developer_uid: rirv938
submission_id: rirv938-anthropic-grpo-4_8100_v1
model_name: rirv938-anthropic-grpo-4_8100_v1
model_group: rirv938/anthropic_grpo_4
status: torndown
timestamp: 2025-05-18T15:18:06+00:00
num_battles: 9420
num_wins: 4638
celo_rating: 1281.55
family_friendly_score: 0.49
family_friendly_standard_error: 0.007069653456853455
submission_type: basic
model_repo: rirv938/anthropic_grpo_40k_cp248_98ff_g8b15_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': 0.6192370884249869, 'latency_mean': 1.6148164033889771, 'latency_p50': 1.616428017616272, 'latency_p90': 1.7872913837432862}, {'batch_size': 3, 'throughput': 1.150050689526405, 'latency_mean': 2.5966156113147734, 'latency_p50': 2.603292465209961, 'latency_p90': 2.8926527976989744}, {'batch_size': 5, 'throughput': 1.3796164707695433, 'latency_mean': 3.6033215606212616, 'latency_p50': 3.6049246788024902, 'latency_p90': 3.9609988927841187}, {'batch_size': 6, 'throughput': 1.4747518093311263, 'latency_mean': 4.038198041915893, 'latency_p50': 4.0696223974227905, 'latency_p90': 4.532429814338684}, {'batch_size': 8, 'throughput': 1.556597173308255, 'latency_mean': 5.093730217218399, 'latency_p50': 5.078597784042358, 'latency_p90': 5.7592415571212765}, {'batch_size': 10, 'throughput': 1.5910852152836807, 'latency_mean': 6.24627564907074, 'latency_p50': 6.270023584365845, 'latency_p90': 7.056977820396423}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-anthropic-grpo-4_8100_v1
is_internal_developer: True
language_model: rirv938/anthropic_grpo_40k_cp248_98ff_g8b15_merged
model_size: 13B
ranking_group: single
throughput_3p7s: 1.41
us_pacific_date: 2025-05-18
win_ratio: 0.4923566878980892
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-4-8100-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-4-8100-v1-mkmlizer to finish
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: Downloaded to shared memory in 85.519s
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpewio7e2d, device:0
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: quantized model in 44.076s
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp248_98ff_g8b15_merged in 129.595s
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-8100-v1
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-8100-v1/config.json
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-8100-v1/special_tokens_map.json
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-8100-v1/tokenizer_config.json
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-8100-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-4-8100-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:24, 14.75it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:16, 20.84it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:17, 19.98it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:13, 25.61it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:12, 26.33it/s]
Loading 0:   7%|▋         | 25/363 [00:01<00:18, 18.52it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 19.18it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:17, 19.24it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:13, 24.65it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:14, 22.49it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:11, 27.25it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:13, 23.76it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:10, 28.18it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 29.58it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:15, 19.19it/s]
Loading 0:  19%|█▉        | 69/363 [00:03<00:12, 23.50it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:12, 23.43it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:13, 21.91it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 26.16it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 23.52it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 27.48it/s]
Loading 0:  26%|██▌       | 95/363 [00:04<00:10, 24.56it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:09, 28.80it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:13, 18.78it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:11, 23.01it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:11, 21.37it/s]
Loading 0:  33%|███▎      | 118/363 [00:05<00:09, 25.40it/s]
Loading 0:  34%|███▎      | 122/363 [00:05<00:10, 22.60it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:08, 26.80it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:09, 23.98it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:08, 28.23it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 29.09it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:10, 20.22it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:10, 19.98it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:08, 24.34it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:09, 22.26it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 25.73it/s]
Loading 0:  46%|████▌     | 167/363 [00:07<00:08, 23.25it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:06, 27.31it/s]
Loading 0:  48%|████▊     | 176/363 [00:07<00:07, 24.66it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 28.82it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:09, 19.19it/s]
Loading 0:  52%|█████▏    | 190/363 [00:08<00:07, 23.45it/s]
Loading 0:  53%|█████▎    | 194/363 [00:08<00:07, 21.98it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:06, 26.32it/s]
Loading 0:  56%|█████▌    | 203/363 [00:08<00:06, 23.74it/s]
Loading 0:  57%|█████▋    | 208/363 [00:08<00:05, 28.00it/s]
Loading 0:  58%|█████▊    | 212/363 [00:08<00:06, 24.44it/s]
Loading 0:  60%|█████▉    | 217/363 [00:09<00:05, 28.71it/s]
Loading 0:  61%|██████    | 222/363 [00:09<00:04, 29.38it/s]
Loading 0:  62%|██████▏   | 226/363 [00:09<00:06, 20.56it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 20.12it/s]
Loading 0:  65%|██████▍   | 235/363 [00:09<00:05, 24.24it/s]
Loading 0:  66%|██████▌   | 239/363 [00:10<00:05, 21.54it/s]
Loading 0:  67%|██████▋   | 244/363 [00:10<00:04, 24.85it/s]
Loading 0:  68%|██████▊   | 248/363 [00:10<00:04, 23.10it/s]
Loading 0:  70%|██████▉   | 253/363 [00:10<00:03, 27.66it/s]
Loading 0:  71%|███████   | 257/363 [00:10<00:04, 24.80it/s]
Loading 0:  72%|███████▏  | 262/363 [00:10<00:03, 29.17it/s]
Loading 0:  73%|███████▎  | 266/363 [00:11<00:04, 19.48it/s]
Loading 0:  75%|███████▍  | 271/363 [00:11<00:03, 23.97it/s]
Loading 0:  76%|███████▌  | 275/363 [00:11<00:03, 22.32it/s]
Loading 0:  77%|███████▋  | 280/363 [00:11<00:03, 26.67it/s]
Loading 0:  78%|███████▊  | 284/363 [00:11<00:03, 24.04it/s]
Loading 0:  80%|███████▉  | 289/363 [00:12<00:02, 28.39it/s]
Loading 0:  81%|████████  | 293/363 [00:12<00:02, 24.88it/s]
Loading 0:  82%|████████▏ | 298/363 [00:12<00:02, 29.23it/s]
Loading 0:  83%|████████▎ | 303/363 [00:12<00:01, 30.03it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 21.17it/s]
Loading 0:  86%|████████▌ | 311/363 [00:13<00:02, 20.51it/s]
Loading 0:  87%|████████▋ | 316/363 [00:13<00:01, 24.82it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:01, 22.92it/s]
Loading 0:  90%|████████▉ | 325/363 [00:13<00:01, 27.46it/s]
Loading 0:  91%|█████████ | 329/363 [00:13<00:01, 24.53it/s]
Loading 0:  92%|█████████▏| 334/363 [00:13<00:01, 28.76it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:00, 25.34it/s]
Loading 0:  94%|█████████▍| 343/363 [00:14<00:00, 29.63it/s]
Loading 0:  96%|█████████▌| 347/363 [00:21<00:08,  1.87it/s]
Loading 0:  96%|█████████▋| 350/363 [00:21<00:05,  2.34it/s]
Loading 0:  97%|█████████▋| 353/363 [00:22<00:03,  2.95it/s]
Loading 0:  98%|█████████▊| 356/363 [00:22<00:01,  3.84it/s]
Loading 0:  99%|█████████▉| 359/363 [00:22<00:00,  4.88it/s]
Loading 0: 100%|█████████▉| 362/363 [00:22<00:00,  6.26it/s]
                                                            

Job rirv938-anthropic-grpo-4-8100-v1-mkmlizer completed after 155.7s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-4-8100-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.24s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-grpo-4-8100-v1
Waiting for inference service rirv938-anthropic-grpo-4-8100-v1 to be ready
Inference service rirv938-anthropic-grpo-4-8100-v1 ready after 151.10075426101685s
Pipeline stage MKMLDeployer completed in 151.97s
run pipeline stage %s
Running pipeline stage StressChecker
{"detail":"HTTPConnectionPool(host='rirv938-anthropic-grpo-4-8100-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by ConnectTimeoutError(<urllib3.connection.HTTPConnection object at 0x7e2144704e50>, 'Connection to rirv938-anthropic-grpo-4-8100-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com timed out. (connect timeout=12.0)'))"}
Received unhealthy response to inference request!
Received healthy response to inference request in 2.028587579727173s
Received healthy response to inference request in 1.8558621406555176s
Received healthy response to inference request in 1.6087329387664795s
Received healthy response to inference request in 1.5193192958831787s
5 requests
1 failed requests
5th percentile: 1.5372020244598388
10th percentile: 1.555084753036499
20th percentile: 1.5908502101898194
30th percentile: 1.658158779144287
40th percentile: 1.7570104598999023
50th percentile: 1.8558621406555176
60th percentile: 1.9249523162841797
70th percentile: 1.9940424919128417
80th percentile: 4.064440584182741
90th percentile: 8.136146593093873
95th percentile: 10.171999597549437
99th percentile: 11.800682001113891
mean time: 3.8440709114074707
%s, retrying in %s seconds...
Received healthy response to inference request in 2.029291868209839s
Received healthy response to inference request in 1.9073057174682617s
Received healthy response to inference request in 1.7022836208343506s
Received healthy response to inference request in 1.7410950660705566s
Received healthy response to inference request in 1.73704195022583s
5 requests
0 failed requests
5th percentile: 1.7092352867126466
10th percentile: 1.7161869525909423
20th percentile: 1.730090284347534
30th percentile: 1.7378525733947754
40th percentile: 1.739473819732666
50th percentile: 1.7410950660705566
60th percentile: 1.8075793266296387
70th percentile: 1.8740635871887206
80th percentile: 1.9317029476165772
90th percentile: 1.980497407913208
95th percentile: 2.0048946380615233
99th percentile: 2.0244124221801756
mean time: 1.8234036445617676
Pipeline stage StressChecker completed in 31.00s
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 0.83s
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 0.68s
Shutdown handler de-registered
rirv938-anthropic-grpo-4_8100_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-anthropic-grpo-4-8100-v1-profiler
Waiting for inference service rirv938-anthropic-grpo-4-8100-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 4898.61s
Shutdown handler de-registered
rirv938-anthropic-grpo-4_8100_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-4_8100_v1 status is now torndown due to DeploymentManager action