rirv938-anthropic-grpo-_49016

developer_uid: rirv938

submission_id: rirv938-anthropic-grpo-_49016_v1

model_name: rirv938-anthropic-grpo-_49016_v1

model_group: rirv938/anthropic_grpo_4

status: torndown

timestamp: 2025-05-14T21:07:04+00:00

num_battles: 6355

num_wins: 3259

celo_rating: 1292.75

family_friendly_score: 0.5542

family_friendly_standard_error: 0.007029400543431851

submission_type: basic

model_repo: rirv938/anthropic_grpo_40k_cp148_95ff_20ww2_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': 0.6404104368757259, 'latency_mean': 1.5613990199565888, 'latency_p50': 1.5680928230285645, 'latency_p90': 1.7386776208877563}, {'batch_size': 3, 'throughput': 1.2179077384793153, 'latency_mean': 2.4512013530731203, 'latency_p50': 2.45929491519928, 'latency_p90': 2.700141859054565}, {'batch_size': 5, 'throughput': 1.4991915148421864, 'latency_mean': 3.3187568831443786, 'latency_p50': 3.3330806493759155, 'latency_p90': 3.664810633659363}, {'batch_size': 6, 'throughput': 1.580339660459508, 'latency_mean': 3.778611227273941, 'latency_p50': 3.7572137117385864, 'latency_p90': 4.242038297653198}, {'batch_size': 8, 'throughput': 1.6740827400964857, 'latency_mean': 4.743920834064483, 'latency_p50': 4.758655309677124, 'latency_p90': 5.34110472202301}, {'batch_size': 10, 'throughput': 1.724560054379159, 'latency_mean': 5.755929478406906, 'latency_p50': 5.765664219856262, 'latency_p90': 6.390458989143371}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-anthropic-grpo-_49016_v1

is_internal_developer: True

language_model: rirv938/anthropic_grpo_40k_cp148_95ff_20ww2_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.58

us_pacific_date: 2025-05-14

win_ratio: 0.5128245476003147

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': ['You:', '</s>', '###', '\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-49016-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-49016-v1-mkmlizer to finish
rirv938-anthropic-grpo-49016-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-49016-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-49016-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-49016-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-49016-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-49016-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-49016-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-49016-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-49016-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-49016-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-49016-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-49016-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-49016-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-49016-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-49016-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-49016-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-49016-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-49016-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-49016-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-49016-v1-mkmlizer: Downloaded to shared memory in 76.454s
rirv938-anthropic-grpo-49016-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpm2ng2iwq, device:0
rirv938-anthropic-grpo-49016-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-49016-v1-mkmlizer: quantized model in 40.812s
rirv938-anthropic-grpo-49016-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp148_95ff_20ww2_merged in 117.266s
rirv938-anthropic-grpo-49016-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-49016-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-49016-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-49016-v1
rirv938-anthropic-grpo-49016-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-49016-v1/config.json
rirv938-anthropic-grpo-49016-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-49016-v1/special_tokens_map.json
rirv938-anthropic-grpo-49016-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-49016-v1/tokenizer_config.json
rirv938-anthropic-grpo-49016-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-49016-v1/tokenizer.json
rirv938-anthropic-grpo-49016-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-49016-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-49016-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 23.33it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:11, 30.11it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 26.78it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:08, 38.25it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:14, 22.95it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:11, 27.80it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:11, 29.17it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:10, 30.77it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:10, 29.61it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.85it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 30.62it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:09, 30.96it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 27.73it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:12, 23.40it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:09, 30.17it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:09, 29.49it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 28.57it/s]
Loading 0:  23%|██▎       | 84/363 [00:02<00:08, 31.43it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 29.97it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 32.29it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 30.67it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 24.56it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:12, 21.05it/s]
Loading 0:  30%|███       | 109/363 [00:03<00:09, 26.02it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:10, 23.71it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 30.16it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 28.53it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.51it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 28.87it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 28.60it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 24.85it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 23.28it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 22.32it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:07, 28.76it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:07, 27.12it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 29.55it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 28.49it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 30.74it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 29.25it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 24.16it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:08, 21.33it/s]
Loading 0:  53%|█████▎    | 192/363 [00:06<00:05, 28.71it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:05, 28.30it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 31.01it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 29.25it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 31.65it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:04, 30.44it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 30.51it/s]
Loading 0:  61%|██████▏   | 223/363 [00:07<00:05, 26.10it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 24.49it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 23.44it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 30.62it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 29.74it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 32.30it/s]
Loading 0:  69%|██████▉   | 250/363 [00:08<00:03, 30.79it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 33.33it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 30.80it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:03, 25.19it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 21.94it/s]
Loading 0:  75%|███████▌  | 273/363 [00:09<00:03, 29.22it/s]
Loading 0:  76%|███████▋  | 277/363 [00:09<00:03, 28.58it/s]
Loading 0:  78%|███████▊  | 282/363 [00:09<00:02, 31.34it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 28.99it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 31.70it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 30.41it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 30.72it/s]
Loading 0:  84%|████████▎ | 304/363 [00:10<00:02, 26.79it/s]
Loading 0:  85%|████████▍ | 307/363 [00:10<00:02, 24.96it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 23.86it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 31.03it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 29.92it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 32.59it/s]
Loading 0:  91%|█████████ | 331/363 [00:11<00:01, 31.03it/s]
Loading 0:  93%|█████████▎| 336/363 [00:11<00:00, 33.27it/s]
Loading 0:  94%|█████████▎| 340/363 [00:11<00:00, 31.27it/s]
Loading 0:  95%|█████████▍| 344/363 [00:18<00:09,  1.98it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.66it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.86it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  5.00it/s]
                                                            
Job rirv938-anthropic-grpo-49016-v1-mkmlizer completed after 146.06s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-49016-v1-mkmlizer
Pipeline stage MKMLizer completed in 146.54s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-grpo-49016-v1
Waiting for inference service rirv938-anthropic-grpo-49016-v1 to be ready
Inference service rirv938-anthropic-grpo-49016-v1 ready after 130.56830644607544s
Pipeline stage MKMLDeployer completed in 131.41s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.247066020965576s
Received healthy response to inference request in 2.072049856185913s
Received healthy response to inference request in 1.6433336734771729s
Received healthy response to inference request in 1.8132874965667725s
Received healthy response to inference request in 2.036879539489746s
5 requests
0 failed requests
5th percentile: 1.6773244380950927
10th percentile: 1.7113152027130127
20th percentile: 1.7792967319488526
30th percentile: 1.858005905151367
40th percentile: 1.9474427223205566
50th percentile: 2.036879539489746
60th percentile: 2.050947666168213
70th percentile: 2.0650157928466797
80th percentile: 2.1070530891418455
90th percentile: 2.177059555053711
95th percentile: 2.2120627880096437
99th percentile: 2.2400653743743897
mean time: 1.9625233173370362
Pipeline stage StressChecker completed in 10.91s
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 0.62s
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 0.69s
Shutdown handler de-registered
rirv938-anthropic-grpo-_49016_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 0.10s
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-49016-v1-profiler
Waiting for inference service rirv938-anthropic-grpo-49016-v1-profiler to be ready
Inference service rirv938-anthropic-grpo-49016-v1-profiler ready after 131.31406950950623s
Pipeline stage MKMLProfilerDeployer completed in 132.04s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-anthropic-gr05816810c061fa2c7c1b4d7d130577ed-deplo9pj65:/code/chaiverse_profiler_1747257412 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-anthropic-gr05816810c061fa2c7c1b4d7d130577ed-deplo9pj65 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1747257412 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 768 --output_tokens 64 --summary /code/chaiverse_profiler_1747257412/summary.json'
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 2459.21s
Shutdown handler de-registered
rirv938-anthropic-grpo-_49016_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_49016_v1 status is now torndown due to DeploymentManager action