rirv938-anthropic-grpo-_10659

developer_uid: rirv938

submission_id: rirv938-anthropic-grpo-_10659_v1

model_name: rirv938-anthropic-grpo-_10659_v1

model_group: rirv938/anthropic_grpo_4

status: torndown

timestamp: 2025-04-30T15:00:40+00:00

num_battles: 7433

num_wins: 4111

celo_rating: 1343.9

family_friendly_score: 0.5032

family_friendly_standard_error: 0.007070922994913747

submission_type: basic

model_repo: rirv938/anthropic_grpo_40k_cp592_0ff_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': 0.6407127783011083, 'latency_mean': 1.5606671357154847, 'latency_p50': 1.5696126222610474, 'latency_p90': 1.7253393173217773}, {'batch_size': 3, 'throughput': 1.2399974011609185, 'latency_mean': 2.409802308082581, 'latency_p50': 2.4057395458221436, 'latency_p90': 2.6532461166381838}, {'batch_size': 5, 'throughput': 1.5313957470844302, 'latency_mean': 3.2440824246406557, 'latency_p50': 3.244016408920288, 'latency_p90': 3.6860187292099}, {'batch_size': 6, 'throughput': 1.6185820279083092, 'latency_mean': 3.6743804347515105, 'latency_p50': 3.6400389671325684, 'latency_p90': 4.181029057502746}, {'batch_size': 8, 'throughput': 1.7066304729898063, 'latency_mean': 4.65495747923851, 'latency_p50': 4.676642060279846, 'latency_p90': 5.168080353736878}, {'batch_size': 10, 'throughput': 1.755661311669669, 'latency_mean': 5.653374222517013, 'latency_p50': 5.655246257781982, 'latency_p90': 6.33448257446289}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-anthropic-grpo-_10659_v1

is_internal_developer: True

language_model: rirv938/anthropic_grpo_40k_cp592_0ff_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.64

us_pacific_date: 2025-04-30

win_ratio: 0.5530741288847033

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-10659-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-10659-v1-mkmlizer to finish
rirv938-anthropic-grpo-10659-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-10659-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-10659-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-10659-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-10659-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-10659-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-10659-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-10659-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-10659-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-10659-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-10659-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-10659-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-10659-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-10659-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-10659-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-10659-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-10659-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-10659-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-10659-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-10659-v1-mkmlizer: Downloaded to shared memory in 90.735s
rirv938-anthropic-grpo-10659-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpoeguqekq, device:0
rirv938-anthropic-grpo-10659-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-10659-v1-mkmlizer: quantized model in 41.559s
rirv938-anthropic-grpo-10659-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp592_0ff_merged in 132.295s
rirv938-anthropic-grpo-10659-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-10659-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-10659-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-10659-v1
rirv938-anthropic-grpo-10659-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-10659-v1/config.json
rirv938-anthropic-grpo-10659-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-10659-v1/special_tokens_map.json
rirv938-anthropic-grpo-10659-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-10659-v1/tokenizer_config.json
rirv938-anthropic-grpo-10659-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-10659-v1/tokenizer.json
rirv938-anthropic-grpo-10659-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-10659-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-10659-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.77it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 27.57it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 24.55it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:11, 30.71it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:14, 23.54it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:16, 20.84it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:12, 26.62it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:11, 27.59it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 28.05it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 26.97it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 29.23it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 27.38it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:11, 27.27it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 30.04it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:14, 20.14it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:11, 25.08it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:11, 25.08it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:11, 23.98it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:09, 30.59it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 29.49it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 31.78it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:09, 29.31it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:11, 21.94it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:12, 20.31it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:09, 25.63it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:10, 24.03it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 30.38it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 29.14it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 31.15it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 30.04it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 29.51it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 25.31it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 24.02it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 22.70it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:07, 29.21it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:07, 28.72it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 30.99it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 29.50it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 31.60it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 30.17it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 24.29it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:08, 21.49it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:06, 26.01it/s]
Loading 0:  53%|█████▎    | 194/363 [00:07<00:07, 24.11it/s]
Loading 0:  55%|█████▍    | 199/363 [00:07<00:05, 29.16it/s]
Loading 0:  56%|█████▌    | 203/363 [00:07<00:06, 26.33it/s]
Loading 0:  58%|█████▊    | 209/363 [00:07<00:04, 33.33it/s]
Loading 0:  59%|█████▊    | 213/363 [00:07<00:05, 28.81it/s]
Loading 0:  60%|█████▉    | 217/363 [00:08<00:04, 30.96it/s]
Loading 0:  61%|██████    | 222/363 [00:08<00:04, 31.90it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:06, 21.83it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:06, 21.44it/s]
Loading 0:  65%|██████▍   | 235/363 [00:08<00:04, 26.24it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:05, 24.19it/s]
Loading 0:  67%|██████▋   | 245/363 [00:09<00:03, 31.08it/s]
Loading 0:  69%|██████▊   | 249/363 [00:09<00:04, 27.07it/s]
Loading 0:  70%|██████▉   | 253/363 [00:09<00:03, 29.40it/s]
Loading 0:  71%|███████   | 257/363 [00:09<00:04, 26.03it/s]
Loading 0:  72%|███████▏  | 262/363 [00:09<00:03, 30.46it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 20.31it/s]
Loading 0:  75%|███████▍  | 271/363 [00:10<00:03, 24.88it/s]
Loading 0:  76%|███████▌  | 275/363 [00:10<00:03, 23.44it/s]
Loading 0:  77%|███████▋  | 280/363 [00:10<00:02, 28.38it/s]
Loading 0:  78%|███████▊  | 284/363 [00:10<00:03, 25.42it/s]
Loading 0:  80%|███████▉  | 289/363 [00:10<00:02, 30.17it/s]
Loading 0:  81%|████████  | 293/363 [00:10<00:02, 26.60it/s]
Loading 0:  82%|████████▏ | 299/363 [00:11<00:02, 30.73it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 26.67it/s]
Loading 0:  85%|████████▍ | 308/363 [00:11<00:02, 26.83it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 23.19it/s]
Loading 0:  87%|████████▋ | 316/363 [00:11<00:01, 27.96it/s]
Loading 0:  88%|████████▊ | 320/363 [00:12<00:01, 25.32it/s]
Loading 0:  90%|████████▉ | 325/363 [00:12<00:01, 30.30it/s]
Loading 0:  91%|█████████ | 329/363 [00:12<00:01, 26.91it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 32.93it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 30.65it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  2.06it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.74it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.92it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  5.04it/s]
Loading 0: 100%|█████████▉| 362/363 [00:20<00:00,  7.15it/s]
                                                            
Job rirv938-anthropic-grpo-10659-v1-mkmlizer completed after 156.17s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-10659-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.66s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.22s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-grpo-10659-v1
Waiting for inference service rirv938-anthropic-grpo-10659-v1 to be ready
Inference service rirv938-anthropic-grpo-10659-v1 ready after 140.49698686599731s
Pipeline stage MKMLDeployer completed in 140.94s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.374091148376465s
Received healthy response to inference request in 1.5970711708068848s
Received healthy response to inference request in 1.736393928527832s
Received healthy response to inference request in 1.5888795852661133s
Received healthy response to inference request in 1.6050894260406494s
5 requests
0 failed requests
5th percentile: 1.5905179023742675
10th percentile: 1.592156219482422
20th percentile: 1.5954328536987306
30th percentile: 1.5986748218536377
40th percentile: 1.6018821239471435
50th percentile: 1.6050894260406494
60th percentile: 1.6576112270355225
70th percentile: 1.7101330280303955
80th percentile: 1.8639333724975586
90th percentile: 2.1190122604370116
95th percentile: 2.246551704406738
99th percentile: 2.3485832595825196
mean time: 1.7803050518035888
Pipeline stage StressChecker completed in 10.19s
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 0.88s
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 0.98s
Shutdown handler de-registered
rirv938-anthropic-grpo-_10659_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 5036.66s
Shutdown handler de-registered
rirv938-anthropic-grpo-_10659_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_10659_v1 status is now torndown due to DeploymentManager action