developer_uid: rirv938
submission_id: rirv938-anthropic-grpo-_62054_v1
model_name: rirv938-anthropic-grpo-_62054_v1
model_group: rirv938/anthropic_grpo_4
status: torndown
timestamp: 2025-05-14T21:56:57+00:00
num_battles: 7014
num_wins: 3629
celo_rating: 1295.82
family_friendly_score: 0.5192
family_friendly_standard_error: 0.007065852531719014
submission_type: basic
model_repo: rirv938/anthropic_grpo_40k_cp296_95ff_60ww_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': 0.6441298150744426, 'latency_mean': 1.552410980463028, 'latency_p50': 1.5576634407043457, 'latency_p90': 1.7233438730239867}, {'batch_size': 3, 'throughput': 1.2360861751436159, 'latency_mean': 2.4114903151988982, 'latency_p50': 2.401463508605957, 'latency_p90': 2.743621754646301}, {'batch_size': 5, 'throughput': 1.5274321609076342, 'latency_mean': 3.2467650401592256, 'latency_p50': 3.2586867809295654, 'latency_p90': 3.6249444246292115}, {'batch_size': 6, 'throughput': 1.6264577088592989, 'latency_mean': 3.664002525806427, 'latency_p50': 3.658239722251892, 'latency_p90': 4.0967309951782225}, {'batch_size': 8, 'throughput': 1.7207728837287615, 'latency_mean': 4.620297704935074, 'latency_p50': 4.657325983047485, 'latency_p90': 5.308464455604553}, {'batch_size': 10, 'throughput': 1.7591158333158161, 'latency_mean': 5.642943975925445, 'latency_p50': 5.685133218765259, 'latency_p90': 6.358250522613526}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-anthropic-grpo-_62054_v1
is_internal_developer: True
language_model: rirv938/anthropic_grpo_40k_cp296_95ff_60ww_merged
model_size: 13B
ranking_group: single
throughput_3p7s: 1.64
us_pacific_date: 2025-05-14
win_ratio: 0.5173937838608498
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-62054-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-62054-v1-mkmlizer to finish
rirv938-anthropic-grpo-62054-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-62054-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-62054-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-62054-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-62054-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-62054-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-62054-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-62054-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-62054-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-62054-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-62054-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-62054-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-62054-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-62054-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-62054-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-62054-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-62054-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-62054-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-62054-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-62054-v1-mkmlizer: Downloaded to shared memory in 78.964s
rirv938-anthropic-grpo-62054-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzi02z6d7, device:0
rirv938-anthropic-grpo-62054-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-62054-v1-mkmlizer: quantized model in 41.238s
rirv938-anthropic-grpo-62054-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp296_95ff_60ww_merged in 120.202s
rirv938-anthropic-grpo-62054-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-62054-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-62054-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-62054-v1
rirv938-anthropic-grpo-62054-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-62054-v1/config.json
rirv938-anthropic-grpo-62054-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-62054-v1/special_tokens_map.json
rirv938-anthropic-grpo-62054-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-62054-v1/tokenizer_config.json
rirv938-anthropic-grpo-62054-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-62054-v1/tokenizer.json
rirv938-anthropic-grpo-62054-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-62054-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-62054-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.64it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:11, 29.50it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 25.99it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 37.19it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:15, 21.24it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:12, 26.02it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:11, 27.38it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 29.13it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 28.21it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 31.14it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 29.64it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:10, 30.40it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 25.98it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 22.21it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:09, 29.45it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:09, 29.05it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 27.83it/s]
Loading 0:  23%|██▎       | 84/363 [00:02<00:09, 30.40it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 28.77it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 31.34it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 29.66it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 24.66it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:12, 21.46it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:08, 28.56it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:08, 27.72it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 30.51it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 28.94it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 31.31it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 29.80it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 29.18it/s]
Loading 0:  39%|███▉      | 141/363 [00:04<00:07, 31.39it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 21.90it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 21.49it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:07, 28.59it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:07, 28.56it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 30.60it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 29.83it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 32.31it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 29.86it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 24.46it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:08, 21.72it/s]
Loading 0:  53%|█████▎    | 192/363 [00:06<00:05, 28.98it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:05, 28.32it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 30.97it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 29.09it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 31.96it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:04, 30.61it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 31.23it/s]
Loading 0:  61%|██████▏   | 223/363 [00:07<00:05, 26.74it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 24.78it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 23.40it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 30.09it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 28.55it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 30.72it/s]
Loading 0:  69%|██████▉   | 250/363 [00:08<00:03, 29.18it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 31.11it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 29.53it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 24.20it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 21.35it/s]
Loading 0:  75%|███████▌  | 273/363 [00:09<00:03, 28.09it/s]
Loading 0:  76%|███████▋  | 277/363 [00:09<00:03, 27.44it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 30.23it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 28.83it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 31.15it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 29.04it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 29.35it/s]
Loading 0:  84%|████████▎ | 304/363 [00:10<00:02, 26.36it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 24.61it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 23.43it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 30.57it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 28.03it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 29.75it/s]
Loading 0:  91%|█████████ | 331/363 [00:11<00:01, 28.96it/s]
Loading 0:  93%|█████████▎| 336/363 [00:11<00:00, 31.74it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 29.92it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  1.97it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.64it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.83it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  4.95it/s]
                                                            

Job rirv938-anthropic-grpo-62054-v1-mkmlizer completed after 145.46s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-62054-v1-mkmlizer
Pipeline stage MKMLizer completed in 145.98s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-grpo-62054-v1
Waiting for inference service rirv938-anthropic-grpo-62054-v1 to be ready
Inference service rirv938-anthropic-grpo-62054-v1 ready after 140.58818125724792s
Pipeline stage MKMLDeployer completed in 141.18s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4661285877227783s
Received healthy response to inference request in 1.7228798866271973s
Received healthy response to inference request in 1.7636854648590088s
Received healthy response to inference request in 1.6835644245147705s
Received healthy response to inference request in 1.7432479858398438s
5 requests
0 failed requests
5th percentile: 1.691427516937256
10th percentile: 1.6992906093597413
20th percentile: 1.7150167942047119
30th percentile: 1.7269535064697266
40th percentile: 1.7351007461547852
50th percentile: 1.7432479858398438
60th percentile: 1.7514229774475099
70th percentile: 1.7595979690551757
80th percentile: 1.9041740894317627
90th percentile: 2.1851513385772705
95th percentile: 2.3256399631500244
99th percentile: 2.4380308628082275
mean time: 1.8759012699127198
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 0.72s
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 0.67s
Shutdown handler de-registered
rirv938-anthropic-grpo-_62054_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-anthropic-grpo-62054-v1-profiler
Waiting for inference service rirv938-anthropic-grpo-62054-v1-profiler to be ready
Inference service rirv938-anthropic-grpo-62054-v1-profiler ready after 131.29069924354553s
Pipeline stage MKMLProfilerDeployer completed in 132.01s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-anthropic-grbb29e915bb53d398550402386dc88b94-deplo6ckt7:/code/chaiverse_profiler_1747260335 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-anthropic-grbb29e915bb53d398550402386dc88b94-deplo6ckt7 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1747260335 && 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_1747260335/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 2426.47s
Shutdown handler de-registered
rirv938-anthropic-grpo-_62054_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_62054_v1 status is now torndown due to DeploymentManager action