rirv938-anthropic-grpo-_55424

developer_uid: rirv938

submission_id: rirv938-anthropic-grpo-_55424_v4

model_name: rirv938-anthropic-grpo-_55424_v4

model_group: rirv938/anthropic_grpo_4

status: torndown

timestamp: 2025-04-29T18:30:19+00:00

num_battles: 5440

num_wins: 2756

celo_rating: 1315.68

family_friendly_score: 0.5842

family_friendly_standard_error: 0.006970084074098389

submission_type: basic

model_repo: rirv938/anthropic_grpo_40k_cp296_95ff_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': 0.637777199123001, 'latency_mean': 1.5678743588924409, 'latency_p50': 1.5725051164627075, 'latency_p90': 1.740524125099182}, {'batch_size': 3, 'throughput': 1.2233680659853707, 'latency_mean': 2.4456010806560515, 'latency_p50': 2.4648547172546387, 'latency_p90': 2.681013083457947}, {'batch_size': 5, 'throughput': 1.511057660870309, 'latency_mean': 3.301383134126663, 'latency_p50': 3.28752601146698, 'latency_p90': 3.6907972574234007}, {'batch_size': 6, 'throughput': 1.581637042138752, 'latency_mean': 3.775167027711868, 'latency_p50': 3.7698802947998047, 'latency_p90': 4.23586859703064}, {'batch_size': 8, 'throughput': 1.6763994539258789, 'latency_mean': 4.741531323194504, 'latency_p50': 4.7569204568862915, 'latency_p90': 5.343700504302978}, {'batch_size': 10, 'throughput': 1.7303974739381176, 'latency_mean': 5.7315018784999845, 'latency_p50': 5.720114827156067, 'latency_p90': 6.473454928398132}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-anthropic-grpo-_55424_v4

is_internal_developer: True

language_model: rirv938/anthropic_grpo_40k_cp296_95ff_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.58

us_pacific_date: 2025-04-29

win_ratio: 0.5066176470588235

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>', 'You:', '<|end_of_text|>'], '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': '### Response:\n{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-55424-v4-mkmlizer
Waiting for job on rirv938-anthropic-grpo-55424-v4-mkmlizer to finish
rirv938-anthropic-grpo-55424-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-55424-v4-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-55424-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-55424-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-55424-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-55424-v4-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-55424-v4-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-55424-v4-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-55424-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-55424-v4-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-55424-v4-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-55424-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-55424-v4-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-55424-v4-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-55424-v4-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-55424-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-55424-v4-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-55424-v4-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-55424-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-55424-v4-mkmlizer: Downloaded to shared memory in 70.679s
rirv938-anthropic-grpo-55424-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6zy4ftpr, device:0
rirv938-anthropic-grpo-55424-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-55424-v4-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-55424-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-55424-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-55424-v4
rirv938-anthropic-grpo-55424-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-55424-v4/config.json
rirv938-anthropic-grpo-55424-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-55424-v4/special_tokens_map.json
rirv938-anthropic-grpo-55424-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-55424-v4/tokenizer_config.json
rirv938-anthropic-grpo-55424-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-55424-v4/tokenizer.json
rirv938-anthropic-grpo-55424-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-55424-v4/flywheel_model.0.safetensors
rirv938-anthropic-grpo-55424-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 20.69it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:13, 25.24it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:15, 22.18it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:12, 27.60it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:17, 19.62it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:19, 17.52it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:14, 22.98it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:14, 21.99it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:14, 22.43it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 23.57it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:14, 21.55it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:14, 21.64it/s]
Loading 0:  13%|█▎        | 49/363 [00:02<00:13, 23.10it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:14, 21.81it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:13, 22.18it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:12, 23.47it/s]
Loading 0:  17%|█▋        | 63/363 [00:03<00:18, 16.45it/s]
Loading 0:  18%|█▊        | 65/363 [00:03<00:18, 15.96it/s]
Loading 0:  19%|█▉        | 69/363 [00:03<00:15, 19.22it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:17, 17.05it/s]
Loading 0:  21%|██        | 76/363 [00:03<00:13, 21.16it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:13, 21.08it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:12, 22.11it/s]
Loading 0:  24%|██▎       | 86/363 [00:04<00:14, 19.39it/s]
Loading 0:  25%|██▌       | 91/363 [00:04<00:11, 24.59it/s]
Loading 0:  26%|██▌       | 95/363 [00:04<00:11, 23.03it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:09, 28.40it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:13, 19.80it/s]
Loading 0:  31%|███       | 111/363 [00:05<00:09, 26.18it/s]
Loading 0:  32%|███▏      | 115/363 [00:05<00:09, 26.60it/s]
Loading 0:  33%|███▎      | 120/363 [00:05<00:08, 29.03it/s]
Loading 0:  34%|███▍      | 124/363 [00:05<00:08, 28.62it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:07, 31.12it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:07, 29.87it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 29.60it/s]
Loading 0:  39%|███▉      | 142/363 [00:06<00:08, 24.65it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:09, 23.29it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:09, 22.50it/s]
Loading 0:  43%|████▎     | 156/363 [00:06<00:07, 28.98it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:07, 28.20it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 30.57it/s]
Loading 0:  47%|████▋     | 169/363 [00:07<00:07, 27.29it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:06, 27.47it/s]
Loading 0:  48%|████▊     | 176/363 [00:07<00:07, 25.12it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:07, 24.22it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:08, 21.30it/s]
Loading 0:  52%|█████▏    | 190/363 [00:08<00:06, 26.10it/s]
Loading 0:  53%|█████▎    | 194/363 [00:08<00:07, 24.12it/s]
Loading 0:  55%|█████▌    | 201/363 [00:08<00:05, 30.21it/s]
Loading 0:  56%|█████▋    | 205/363 [00:08<00:05, 28.82it/s]
Loading 0:  58%|█████▊    | 210/363 [00:08<00:04, 30.75it/s]
Loading 0:  59%|█████▉    | 214/363 [00:08<00:05, 29.52it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:05, 28.38it/s]
Loading 0:  61%|██████    | 222/363 [00:09<00:04, 29.02it/s]
Loading 0:  62%|██████▏   | 225/363 [00:09<00:07, 19.42it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 21.48it/s]
Loading 0:  65%|██████▌   | 237/363 [00:09<00:04, 27.76it/s]
Loading 0:  66%|██████▋   | 241/363 [00:09<00:04, 27.38it/s]
Loading 0:  68%|██████▊   | 246/363 [00:10<00:03, 29.81it/s]
Loading 0:  69%|██████▉   | 250/363 [00:10<00:03, 28.86it/s]
Loading 0:  70%|███████   | 255/363 [00:10<00:03, 30.99it/s]
Loading 0:  71%|███████▏  | 259/363 [00:10<00:03, 29.54it/s]
Loading 0:  72%|███████▏  | 263/363 [00:10<00:04, 23.74it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 21.58it/s]
Loading 0:  75%|███████▌  | 273/363 [00:11<00:03, 28.45it/s]
Loading 0:  76%|███████▋  | 277/363 [00:11<00:03, 28.02it/s]
Loading 0:  78%|███████▊  | 282/363 [00:11<00:02, 30.62it/s]
Loading 0:  79%|███████▉  | 286/363 [00:11<00:02, 29.51it/s]
Loading 0:  80%|████████  | 291/363 [00:11<00:02, 31.52it/s]
Loading 0:  81%|████████▏ | 295/363 [00:11<00:02, 28.97it/s]
Loading 0:  82%|████████▏ | 298/363 [00:11<00:02, 28.91it/s]
Loading 0:  83%|████████▎ | 303/363 [00:12<00:02, 29.64it/s]
Loading 0:  84%|████████▍ | 306/363 [00:12<00:02, 19.37it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:02, 21.25it/s]
Loading 0:  87%|████████▋ | 316/363 [00:12<00:01, 25.79it/s]
Loading 0:  88%|████████▊ | 320/363 [00:12<00:01, 23.82it/s]
Loading 0:  90%|████████▉ | 325/363 [00:13<00:01, 28.40it/s]
Loading 0:  91%|█████████ | 329/363 [00:13<00:01, 25.58it/s]
Loading 0:  92%|█████████▏| 334/363 [00:13<00:00, 30.02it/s]
Loading 0:  93%|█████████▎| 338/363 [00:13<00:00, 26.16it/s]
Loading 0:  94%|█████████▍| 343/363 [00:13<00:00, 29.82it/s]
Loading 0:  96%|█████████▌| 347/363 [00:20<00:08,  1.98it/s]
Loading 0:  96%|█████████▋| 350/363 [00:20<00:05,  2.48it/s]
Loading 0:  97%|█████████▋| 353/363 [00:21<00:03,  3.16it/s]
Loading 0:  98%|█████████▊| 357/363 [00:21<00:01,  4.30it/s]
Loading 0: 100%|█████████▉| 362/363 [00:21<00:00,  6.39it/s]
                                                            
Job rirv938-anthropic-grpo-55424-v4-mkmlizer completed after 145.92s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-55424-v4-mkmlizer
Pipeline stage MKMLizer completed in 146.41s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.43s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-grpo-55424-v4
Waiting for inference service rirv938-anthropic-grpo-55424-v4 to be ready
Inference service rirv938-anthropic-grpo-55424-v4 ready after 140.4666783809662s
Pipeline stage MKMLDeployer completed in 140.99s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.033576011657715s
Received healthy response to inference request in 2.133056402206421s
Received healthy response to inference request in 1.9622840881347656s
Received healthy response to inference request in 1.5843312740325928s
Received healthy response to inference request in 1.8827049732208252s
5 requests
0 failed requests
5th percentile: 1.6440060138702393
10th percentile: 1.7036807537078857
20th percentile: 1.8230302333831787
30th percentile: 1.8986207962036132
40th percentile: 1.9304524421691895
50th percentile: 1.9622840881347656
60th percentile: 1.9908008575439453
70th percentile: 2.019317626953125
80th percentile: 2.053472089767456
90th percentile: 2.0932642459869384
95th percentile: 2.11316032409668
99th percentile: 2.129077186584473
mean time: 1.9191905498504638
Pipeline stage StressChecker completed in 11.27s
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 0.85s
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 0.80s
Shutdown handler de-registered
rirv938-anthropic-grpo-_55424_v4 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 2886.68s
Shutdown handler de-registered
rirv938-anthropic-grpo-_55424_v4 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_55424_v4 status is now torndown due to DeploymentManager action