rirv938-anthropic-grpo-_34483

developer_uid: rirv938

submission_id: rirv938-anthropic-grpo-_34483_v1

model_name: rirv938-anthropic-grpo-_34483_v1

model_group: rirv938/anthropic_grpo_4

status: torndown

timestamp: 2025-05-20T15:06:29+00:00

num_battles: 6761

num_wins: 3749

celo_rating: 1338.15

family_friendly_score: 0.5680000000000001

family_friendly_standard_error: 0.007005369369276684

submission_type: basic

model_repo: rirv938/anthropic_grpo_40k_cp2184_96ff_new_rm_merged

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 768

max_output_tokens: 64

reward_model: default

display_name: rirv938-anthropic-grpo-_34483_v1

is_internal_developer: True

language_model: rirv938/anthropic_grpo_40k_cp2184_96ff_new_rm_merged

model_size: 13B

ranking_group: single

us_pacific_date: 2025-05-20

win_ratio: 0.5545037716314155

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-34483-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-34483-v1-mkmlizer to finish
rirv938-anthropic-grpo-34483-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-34483-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-34483-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-34483-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-34483-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-34483-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-34483-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-34483-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-34483-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-34483-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-34483-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-34483-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-34483-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-34483-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-34483-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-34483-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-34483-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-34483-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-34483-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-34483-v1-mkmlizer: Downloaded to shared memory in 94.087s
rirv938-anthropic-grpo-34483-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphfhk__qk, device:0
rirv938-anthropic-grpo-34483-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-34483-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-34483-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-34483-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-34483-v1
rirv938-anthropic-grpo-34483-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-34483-v1/config.json
rirv938-anthropic-grpo-34483-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-34483-v1/special_tokens_map.json
rirv938-anthropic-grpo-34483-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-34483-v1/tokenizer_config.json
rirv938-anthropic-grpo-34483-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-34483-v1/tokenizer.json
Job rirv938-anthropic-grpo-34483-v1-mkmlizer completed after 195.76s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-34483-v1-mkmlizer
Pipeline stage MKMLizer completed in 196.22s
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-34483-v1
Waiting for inference service rirv938-anthropic-grpo-34483-v1 to be ready
Inference service rirv938-anthropic-grpo-34483-v1 ready after 140.55049109458923s
Pipeline stage MKMLDeployer completed in 141.14s
run pipeline stage %s
Running pipeline stage StressChecker
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 2.2804815769195557s
Received healthy response to inference request in 1.6140427589416504s
Received healthy response to inference request in 1.7369310855865479s
Received healthy response to inference request in 1.9823389053344727s
Received healthy response to inference request in 2.2850468158721924s
5 requests
0 failed requests
5th percentile: 1.63862042427063
10th percentile: 1.6631980895996095
20th percentile: 1.7123534202575683
30th percentile: 1.7860126495361328
40th percentile: 1.8841757774353027
50th percentile: 1.9823389053344727
60th percentile: 2.101595973968506
70th percentile: 2.220853042602539
80th percentile: 2.281394624710083
90th percentile: 2.283220720291138
95th percentile: 2.284133768081665
99th percentile: 2.284864206314087
mean time: 1.9797682285308837
Pipeline stage StressChecker completed in 11.17s
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 0.72s
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 0.68s
Shutdown handler de-registered
rirv938-anthropic-grpo-_34483_v1 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 2825.46s
Shutdown handler de-registered
rirv938-anthropic-grpo-_34483_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of rirv938-anthropic-grpo-_34483_v1
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLDeleter
Checking if service rirv938-anthropic-grpo-34483-v1 is running
rirv938-anthropic-grpo-_34483_v1 status is now torndown due to DeploymentManager action