rirv938-anthropic-grpo-4_5638

developer_uid: rirv938

submission_id: rirv938-anthropic-grpo-4_5638_v1

model_name: rirv938-anthropic-grpo-4_5638_v1

model_group: rirv938/anthropic_grpo_4

status: torndown

timestamp: 2025-05-15T19:11:43+00:00

num_battles: 8040

num_wins: 4010

celo_rating: 1285.31

family_friendly_score: 0.548

family_friendly_standard_error: 0.0070384089111105224

submission_type: basic

model_repo: rirv938/anthropic_grpo_40k_cp78_95ff_beta4_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': 0.6476888251674203, 'latency_mean': 1.5438879895210267, 'latency_p50': 1.5340882539749146, 'latency_p90': 1.7163646459579467}, {'batch_size': 3, 'throughput': 1.2322585152329972, 'latency_mean': 2.4246965157985687, 'latency_p50': 2.43185293674469, 'latency_p90': 2.670370626449585}, {'batch_size': 5, 'throughput': 1.5228801090131754, 'latency_mean': 3.261921660900116, 'latency_p50': 3.2428964376449585, 'latency_p90': 3.6613900661468506}, {'batch_size': 6, 'throughput': 1.6260986179467882, 'latency_mean': 3.6737440931797027, 'latency_p50': 3.647482991218567, 'latency_p90': 4.112064003944397}, {'batch_size': 8, 'throughput': 1.7071282393831977, 'latency_mean': 4.649530328512192, 'latency_p50': 4.643894553184509, 'latency_p90': 5.215680432319641}, {'batch_size': 10, 'throughput': 1.7493510128935197, 'latency_mean': 5.664219547510147, 'latency_p50': 5.656277656555176, 'latency_p90': 6.420229578018188}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-anthropic-grpo-4_5638_v1

is_internal_developer: True

language_model: rirv938/anthropic_grpo_40k_cp78_95ff_beta4_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.64

us_pacific_date: 2025-05-15

win_ratio: 0.4987562189054726

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': ['</s>', '###', 'You:', '\n'], '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-4-5638-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-4-5638-v1-mkmlizer to finish
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: Downloaded to shared memory in 86.067s
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpydmsuf5n, device:0
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: quantized model in 43.782s
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp78_95ff_beta4_merged in 129.849s
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-5638-v1
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-5638-v1/config.json
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-5638-v1/special_tokens_map.json
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-5638-v1/tokenizer_config.json
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-5638-v1/tokenizer.json
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-5638-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-4-5638-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 20.75it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:13, 25.84it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 23.54it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:10, 32.07it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:15, 22.44it/s]
Loading 0:   7%|▋         | 27/363 [00:01<00:15, 21.68it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 24.86it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:14, 22.99it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:13, 24.48it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:14, 22.56it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:11, 28.25it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:12, 24.30it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:10, 29.40it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:09, 30.64it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:14, 20.31it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 26.61it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:10, 26.69it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:10, 26.34it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:09, 28.93it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 28.04it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 28.45it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:10, 25.03it/s]
Loading 0:  28%|██▊       | 100/363 [00:03<00:08, 30.22it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:12, 20.15it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:10, 24.69it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:11, 22.21it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:09, 26.87it/s]
Loading 0:  34%|███▎      | 122/363 [00:04<00:09, 24.23it/s]
Loading 0:  35%|███▍      | 127/363 [00:04<00:08, 28.83it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:09, 25.09it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:07, 29.57it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 29.84it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:10, 21.54it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:10, 20.66it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:08, 24.64it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:08, 25.25it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 25.00it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 25.53it/s]
Loading 0:  46%|████▌     | 167/363 [00:06<00:08, 22.62it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:06, 27.53it/s]
Loading 0:  48%|████▊     | 176/363 [00:06<00:07, 24.07it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 28.39it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:09, 18.51it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.93it/s]
Loading 0:  53%|█████▎    | 194/363 [00:07<00:07, 21.68it/s]
Loading 0:  55%|█████▍    | 199/363 [00:07<00:06, 26.13it/s]
Loading 0:  56%|█████▌    | 203/363 [00:08<00:06, 23.29it/s]
Loading 0:  57%|█████▋    | 208/363 [00:08<00:05, 27.51it/s]
Loading 0:  58%|█████▊    | 212/363 [00:08<00:06, 24.35it/s]
Loading 0:  60%|█████▉    | 217/363 [00:08<00:05, 28.44it/s]
Loading 0:  61%|██████    | 222/363 [00:08<00:04, 29.19it/s]
Loading 0:  62%|██████▏   | 226/363 [00:09<00:06, 20.83it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 20.29it/s]
Loading 0:  65%|██████▍   | 235/363 [00:09<00:05, 24.49it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:05, 22.33it/s]
Loading 0:  67%|██████▋   | 244/363 [00:09<00:04, 26.51it/s]
Loading 0:  68%|██████▊   | 248/363 [00:10<00:04, 23.60it/s]
Loading 0:  70%|██████▉   | 253/363 [00:10<00:03, 27.80it/s]
Loading 0:  71%|███████   | 257/363 [00:10<00:04, 24.50it/s]
Loading 0:  72%|███████▏  | 262/363 [00:10<00:03, 28.42it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:05, 18.89it/s]
Loading 0:  75%|███████▍  | 271/363 [00:10<00:03, 23.20it/s]
Loading 0:  76%|███████▌  | 275/363 [00:11<00:04, 21.82it/s]
Loading 0:  77%|███████▋  | 280/363 [00:11<00:03, 25.97it/s]
Loading 0:  78%|███████▊  | 284/363 [00:11<00:03, 23.46it/s]
Loading 0:  80%|███████▉  | 289/363 [00:11<00:02, 27.52it/s]
Loading 0:  81%|████████  | 293/363 [00:11<00:02, 23.80it/s]
Loading 0:  82%|████████▏ | 298/363 [00:11<00:02, 27.77it/s]
Loading 0:  83%|████████▎ | 303/363 [00:12<00:02, 28.69it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 20.37it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:02, 19.94it/s]
Loading 0:  87%|████████▋ | 316/363 [00:12<00:01, 24.24it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:01, 22.08it/s]
Loading 0:  90%|████████▉ | 325/363 [00:13<00:01, 26.42it/s]
Loading 0:  91%|█████████ | 329/363 [00:13<00:01, 23.83it/s]
Loading 0:  92%|█████████▏| 334/363 [00:13<00:01, 28.09it/s]
Loading 0:  93%|█████████▎| 338/363 [00:13<00:01, 24.70it/s]
Loading 0:  94%|█████████▍| 343/363 [00:13<00:00, 28.97it/s]
Loading 0:  96%|█████████▌| 347/363 [00:20<00:08,  1.97it/s]
Loading 0:  96%|█████████▋| 350/363 [00:21<00:05,  2.49it/s]
Loading 0:  97%|█████████▋| 353/363 [00:21<00:03,  3.18it/s]
Loading 0:  98%|█████████▊| 357/363 [00:21<00:01,  4.34it/s]
                                                            
Job rirv938-anthropic-grpo-4-5638-v1-mkmlizer completed after 155.87s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-4-5638-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.41s
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-4-5638-v1
Waiting for inference service rirv938-anthropic-grpo-4-5638-v1 to be ready
Inference service rirv938-anthropic-grpo-4-5638-v1 ready after 130.56100630760193s
Pipeline stage MKMLDeployer completed in 131.17s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4837889671325684s
Received healthy response to inference request in 1.7369341850280762s
Received healthy response to inference request in 1.8684632778167725s
Received healthy response to inference request in 1.559800386428833s
Received healthy response to inference request in 1.7320387363433838s
5 requests
0 failed requests
5th percentile: 1.5942480564117432
10th percentile: 1.6286957263946533
20th percentile: 1.6975910663604736
30th percentile: 1.7330178260803222
40th percentile: 1.7349760055541992
50th percentile: 1.7369341850280762
60th percentile: 1.7895458221435547
70th percentile: 1.8421574592590333
80th percentile: 1.9915284156799318
90th percentile: 2.23765869140625
95th percentile: 2.3607238292694093
99th percentile: 2.4591759395599366
mean time: 1.8762051105499267
Pipeline stage StressChecker completed in 10.84s
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 0.77s
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-4_5638_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-anthropic-grpo-4-5638-v1-profiler
Waiting for inference service rirv938-anthropic-grpo-4-5638-v1-profiler to be ready
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 2996.10s
Shutdown handler de-registered
rirv938-anthropic-grpo-4_5638_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-4_5638_v1 status is now torndown due to DeploymentManager action