developer_uid: rirv938
submission_id: rirv938-anthropic-grpo-4_2727_v2
model_name: rirv938-anthropic-grpo-4_2727_v2
model_group: rirv938/anthropic_grpo_4
status: torndown
timestamp: 2025-05-15T15:51:00+00:00
num_battles: 7420
num_wins: 3902
celo_rating: 1304.63
family_friendly_score: 0.5436000000000001
family_friendly_standard_error: 0.007044132877792696
submission_type: basic
model_repo: rirv938/anthropic_grpo_40k_cp888_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': 0.6430765323550437, 'latency_mean': 1.5549261605739593, 'latency_p50': 1.5433588027954102, 'latency_p90': 1.7343406200408935}, {'batch_size': 3, 'throughput': 1.2207533879494148, 'latency_mean': 2.4487334096431734, 'latency_p50': 2.456711173057556, 'latency_p90': 2.718113327026367}, {'batch_size': 5, 'throughput': 1.509658491067309, 'latency_mean': 3.297615797519684, 'latency_p50': 3.3178731203079224, 'latency_p90': 3.6612592935562134}, {'batch_size': 6, 'throughput': 1.5859743778961597, 'latency_mean': 3.758881620168686, 'latency_p50': 3.7944852113723755, 'latency_p90': 4.19390287399292}, {'batch_size': 8, 'throughput': 1.687735658009834, 'latency_mean': 4.696572530269623, 'latency_p50': 4.685563445091248, 'latency_p90': 5.270665621757507}, {'batch_size': 10, 'throughput': 1.723444882265237, 'latency_mean': 5.761427544355392, 'latency_p50': 5.762396931648254, 'latency_p90': 6.451534748077393}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-anthropic-grpo-4_2727_v2
is_internal_developer: True
language_model: rirv938/anthropic_grpo_40k_cp888_95ff_20ww2_merged
model_size: 13B
ranking_group: single
throughput_3p7s: 1.59
us_pacific_date: 2025-05-15
win_ratio: 0.5258760107816711
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-4-2727-v2-mkmlizer
Waiting for job on rirv938-anthropic-grpo-4-2727-v2-mkmlizer to finish
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: ║ _____ __ __ ║
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: ║ /___/ ║
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: ║ ║
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: ║ Version: 0.12.8 ║
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: ║ https://mk1.ai ║
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: ║ ║
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: ║ belonging to: ║
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: ║ ║
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: ║ Chai Research Corp. ║
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: ║ ║
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: Downloaded to shared memory in 76.818s
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppm9tr7d4, device:0
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: quantized model in 40.997s
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp888_95ff_20ww2_merged in 117.816s
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-2727-v2
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-2727-v2/config.json
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-2727-v2/special_tokens_map.json
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-2727-v2/tokenizer_config.json
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-2727-v2/tokenizer.json
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-2727-v2/flywheel_model.0.safetensors
rirv938-anthropic-grpo-4-2727-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:16, 22.19it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:12, 28.11it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:14, 24.68it/s] Loading 0: 6%|▌ | 21/363 [00:00<00:09, 35.31it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:14, 23.51it/s] Loading 0: 8%|▊ | 29/363 [00:01<00:13, 25.38it/s] Loading 0: 9%|▉ | 33/363 [00:01<00:13, 24.15it/s] Loading 0: 11%|█ | 39/363 [00:01<00:11, 29.42it/s] Loading 0: 12%|█▏ | 43/363 [00:01<00:11, 28.85it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:09, 31.70it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:10, 30.62it/s] Loading 0: 15%|█▌ | 56/363 [00:01<00:09, 30.78it/s] Loading 0: 17%|█▋ | 61/363 [00:02<00:11, 26.75it/s] Loading 0: 18%|█▊ | 64/363 [00:02<00:12, 23.10it/s] Loading 0: 20%|█▉ | 71/363 [00:02<00:10, 28.89it/s] Loading 0: 21%|██ | 75/363 [00:02<00:10, 28.14it/s] Loading 0: 21%|██▏ | 78/363 [00:02<00:11, 25.42it/s] Loading 0: 23%|██▎ | 82/363 [00:02<00:10, 28.02it/s] Loading 0: 24%|██▎ | 86/363 [00:03<00:10, 25.21it/s] Loading 0: 26%|██▌ | 93/363 [00:03<00:08, 32.40it/s] Loading 0: 27%|██▋ | 97/363 [00:03<00:08, 31.09it/s] Loading 0: 28%|██▊ | 101/363 [00:03<00:10, 25.30it/s] Loading 0: 29%|██▊ | 104/363 [00:03<00:11, 22.30it/s] Loading 0: 31%|███ | 111/363 [00:04<00:08, 28.71it/s] Loading 0: 32%|███▏ | 115/363 [00:04<00:08, 28.27it/s] Loading 0: 33%|███▎ | 120/363 [00:04<00:07, 30.39it/s] Loading 0: 34%|███▍ | 124/363 [00:04<00:08, 29.07it/s] Loading 0: 36%|███▌ | 129/363 [00:04<00:07, 32.04it/s] Loading 0: 37%|███▋ | 133/363 [00:04<00:07, 31.01it/s] Loading 0: 38%|███▊ | 137/363 [00:04<00:07, 31.26it/s] Loading 0: 39%|███▉ | 142/363 [00:05<00:07, 27.83it/s] Loading 0: 40%|███▉ | 145/363 [00:05<00:08, 25.79it/s] Loading 0: 41%|████ | 149/363 [00:05<00:08, 23.88it/s] Loading 0: 43%|████▎ | 156/363 [00:05<00:06, 31.08it/s] Loading 0: 44%|████▍ | 160/363 [00:05<00:06, 30.46it/s] Loading 0: 45%|████▌ | 165/363 [00:05<00:06, 32.93it/s] Loading 0: 47%|████▋ | 169/363 [00:05<00:06, 30.89it/s] Loading 0: 48%|████▊ | 174/363 [00:06<00:05, 32.89it/s] Loading 0: 49%|████▉ | 178/363 [00:06<00:05, 31.54it/s] Loading 0: 50%|█████ | 182/363 [00:06<00:06, 26.14it/s] Loading 0: 51%|█████ | 185/363 [00:06<00:07, 22.40it/s] Loading 0: 53%|█████▎ | 192/363 [00:06<00:05, 29.11it/s] Loading 0: 54%|█████▍ | 196/363 [00:06<00:05, 28.04it/s] Loading 0: 55%|█████▌ | 201/363 [00:07<00:05, 31.08it/s] Loading 0: 56%|█████▋ | 205/363 [00:07<00:05, 30.48it/s] Loading 0: 58%|█████▊ | 210/363 [00:07<00:04, 32.84it/s] Loading 0: 59%|█████▉ | 214/363 [00:07<00:04, 30.16it/s] Loading 0: 60%|██████ | 218/363 [00:07<00:04, 30.82it/s] Loading 0: 61%|██████▏ | 223/363 [00:07<00:05, 27.24it/s] Loading 0: 62%|██████▏ | 226/363 [00:08<00:05, 25.24it/s] Loading 0: 63%|██████▎ | 230/363 [00:08<00:05, 24.34it/s] Loading 0: 65%|██████▌ | 237/363 [00:08<00:04, 31.39it/s] Loading 0: 66%|██████▋ | 241/363 [00:08<00:04, 30.18it/s] Loading 0: 68%|██████▊ | 246/363 [00:08<00:03, 32.90it/s] Loading 0: 69%|██████▉ | 250/363 [00:08<00:03, 31.39it/s] Loading 0: 70%|███████ | 255/363 [00:08<00:03, 33.30it/s] Loading 0: 71%|███████▏ | 259/363 [00:09<00:03, 31.52it/s] Loading 0: 72%|███████▏ | 263/363 [00:09<00:03, 25.51it/s] Loading 0: 73%|███████▎ | 266/363 [00:09<00:04, 22.16it/s] Loading 0: 75%|███████▌ | 273/363 [00:09<00:03, 28.98it/s] Loading 0: 76%|███████▋ | 277/363 [00:09<00:03, 28.24it/s] Loading 0: 78%|███████▊ | 282/363 [00:09<00:02, 31.19it/s] Loading 0: 79%|███████▉ | 286/363 [00:10<00:02, 29.80it/s] Loading 0: 80%|████████ | 291/363 [00:10<00:02, 32.26it/s] Loading 0: 81%|████████▏ | 295/363 [00:10<00:02, 30.60it/s] Loading 0: 82%|████████▏ | 299/363 [00:10<00:02, 31.11it/s] Loading 0: 84%|████████▎ | 304/363 [00:10<00:02, 26.50it/s] Loading 0: 85%|████████▍ | 307/363 [00:10<00:02, 24.35it/s] Loading 0: 86%|████████▌ | 311/363 [00:11<00:02, 22.76it/s] Loading 0: 88%|████████▊ | 318/363 [00:11<00:01, 29.78it/s] Loading 0: 89%|████████▊ | 322/363 [00:11<00:01, 28.79it/s] Loading 0: 90%|█████████ | 327/363 [00:11<00:01, 31.25it/s] Loading 0: 91%|█████████ | 331/363 [00:11<00:01, 28.92it/s] Loading 0: 93%|█████████▎| 336/363 [00:11<00:00, 30.70it/s] Loading 0: 94%|█████████▎| 340/363 [00:11<00:00, 30.09it/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, 3.87it/s] Loading 0: 98%|█████████▊| 357/363 [00:19<00:01, 5.03it/s]
Job rirv938-anthropic-grpo-4-2727-v2-mkmlizer completed after 145.13s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-4-2727-v2-mkmlizer
Pipeline stage MKMLizer completed in 145.67s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-grpo-4-2727-v2
Waiting for inference service rirv938-anthropic-grpo-4-2727-v2 to be ready
Inference service rirv938-anthropic-grpo-4-2727-v2 ready after 130.5446252822876s
Pipeline stage MKMLDeployer completed in 131.30s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3375513553619385s
Received healthy response to inference request in 1.6516242027282715s
Received healthy response to inference request in 1.7994327545166016s
Received healthy response to inference request in 1.6427581310272217s
Received healthy response to inference request in 1.7423994541168213s
5 requests
0 failed requests
5th percentile: 1.6445313453674317
10th percentile: 1.6463045597076416
20th percentile: 1.6498509883880614
30th percentile: 1.6697792530059814
40th percentile: 1.7060893535614015
50th percentile: 1.7423994541168213
60th percentile: 1.7652127742767334
70th percentile: 1.7880260944366455
80th percentile: 1.907056474685669
90th percentile: 2.122303915023804
95th percentile: 2.229927635192871
99th percentile: 2.316026611328125
mean time: 1.8347531795501708
Pipeline stage StressChecker completed in 10.44s
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 0.66s
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 0.77s
Shutdown handler de-registered
rirv938-anthropic-grpo-4_2727_v2 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-4-2727-v2-profiler
Waiting for inference service rirv938-anthropic-grpo-4-2727-v2-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 5085.02s
Shutdown handler de-registered
rirv938-anthropic-grpo-4_2727_v2 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-4_2727_v2 status is now torndown due to DeploymentManager action