developer_uid: rirv938
submission_id: rirv938-anthropic-grpo-_55424_v6
model_name: rirv938-anthropic-grpo-_55424_v6
model_group: rirv938/anthropic_grpo_4
status: torndown
timestamp: 2025-05-13T17:20:20+00:00
num_battles: 7120
num_wins: 3766
celo_rating: 1308.16
family_friendly_score: 0.5611999999999999
family_friendly_standard_error: 0.0070178994008178825
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: 768
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.6457523069824805, 'latency_mean': 1.5484936082363128, 'latency_p50': 1.5585854053497314, 'latency_p90': 1.719294786453247}, {'batch_size': 3, 'throughput': 1.2344960836780046, 'latency_mean': 2.4188350975513457, 'latency_p50': 2.4043489694595337, 'latency_p90': 2.679029655456543}, {'batch_size': 5, 'throughput': 1.5060399737845236, 'latency_mean': 3.306121747493744, 'latency_p50': 3.2950382232666016, 'latency_p90': 3.61559202671051}, {'batch_size': 6, 'throughput': 1.5967636274564079, 'latency_mean': 3.7416108095645906, 'latency_p50': 3.747270345687866, 'latency_p90': 4.141454815864563}, {'batch_size': 8, 'throughput': 1.669508772141136, 'latency_mean': 4.755768240690231, 'latency_p50': 4.758231163024902, 'latency_p90': 5.354399800300598}, {'batch_size': 10, 'throughput': 1.7190383075331312, 'latency_mean': 5.754823323488235, 'latency_p50': 5.720027565956116, 'latency_p90': 6.547767543792725}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-anthropic-grpo-_55424_v6
is_internal_developer: True
language_model: rirv938/anthropic_grpo_40k_cp296_95ff_merged
model_size: 13B
ranking_group: single
throughput_3p7s: 1.6
us_pacific_date: 2025-05-13
win_ratio: 0.5289325842696629
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-55424-v6-mkmlizer
Waiting for job on rirv938-anthropic-grpo-55424-v6-mkmlizer to finish
rirv938-anthropic-grpo-55424-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-55424-v6-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-55424-v6-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-55424-v6-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-55424-v6-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-55424-v6-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-55424-v6-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-55424-v6-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-55424-v6-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-55424-v6-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-55424-v6-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-55424-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-55424-v6-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-55424-v6-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-55424-v6-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-55424-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-55424-v6-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-55424-v6-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-55424-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-55424-v6-mkmlizer: Downloaded to shared memory in 114.558s
rirv938-anthropic-grpo-55424-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5yo31v7b, device:0
rirv938-anthropic-grpo-55424-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-55424-v6-mkmlizer: quantized model in 41.795s
rirv938-anthropic-grpo-55424-v6-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp296_95ff_merged in 156.354s
rirv938-anthropic-grpo-55424-v6-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-55424-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-55424-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-55424-v6
rirv938-anthropic-grpo-55424-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-55424-v6/special_tokens_map.json
rirv938-anthropic-grpo-55424-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-55424-v6/config.json
rirv938-anthropic-grpo-55424-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-55424-v6/tokenizer_config.json
rirv938-anthropic-grpo-55424-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-55424-v6/tokenizer.json
rirv938-anthropic-grpo-55424-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-55424-v6/flywheel_model.0.safetensors
Job rirv938-anthropic-grpo-55424-v6-mkmlizer completed after 198.73s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-55424-v6-mkmlizer
Pipeline stage MKMLizer completed in 199.23s
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-55424-v6
Waiting for inference service rirv938-anthropic-grpo-55424-v6 to be ready
Inference service rirv938-anthropic-grpo-55424-v6 ready after 130.5651683807373s
Pipeline stage MKMLDeployer completed in 131.12s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.350811719894409s
Received healthy response to inference request in 1.868661880493164s
Received healthy response to inference request in 1.9830498695373535s
Received healthy response to inference request in 1.5663301944732666s
Received healthy response to inference request in 1.9277124404907227s
5 requests
0 failed requests
5th percentile: 1.6267965316772461
10th percentile: 1.6872628688812257
20th percentile: 1.8081955432891845
30th percentile: 1.8804719924926758
40th percentile: 1.9040922164916991
50th percentile: 1.9277124404907227
60th percentile: 1.949847412109375
70th percentile: 1.9719823837280273
80th percentile: 2.0566022396087646
90th percentile: 2.203706979751587
95th percentile: 2.277259349822998
99th percentile: 2.336101245880127
mean time: 1.9393132209777832
Pipeline stage StressChecker completed in 10.95s
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 0.67s
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 0.66s
Shutdown handler de-registered
rirv938-anthropic-grpo-_55424_v6 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
Received signal 15, running shutdown handler
Shutdown handler de-registered
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 2576.27s
Shutdown handler de-registered
rirv938-anthropic-grpo-_55424_v6 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_55424_v6 status is now torndown due to DeploymentManager action