rirv938-anthropic-grpo-_86434

developer_uid: rirv938

submission_id: rirv938-anthropic-grpo-_86434_v1

model_name: rirv938-anthropic-grpo-_86434_v1

model_group: rirv938/anthropic_grpo_4

status: torndown

timestamp: 2025-05-18T04:10:16+00:00

num_battles: 7589

num_wins: 3885

celo_rating: 1292.04

family_friendly_score: 0.5266

family_friendly_standard_error: 0.007061054312211456

submission_type: basic

model_repo: rirv938/anthropic_grpo_40k_cp248_98ff_g8b3_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': 0.6364291788933474, 'latency_mean': 1.5712064933776855, 'latency_p50': 1.587979793548584, 'latency_p90': 1.7374293804168701}, {'batch_size': 3, 'throughput': 1.2300209525510069, 'latency_mean': 2.4283228588104246, 'latency_p50': 2.4039489030838013, 'latency_p90': 2.7066396713256835}, {'batch_size': 5, 'throughput': 1.510573285316695, 'latency_mean': 3.294623898267746, 'latency_p50': 3.294291615486145, 'latency_p90': 3.674441933631897}, {'batch_size': 6, 'throughput': 1.5994392682367358, 'latency_mean': 3.728069851398468, 'latency_p50': 3.726385712623596, 'latency_p90': 4.201126575469971}, {'batch_size': 8, 'throughput': 1.6891465786847517, 'latency_mean': 4.709094604253769, 'latency_p50': 4.688192963600159, 'latency_p90': 5.264087414741516}, {'batch_size': 10, 'throughput': 1.7167994017162607, 'latency_mean': 5.770226310491562, 'latency_p50': 5.771573424339294, 'latency_p90': 6.43074266910553}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-anthropic-grpo-_86434_v1

is_internal_developer: True

language_model: rirv938/anthropic_grpo_40k_cp248_98ff_g8b3_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.6

us_pacific_date: 2025-05-17

win_ratio: 0.5119251548293583

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-86434-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-86434-v1-mkmlizer to finish
rirv938-anthropic-grpo-86434-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-86434-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-86434-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-86434-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-86434-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-86434-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-86434-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-86434-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-86434-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-86434-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-86434-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-86434-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-86434-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-86434-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-86434-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-86434-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-86434-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-86434-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-86434-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-86434-v1-mkmlizer: Downloaded to shared memory in 79.363s
rirv938-anthropic-grpo-86434-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpntc4zm2u, device:0
rirv938-anthropic-grpo-86434-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-86434-v1-mkmlizer: quantized model in 42.089s
rirv938-anthropic-grpo-86434-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp248_98ff_g8b3_merged in 121.453s
rirv938-anthropic-grpo-86434-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-86434-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-86434-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-86434-v1
rirv938-anthropic-grpo-86434-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-86434-v1/config.json
rirv938-anthropic-grpo-86434-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-86434-v1/special_tokens_map.json
rirv938-anthropic-grpo-86434-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-86434-v1/tokenizer_config.json
rirv938-anthropic-grpo-86434-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-86434-v1/tokenizer.json
rirv938-anthropic-grpo-86434-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-86434-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-86434-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.45it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 27.79it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:12, 28.05it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 27.31it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 33.87it/s]
Loading 0:   7%|▋         | 25/363 [00:01<00:16, 20.25it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:15, 20.95it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 20.85it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 26.59it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 24.16it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.55it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 28.60it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 28.58it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 23.93it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:14, 20.94it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 27.05it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 26.35it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:12, 22.05it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 27.40it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 23.93it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 30.32it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:09, 28.82it/s]
Loading 0:  28%|██▊       | 101/363 [00:04<00:11, 23.23it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:12, 20.56it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 27.06it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 26.55it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 29.34it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 28.18it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 31.09it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:07, 28.94it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 29.00it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 24.81it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:10, 21.78it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:10, 21.25it/s]
Loading 0:  43%|████▎     | 156/363 [00:06<00:07, 28.32it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:07, 27.92it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 30.41it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 29.50it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 31.48it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 30.17it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 23.99it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:08, 21.11it/s]
Loading 0:  53%|█████▎    | 192/363 [00:07<00:06, 28.29it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 27.51it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 29.93it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 29.19it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 31.26it/s]
Loading 0:  59%|█████▉    | 214/363 [00:08<00:05, 29.59it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:04, 30.04it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 24.86it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 23.35it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 22.54it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 29.41it/s]
Loading 0:  66%|██████▋   | 241/363 [00:09<00:04, 28.55it/s]
Loading 0:  68%|██████▊   | 246/363 [00:09<00:03, 30.78it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:03, 29.79it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 31.86it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 30.01it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 24.94it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 21.65it/s]
Loading 0:  75%|███████▌  | 273/363 [00:10<00:03, 28.69it/s]
Loading 0:  76%|███████▋  | 277/363 [00:10<00:03, 28.20it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 30.53it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 28.90it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 31.38it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 29.75it/s]
Loading 0:  82%|████████▏ | 299/363 [00:11<00:02, 29.76it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 25.46it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 23.68it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 22.39it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 29.20it/s]
Loading 0:  89%|████████▊ | 322/363 [00:12<00:01, 28.02it/s]
Loading 0:  90%|█████████ | 327/363 [00:12<00:01, 30.66it/s]
Loading 0:  91%|█████████ | 331/363 [00:12<00:01, 28.98it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 31.29it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 29.60it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  1.95it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.61it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.80it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  4.91it/s]
                                                            
Job rirv938-anthropic-grpo-86434-v1-mkmlizer completed after 145.58s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-86434-v1-mkmlizer
Pipeline stage MKMLizer completed in 146.07s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-grpo-86434-v1
Waiting for inference service rirv938-anthropic-grpo-86434-v1 to be ready
Inference service rirv938-anthropic-grpo-86434-v1 ready after 150.62815690040588s
Pipeline stage MKMLDeployer completed in 151.30s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.385104179382324s
Received healthy response to inference request in 1.5663940906524658s
Received healthy response to inference request in 1.6274685859680176s
Received healthy response to inference request in 1.7146575450897217s
Received healthy response to inference request in 1.6306052207946777s
5 requests
0 failed requests
5th percentile: 1.5786089897155762
10th percentile: 1.5908238887786865
20th percentile: 1.6152536869049072
30th percentile: 1.6280959129333497
40th percentile: 1.6293505668640136
50th percentile: 1.6306052207946777
60th percentile: 1.6642261505126954
70th percentile: 1.6978470802307128
80th percentile: 1.8487468719482423
90th percentile: 2.116925525665283
95th percentile: 2.2510148525238036
99th percentile: 2.3582863140106203
mean time: 1.7848459243774415
Pipeline stage StressChecker completed in 10.09s
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 0.70s
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 0.68s
Shutdown handler de-registered
rirv938-anthropic-grpo-_86434_v1 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-86434-v1-profiler
Waiting for inference service rirv938-anthropic-grpo-86434-v1-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 2695.40s
Shutdown handler de-registered
rirv938-anthropic-grpo-_86434_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_86434_v1 status is now torndown due to DeploymentManager action