developer_uid: rirv938
submission_id: rirv938-anthropic-grpo-_74526_v1
model_name: rirv938-anthropic-grpo-_74526_v1
model_group: rirv938/anthropic_grpo_4
status: torndown
timestamp: 2025-05-17T17:37:14+00:00
num_battles: 9684
num_wins: 5052
celo_rating: 1302.07
family_friendly_score: 0.5449999999999999
family_friendly_standard_error: 0.0070423717595707765
submission_type: basic
model_repo: rirv938/anthropic_grpo_40k_cp592_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': 0.6428936817660794, 'latency_mean': 1.55537801861763, 'latency_p50': 1.5509788990020752, 'latency_p90': 1.7215409994125366}, {'batch_size': 3, 'throughput': 1.2294151782246103, 'latency_mean': 2.436889833211899, 'latency_p50': 2.4427602291107178, 'latency_p90': 2.7067086696624756}, {'batch_size': 5, 'throughput': 1.5383636717447033, 'latency_mean': 3.2334429848194124, 'latency_p50': 3.2405712604522705, 'latency_p90': 3.589849829673767}, {'batch_size': 6, 'throughput': 1.6181048066891077, 'latency_mean': 3.6929543018341064, 'latency_p50': 3.6880457401275635, 'latency_p90': 4.158969616889953}, {'batch_size': 8, 'throughput': 1.6895541525909812, 'latency_mean': 4.693943175077439, 'latency_p50': 4.729753375053406, 'latency_p90': 5.150813794136047}, {'batch_size': 10, 'throughput': 1.7488185302154717, 'latency_mean': 5.658625550270081, 'latency_p50': 5.653599262237549, 'latency_p90': 6.369230151176453}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-anthropic-grpo-_74526_v1
is_internal_developer: True
language_model: rirv938/anthropic_grpo_40k_cp592_95ff_beta6_3_merged
model_size: 13B
ranking_group: single
throughput_3p7s: 1.63
us_pacific_date: 2025-05-17
win_ratio: 0.5216852540272615
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': ['</s>', '###', '\n', '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-74526-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-74526-v1-mkmlizer to finish
rirv938-anthropic-grpo-74526-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-74526-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-74526-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-74526-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-74526-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-74526-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-74526-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-74526-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-74526-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-74526-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-74526-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-74526-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-74526-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-74526-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-74526-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-74526-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-74526-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-74526-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-74526-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-74526-v1-mkmlizer: Downloaded to shared memory in 77.201s
rirv938-anthropic-grpo-74526-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_5hjfoxy, device:0
rirv938-anthropic-grpo-74526-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-74526-v1-mkmlizer: quantized model in 43.561s
rirv938-anthropic-grpo-74526-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp592_95ff_beta6_3_merged in 120.763s
rirv938-anthropic-grpo-74526-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-74526-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-74526-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-74526-v1
rirv938-anthropic-grpo-74526-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-74526-v1/config.json
rirv938-anthropic-grpo-74526-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-74526-v1/special_tokens_map.json
rirv938-anthropic-grpo-74526-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-74526-v1/tokenizer_config.json
rirv938-anthropic-grpo-74526-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-74526-v1/tokenizer.json
rirv938-anthropic-grpo-74526-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-74526-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-74526-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:18, 19.09it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:14, 24.74it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:16, 21.75it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:12, 27.94it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:16, 20.74it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:18, 18.44it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:14, 23.71it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:14, 23.20it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:13, 24.59it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:12, 25.71it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:12, 24.75it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:12, 25.46it/s]
Loading 0:  13%|█▎        | 49/363 [00:02<00:11, 26.35it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:12, 25.13it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:12, 25.44it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:11, 27.04it/s]
Loading 0:  17%|█▋        | 63/363 [00:02<00:15, 18.98it/s]
Loading 0:  18%|█▊        | 66/363 [00:02<00:15, 19.75it/s]
Loading 0:  19%|█▉        | 69/363 [00:03<00:13, 21.58it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:14, 20.06it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:13, 20.58it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 25.64it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:12, 22.42it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:10, 26.47it/s]
Loading 0:  26%|██▌       | 95/363 [00:04<00:11, 23.26it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:09, 27.43it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:14, 18.33it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:11, 22.76it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:11, 21.13it/s]
Loading 0:  33%|███▎      | 118/363 [00:05<00:09, 25.45it/s]
Loading 0:  34%|███▎      | 122/363 [00:05<00:10, 23.02it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:08, 27.51it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:09, 24.47it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:07, 28.93it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 28.78it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:10, 20.52it/s]
Loading 0:  41%|████      | 148/363 [00:06<00:09, 21.94it/s]
Loading 0:  42%|████▏     | 151/363 [00:06<00:09, 22.27it/s]
Loading 0:  43%|████▎     | 156/363 [00:06<00:08, 25.25it/s]
Loading 0:  44%|████▍     | 159/363 [00:06<00:08, 22.94it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 26.06it/s]
Loading 0:  46%|████▌     | 167/363 [00:07<00:08, 23.17it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:06, 28.21it/s]
Loading 0:  48%|████▊     | 176/363 [00:07<00:07, 24.29it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:07, 23.18it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:08, 20.59it/s]
Loading 0:  52%|█████▏    | 190/363 [00:08<00:06, 25.42it/s]
Loading 0:  53%|█████▎    | 193/363 [00:08<00:06, 26.02it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:06, 25.17it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:06, 25.89it/s]
Loading 0:  56%|█████▌    | 203/363 [00:08<00:06, 22.92it/s]
Loading 0:  58%|█████▊    | 210/363 [00:08<00:05, 29.89it/s]
Loading 0:  59%|█████▉    | 214/363 [00:08<00:05, 28.34it/s]
Loading 0:  60%|██████    | 218/363 [00:09<00:05, 28.54it/s]
Loading 0:  61%|██████▏   | 223/363 [00:09<00:05, 24.71it/s]
Loading 0:  62%|██████▏   | 226/363 [00:09<00:05, 23.03it/s]
Loading 0:  63%|██████▎   | 229/363 [00:09<00:05, 24.22it/s]
Loading 0:  64%|██████▍   | 232/363 [00:09<00:05, 24.20it/s]
Loading 0:  65%|██████▌   | 237/363 [00:09<00:04, 27.87it/s]
Loading 0:  66%|██████▌   | 240/363 [00:09<00:04, 25.25it/s]
Loading 0:  68%|██████▊   | 246/363 [00:10<00:03, 30.00it/s]
Loading 0:  69%|██████▉   | 250/363 [00:10<00:03, 28.41it/s]
Loading 0:  70%|███████   | 255/363 [00:10<00:03, 30.28it/s]
Loading 0:  71%|███████▏  | 259/363 [00:10<00:03, 28.96it/s]
Loading 0:  72%|███████▏  | 262/363 [00:10<00:03, 29.03it/s]
Loading 0:  73%|███████▎  | 265/363 [00:10<00:04, 21.39it/s]
Loading 0:  74%|███████▍  | 268/363 [00:11<00:04, 22.18it/s]
Loading 0:  75%|███████▌  | 273/363 [00:11<00:03, 26.00it/s]
Loading 0:  76%|███████▌  | 276/363 [00:11<00:03, 24.22it/s]
Loading 0:  78%|███████▊  | 282/363 [00:11<00:02, 29.40it/s]
Loading 0:  79%|███████▉  | 286/363 [00:11<00:02, 27.87it/s]
Loading 0:  80%|████████  | 291/363 [00:11<00:02, 30.03it/s]
Loading 0:  81%|████████▏ | 295/363 [00:11<00:02, 28.23it/s]
Loading 0:  82%|████████▏ | 299/363 [00:12<00:02, 27.62it/s]
Loading 0:  83%|████████▎ | 303/363 [00:12<00:01, 30.32it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 21.24it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:02, 20.53it/s]
Loading 0:  87%|████████▋ | 316/363 [00:12<00:01, 25.73it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:01, 22.95it/s]
Loading 0:  90%|████████▉ | 325/363 [00:13<00:01, 27.63it/s]
Loading 0:  91%|█████████ | 329/363 [00:13<00:01, 24.67it/s]
Loading 0:  93%|█████████▎| 336/363 [00:13<00:00, 30.77it/s]
Loading 0:  94%|█████████▎| 340/363 [00:13<00:00, 28.98it/s]
Loading 0:  95%|█████████▍| 344/363 [00:20<00:09,  2.04it/s]
Loading 0:  96%|█████████▌| 348/363 [00:20<00:05,  2.70it/s]
Loading 0:  97%|█████████▋| 353/363 [00:21<00:02,  3.86it/s]
Loading 0:  98%|█████████▊| 357/363 [00:21<00:01,  4.96it/s]
                                                            

Job rirv938-anthropic-grpo-74526-v1-mkmlizer completed after 155.58s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-74526-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.04s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-grpo-74526-v1
Waiting for inference service rirv938-anthropic-grpo-74526-v1 to be ready
Inference service rirv938-anthropic-grpo-74526-v1 ready after 140.55361080169678s
Pipeline stage MKMLDeployer completed in 141.09s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4303998947143555s
Received healthy response to inference request in 1.8747520446777344s
Received healthy response to inference request in 1.7210736274719238s
Received healthy response to inference request in 1.8350634574890137s
Received healthy response to inference request in 1.784043312072754s
5 requests
0 failed requests
5th percentile: 1.7336675643920898
10th percentile: 1.7462615013122558
20th percentile: 1.771449375152588
30th percentile: 1.7942473411560058
40th percentile: 1.8146553993225099
50th percentile: 1.8350634574890137
60th percentile: 1.850938892364502
70th percentile: 1.8668143272399902
80th percentile: 1.9858816146850586
90th percentile: 2.208140754699707
95th percentile: 2.319270324707031
99th percentile: 2.4081739807128906
mean time: 1.9290664672851563
Pipeline stage StressChecker completed in 11.16s
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 0.72s
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-_74526_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4896.78s
Shutdown handler de-registered
rirv938-anthropic-grpo-_74526_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_74526_v1 status is now torndown due to DeploymentManager action