developer_uid: rirv938
submission_id: rirv938-anthropic-grpo-_90777_v1
model_name: rirv938-anthropic-grpo-_90777_v1
model_group: rirv938/anthropic_grpo_4
status: torndown
timestamp: 2025-04-29T18:36:03+00:00
num_battles: 6352
num_wins: 3459
celo_rating: 1336.35
family_friendly_score: 0.5578000000000001
family_friendly_standard_error: 0.007023662292565041
submission_type: basic
model_repo: rirv938/anthropic_grpo_40k_cp1184_95ff_merged
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.5798595892143408, 'latency_mean': 1.7244848120212555, 'latency_p50': 1.7174317836761475, 'latency_p90': 1.918249249458313}, {'batch_size': 3, 'throughput': 0.9816078843274821, 'latency_mean': 3.052235847711563, 'latency_p50': 3.054492473602295, 'latency_p90': 3.330203628540039}, {'batch_size': 5, 'throughput': 1.1656205538100777, 'latency_mean': 4.270018572807312, 'latency_p50': 4.2944735288619995, 'latency_p90': 4.75743157863617}, {'batch_size': 6, 'throughput': 1.201379600541134, 'latency_mean': 4.954947466850281, 'latency_p50': 4.977314352989197, 'latency_p90': 5.547279715538025}, {'batch_size': 8, 'throughput': 1.2531675798622839, 'latency_mean': 6.349795149564743, 'latency_p50': 6.408201098442078, 'latency_p90': 7.139740443229675}, {'batch_size': 10, 'throughput': 1.293130503485861, 'latency_mean': 7.680952197313308, 'latency_p50': 7.68377959728241, 'latency_p90': 8.69717252254486}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-anthropic-grpo-_90777_v1
is_internal_developer: True
language_model: rirv938/anthropic_grpo_40k_cp1184_95ff_merged
model_size: 13B
ranking_group: single
throughput_3p7s: 1.1
us_pacific_date: 2025-04-29
win_ratio: 0.5445528967254408
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': 1024, '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-90777-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-90777-v1-mkmlizer to finish
rirv938-anthropic-grpo-90777-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-90777-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-90777-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-90777-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-90777-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-90777-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-90777-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-90777-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-90777-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-90777-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-90777-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-90777-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-90777-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-90777-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-90777-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-90777-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-90777-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-90777-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-90777-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-90777-v1-mkmlizer: Downloaded to shared memory in 75.646s
rirv938-anthropic-grpo-90777-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcahos8n5, device:0
rirv938-anthropic-grpo-90777-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-90777-v1-mkmlizer: quantized model in 42.642s
rirv938-anthropic-grpo-90777-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp1184_95ff_merged in 118.288s
rirv938-anthropic-grpo-90777-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-90777-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-90777-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-90777-v1
rirv938-anthropic-grpo-90777-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-90777-v1/config.json
rirv938-anthropic-grpo-90777-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-90777-v1/special_tokens_map.json
rirv938-anthropic-grpo-90777-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-90777-v1/tokenizer_config.json
rirv938-anthropic-grpo-90777-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-90777-v1/tokenizer.json
rirv938-anthropic-grpo-90777-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-90777-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-90777-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.69it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 28.19it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 24.96it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:10, 33.75it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:14, 23.36it/s]
Loading 0:   7%|▋         | 27/363 [00:01<00:14, 22.52it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 23.35it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:10, 29.82it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 28.77it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.84it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 29.51it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 29.38it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 25.20it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:14, 21.06it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:12, 23.53it/s]
Loading 0:  20%|█▉        | 72/363 [00:02<00:13, 22.28it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:12, 22.59it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 27.08it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 24.32it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 28.38it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:10, 25.16it/s]
Loading 0:  28%|██▊       | 100/363 [00:03<00:08, 29.36it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:13, 19.36it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:10, 23.61it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:11, 22.30it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:09, 26.44it/s]
Loading 0:  34%|███▎      | 122/363 [00:04<00:10, 24.10it/s]
Loading 0:  35%|███▍      | 127/363 [00:04<00:08, 28.07it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:09, 24.95it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:07, 29.07it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 30.31it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:10, 21.25it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:10, 20.70it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:08, 24.88it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:08, 23.16it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 27.24it/s]
Loading 0:  46%|████▌     | 167/363 [00:06<00:07, 24.64it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:06, 28.52it/s]
Loading 0:  48%|████▊     | 176/363 [00:06<00:07, 25.30it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 29.83it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:08, 19.93it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 23.86it/s]
Loading 0:  53%|█████▎    | 194/363 [00:07<00:07, 22.26it/s]
Loading 0:  55%|█████▍    | 199/363 [00:07<00:06, 26.25it/s]
Loading 0:  56%|█████▌    | 203/363 [00:08<00:06, 23.58it/s]
Loading 0:  57%|█████▋    | 208/363 [00:08<00:05, 27.30it/s]
Loading 0:  58%|█████▊    | 212/363 [00:08<00:06, 24.39it/s]
Loading 0:  60%|█████▉    | 217/363 [00:08<00:05, 28.08it/s]
Loading 0:  61%|██████    | 222/363 [00:08<00:04, 29.34it/s]
Loading 0:  62%|██████▏   | 226/363 [00:09<00:06, 20.49it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 20.13it/s]
Loading 0:  65%|██████▍   | 235/363 [00:09<00:05, 24.15it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:05, 22.69it/s]
Loading 0:  67%|██████▋   | 244/363 [00:09<00:04, 26.67it/s]
Loading 0:  68%|██████▊   | 248/363 [00:09<00:04, 23.99it/s]
Loading 0:  70%|██████▉   | 253/363 [00:10<00:04, 27.11it/s]
Loading 0:  71%|███████   | 257/363 [00:10<00:04, 24.16it/s]
Loading 0:  72%|███████▏  | 262/363 [00:10<00:03, 28.76it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:05, 19.30it/s]
Loading 0:  75%|███████▍  | 271/363 [00:10<00:03, 23.39it/s]
Loading 0:  76%|███████▌  | 275/363 [00:11<00:03, 22.12it/s]
Loading 0:  77%|███████▋  | 280/363 [00:11<00:03, 26.31it/s]
Loading 0:  78%|███████▊  | 284/363 [00:11<00:03, 24.01it/s]
Loading 0:  80%|███████▉  | 289/363 [00:11<00:02, 27.84it/s]
Loading 0:  81%|████████  | 293/363 [00:11<00:02, 24.81it/s]
Loading 0:  82%|████████▏ | 298/363 [00:11<00:02, 28.71it/s]
Loading 0:  83%|████████▎ | 303/363 [00:12<00:02, 29.33it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 20.58it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:02, 20.14it/s]
Loading 0:  87%|████████▋ | 316/363 [00:12<00:01, 24.40it/s]
Loading 0:  88%|████████▊ | 320/363 [00:12<00:01, 22.48it/s]
Loading 0:  90%|████████▉ | 325/363 [00:13<00:01, 26.77it/s]
Loading 0:  91%|█████████ | 329/363 [00:13<00:01, 24.12it/s]
Loading 0:  92%|█████████▏| 334/363 [00:13<00:01, 28.17it/s]
Loading 0:  93%|█████████▎| 338/363 [00:13<00:01, 24.95it/s]
Loading 0:  94%|█████████▍| 343/363 [00:13<00:00, 29.59it/s]
Loading 0:  96%|█████████▌| 347/363 [00:20<00:08,  2.00it/s]
Loading 0:  96%|█████████▋| 350/363 [00:20<00:05,  2.52it/s]
Loading 0:  97%|█████████▋| 353/363 [00:20<00:03,  3.22it/s]
Loading 0:  98%|█████████▊| 357/363 [00:21<00:01,  4.41it/s]
                                                            

Job rirv938-anthropic-grpo-90777-v1-mkmlizer completed after 145.64s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-90777-v1-mkmlizer
Pipeline stage MKMLizer completed in 146.14s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-grpo-90777-v1
Waiting for inference service rirv938-anthropic-grpo-90777-v1 to be ready
Inference service rirv938-anthropic-grpo-90777-v1 ready after 140.5236837863922s
Pipeline stage MKMLDeployer completed in 141.05s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.663269519805908s
Received healthy response to inference request in 1.777831792831421s
Received healthy response to inference request in 1.7257025241851807s
Received healthy response to inference request in 1.6592774391174316s
Received healthy response to inference request in 1.8779902458190918s
5 requests
0 failed requests
5th percentile: 1.6725624561309815
10th percentile: 1.6858474731445312
20th percentile: 1.7124175071716308
30th percentile: 1.7361283779144288
40th percentile: 1.7569800853729247
50th percentile: 1.777831792831421
60th percentile: 1.8178951740264893
70th percentile: 1.8579585552215576
80th percentile: 2.035046100616455
90th percentile: 2.3491578102111816
95th percentile: 2.506213665008545
99th percentile: 2.6318583488464355
mean time: 1.9408143043518067
Pipeline stage StressChecker completed in 10.94s
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 0.73s
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-_90777_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-anthropic-grpo-90777-v1-profiler
Waiting for inference service rirv938-anthropic-grpo-90777-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5506.74s
Shutdown handler de-registered
rirv938-anthropic-grpo-_90777_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_90777_v1 status is now torndown due to DeploymentManager action