rirv938-anthropic-grpo-_62978

developer_uid: rirv938

submission_id: rirv938-anthropic-grpo-_62978_v1

model_name: rirv938-anthropic-grpo-_62978_v1

model_group: rirv938/anthropic_grpo_4

status: torndown

timestamp: 2025-05-14T00:12:40+00:00

num_battles: 7776

num_wins: 4173

celo_rating: 1301.43

family_friendly_score: 0.5456

family_friendly_standard_error: 0.007041599818223129

submission_type: basic

model_repo: rirv938/anthropic_grpo_40k_cp1184_95ff_6ww_v2_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': 0.6456802432691401, 'latency_mean': 1.5486921286582946, 'latency_p50': 1.5400437116622925, 'latency_p90': 1.7132258176803588}, {'batch_size': 3, 'throughput': 1.2130560569926816, 'latency_mean': 2.4635276675224302, 'latency_p50': 2.4746286869049072, 'latency_p90': 2.732846975326538}, {'batch_size': 5, 'throughput': 1.5275517567879158, 'latency_mean': 3.252967393398285, 'latency_p50': 3.2504407167434692, 'latency_p90': 3.68481011390686}, {'batch_size': 6, 'throughput': 1.5845612928656845, 'latency_mean': 3.757875006198883, 'latency_p50': 3.7673630714416504, 'latency_p90': 4.152596020698548}, {'batch_size': 8, 'throughput': 1.674345142375408, 'latency_mean': 4.750772998332978, 'latency_p50': 4.735873103141785, 'latency_p90': 5.279572176933288}, {'batch_size': 10, 'throughput': 1.7418459263850135, 'latency_mean': 5.691640412807464, 'latency_p50': 5.7176830768585205, 'latency_p90': 6.445278573036194}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-anthropic-grpo-_62978_v1

is_internal_developer: True

language_model: rirv938/anthropic_grpo_40k_cp1184_95ff_6ww_v2_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.59

us_pacific_date: 2025-05-13

win_ratio: 0.5366512345679012

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': ['\n', '###', 'You:', '</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-62978-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-62978-v1-mkmlizer to finish
rirv938-anthropic-grpo-62978-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-62978-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-62978-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-62978-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-62978-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-62978-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-62978-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-62978-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-62978-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-62978-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-62978-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-62978-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-62978-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-62978-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-62978-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-62978-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-62978-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-62978-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-62978-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-62978-v1-mkmlizer: Downloaded to shared memory in 79.397s
rirv938-anthropic-grpo-62978-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpr3ax0c7_, device:0
rirv938-anthropic-grpo-62978-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-62978-v1-mkmlizer: quantized model in 43.185s
rirv938-anthropic-grpo-62978-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp1184_95ff_6ww_v2_merged in 122.583s
rirv938-anthropic-grpo-62978-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-62978-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-62978-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-62978-v1
rirv938-anthropic-grpo-62978-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-62978-v1/config.json
rirv938-anthropic-grpo-62978-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-62978-v1/special_tokens_map.json
rirv938-anthropic-grpo-62978-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-62978-v1/tokenizer_config.json
rirv938-anthropic-grpo-62978-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-62978-v1/tokenizer.json
rirv938-anthropic-grpo-62978-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-62978-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-62978-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.58it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 27.18it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 23.58it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:10, 32.53it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:14, 23.01it/s]
Loading 0:   7%|▋         | 27/363 [00:01<00:15, 21.83it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 25.17it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:13, 24.94it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 28.91it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 27.41it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.46it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 29.40it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 30.13it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 25.90it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 22.17it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 29.08it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:09, 28.82it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 27.76it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:09, 30.34it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 29.49it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 32.15it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 29.84it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 24.28it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:12, 21.42it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:08, 28.77it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 27.27it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 29.31it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 28.01it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.15it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 27.99it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:08, 28.16it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:09, 22.92it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:10, 21.33it/s]
Loading 0:  41%|████      | 148/363 [00:05<00:09, 22.76it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:09, 23.26it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:07, 27.27it/s]
Loading 0:  44%|████▍     | 159/363 [00:05<00:08, 24.78it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 29.88it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 28.96it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 31.35it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 28.87it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:08, 22.30it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:09, 19.38it/s]
Loading 0:  53%|█████▎    | 192/363 [00:07<00:06, 26.00it/s]
Loading 0:  54%|█████▎    | 195/363 [00:07<00:06, 24.59it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 29.05it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 27.84it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:05, 29.91it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:05, 28.66it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:05, 28.69it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 23.73it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:06, 22.63it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:06, 21.52it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 28.32it/s]
Loading 0:  66%|██████▋   | 241/363 [00:09<00:04, 26.45it/s]
Loading 0:  67%|██████▋   | 244/363 [00:09<00:04, 26.81it/s]
Loading 0:  68%|██████▊   | 248/363 [00:09<00:04, 23.51it/s]
Loading 0:  70%|██████▉   | 253/363 [00:09<00:03, 27.62it/s]
Loading 0:  71%|███████   | 257/363 [00:09<00:04, 24.50it/s]
Loading 0:  72%|███████▏  | 263/363 [00:10<00:04, 22.50it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 19.82it/s]
Loading 0:  75%|███████▌  | 273/363 [00:10<00:03, 26.17it/s]
Loading 0:  76%|███████▌  | 276/363 [00:10<00:03, 24.18it/s]
Loading 0:  77%|███████▋  | 281/363 [00:10<00:02, 29.05it/s]
Loading 0:  79%|███████▊  | 285/363 [00:10<00:03, 25.78it/s]
Loading 0:  80%|████████  | 291/363 [00:11<00:02, 29.78it/s]
Loading 0:  81%|████████▏ | 295/363 [00:11<00:02, 28.27it/s]
Loading 0:  82%|████████▏ | 299/363 [00:11<00:02, 28.81it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 24.44it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 23.21it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 22.27it/s]
Loading 0:  88%|████████▊ | 318/363 [00:12<00:01, 29.15it/s]
Loading 0:  89%|████████▊ | 322/363 [00:12<00:01, 27.34it/s]
Loading 0:  90%|█████████ | 327/363 [00:12<00:01, 29.93it/s]
Loading 0:  91%|█████████ | 331/363 [00:12<00:01, 28.40it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 30.50it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 28.19it/s]
Loading 0:  95%|█████████▍| 344/363 [00:20<00:09,  1.91it/s]
Loading 0:  96%|█████████▌| 348/363 [00:20<00:05,  2.57it/s]
Loading 0:  97%|█████████▋| 353/363 [00:20<00:02,  3.73it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  4.81it/s]
                                                            
Job rirv938-anthropic-grpo-62978-v1-mkmlizer completed after 156.29s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-62978-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.81s
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-62978-v1
Waiting for inference service rirv938-anthropic-grpo-62978-v1 to be ready
Inference service rirv938-anthropic-grpo-62978-v1 ready after 120.52008581161499s
Pipeline stage MKMLDeployer completed in 121.11s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.100050926208496s
Received healthy response to inference request in 1.6229770183563232s
Received healthy response to inference request in 1.6204884052276611s
Received healthy response to inference request in 1.762359857559204s
Received healthy response to inference request in 1.569343090057373s
5 requests
0 failed requests
5th percentile: 1.5795721530914306
10th percentile: 1.5898012161254882
20th percentile: 1.6102593421936036
30th percentile: 1.6209861278533935
40th percentile: 1.6219815731048584
50th percentile: 1.6229770183563232
60th percentile: 1.6787301540374755
70th percentile: 1.734483289718628
80th percentile: 1.8298980712890627
90th percentile: 1.9649744987487794
95th percentile: 2.0325127124786375
99th percentile: 2.0865432834625244
mean time: 1.7350438594818116
Pipeline stage StressChecker completed in 10.05s
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 0.76s
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 0.89s
Shutdown handler de-registered
rirv938-anthropic-grpo-_62978_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 4889.70s
Shutdown handler de-registered
rirv938-anthropic-grpo-_62978_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_62978_v1 status is now torndown due to DeploymentManager action