developer_uid: rica40325
submission_id: rica40325-filter-mulsft_36664_v2
model_name: rica40325-filter-mulsft_36664_v2
model_group: rica40325/filter-mulsft-
status: torndown
timestamp: 2025-06-19T08:08:30+00:00
num_battles: 7123
num_wins: 3168
celo_rating: 1242.51
family_friendly_score: 0.5436000000000001
family_friendly_standard_error: 0.007044132877792696
submission_type: basic
model_repo: rica40325/filter-mulsft-v5-200
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
display_name: rica40325-filter-mulsft_36664_v2
is_internal_developer: False
language_model: rica40325/filter-mulsft-v5-200
model_size: 13B
ranking_group: single
us_pacific_date: 2025-06-19
win_ratio: 0.4447564228555384
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{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 rica40325-filter-mulsft-36664-v2-mkmlizer
Waiting for job on rica40325-filter-mulsft-36664-v2-mkmlizer to finish
rica40325-filter-mulsft-36664-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-filter-mulsft-36664-v2-mkmlizer: ║                                                                     ║
rica40325-filter-mulsft-36664-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rica40325-filter-mulsft-36664-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rica40325-filter-mulsft-36664-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rica40325-filter-mulsft-36664-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rica40325-filter-mulsft-36664-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rica40325-filter-mulsft-36664-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rica40325-filter-mulsft-36664-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rica40325-filter-mulsft-36664-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rica40325-filter-mulsft-36664-v2-mkmlizer: ║                                                                     ║
rica40325-filter-mulsft-36664-v2-mkmlizer: ║  Version: 0.27.1+vampire_v3                                         ║
rica40325-filter-mulsft-36664-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rica40325-filter-mulsft-36664-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rica40325-filter-mulsft-36664-v2-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-filter-mulsft-36664-v2-mkmlizer: ║                                                                     ║
rica40325-filter-mulsft-36664-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-filter-mulsft-36664-v2-mkmlizer: ║  belonging to:                                                      ║
rica40325-filter-mulsft-36664-v2-mkmlizer: ║                                                                     ║
rica40325-filter-mulsft-36664-v2-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-filter-mulsft-36664-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-filter-mulsft-36664-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rica40325-filter-mulsft-36664-v2-mkmlizer: ║                                                                     ║
rica40325-filter-mulsft-36664-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-filter-mulsft-36664-v2-mkmlizer: Downloaded to shared memory in 60.416s
rica40325-filter-mulsft-36664-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6avpg8h_, device:0
rica40325-filter-mulsft-36664-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-filter-mulsft-36664-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/mk1/flywheel/functional/loader.py:55: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
rica40325-filter-mulsft-36664-v2-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
rica40325-filter-mulsft-36664-v2-mkmlizer: creating bucket guanaco-mkml-models
rica40325-filter-mulsft-36664-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-filter-mulsft-36664-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-filter-mulsft-36664-v2
rica40325-filter-mulsft-36664-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-filter-mulsft-36664-v2/special_tokens_map.json
rica40325-filter-mulsft-36664-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-filter-mulsft-36664-v2/config.json
rica40325-filter-mulsft-36664-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-filter-mulsft-36664-v2/tokenizer_config.json
rica40325-filter-mulsft-36664-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-filter-mulsft-36664-v2/tokenizer.json
rica40325-filter-mulsft-36664-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-filter-mulsft-36664-v2/flywheel_model.0.safetensors
Job rica40325-filter-mulsft-36664-v2-mkmlizer completed after 125.14s with status: succeeded
Stopping job with name rica40325-filter-mulsft-36664-v2-mkmlizer
Pipeline stage MKMLizer completed in 125.71s
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 rica40325-filter-mulsft-36664-v2
Waiting for inference service rica40325-filter-mulsft-36664-v2 to be ready
Inference service rica40325-filter-mulsft-36664-v2 ready after 120.52890872955322s
Pipeline stage MKMLDeployer completed in 121.09s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.305004358291626s
Received healthy response to inference request in 1.6160295009613037s
Received healthy response to inference request in 2.0519137382507324s
Received healthy response to inference request in 2.067373752593994s
Received healthy response to inference request in 2.0434532165527344s
5 requests
0 failed requests
5th percentile: 1.7015142440795898
10th percentile: 1.786998987197876
20th percentile: 1.9579684734344482
30th percentile: 2.045145320892334
40th percentile: 2.048529529571533
50th percentile: 2.0519137382507324
60th percentile: 2.058097743988037
70th percentile: 2.0642817497253416
80th percentile: 2.1148998737335205
90th percentile: 2.2099521160125732
95th percentile: 2.2574782371520996
99th percentile: 2.2954991340637205
mean time: 2.016754913330078
Pipeline stage StressChecker completed in 11.73s
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
rica40325-filter-mulsft_36664_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5191.75s
Shutdown handler de-registered
rica40325-filter-mulsft_36664_v2 status is now inactive due to auto deactivation removed underperforming models
rica40325-filter-mulsft_36664_v2 status is now torndown due to DeploymentManager action