rirv938-anthropic-grpo-_91303

developer_uid: rirv938

submission_id: rirv938-anthropic-grpo-_91303_v1

model_name: rirv938-anthropic-grpo-_91303_v1

model_group: rirv938/anthropic_grpo_4

status: torndown

timestamp: 2025-04-30T02:49:24+00:00

num_battles: 5435

num_wins: 2925

celo_rating: 1320.3

family_friendly_score: 0.5369999999999999

family_friendly_standard_error: 0.007051680650738517

submission_type: basic

model_repo: rirv938/anthropic_grpo_40k_cp296_99ff_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': 0.6427097055432192, 'latency_mean': 1.5558547496795654, 'latency_p50': 1.556374192237854, 'latency_p90': 1.7196718215942384}, {'batch_size': 3, 'throughput': 1.217364918031392, 'latency_mean': 2.460210243463516, 'latency_p50': 2.4777190685272217, 'latency_p90': 2.7242435216903687}, {'batch_size': 5, 'throughput': 1.4843372716262777, 'latency_mean': 3.3526224589347837, 'latency_p50': 3.399931311607361, 'latency_p90': 3.7127228498458864}, {'batch_size': 6, 'throughput': 1.593104449784549, 'latency_mean': 3.7523731386661527, 'latency_p50': 3.7512060403823853, 'latency_p90': 4.194737482070923}, {'batch_size': 8, 'throughput': 1.6673194010047372, 'latency_mean': 4.76292289018631, 'latency_p50': 4.749542593955994, 'latency_p90': 5.439091348648072}, {'batch_size': 10, 'throughput': 1.7134887727312496, 'latency_mean': 5.800981130599975, 'latency_p50': 5.769322752952576, 'latency_p90': 6.580356407165527}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-anthropic-grpo-_91303_v1

ineligible_reason: num_battles<10000

is_internal_developer: True

language_model: rirv938/anthropic_grpo_40k_cp296_99ff_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.59

us_pacific_date: 2025-04-29

win_ratio: 0.5381784728610856

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>', 'You:', '\n', '###'], '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-91303-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-91303-v1-mkmlizer to finish
rirv938-anthropic-grpo-91303-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-91303-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-91303-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-91303-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-91303-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-91303-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-91303-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-91303-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-91303-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-91303-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-91303-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-91303-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-91303-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-91303-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-91303-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-91303-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-91303-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-91303-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-91303-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-91303-v1-mkmlizer: Downloaded to shared memory in 92.279s
rirv938-anthropic-grpo-91303-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmprsu9g5j9, device:0
rirv938-anthropic-grpo-91303-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-91303-v1-mkmlizer: quantized model in 45.345s
rirv938-anthropic-grpo-91303-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp296_99ff_merged in 137.625s
rirv938-anthropic-grpo-91303-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-91303-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-91303-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-91303-v1
rirv938-anthropic-grpo-91303-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-91303-v1/config.json
rirv938-anthropic-grpo-91303-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-91303-v1/special_tokens_map.json
rirv938-anthropic-grpo-91303-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-91303-v1/tokenizer_config.json
rirv938-anthropic-grpo-91303-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-91303-v1/tokenizer.json
rirv938-anthropic-grpo-91303-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-91303-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-91303-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 22.14it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 27.32it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:15, 22.84it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:12, 27.26it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:16, 20.69it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:18, 18.65it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 24.32it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:13, 23.96it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:13, 24.87it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:14, 22.38it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:11, 27.58it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:12, 24.15it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:10, 29.00it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 30.14it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:14, 20.30it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:11, 24.94it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:11, 24.73it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:12, 22.95it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 27.35it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 24.73it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 28.84it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:10, 24.76it/s]
Loading 0:  28%|██▊       | 100/363 [00:03<00:09, 28.95it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:13, 19.20it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:14, 17.88it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:13, 18.09it/s]
Loading 0:  33%|███▎      | 118/363 [00:05<00:10, 22.63it/s]
Loading 0:  34%|███▎      | 122/363 [00:05<00:11, 21.82it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:09, 26.05it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:09, 24.05it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:07, 28.50it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 29.72it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:10, 21.32it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:10, 20.90it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:08, 25.51it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:08, 23.25it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 27.96it/s]
Loading 0:  46%|████▌     | 167/363 [00:06<00:07, 24.91it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:06, 29.40it/s]
Loading 0:  48%|████▊     | 176/363 [00:07<00:07, 25.27it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 29.54it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:09, 19.13it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 23.33it/s]
Loading 0:  53%|█████▎    | 194/363 [00:08<00:07, 21.41it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:06, 25.49it/s]
Loading 0:  56%|█████▌    | 203/363 [00:08<00:06, 23.16it/s]
Loading 0:  57%|█████▋    | 208/363 [00:08<00:05, 27.30it/s]
Loading 0:  58%|█████▊    | 212/363 [00:08<00:06, 24.10it/s]
Loading 0:  60%|█████▉    | 217/363 [00:08<00:05, 27.95it/s]
Loading 0:  61%|██████    | 222/363 [00:09<00:04, 28.67it/s]
Loading 0:  62%|██████▏   | 226/363 [00:09<00:07, 19.12it/s]
Loading 0:  63%|██████▎   | 229/363 [00:09<00:06, 20.60it/s]
Loading 0:  64%|██████▍   | 232/363 [00:09<00:06, 20.58it/s]
Loading 0:  65%|██████▍   | 235/363 [00:09<00:05, 21.77it/s]
Loading 0:  66%|██████▌   | 238/363 [00:09<00:05, 23.37it/s]
Loading 0:  66%|██████▋   | 241/363 [00:10<00:05, 22.79it/s]
Loading 0:  67%|██████▋   | 244/363 [00:10<00:04, 23.89it/s]
Loading 0:  68%|██████▊   | 247/363 [00:10<00:04, 25.13it/s]
Loading 0:  69%|██████▉   | 250/363 [00:10<00:04, 23.67it/s]
Loading 0:  70%|██████▉   | 253/363 [00:10<00:04, 23.87it/s]
Loading 0:  71%|███████   | 257/363 [00:10<00:05, 21.07it/s]
Loading 0:  72%|███████▏  | 262/363 [00:10<00:03, 25.52it/s]
Loading 0:  73%|███████▎  | 265/363 [00:11<00:05, 17.24it/s]
Loading 0:  74%|███████▍  | 268/363 [00:11<00:05, 18.10it/s]
Loading 0:  75%|███████▍  | 271/363 [00:11<00:04, 19.82it/s]
Loading 0:  76%|███████▌  | 275/363 [00:11<00:04, 19.26it/s]
Loading 0:  77%|███████▋  | 280/363 [00:11<00:03, 24.18it/s]
Loading 0:  78%|███████▊  | 284/363 [00:12<00:03, 21.78it/s]
Loading 0:  80%|███████▉  | 289/363 [00:12<00:02, 25.16it/s]
Loading 0:  80%|████████  | 292/363 [00:12<00:02, 25.82it/s]
Loading 0:  81%|████████▏ | 295/363 [00:12<00:02, 24.62it/s]
Loading 0:  82%|████████▏ | 298/363 [00:12<00:02, 25.27it/s]
Loading 0:  83%|████████▎ | 303/363 [00:12<00:02, 26.82it/s]
Loading 0:  84%|████████▍ | 306/363 [00:13<00:03, 17.32it/s]
Loading 0:  86%|████████▌ | 311/363 [00:13<00:02, 19.38it/s]
Loading 0:  87%|████████▋ | 316/363 [00:13<00:01, 24.13it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:01, 22.76it/s]
Loading 0:  90%|████████▉ | 325/363 [00:13<00:01, 27.46it/s]
Loading 0:  91%|█████████ | 329/363 [00:13<00:01, 24.65it/s]
Loading 0:  92%|█████████▏| 334/363 [00:14<00:00, 29.13it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:00, 25.66it/s]
Loading 0:  94%|█████████▍| 343/363 [00:14<00:00, 29.68it/s]
Loading 0:  96%|█████████▌| 347/363 [00:21<00:08,  1.90it/s]
Loading 0:  96%|█████████▋| 350/363 [00:21<00:05,  2.39it/s]
Loading 0:  97%|█████████▋| 353/363 [00:22<00:03,  3.04it/s]
Loading 0:  98%|█████████▊| 357/363 [00:22<00:01,  4.14it/s]
Loading 0: 100%|█████████▉| 362/363 [00:22<00:00,  6.15it/s]
                                                            
Job rirv938-anthropic-grpo-91303-v1-mkmlizer completed after 176.55s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-91303-v1-mkmlizer
Pipeline stage MKMLizer completed in 177.08s
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-91303-v1
Waiting for inference service rirv938-anthropic-grpo-91303-v1 to be ready
Inference service rirv938-anthropic-grpo-91303-v1 ready after 150.6837956905365s
Pipeline stage MKMLDeployer completed in 151.12s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.2097244262695312s
Received healthy response to inference request in 2.4884567260742188s
Received healthy response to inference request in 1.7100903987884521s
Received healthy response to inference request in 1.5388596057891846s
5 requests
1 failed requests
5th percentile: 1.573105764389038
10th percentile: 1.6073519229888915
20th percentile: 1.6758442401885987
30th percentile: 1.810017204284668
40th percentile: 2.0098708152770994
50th percentile: 2.2097244262695312
60th percentile: 2.321217346191406
70th percentile: 2.4327102661132813
80th percentile: 6.018385219573977
90th percentile: 13.078242206573488
95th percentile: 16.608170700073238
99th percentile: 19.432113494873047
mean time: 5.617046070098877
%s, retrying in %s seconds...
Received healthy response to inference request in 2.0517868995666504s
Received healthy response to inference request in 1.7522757053375244s
Received healthy response to inference request in 1.587543249130249s
Received healthy response to inference request in 1.5989301204681396s
Received healthy response to inference request in 1.5047898292541504s
5 requests
0 failed requests
5th percentile: 1.52134051322937
10th percentile: 1.5378911972045899
20th percentile: 1.5709925651550294
30th percentile: 1.5898206233978271
40th percentile: 1.5943753719329834
50th percentile: 1.5989301204681396
60th percentile: 1.6602683544158936
70th percentile: 1.7216065883636473
80th percentile: 1.8121779441833497
90th percentile: 1.931982421875
95th percentile: 1.9918846607208252
99th percentile: 2.039806451797485
mean time: 1.6990651607513427
Pipeline stage StressChecker completed in 39.39s
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 0.73s
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 0.71s
Shutdown handler de-registered
rirv938-anthropic-grpo-_91303_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 2830.31s
Shutdown handler de-registered
rirv938-anthropic-grpo-_91303_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_91303_v1 status is now torndown due to DeploymentManager action