developer_uid: rirv938
submission_id: rirv938-exp-grpo-cp312-_28460_v1
model_name: rirv938-exp-grpo-cp312-_28460_v1
model_group: rirv938/exp_grpo_cp312_9
status: torndown
timestamp: 2025-05-25T17:00:28+00:00
num_battles: 8683
num_wins: 4662
celo_rating: 1324.3
family_friendly_score: 0.5402
family_friendly_standard_error: 0.0070481765017627075
submission_type: basic
model_repo: rirv938/exp_grpo_cp312_96ff_b2_r1_merged
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
display_name: rirv938-exp-grpo-cp312-_28460_v1
is_internal_developer: True
language_model: rirv938/exp_grpo_cp312_96ff_b2_r1_merged
model_size: 24B
ranking_group: single
us_pacific_date: 2025-05-25
win_ratio: 0.5369112058044455
generation_params: {'temperature': 0.9, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['</s>', '###', '\n', 'You:'], 'max_input_tokens': 1024, '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-exp-grpo-cp312-28460-v1-mkmlizer
Waiting for job on rirv938-exp-grpo-cp312-28460-v1-mkmlizer to finish
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: ║ _____ __ __ ║
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: ║ /___/ ║
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: ║ ║
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: ║ Version: 0.12.8 ║
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: ║ ║
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: ║ belonging to: ║
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: ║ ║
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: ║ ║
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Retrying (%r) after connection broken by '%r': %s
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: Downloaded to shared memory in 164.170s
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmptln7cuxf, device:0
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: quantized model in 64.321s
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: Processed model rirv938/exp_grpo_cp312_96ff_b2_r1_merged in 228.492s
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-exp-grpo-cp312-28460-v1
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-exp-grpo-cp312-28460-v1/config.json
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-exp-grpo-cp312-28460-v1/special_tokens_map.json
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-exp-grpo-cp312-28460-v1/tokenizer_config.json
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-exp-grpo-cp312-28460-v1/tokenizer.json
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-exp-grpo-cp312-28460-v1/flywheel_model.1.safetensors
rirv938-exp-grpo-cp312-28460-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-exp-grpo-cp312-28460-v1/flywheel_model.0.safetensors
Job rirv938-exp-grpo-cp312-28460-v1-mkmlizer completed after 269.56s with status: succeeded
Stopping job with name rirv938-exp-grpo-cp312-28460-v1-mkmlizer
Pipeline stage MKMLizer completed in 270.21s
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-exp-grpo-cp312-28460-v1
Waiting for inference service rirv938-exp-grpo-cp312-28460-v1 to be ready
Inference service rirv938-exp-grpo-cp312-28460-v1 ready after 160.87780618667603s
Pipeline stage MKMLDeployer completed in 161.34s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.777888059616089s
Received healthy response to inference request in 2.158433675765991s
Received healthy response to inference request in 1.8742039203643799s
Received healthy response to inference request in 2.087909460067749s
5 requests
1 failed requests
5th percentile: 1.9169450283050538
10th percentile: 1.9596861362457276
20th percentile: 2.0451683521270754
30th percentile: 2.1020143032073975
40th percentile: 2.1302239894866943
50th percentile: 2.158433675765991
60th percentile: 2.4062154293060303
70th percentile: 2.6539971828460693
80th percentile: 6.251151466369632
90th percentile: 13.197678279876712
95th percentile: 16.670941686630247
99th percentile: 19.449552412033082
mean time: 5.808528041839599
%s, retrying in %s seconds...
Received healthy response to inference request in 1.8916139602661133s
Received healthy response to inference request in 1.9132895469665527s
Received healthy response to inference request in 2.1924052238464355s
Received healthy response to inference request in 2.009599208831787s
Received healthy response to inference request in 1.8398761749267578s
5 requests
0 failed requests
5th percentile: 1.8502237319946289
10th percentile: 1.8605712890625
20th percentile: 1.8812664031982422
30th percentile: 1.8959490776062011
40th percentile: 1.904619312286377
50th percentile: 1.9132895469665527
60th percentile: 1.9518134117126464
70th percentile: 1.9903372764587401
80th percentile: 2.046160411834717
90th percentile: 2.1192828178405763
95th percentile: 2.1558440208435057
99th percentile: 2.1850929832458497
mean time: 1.9693568229675293
Pipeline stage StressChecker completed in 41.39s
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 0.69s
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-exp-grpo-cp312-_28460_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 3066.78s
Shutdown handler de-registered
rirv938-exp-grpo-cp312-_28460_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-exp-grpo-cp312-_28460_v1 status is now torndown due to DeploymentManager action