rirv938-anthropic-grpo-_53872

developer_uid: rirv938

submission_id: rirv938-anthropic-grpo-_53872_v1

model_name: rirv938-anthropic-grpo-_53872_v1

model_group: rirv938/anthropic_grpo_4

status: torndown

timestamp: 2025-05-15T21:58:14+00:00

num_battles: 6384

num_wins: 3265

celo_rating: 1296.58

family_friendly_score: 0.5691999999999999

family_friendly_standard_error: 0.0070030187776415394

submission_type: basic

model_repo: rirv938/anthropic_grpo_40k_cp234_95ff_baseline_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': 0.6448091912256331, 'latency_mean': 1.5507807970046996, 'latency_p50': 1.5511014461517334, 'latency_p90': 1.7078434944152832}, {'batch_size': 3, 'throughput': 1.2246431866949459, 'latency_mean': 2.4369245862960813, 'latency_p50': 2.420895576477051, 'latency_p90': 2.761899638175964}, {'batch_size': 5, 'throughput': 1.5305709925701638, 'latency_mean': 3.251393622159958, 'latency_p50': 3.2206571102142334, 'latency_p90': 3.6767675638198853}, {'batch_size': 6, 'throughput': 1.3885391101524, 'latency_mean': 4.297464443445206, 'latency_p50': 3.907999634742737, 'latency_p90': 6.13688428401947}, {'batch_size': 8, 'throughput': 1.6793520762133873, 'latency_mean': 4.725053226947784, 'latency_p50': 4.7363234758377075, 'latency_p90': 5.263904571533203}, {'batch_size': 10, 'throughput': 1.7330361522594784, 'latency_mean': 5.717161065340042, 'latency_p50': 5.697150111198425, 'latency_p90': 6.439275217056275}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-anthropic-grpo-_53872_v1

is_internal_developer: True

language_model: rirv938/anthropic_grpo_40k_cp234_95ff_baseline_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.47

us_pacific_date: 2025-05-15

win_ratio: 0.5114348370927319

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-53872-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-53872-v1-mkmlizer to finish
rirv938-anthropic-grpo-53872-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-53872-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-53872-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-53872-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-53872-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-53872-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-53872-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-53872-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-53872-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-53872-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-53872-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-53872-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-53872-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-53872-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-53872-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-53872-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-53872-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-53872-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-53872-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-53872-v1-mkmlizer: Downloaded to shared memory in 79.352s
rirv938-anthropic-grpo-53872-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5f_r9tzj, device:0
rirv938-anthropic-grpo-53872-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-53872-v1-mkmlizer: quantized model in 42.397s
rirv938-anthropic-grpo-53872-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp234_95ff_baseline_merged in 121.750s
rirv938-anthropic-grpo-53872-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-53872-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-53872-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-53872-v1
rirv938-anthropic-grpo-53872-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-53872-v1/config.json
rirv938-anthropic-grpo-53872-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-53872-v1/special_tokens_map.json
rirv938-anthropic-grpo-53872-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-53872-v1/tokenizer_config.json
rirv938-anthropic-grpo-53872-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-53872-v1/tokenizer.json
rirv938-anthropic-grpo-53872-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-53872-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-53872-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.83it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:13, 26.69it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 23.61it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:11, 29.81it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:15, 21.57it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:17, 19.46it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 25.33it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:12, 26.60it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 27.39it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 26.70it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:11, 27.37it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:12, 24.37it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:10, 29.46it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:09, 30.51it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:14, 20.09it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:11, 24.79it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:11, 24.50it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:12, 22.90it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 27.53it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 24.82it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 29.27it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:10, 25.73it/s]
Loading 0:  28%|██▊       | 100/363 [00:03<00:08, 30.07it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:13, 19.88it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:10, 24.46it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:10, 23.09it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:08, 27.58it/s]
Loading 0:  34%|███▎      | 122/363 [00:04<00:09, 24.86it/s]
Loading 0:  35%|███▍      | 127/363 [00:04<00:08, 29.26it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:09, 25.77it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:07, 30.06it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 30.83it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:10, 21.64it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:10, 21.20it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:08, 25.83it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:08, 23.50it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 28.18it/s]
Loading 0:  46%|████▌     | 167/363 [00:06<00:07, 24.96it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:06, 29.57it/s]
Loading 0:  48%|████▊     | 176/363 [00:06<00:07, 26.06it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:05, 30.57it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:08, 20.20it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 23.65it/s]
Loading 0:  53%|█████▎    | 194/363 [00:07<00:07, 22.68it/s]
Loading 0:  55%|█████▍    | 199/363 [00:07<00:06, 27.10it/s]
Loading 0:  56%|█████▌    | 203/363 [00:08<00:06, 24.35it/s]
Loading 0:  57%|█████▋    | 208/363 [00:08<00:05, 28.69it/s]
Loading 0:  58%|█████▊    | 212/363 [00:08<00:05, 25.22it/s]
Loading 0:  60%|█████▉    | 217/363 [00:08<00:04, 29.64it/s]
Loading 0:  61%|██████    | 222/363 [00:08<00:04, 30.51it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:06, 21.46it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 21.11it/s]
Loading 0:  65%|██████▍   | 235/363 [00:09<00:04, 25.83it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:05, 23.44it/s]
Loading 0:  67%|██████▋   | 244/363 [00:09<00:04, 27.89it/s]
Loading 0:  68%|██████▊   | 248/363 [00:09<00:04, 24.67it/s]
Loading 0:  70%|██████▉   | 253/363 [00:09<00:03, 28.88it/s]
Loading 0:  71%|███████   | 257/363 [00:10<00:04, 25.51it/s]
Loading 0:  72%|███████▏  | 262/363 [00:10<00:03, 29.88it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 19.81it/s]
Loading 0:  75%|███████▍  | 271/363 [00:10<00:03, 24.28it/s]
Loading 0:  76%|███████▌  | 275/363 [00:10<00:03, 22.77it/s]
Loading 0:  77%|███████▋  | 280/363 [00:11<00:03, 27.44it/s]
Loading 0:  78%|███████▊  | 284/363 [00:11<00:03, 24.66it/s]
Loading 0:  80%|███████▉  | 289/363 [00:11<00:02, 28.76it/s]
Loading 0:  81%|████████  | 293/363 [00:11<00:02, 25.21it/s]
Loading 0:  82%|████████▏ | 298/363 [00:11<00:02, 29.50it/s]
Loading 0:  83%|████████▎ | 303/363 [00:11<00:01, 30.52it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 21.40it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:02, 21.23it/s]
Loading 0:  87%|████████▋ | 316/363 [00:12<00:01, 25.66it/s]
Loading 0:  88%|████████▊ | 320/363 [00:12<00:01, 23.74it/s]
Loading 0:  90%|████████▉ | 325/363 [00:12<00:01, 28.10it/s]
Loading 0:  91%|█████████ | 329/363 [00:12<00:01, 25.44it/s]
Loading 0:  93%|█████████▎| 336/363 [00:13<00:00, 31.48it/s]
Loading 0:  94%|█████████▎| 340/363 [00:13<00:00, 29.91it/s]
Loading 0:  95%|█████████▍| 344/363 [00:20<00:09,  2.09it/s]
Loading 0:  96%|█████████▌| 348/363 [00:20<00:05,  2.77it/s]
Loading 0:  97%|█████████▋| 353/363 [00:20<00:02,  3.95it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  5.07it/s]
Loading 0: 100%|█████████▉| 362/363 [00:20<00:00,  7.18it/s]
                                                            
Job rirv938-anthropic-grpo-53872-v1-mkmlizer completed after 145.13s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-53872-v1-mkmlizer
Pipeline stage MKMLizer completed in 145.63s
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-53872-v1
Waiting for inference service rirv938-anthropic-grpo-53872-v1 to be ready
Inference service rirv938-anthropic-grpo-53872-v1 ready after 130.56420707702637s
Pipeline stage MKMLDeployer completed in 131.11s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.200296640396118s
Received healthy response to inference request in 1.6917471885681152s
Received healthy response to inference request in 1.678251028060913s
Received healthy response to inference request in 1.759587287902832s
Received healthy response to inference request in 1.683579444885254s
5 requests
0 failed requests
5th percentile: 1.6793167114257812
10th percentile: 1.6803823947906493
20th percentile: 1.6825137615203858
30th percentile: 1.685212993621826
40th percentile: 1.6884800910949707
50th percentile: 1.6917471885681152
60th percentile: 1.718883228302002
70th percentile: 1.7460192680358886
80th percentile: 1.8477291584014894
90th percentile: 2.024012899398804
95th percentile: 2.1121547698974608
99th percentile: 2.1826682662963868
mean time: 1.8026923179626464
Pipeline stage StressChecker completed in 10.37s
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 0.65s
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 0.70s
Shutdown handler de-registered
rirv938-anthropic-grpo-_53872_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 2749.41s
Shutdown handler de-registered
rirv938-anthropic-grpo-_53872_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_53872_v1 status is now torndown due to DeploymentManager action