103, 'latency_p50': 2.396330952644348, 'latency_p90': 2.6605183362960814}, {'batch_size': 5, 'throughput': 1.5395112931898864, 'latency_mean': 3.2287805426120757, 'latency_p50': 3.238094925880432, 'latency_p90': 3.6142418146133424}, {'batch_size': 6, 'throughput': 1.6436020743991602, 'latency_mean': 3.6306317687034606, 'latency_p50': 3.6446889638900757, 'latency_p90': 4.042825031280517}, {'batch_size': 8, 'throughput': 1.7182034492027765, 'latency_mean': 4.619460861682892, 'latency_p50': 4.631585240364075, 'latency_p90': 5.167651653289795}, {'batch_size': 10, 'throughput': 1.7783330206742538, 'latency_mean': 5.574800546169281, 'latency_p50': 5.627141237258911, 'latency_p90': 6.225624632835388}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-anthropic-grpo-_19396_v1

is_internal_developer: True

language_model: rirv938/anthropic_grpo_40k_cp78_95ff_baseline_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.66

us_pacific_date: 2025-05-15

win_ratio: 0.5002492522432702

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-19396-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-19396-v1-mkmlizer to finish
rirv938-anthropic-grpo-19396-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-19396-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-19396-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-19396-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-19396-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-19396-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-19396-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-19396-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-19396-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-19396-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-19396-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-19396-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-19396-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-19396-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-19396-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-19396-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-19396-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-19396-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-19396-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-19396-v1-mkmlizer: Downloaded to shared memory in 83.156s
rirv938-anthropic-grpo-19396-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpz6onm9iz, device:0
rirv938-anthropic-grpo-19396-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-19396-v1-mkmlizer: quantized model in 43.142s
rirv938-anthropic-grpo-19396-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp78_95ff_baseline_merged in 126.299s
rirv938-anthropic-grpo-19396-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-19396-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-19396-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-19396-v1
rirv938-anthropic-grpo-19396-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-19396-v1/config.json
rirv938-anthropic-grpo-19396-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-19396-v1/special_tokens_map.json
rirv938-anthropic-grpo-19396-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-19396-v1/tokenizer_config.json
rirv938-anthropic-grpo-19396-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-19396-v1/tokenizer.json
rirv938-anthropic-grpo-19396-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-19396-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-19396-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 20.11it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:13, 25.85it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:15, 23.07it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:11, 29.68it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:15, 21.92it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:17, 19.29it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 24.30it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:13, 24.25it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:13, 25.07it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:14, 22.49it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:11, 27.54it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:12, 24.16it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:10, 28.77it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 29.99it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:15, 19.11it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:12, 23.29it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:12, 23.26it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:13, 21.84it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 26.05it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 24.03it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 28.41it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:10, 25.20it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:08, 29.67it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:13, 19.66it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:10, 24.04it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:11, 22.39it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:09, 26.71it/s]
Loading 0:  34%|███▎      | 122/363 [00:05<00:09, 24.27it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:08, 28.45it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:09, 25.17it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:07, 29.34it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 29.80it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:10, 21.03it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:10, 20.48it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:08, 24.87it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:08, 22.92it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 27.25it/s]
Loading 0:  46%|████▌     | 167/363 [00:06<00:08, 24.37it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:06, 28.37it/s]
Loading 0:  48%|████▊     | 176/363 [00:07<00:07, 24.49it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 28.28it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:09, 19.24it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 23.47it/s]
Loading 0:  53%|█████▎    | 194/363 [00:08<00:07, 22.23it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:06, 26.55it/s]
Loading 0:  56%|█████▌    | 203/363 [00:08<00:06, 23.99it/s]
Loading 0:  57%|█████▋    | 208/363 [00:08<00:05, 28.17it/s]
Loading 0:  58%|█████▊    | 212/363 [00:08<00:06, 24.78it/s]
Loading 0:  60%|█████▉    | 217/363 [00:08<00:05, 28.83it/s]
Loading 0:  61%|██████    | 222/363 [00:08<00:04, 29.76it/s]
Loading 0:  62%|██████▏   | 226/363 [00:09<00:06, 20.97it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 20.43it/s]
Loading 0:  65%|██████▍   | 235/363 [00:09<00:05, 24.94it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:05, 23.17it/s]
Loading 0:  67%|██████▋   | 244/363 [00:09<00:04, 27.45it/s]
Loading 0:  68%|██████▊   | 248/363 [00:10<00:04, 24.65it/s]
Loading 0:  70%|██████▉   | 253/363 [00:10<00:03, 28.68it/s]
Loading 0:  71%|███████   | 257/363 [00:10<00:04, 23.82it/s]
Loading 0:  72%|███████▏  | 262/363 [00:10<00:03, 28.31it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 19.55it/s]
Loading 0:  75%|███████▍  | 271/363 [00:11<00:03, 24.00it/s]
Loading 0:  76%|███████▌  | 275/363 [00:11<00:03, 22.71it/s]
Loading 0:  77%|███████▋  | 280/363 [00:11<00:03, 27.22it/s]
Loading 0:  78%|███████▊  | 284/363 [00:11<00:03, 24.53it/s]
Loading 0:  80%|███████▉  | 289/363 [00:11<00:02, 28.99it/s]
Loading 0:  81%|████████  | 293/363 [00:11<00:02, 25.72it/s]
Loading 0:  82%|████████▏ | 298/363 [00:12<00:02, 30.05it/s]
Loading 0:  83%|████████▎ | 303/363 [00:12<00:01, 31.08it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 21.87it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:02, 21.32it/s]
Loading 0:  87%|████████▋ | 316/363 [00:12<00:01, 25.84it/s]
Loading 0:  88%|████████▊ | 320/363 [00:12<00:01, 23.91it/s]
Loading 0:  90%|████████▉ | 325/363 [00:13<00:01, 28.41it/s]
Loading 0:  91%|█████████ | 329/363 [00:13<00:01, 25.28it/s]
Loading 0:  92%|█████████▏| 334/363 [00:13<00:00, 29.68it/s]
Loading 0:  93%|█████████▎| 338/363 [00:13<00:00, 26.20it/s]
Loading 0:  94%|█████████▍| 343/363 [00:13<00:00, 30.60it/s]
Loading 0:  96%|█████████▌| 347/363 [00:20<00:07,  2.00it/s]
Loading 0:  96%|█████████▋| 350/363 [00:20<00:05,  2.53it/s]
Loading 0:  97%|█████████▋| 353/363 [00:20<00:03,  3.22it/s]
Loading 0:  98%|█████████▊| 357/363 [00:21<00:01,  4.42it/s]
                                                            
Job rirv938-anthropic-grpo-19396-v1-mkmlizer completed after 156.18s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-19396-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.72s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-grpo-19396-v1
Waiting for inference service rirv938-anthropic-grpo-19396-v1 to be ready
Inference service rirv938-anthropic-grpo-19396-v1 ready after 130.80781364440918s
Pipeline stage MKMLDeployer completed in 131.39s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1277570724487305s
Received healthy response to inference request in 1.9858887195587158s
Received healthy response to inference request in 1.9936552047729492s
Received healthy response to inference request in 1.565061092376709s
Received healthy response to inference request in 1.729156494140625s
5 requests
0 failed requests
5th percentile: 1.5978801727294922
10th percentile: 1.6306992530822755
20th percentile: 1.6963374137878418
30th percentile: 1.780502939224243
40th percentile: 1.8831958293914794
50th percentile: 1.9858887195587158
60th percentile: 1.9889953136444092
70th percentile: 1.9921019077301025
80th percentile: 2.0204755783081056
90th percentile: 2.074116325378418
95th percentile: 2.100936698913574
99th percentile: 2.122392997741699
mean time: 1.880303716659546
Pipeline stage StressChecker completed in 10.86s
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 0.89s
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 0.70s
Shutdown handler de-registered
rirv938-anthropic-grpo-_19396_v1 status is now deployed due to DeploymentManager action
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 2714.05s
Shutdown handler de-registered
rirv938-anthropic-grpo-_19396_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_19396_v1 status is now torndown due to DeploymentManager action