developer_uid: rirv938
submission_id: rirv938-anthropic-grpo-_55424_v3
model_name: rirv938-anthropic-grpo-_55424_v3
model_group: rirv938/anthropic_grpo_4
status: torndown
timestamp: 2025-04-29T18:30:18+00:00
num_battles: 5548
num_wins: 2889
celo_rating: 1319.35
family_friendly_score: 0.5748
family_friendly_standard_error: 0.006991494260885866
submission_type: basic
model_repo: rirv938/anthropic_grpo_40k_cp296_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': 0.6088332317458248, 'latency_mean': 1.6424223399162292, 'latency_p50': 1.6343873739242554, 'latency_p90': 1.8089697122573853}, {'batch_size': 3, 'throughput': 1.115215869244785, 'latency_mean': 2.6813290202617646, 'latency_p50': 2.672635078430176, 'latency_p90': 2.9721027851104735}, {'batch_size': 5, 'throughput': 1.3428280015584064, 'latency_mean': 3.69956125497818, 'latency_p50': 3.6625930070877075, 'latency_p90': 4.12440299987793}, {'batch_size': 6, 'throughput': 1.40687476144673, 'latency_mean': 4.240586636066436, 'latency_p50': 4.256845593452454, 'latency_p90': 4.759073233604431}, {'batch_size': 8, 'throughput': 1.4843942449463945, 'latency_mean': 5.356335605382919, 'latency_p50': 5.311890006065369, 'latency_p90': 6.095395302772522}, {'batch_size': 10, 'throughput': 1.5042543166105151, 'latency_mean': 6.593435968160629, 'latency_p50': 6.651076078414917, 'latency_p90': 7.382323288917541}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-anthropic-grpo-_55424_v3
is_internal_developer: True
language_model: rirv938/anthropic_grpo_40k_cp296_95ff_merged
model_size: 13B
ranking_group: single
throughput_3p7s: 1.35
us_pacific_date: 2025-04-29
win_ratio: 0.5207281903388609
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', '</s>', 'You:'], '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-55424-v3-mkmlizer
Waiting for job on rirv938-anthropic-grpo-55424-v3-mkmlizer to finish
rirv938-anthropic-grpo-55424-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-55424-v3-mkmlizer: ║ _____ __ __ ║
rirv938-anthropic-grpo-55424-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-anthropic-grpo-55424-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-anthropic-grpo-55424-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-anthropic-grpo-55424-v3-mkmlizer: ║ /___/ ║
rirv938-anthropic-grpo-55424-v3-mkmlizer: ║ ║
rirv938-anthropic-grpo-55424-v3-mkmlizer: ║ Version: 0.12.8 ║
rirv938-anthropic-grpo-55424-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-anthropic-grpo-55424-v3-mkmlizer: ║ https://mk1.ai ║
rirv938-anthropic-grpo-55424-v3-mkmlizer: ║ ║
rirv938-anthropic-grpo-55424-v3-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-anthropic-grpo-55424-v3-mkmlizer: ║ belonging to: ║
rirv938-anthropic-grpo-55424-v3-mkmlizer: ║ ║
rirv938-anthropic-grpo-55424-v3-mkmlizer: ║ Chai Research Corp. ║
rirv938-anthropic-grpo-55424-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-anthropic-grpo-55424-v3-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
rirv938-anthropic-grpo-55424-v3-mkmlizer: ║ ║
rirv938-anthropic-grpo-55424-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-55424-v3-mkmlizer: Downloaded to shared memory in 73.955s
rirv938-anthropic-grpo-55424-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp21b00iog, device:0
rirv938-anthropic-grpo-55424-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-55424-v3-mkmlizer: quantized model in 41.464s
rirv938-anthropic-grpo-55424-v3-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp296_95ff_merged in 115.420s
rirv938-anthropic-grpo-55424-v3-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-55424-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-55424-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-55424-v3
rirv938-anthropic-grpo-55424-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-55424-v3/special_tokens_map.json
rirv938-anthropic-grpo-55424-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-55424-v3/config.json
rirv938-anthropic-grpo-55424-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-55424-v3/tokenizer_config.json
rirv938-anthropic-grpo-55424-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-55424-v3/flywheel_model.0.safetensors
rirv938-anthropic-grpo-55424-v3-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:15, 22.86it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:12, 28.10it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:13, 25.00it/s] Loading 0: 6%|▌ | 20/363 [00:00<00:10, 33.92it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:14, 23.57it/s] Loading 0: 7%|▋ | 27/363 [00:01<00:14, 22.65it/s] Loading 0: 9%|▊ | 31/363 [00:01<00:12, 26.23it/s] Loading 0: 10%|▉ | 35/363 [00:01<00:11, 27.96it/s] Loading 0: 11%|█ | 39/363 [00:01<00:11, 29.36it/s] Loading 0: 12%|█▏ | 43/363 [00:01<00:11, 28.30it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:10, 30.76it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:10, 29.27it/s] Loading 0: 15%|█▌ | 56/363 [00:02<00:10, 28.89it/s] Loading 0: 17%|█▋ | 61/363 [00:02<00:12, 25.11it/s] Loading 0: 18%|█▊ | 64/363 [00:02<00:13, 22.29it/s] Loading 0: 20%|█▉ | 71/363 [00:02<00:10, 29.15it/s] Loading 0: 21%|██ | 75/363 [00:02<00:10, 28.59it/s] Loading 0: 21%|██▏ | 78/363 [00:02<00:10, 26.45it/s] Loading 0: 23%|██▎ | 84/363 [00:03<00:09, 30.72it/s] Loading 0: 24%|██▍ | 88/363 [00:03<00:09, 28.94it/s] Loading 0: 26%|██▌ | 93/363 [00:03<00:08, 31.19it/s] Loading 0: 27%|██▋ | 97/363 [00:03<00:08, 29.68it/s] Loading 0: 28%|██▊ | 101/363 [00:03<00:10, 24.33it/s] Loading 0: 29%|██▊ | 104/363 [00:03<00:11, 21.70it/s] Loading 0: 31%|███ | 111/363 [00:04<00:08, 28.69it/s] Loading 0: 32%|███▏ | 115/363 [00:04<00:08, 27.60it/s] Loading 0: 33%|███▎ | 120/363 [00:04<00:08, 30.15it/s] Loading 0: 34%|███▍ | 124/363 [00:04<00:08, 29.25it/s] Loading 0: 36%|███▌ | 129/363 [00:04<00:07, 31.32it/s] Loading 0: 37%|███▋ | 133/363 [00:04<00:07, 29.65it/s] Loading 0: 38%|███▊ | 137/363 [00:04<00:07, 29.63it/s] Loading 0: 39%|███▉ | 142/363 [00:05<00:08, 25.76it/s] Loading 0: 40%|███▉ | 145/363 [00:05<00:08, 24.25it/s] Loading 0: 41%|████ | 149/363 [00:05<00:09, 23.18it/s] Loading 0: 43%|████▎ | 156/363 [00:05<00:06, 29.72it/s] Loading 0: 44%|████▍ | 160/363 [00:05<00:07, 27.98it/s] Loading 0: 45%|████▌ | 165/363 [00:05<00:06, 30.24it/s] Loading 0: 47%|████▋ | 169/363 [00:06<00:06, 28.64it/s] Loading 0: 48%|████▊ | 174/363 [00:06<00:06, 30.77it/s] Loading 0: 49%|████▉ | 178/363 [00:06<00:06, 29.15it/s] Loading 0: 50%|█████ | 182/363 [00:06<00:07, 23.84it/s] Loading 0: 51%|█████ | 185/363 [00:06<00:08, 21.30it/s] Loading 0: 53%|█████▎ | 192/363 [00:06<00:06, 28.05it/s] Loading 0: 54%|█████▍ | 196/363 [00:07<00:06, 27.31it/s] Loading 0: 55%|█████▌ | 201/363 [00:07<00:05, 29.49it/s] Loading 0: 56%|█████▋ | 205/363 [00:07<00:05, 28.33it/s] Loading 0: 58%|█████▊ | 210/363 [00:07<00:05, 30.36it/s] Loading 0: 59%|█████▉ | 214/363 [00:07<00:05, 27.93it/s] Loading 0: 60%|██████ | 218/363 [00:07<00:05, 27.72it/s] Loading 0: 61%|██████▏ | 223/363 [00:08<00:05, 23.73it/s] Loading 0: 62%|██████▏ | 226/363 [00:08<00:06, 22.31it/s] Loading 0: 63%|██████▎ | 230/363 [00:08<00:06, 21.12it/s] Loading 0: 65%|██████▍ | 235/363 [00:08<00:04, 26.02it/s] Loading 0: 66%|██████▌ | 238/363 [00:08<00:04, 26.51it/s] Loading 0: 66%|██████▋ | 241/363 [00:08<00:04, 25.97it/s] Loading 0: 68%|██████▊ | 246/363 [00:09<00:04, 27.99it/s] Loading 0: 69%|██████▊ | 249/363 [00:09<00:04, 25.16it/s] Loading 0: 70%|███████ | 255/363 [00:09<00:03, 29.45it/s] Loading 0: 71%|███████ | 258/363 [00:09<00:04, 26.18it/s] Loading 0: 72%|███████▏ | 262/363 [00:09<00:03, 29.12it/s] Loading 0: 73%|███████▎ | 266/363 [00:10<00:05, 17.61it/s] Loading 0: 75%|███████▍ | 271/363 [00:10<00:04, 22.74it/s] Loading 0: 76%|███████▌ | 275/363 [00:10<00:04, 21.63it/s] Loading 0: 77%|███████▋ | 280/363 [00:10<00:03, 26.38it/s] Loading 0: 78%|███████▊ | 284/363 [00:10<00:03, 23.94it/s] Loading 0: 80%|███████▉ | 289/363 [00:10<00:02, 28.91it/s] Loading 0: 81%|████████ | 293/363 [00:10<00:02, 25.49it/s] Loading 0: 82%|████████▏ | 299/363 [00:11<00:02, 29.28it/s] Loading 0: 83%|████████▎ | 303/363 [00:11<00:01, 31.39it/s] Loading 0: 85%|████████▍ | 307/363 [00:11<00:02, 21.28it/s] Loading 0: 86%|████████▌ | 311/363 [00:11<00:02, 20.77it/s] Loading 0: 87%|████████▋ | 316/363 [00:11<00:01, 25.56it/s] Loading 0: 88%|████████▊ | 320/363 [00:12<00:01, 23.71it/s] Loading 0: 90%|█████████ | 327/363 [00:12<00:01, 29.76it/s] Loading 0: 91%|█████████ | 331/363 [00:12<00:01, 28.53it/s] Loading 0: 93%|█████████▎| 336/363 [00:12<00:00, 30.21it/s] Loading 0: 94%|█████████▎| 340/363 [00:12<00:00, 28.61it/s] Loading 0: 95%|█████████▍| 344/363 [00:19<00:09, 2.00it/s] Loading 0: 96%|█████████▌| 348/363 [00:19<00:05, 2.67it/s] Loading 0: 97%|█████████▋| 353/363 [00:20<00:02, 3.85it/s] Loading 0: 98%|█████████▊| 357/363 [00:20<00:01, 4.95it/s] Loading 0: 100%|█████████▉| 362/363 [00:20<00:00, 7.04it/s]
Job rirv938-anthropic-grpo-55424-v3-mkmlizer completed after 146.01s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-55424-v3-mkmlizer
Pipeline stage MKMLizer completed in 146.49s
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-55424-v3
Waiting for inference service rirv938-anthropic-grpo-55424-v3 to be ready
Inference service rirv938-anthropic-grpo-55424-v3 ready after 140.48258900642395s
Pipeline stage MKMLDeployer completed in 140.93s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.228192090988159s
Received healthy response to inference request in 1.6395127773284912s
Received healthy response to inference request in 1.852719783782959s
Received healthy response to inference request in 1.8096494674682617s
Received healthy response to inference request in 1.5046849250793457s
5 requests
0 failed requests
5th percentile: 1.5316504955291748
10th percentile: 1.5586160659790038
20th percentile: 1.6125472068786622
30th percentile: 1.6735401153564453
40th percentile: 1.7415947914123535
50th percentile: 1.8096494674682617
60th percentile: 1.8268775939941406
70th percentile: 1.8441057205200195
80th percentile: 1.927814245223999
90th percentile: 2.078003168106079
95th percentile: 2.153097629547119
99th percentile: 2.213173198699951
mean time: 1.8069518089294434
Pipeline stage StressChecker completed in 10.73s
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 0.80s
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 0.95s
Shutdown handler de-registered
rirv938-anthropic-grpo-_55424_v3 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-55424-v3-profiler
Waiting for inference service rirv938-anthropic-grpo-55424-v3-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 3237.21s
Shutdown handler de-registered
rirv938-anthropic-grpo-_55424_v3 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_55424_v3 status is now torndown due to DeploymentManager action