developer_uid: rirv938
submission_id: rirv938-anthropic-grpo-_64392_v1
model_name: rirv938-anthropic-grpo-_64392_v1
model_group: rirv938/anthropic_grpo_4
status: torndown
timestamp: 2025-05-15T22:35:07+00:00
num_battles: 5825
num_wins: 2886
celo_rating: 1288.36
family_friendly_score: 0.5686
family_friendly_standard_error: 0.007004199311841433
submission_type: basic
model_repo: rirv938/anthropic_grpo_40k_cp624_95ff_beta6_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': 0.641860317088626, 'latency_mean': 1.55791002035141, 'latency_p50': 1.5592782497406006, 'latency_p90': 1.7376548051834106}, {'batch_size': 3, 'throughput': 1.236514314547686, 'latency_mean': 2.420636109113693, 'latency_p50': 2.437749743461609, 'latency_p90': 2.6608274459838865}, {'batch_size': 5, 'throughput': 1.5268200753718673, 'latency_mean': 3.2613117396831512, 'latency_p50': 3.278179168701172, 'latency_p90': 3.6476576566696166}, {'batch_size': 6, 'throughput': 1.6121060373025253, 'latency_mean': 3.7010310173034666, 'latency_p50': 3.683852434158325, 'latency_p90': 4.141001987457275}, {'batch_size': 8, 'throughput': 1.6886854680810477, 'latency_mean': 4.698949213027954, 'latency_p50': 4.728153824806213, 'latency_p90': 5.32468090057373}, {'batch_size': 10, 'throughput': 1.73913887547225, 'latency_mean': 5.710277502536774, 'latency_p50': 5.771133184432983, 'latency_p90': 6.365000247955321}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-anthropic-grpo-_64392_v1
is_internal_developer: True
language_model: rirv938/anthropic_grpo_40k_cp624_95ff_beta6_merged
model_size: 13B
ranking_group: single
throughput_3p7s: 1.62
us_pacific_date: 2025-05-15
win_ratio: 0.495450643776824
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-64392-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-64392-v1-mkmlizer to finish
rirv938-anthropic-grpo-64392-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-64392-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-64392-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-64392-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-64392-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-64392-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-64392-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-64392-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-64392-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-64392-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-64392-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-64392-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-64392-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-64392-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-64392-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-64392-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-64392-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-64392-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-64392-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-64392-v1-mkmlizer: Downloaded to shared memory in 77.407s
rirv938-anthropic-grpo-64392-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4vs5fqd6, device:0
rirv938-anthropic-grpo-64392-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-64392-v1-mkmlizer: quantized model in 43.613s
rirv938-anthropic-grpo-64392-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp624_95ff_beta6_merged in 121.020s
rirv938-anthropic-grpo-64392-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-64392-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-64392-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-64392-v1
rirv938-anthropic-grpo-64392-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-64392-v1/config.json
rirv938-anthropic-grpo-64392-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-64392-v1/special_tokens_map.json
rirv938-anthropic-grpo-64392-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-64392-v1/tokenizer_config.json
rirv938-anthropic-grpo-64392-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-64392-v1/tokenizer.json
rirv938-anthropic-grpo-64392-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.42it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 27.75it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 24.47it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:10, 33.17it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:15, 22.56it/s]
Loading 0:   7%|▋         | 27/363 [00:01<00:15, 21.79it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 25.46it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:12, 26.92it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 28.15it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 27.08it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:11, 27.12it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:13, 24.05it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:10, 29.31it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:09, 30.43it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:15, 19.81it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:11, 24.62it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:11, 24.83it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:12, 23.27it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 28.00it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 24.48it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 27.46it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:11, 23.86it/s]
Loading 0:  28%|██▊       | 100/363 [00:03<00:09, 28.22it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:13, 18.89it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:10, 23.27it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:11, 21.90it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:09, 26.47it/s]
Loading 0:  34%|███▎      | 122/363 [00:04<00:10, 23.93it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:08, 28.37it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:09, 24.83it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:07, 29.09it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 30.00it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:10, 20.72it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:10, 19.71it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:08, 24.03it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:09, 22.09it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 26.19it/s]
Loading 0:  46%|████▌     | 167/363 [00:06<00:08, 23.47it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:07, 27.21it/s]
Loading 0:  48%|████▊     | 176/363 [00:07<00:07, 23.90it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 27.89it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:09, 18.35it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.79it/s]
Loading 0:  53%|█████▎    | 194/363 [00:07<00:07, 21.48it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:06, 25.97it/s]
Loading 0:  56%|█████▌    | 203/363 [00:08<00:06, 23.48it/s]
Loading 0:  57%|█████▋    | 208/363 [00:08<00:05, 27.46it/s]
Loading 0:  58%|█████▊    | 212/363 [00:08<00:06, 24.35it/s]
Loading 0:  60%|█████▉    | 217/363 [00:08<00:05, 28.76it/s]
Loading 0:  61%|██████    | 222/363 [00:08<00:04, 29.49it/s]
Loading 0:  62%|██████▏   | 226/363 [00:09<00:06, 20.71it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 19.80it/s]
Loading 0:  65%|██████▍   | 235/363 [00:09<00:05, 24.05it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:05, 22.07it/s]
Loading 0:  67%|██████▋   | 244/363 [00:09<00:04, 26.31it/s]
Loading 0:  68%|██████▊   | 248/363 [00:10<00:04, 23.40it/s]
Loading 0:  70%|██████▉   | 253/363 [00:10<00:03, 27.59it/s]
Loading 0:  71%|███████   | 257/363 [00:10<00:04, 24.57it/s]
Loading 0:  72%|███████▏  | 262/363 [00:10<00:03, 28.58it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:05, 19.07it/s]
Loading 0:  75%|███████▍  | 271/363 [00:11<00:03, 23.24it/s]
Loading 0:  76%|███████▌  | 275/363 [00:11<00:03, 22.13it/s]
Loading 0:  77%|███████▋  | 280/363 [00:11<00:03, 26.34it/s]
Loading 0:  78%|███████▊  | 284/363 [00:11<00:03, 23.49it/s]
Loading 0:  80%|███████▉  | 289/363 [00:11<00:02, 27.69it/s]
Loading 0:  81%|████████  | 293/363 [00:11<00:02, 24.51it/s]
Loading 0:  82%|████████▏ | 298/363 [00:12<00:02, 28.50it/s]
Loading 0:  83%|████████▎ | 303/363 [00:12<00:02, 29.30it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 20.16it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:02, 19.68it/s]
Loading 0:  87%|████████▋ | 316/363 [00:12<00:01, 24.03it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:01, 21.85it/s]
Loading 0:  90%|████████▉ | 325/363 [00:13<00:01, 25.63it/s]
Loading 0:  91%|█████████ | 329/363 [00:13<00:01, 22.91it/s]
Loading 0:  92%|█████████▏| 334/363 [00:13<00:01, 26.78it/s]
Loading 0:  93%|█████████▎| 338/363 [00:13<00:01, 23.48it/s]
Loading 0:  94%|█████████▍| 343/363 [00:13<00:00, 27.38it/s]
Loading 0:  96%|█████████▌| 347/363 [00:21<00:08,  1.93it/s]
Loading 0:  96%|█████████▋| 350/363 [00:21<00:05,  2.43it/s]
Loading 0:  97%|█████████▋| 353/363 [00:21<00:03,  3.10it/s]
Loading 0:  98%|█████████▊| 357/363 [00:21<00:01,  4.23it/s]
Loading 0: 100%|█████████▉| 362/363 [00:21<00:00,  6.29it/s]
                                                            

Job rirv938-anthropic-grpo-64392-v1-mkmlizer completed after 160.38s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-64392-v1-mkmlizer
Pipeline stage MKMLizer completed in 160.91s
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-64392-v1
Waiting for inference service rirv938-anthropic-grpo-64392-v1 to be ready
Inference service rirv938-anthropic-grpo-64392-v1 ready after 140.6333088874817s
Pipeline stage MKMLDeployer completed in 141.24s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4699623584747314s
Received healthy response to inference request in 1.6174426078796387s
Received healthy response to inference request in 1.6784331798553467s
Received healthy response to inference request in 1.740201711654663s
Received healthy response to inference request in 1.7679672241210938s
5 requests
0 failed requests
5th percentile: 1.6296407222747802
10th percentile: 1.641838836669922
20th percentile: 1.6662350654602052
30th percentile: 1.69078688621521
40th percentile: 1.7154942989349364
50th percentile: 1.740201711654663
60th percentile: 1.7513079166412353
70th percentile: 1.7624141216278075
80th percentile: 1.9083662509918213
90th percentile: 2.1891643047332763
95th percentile: 2.3295633316040036
99th percentile: 2.441882553100586
mean time: 1.8548014163970947
Pipeline stage StressChecker completed in 10.91s
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 0.71s
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 0.75s
Shutdown handler de-registered
rirv938-anthropic-grpo-_64392_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 2846.07s
Shutdown handler de-registered
rirv938-anthropic-grpo-_64392_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_64392_v1 status is now torndown due to DeploymentManager action