rirv938-anthropic-grpo-_25164

developer_uid: rirv938

submission_id: rirv938-anthropic-grpo-_25164_v1

model_name: rirv938-anthropic-grpo-_25164_v1

model_group: rirv938/anthropic_grpo_4

status: torndown

timestamp: 2025-05-16T16:32:55+00:00

num_battles: 10102

num_wins: 5156

celo_rating: 1288.63

family_friendly_score: 0.5506

family_friendly_standard_error: 0.007034765667739047

submission_type: basic

model_repo: rirv938/anthropic_grpo_40k_cp1776_95ff_beta6_2_2_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': 0.6436142071540499, 'latency_mean': 1.5536578619480133, 'latency_p50': 1.548438310623169, 'latency_p90': 1.720567488670349}, {'batch_size': 3, 'throughput': 1.232730141119325, 'latency_mean': 2.4264832055568695, 'latency_p50': 2.4072325229644775, 'latency_p90': 2.694916868209839}, {'batch_size': 5, 'throughput': 1.5172685346349286, 'latency_mean': 3.279936088323593, 'latency_p50': 3.2935069799423218, 'latency_p90': 3.6713852882385254}, {'batch_size': 6, 'throughput': 1.6101088991775647, 'latency_mean': 3.699952610731125, 'latency_p50': 3.690956711769104, 'latency_p90': 4.19356644153595}, {'batch_size': 8, 'throughput': 1.6933273933097672, 'latency_mean': 4.694546957015991, 'latency_p50': 4.696736931800842, 'latency_p90': 5.247729182243347}, {'batch_size': 10, 'throughput': 1.7406147849458333, 'latency_mean': 5.701640450954438, 'latency_p50': 5.651401162147522, 'latency_p90': 6.437829852104187}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-anthropic-grpo-_25164_v1

is_internal_developer: True

language_model: rirv938/anthropic_grpo_40k_cp1776_95ff_beta6_2_2_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.62

us_pacific_date: 2025-05-16

win_ratio: 0.5103939813898238

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-25164-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-25164-v1-mkmlizer to finish
rirv938-anthropic-grpo-25164-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-25164-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-25164-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-25164-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-25164-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-25164-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-25164-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-25164-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-25164-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-25164-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-25164-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-25164-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-25164-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-25164-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-25164-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-25164-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-25164-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-25164-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-25164-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-25164-v1-mkmlizer: Downloaded to shared memory in 77.767s
rirv938-anthropic-grpo-25164-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpf7qxu2lj, device:0
rirv938-anthropic-grpo-25164-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-25164-v1-mkmlizer: quantized model in 41.096s
rirv938-anthropic-grpo-25164-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp1776_95ff_beta6_2_2_merged in 118.863s
rirv938-anthropic-grpo-25164-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-25164-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-25164-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-25164-v1
rirv938-anthropic-grpo-25164-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-25164-v1/config.json
rirv938-anthropic-grpo-25164-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-25164-v1/special_tokens_map.json
rirv938-anthropic-grpo-25164-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-25164-v1/tokenizer_config.json
rirv938-anthropic-grpo-25164-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-25164-v1/tokenizer.json
rirv938-anthropic-grpo-25164-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.69it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:13, 26.89it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 23.91it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:10, 32.52it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:15, 22.10it/s]
Loading 0:   7%|▋         | 27/363 [00:01<00:15, 21.66it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 25.37it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:12, 27.11it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 28.72it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 27.74it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.26it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 28.99it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 28.76it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 23.95it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 21.55it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 28.40it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:10, 28.08it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:10, 26.06it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:09, 30.40it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 29.14it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 31.22it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:09, 29.36it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:11, 23.35it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:12, 20.99it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 27.91it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 27.37it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 30.19it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 29.27it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 31.17it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 29.75it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 29.76it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 25.67it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:08, 24.46it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 23.45it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:06, 30.00it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:07, 28.94it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 31.10it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 29.99it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 31.95it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 30.23it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 24.28it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:08, 21.69it/s]
Loading 0:  53%|█████▎    | 192/363 [00:07<00:05, 28.61it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:05, 28.22it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 30.54it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 29.11it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 31.36it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:05, 29.42it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 29.52it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 25.11it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 23.97it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 23.23it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 29.88it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 28.99it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 31.25it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:03, 29.46it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 31.67it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 30.10it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 23.71it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 21.35it/s]
Loading 0:  75%|███████▌  | 273/363 [00:09<00:03, 28.11it/s]
Loading 0:  76%|███████▋  | 277/363 [00:10<00:03, 27.54it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 29.37it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 28.04it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 30.49it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 29.18it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 28.87it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 24.90it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 23.51it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 22.78it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 29.26it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 28.10it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 30.46it/s]
Loading 0:  91%|█████████ | 331/363 [00:12<00:01, 29.46it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 31.40it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 29.80it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  2.00it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.68it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.88it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  5.02it/s]
                                                            
Job rirv938-anthropic-grpo-25164-v1-mkmlizer completed after 145.41s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-25164-v1-mkmlizer
Pipeline stage MKMLizer completed in 145.88s
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-25164-v1
Waiting for inference service rirv938-anthropic-grpo-25164-v1 to be ready
Inference service rirv938-anthropic-grpo-25164-v1 ready after 130.54552698135376s
Pipeline stage MKMLDeployer completed in 131.08s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1197590827941895s
Received healthy response to inference request in 1.7100257873535156s
Received healthy response to inference request in 1.921384572982788s
Received healthy response to inference request in 1.7413482666015625s
Received healthy response to inference request in 1.5683939456939697s
5 requests
0 failed requests
5th percentile: 1.596720314025879
10th percentile: 1.625046682357788
20th percentile: 1.6816994190216064
30th percentile: 1.716290283203125
40th percentile: 1.7288192749023437
50th percentile: 1.7413482666015625
60th percentile: 1.8133627891540527
70th percentile: 1.8853773117065429
80th percentile: 1.9610594749450685
90th percentile: 2.040409278869629
95th percentile: 2.0800841808319093
99th percentile: 2.1118241024017332
mean time: 1.812182331085205
Pipeline stage StressChecker completed in 10.48s
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 0.77s
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 0.65s
Shutdown handler de-registered
rirv938-anthropic-grpo-_25164_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 2556.91s
Shutdown handler de-registered
rirv938-anthropic-grpo-_25164_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_25164_v1 status is now torndown due to DeploymentManager action