developer_uid: rirv938
submission_id: rirv938-anthropic-grpo-_72536_v1
model_name: rirv938-anthropic-grpo-_72536_v1
model_group: rirv938/anthropic_grpo_4
status: torndown
timestamp: 2025-05-15T21:58:07+00:00
num_battles: 6250
num_wins: 3093
celo_rating: 1285.08
family_friendly_score: 0.5596
family_friendly_standard_error: 0.0070206529610856
submission_type: basic
model_repo: rirv938/anthropic_grpo_40k_cp234_95ff_beta6_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': 0.6387970791888484, 'latency_mean': 1.5653762471675874, 'latency_p50': 1.5674883127212524, 'latency_p90': 1.729775857925415}, {'batch_size': 3, 'throughput': 1.2199763696011963, 'latency_mean': 2.4545041716098783, 'latency_p50': 2.4685263633728027, 'latency_p90': 2.736701416969299}, {'batch_size': 5, 'throughput': 1.4928332788314278, 'latency_mean': 3.3224985015392305, 'latency_p50': 3.333998918533325, 'latency_p90': 3.7086709499359127}, {'batch_size': 6, 'throughput': 1.5917402093768058, 'latency_mean': 3.7453632271289825, 'latency_p50': 3.7514182329177856, 'latency_p90': 4.192927050590515}, {'batch_size': 8, 'throughput': 1.6735231888644928, 'latency_mean': 4.758828134536743, 'latency_p50': 4.753318667411804, 'latency_p90': 5.339351296424866}, {'batch_size': 10, 'throughput': 1.72025148409692, 'latency_mean': 5.770591589212418, 'latency_p50': 5.721460938453674, 'latency_p90': 6.441695261001587}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-anthropic-grpo-_72536_v1
is_internal_developer: True
language_model: rirv938/anthropic_grpo_40k_cp234_95ff_beta6_merged
model_size: 13B
ranking_group: single
throughput_3p7s: 1.59
us_pacific_date: 2025-05-15
win_ratio: 0.49488
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': ['You:', '</s>', '###', '\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-72536-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-72536-v1-mkmlizer to finish
rirv938-anthropic-grpo-72536-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-72536-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-72536-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-72536-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-72536-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-72536-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-72536-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-72536-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-72536-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-72536-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-72536-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-72536-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-72536-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-72536-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-72536-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-72536-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-72536-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-72536-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-72536-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-72536-v1-mkmlizer: Downloaded to shared memory in 81.521s
rirv938-anthropic-grpo-72536-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_fa3y54s, device:0
rirv938-anthropic-grpo-72536-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-72536-v1-mkmlizer: quantized model in 42.299s
rirv938-anthropic-grpo-72536-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp234_95ff_beta6_merged in 123.821s
rirv938-anthropic-grpo-72536-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-72536-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-72536-v1/config.json
rirv938-anthropic-grpo-72536-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-72536-v1/special_tokens_map.json
rirv938-anthropic-grpo-72536-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-72536-v1/tokenizer_config.json
rirv938-anthropic-grpo-72536-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-72536-v1/tokenizer.json
rirv938-anthropic-grpo-72536-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-72536-v1/flywheel_model.0.safetensors
Job rirv938-anthropic-grpo-72536-v1-mkmlizer completed after 155.3s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-72536-v1-mkmlizer
Pipeline stage MKMLizer completed in 155.83s
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-72536-v1
Waiting for inference service rirv938-anthropic-grpo-72536-v1 to be ready
Inference service rirv938-anthropic-grpo-72536-v1 ready after 140.5755832195282s
Pipeline stage MKMLDeployer completed in 141.13s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1875736713409424s
Received healthy response to inference request in 1.5748767852783203s
Received healthy response to inference request in 1.572932481765747s
Received healthy response to inference request in 1.5297255516052246s
Received healthy response to inference request in 1.574789047241211s
5 requests
0 failed requests
5th percentile: 1.538366937637329
10th percentile: 1.5470083236694336
20th percentile: 1.5642910957336427
30th percentile: 1.57330379486084
40th percentile: 1.5740464210510254
50th percentile: 1.574789047241211
60th percentile: 1.5748241424560547
70th percentile: 1.5748592376708985
80th percentile: 1.6974161624908448
90th percentile: 1.9424949169158936
95th percentile: 2.065034294128418
99th percentile: 2.1630657958984374
mean time: 1.687979507446289
Pipeline stage StressChecker completed in 9.71s
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 0.64s
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-_72536_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-72536-v1-profiler
Waiting for inference service rirv938-anthropic-grpo-72536-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2745.88s
Shutdown handler de-registered
rirv938-anthropic-grpo-_72536_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_72536_v1 status is now torndown due to DeploymentManager action