rirv938-anthropic-grpo-_51278

developer_uid: rirv938

submission_id: rirv938-anthropic-grpo-_51278_v1

model_name: rirv938-anthropic-grpo-_51278_v1

model_group: rirv938/anthropic_grpo_4

status: torndown

timestamp: 2025-05-16T16:32:59+00:00

num_battles: 9192

num_wins: 4749

celo_rating: 1292.78

family_friendly_score: 0.556

family_friendly_standard_error: 0.007026578114559035

submission_type: basic

model_repo: rirv938/anthropic_grpo_40k_cp2368_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': 0.6428651705900144, 'latency_mean': 1.5554601430892945, 'latency_p50': 1.5517739057540894, 'latency_p90': 1.7228440046310425}, {'batch_size': 3, 'throughput': 1.2138921460996916, 'latency_mean': 2.4669366121292113, 'latency_p50': 2.4764657020568848, 'latency_p90': 2.7366911649703978}, {'batch_size': 5, 'throughput': 1.5173004105998817, 'latency_mean': 3.2828435814380645, 'latency_p50': 3.2913111448287964, 'latency_p90': 3.6753421545028684}, {'batch_size': 6, 'throughput': 1.5996890130940045, 'latency_mean': 3.720870314836502, 'latency_p50': 3.7339459657669067, 'latency_p90': 4.1389710187911986}, {'batch_size': 8, 'throughput': 1.6783389736347736, 'latency_mean': 4.730867999792099, 'latency_p50': 4.734602212905884, 'latency_p90': 5.324566674232483}, {'batch_size': 10, 'throughput': 1.7348950669307013, 'latency_mean': 5.712592481374741, 'latency_p50': 5.670557141304016, 'latency_p90': 6.427758359909057}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-anthropic-grpo-_51278_v1

is_internal_developer: True

language_model: rirv938/anthropic_grpo_40k_cp2368_95ff_beta6_2_2_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.61

us_pacific_date: 2025-05-16

win_ratio: 0.516644908616188

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', '</s>', '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-51278-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-51278-v1-mkmlizer to finish
rirv938-anthropic-grpo-51278-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-51278-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-51278-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-51278-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-51278-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-51278-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-51278-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-51278-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-51278-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-51278-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-51278-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-51278-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-51278-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-51278-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-51278-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-51278-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-51278-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-51278-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-51278-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-51278-v1-mkmlizer: Downloaded to shared memory in 78.611s
rirv938-anthropic-grpo-51278-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppdpavdae, device:0
rirv938-anthropic-grpo-51278-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-51278-v1-mkmlizer: quantized model in 41.023s
rirv938-anthropic-grpo-51278-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp2368_95ff_beta6_2_2_merged in 119.635s
rirv938-anthropic-grpo-51278-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-51278-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-51278-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-51278-v1
rirv938-anthropic-grpo-51278-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-51278-v1/config.json
rirv938-anthropic-grpo-51278-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-51278-v1/special_tokens_map.json
rirv938-anthropic-grpo-51278-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-51278-v1/tokenizer_config.json
rirv938-anthropic-grpo-51278-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-51278-v1/tokenizer.json
rirv938-anthropic-grpo-51278-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 22.09it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 27.18it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 23.96it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:10, 32.83it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:14, 23.04it/s]
Loading 0:   7%|▋         | 27/363 [00:01<00:14, 22.40it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 23.38it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:11, 28.60it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:12, 25.70it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.79it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 29.21it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 29.57it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.05it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 22.89it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:09, 29.37it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:10, 28.32it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:10, 26.11it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:09, 30.21it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 29.20it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 31.30it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 29.72it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:11, 23.42it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:12, 20.92it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:09, 26.05it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:10, 24.32it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 30.83it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 29.77it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 32.19it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 30.85it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 30.36it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 25.66it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:08, 24.49it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 23.56it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:06, 30.67it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:06, 29.87it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.85it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 30.51it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 32.78it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:05, 31.26it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 24.93it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:08, 22.07it/s]
Loading 0:  52%|█████▏    | 190/363 [00:06<00:06, 27.48it/s]
Loading 0:  53%|█████▎    | 194/363 [00:07<00:06, 25.04it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 31.90it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 30.61it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 32.21it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:04, 30.30it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 29.94it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 26.03it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 24.86it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 23.62it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 30.43it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 29.25it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 31.48it/s]
Loading 0:  69%|██████▉   | 250/363 [00:08<00:03, 30.21it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 32.61it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 31.17it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:03, 25.10it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 22.37it/s]
Loading 0:  75%|███████▌  | 273/363 [00:09<00:03, 29.05it/s]
Loading 0:  76%|███████▋  | 277/363 [00:09<00:03, 28.63it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 31.22it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 30.07it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 32.20it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 30.05it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 28.95it/s]
Loading 0:  83%|████████▎ | 303/363 [00:10<00:01, 31.29it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 22.28it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 21.63it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 28.14it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 27.64it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 29.20it/s]
Loading 0:  91%|█████████ | 331/363 [00:11<00:01, 28.42it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 30.86it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 29.41it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  1.98it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.67it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.87it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  5.03it/s]
                                                            
Job rirv938-anthropic-grpo-51278-v1-mkmlizer completed after 145.56s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-51278-v1-mkmlizer
Pipeline stage MKMLizer completed in 146.15s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-grpo-51278-v1
Waiting for inference service rirv938-anthropic-grpo-51278-v1 to be ready
Inference service rirv938-anthropic-grpo-51278-v1 ready after 130.5229229927063s
Pipeline stage MKMLDeployer completed in 131.11s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5978569984436035s
Received healthy response to inference request in 1.5699238777160645s
Received healthy response to inference request in 2.087653636932373s
Received healthy response to inference request in 2.0112102031707764s
Received healthy response to inference request in 1.542266607284546s
5 requests
0 failed requests
5th percentile: 1.5477980613708495
10th percentile: 1.5533295154571534
20th percentile: 1.5643924236297608
30th percentile: 1.6581811428070068
40th percentile: 1.8346956729888917
50th percentile: 2.0112102031707764
60th percentile: 2.041787576675415
70th percentile: 2.0723649501800536
80th percentile: 2.189694309234619
90th percentile: 2.3937756538391115
95th percentile: 2.4958163261413575
99th percentile: 2.5774488639831543
mean time: 1.9617822647094727
Pipeline stage StressChecker completed in 11.22s
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 0.73s
Shutdown handler de-registered
rirv938-anthropic-grpo-_51278_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 2675.45s
Shutdown handler de-registered
rirv938-anthropic-grpo-_51278_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_51278_v1 status is now torndown due to DeploymentManager action