developer_uid: rirv938
submission_id: rirv938-anthropic-grpo-_74918_v2
model_name: rirv938-anthropic-grpo-_74918_v2
model_group: rirv938/anthropic_grpo_4
status: torndown
timestamp: 2025-05-13T16:36:53+00:00
num_battles: 8750
num_wins: 4559
celo_rating: 1299.16
family_friendly_score: 0.5549999999999999
family_friendly_standard_error: 0.007028157653325657
submission_type: basic
model_repo: rirv938/anthropic_grpo_40k_cp1184_95ff_20ww_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': 0.6432984229458266, 'latency_mean': 1.5543953609466552, 'latency_p50': 1.5722798109054565, 'latency_p90': 1.7070597410202026}, {'batch_size': 3, 'throughput': 1.2284916306052351, 'latency_mean': 2.4349069464206696, 'latency_p50': 2.4306488037109375, 'latency_p90': 2.671832323074341}, {'batch_size': 5, 'throughput': 1.509936390223754, 'latency_mean': 3.2876861572265623, 'latency_p50': 3.3084388971328735, 'latency_p90': 3.6404104471206664}, {'batch_size': 6, 'throughput': 1.6066269746715842, 'latency_mean': 3.7142657268047334, 'latency_p50': 3.7143566608428955, 'latency_p90': 4.107903528213501}, {'batch_size': 8, 'throughput': 1.692419361790046, 'latency_mean': 4.6861239361763, 'latency_p50': 4.6746920347213745, 'latency_p90': 5.231846213340759}, {'batch_size': 10, 'throughput': 1.7218363878453065, 'latency_mean': 5.74949450135231, 'latency_p50': 5.749223589897156, 'latency_p90': 6.434492373466491}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-anthropic-grpo-_74918_v2
is_internal_developer: True
language_model: rirv938/anthropic_grpo_40k_cp1184_95ff_20ww_merged
model_size: 13B
ranking_group: single
throughput_3p7s: 1.61
us_pacific_date: 2025-05-13
win_ratio: 0.5210285714285714
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': 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-74918-v2-mkmlizer
Waiting for job on rirv938-anthropic-grpo-74918-v2-mkmlizer to finish
rirv938-anthropic-grpo-74918-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-74918-v2-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-74918-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-74918-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-74918-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-74918-v2-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-74918-v2-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-74918-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-74918-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-74918-v2-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-74918-v2-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-74918-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-74918-v2-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-74918-v2-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-74918-v2-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-74918-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-74918-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-74918-v2-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-74918-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-74918-v2-mkmlizer: Downloaded to shared memory in 76.348s
rirv938-anthropic-grpo-74918-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmph0wgv634, device:0
rirv938-anthropic-grpo-74918-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-74918-v2-mkmlizer: quantized model in 41.388s
rirv938-anthropic-grpo-74918-v2-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp1184_95ff_20ww_merged in 117.736s
rirv938-anthropic-grpo-74918-v2-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-74918-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-74918-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-74918-v2
rirv938-anthropic-grpo-74918-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-74918-v2/config.json
rirv938-anthropic-grpo-74918-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-74918-v2/special_tokens_map.json
rirv938-anthropic-grpo-74918-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-74918-v2/tokenizer_config.json
rirv938-anthropic-grpo-74918-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-74918-v2/tokenizer.json
rirv938-anthropic-grpo-74918-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-74918-v2/flywheel_model.0.safetensors
Job rirv938-anthropic-grpo-74918-v2-mkmlizer completed after 146.02s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-74918-v2-mkmlizer
Pipeline stage MKMLizer completed in 146.48s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-grpo-74918-v2
Waiting for inference service rirv938-anthropic-grpo-74918-v2 to be ready
Inference service rirv938-anthropic-grpo-74918-v2 ready after 120.45827651023865s
Pipeline stage MKMLDeployer completed in 120.98s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.286639928817749s
Received healthy response to inference request in 1.8178284168243408s
Received healthy response to inference request in 1.828291893005371s
Received healthy response to inference request in 1.7909026145935059s
Received healthy response to inference request in 1.5410747528076172s
5 requests
0 failed requests
5th percentile: 1.5910403251647949
10th percentile: 1.6410058975219726
20th percentile: 1.7409370422363282
30th percentile: 1.7962877750396729
40th percentile: 1.8070580959320068
50th percentile: 1.8178284168243408
60th percentile: 1.8220138072967529
70th percentile: 1.826199197769165
80th percentile: 1.9199615001678467
90th percentile: 2.1033007144927978
95th percentile: 2.194970321655273
99th percentile: 2.2683060073852537
mean time: 1.8529475212097168
Pipeline stage StressChecker completed in 10.45s
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 0.77s
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 0.64s
Shutdown handler de-registered
rirv938-anthropic-grpo-_74918_v2 status is now deployed due to DeploymentManager action
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 2784.84s
Shutdown handler de-registered
rirv938-anthropic-grpo-_74918_v2 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_74918_v2 status is now torndown due to DeploymentManager action