developer_uid: rica40325
submission_id: rica40325-filter-mulsft_88200_v2
model_name: rica40325-filter-mulsft_88200_v2
model_group: rica40325/filter-mulsft-
status: torndown
timestamp: 2025-06-19T07:31:43+00:00
num_battles: 9181
num_wins: 4034
celo_rating: 1237.81
family_friendly_score: 0.53
family_friendly_standard_error: 0.007058328414008518
submission_type: basic
model_repo: rica40325/filter-mulsft-v5-100
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_88200_v2
is_internal_developer: False
language_model: rica40325/filter-mulsft-v5-100
model_size: 13B
ranking_group: single
us_pacific_date: 2025-06-19
win_ratio: 0.43938568783356935
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-88200-v2-mkmlizer
Waiting for job on rica40325-filter-mulsft-88200-v2-mkmlizer to finish
rica40325-filter-mulsft-88200-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-filter-mulsft-88200-v2-mkmlizer: ║ ║
rica40325-filter-mulsft-88200-v2-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
rica40325-filter-mulsft-88200-v2-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
rica40325-filter-mulsft-88200-v2-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
rica40325-filter-mulsft-88200-v2-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
rica40325-filter-mulsft-88200-v2-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
rica40325-filter-mulsft-88200-v2-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
rica40325-filter-mulsft-88200-v2-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
rica40325-filter-mulsft-88200-v2-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
rica40325-filter-mulsft-88200-v2-mkmlizer: ║ ║
rica40325-filter-mulsft-88200-v2-mkmlizer: ║ Version: 0.27.1+vampire_v3 ║
rica40325-filter-mulsft-88200-v2-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
rica40325-filter-mulsft-88200-v2-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
rica40325-filter-mulsft-88200-v2-mkmlizer: ║ https://mk1.ai ║
rica40325-filter-mulsft-88200-v2-mkmlizer: ║ ║
rica40325-filter-mulsft-88200-v2-mkmlizer: ║ The license key for the current software has been verified as ║
rica40325-filter-mulsft-88200-v2-mkmlizer: ║ belonging to: ║
rica40325-filter-mulsft-88200-v2-mkmlizer: ║ ║
rica40325-filter-mulsft-88200-v2-mkmlizer: ║ Chai Research Corp. ║
rica40325-filter-mulsft-88200-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rica40325-filter-mulsft-88200-v2-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
rica40325-filter-mulsft-88200-v2-mkmlizer: ║ ║
rica40325-filter-mulsft-88200-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-filter-mulsft-88200-v2-mkmlizer: Downloaded to shared memory in 61.337s
rica40325-filter-mulsft-88200-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmph1vnm4h0, device:0
rica40325-filter-mulsft-88200-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-filter-mulsft-88200-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-88200-v2-mkmlizer: tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
rica40325-filter-mulsft-88200-v2-mkmlizer: quantized model in 37.443s
rica40325-filter-mulsft-88200-v2-mkmlizer: Processed model rica40325/filter-mulsft-v5-100 in 98.781s
rica40325-filter-mulsft-88200-v2-mkmlizer: creating bucket guanaco-mkml-models
rica40325-filter-mulsft-88200-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-filter-mulsft-88200-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-filter-mulsft-88200-v2
rica40325-filter-mulsft-88200-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-filter-mulsft-88200-v2/special_tokens_map.json
rica40325-filter-mulsft-88200-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-filter-mulsft-88200-v2/config.json
rica40325-filter-mulsft-88200-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-filter-mulsft-88200-v2/tokenizer_config.json
rica40325-filter-mulsft-88200-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-filter-mulsft-88200-v2/tokenizer.json
rica40325-filter-mulsft-88200-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-filter-mulsft-88200-v2/flywheel_model.0.safetensors
rica40325-filter-mulsft-88200-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 4/363 [00:00<00:09, 36.64it/s] Loading 0: 3%|▎ | 11/363 [00:00<00:07, 44.50it/s] Loading 0: 5%|▍ | 18/363 [00:00<00:07, 46.68it/s] Loading 0: 6%|▋ | 23/363 [00:01<00:30, 11.30it/s] Loading 0: 8%|▊ | 28/363 [00:01<00:23, 14.25it/s] Loading 0: 10%|▉ | 35/363 [00:01<00:16, 19.75it/s] Loading 0: 12%|█▏ | 42/363 [00:01<00:12, 24.93it/s] Loading 0: 13%|█▎ | 49/363 [00:03<00:26, 11.66it/s] Loading 0: 15%|█▌ | 56/363 [00:03<00:19, 15.52it/s] Loading 0: 17%|█▋ | 63/363 [00:03<00:15, 19.74it/s] Loading 0: 19%|█▉ | 70/363 [00:03<00:12, 24.21it/s] Loading 0: 21%|██ | 77/363 [00:03<00:10, 27.99it/s] Loading 0: 23%|██▎ | 82/363 [00:04<00:22, 12.52it/s] Loading 0: 24%|██▍ | 88/363 [00:05<00:17, 15.73it/s] Loading 0: 26%|██▌ | 95/363 [00:05<00:13, 19.80it/s] Loading 0: 28%|██▊ | 102/363 [00:05<00:10, 24.30it/s] Loading 0: 30%|███ | 109/363 [00:05<00:08, 28.65it/s] Loading 0: 31%|███▏ | 114/363 [00:06<00:20, 12.26it/s] Loading 0: 33%|███▎ | 119/363 [00:06<00:16, 14.73it/s] Loading 0: 35%|███▍ | 126/363 [00:06<00:12, 19.02it/s] Loading 0: 37%|███▋ | 133/363 [00:07<00:09, 23.79it/s] Loading 0: 39%|███▊ | 140/363 [00:07<00:07, 28.31it/s] Loading 0: 40%|███▉ | 145/363 [00:08<00:17, 12.55it/s] Loading 0: 42%|████▏ | 151/363 [00:08<00:13, 15.80it/s] Loading 0: 44%|████▎ | 158/363 [00:08<00:10, 19.99it/s] Loading 0: 45%|████▌ | 165/363 [00:08<00:08, 24.42it/s] Loading 0: 47%|████▋ | 172/363 [00:08<00:06, 28.27it/s] Loading 0: 49%|████▉ | 177/363 [00:10<00:15, 12.36it/s] Loading 0: 50%|█████ | 182/363 [00:10<00:12, 14.59it/s] Loading 0: 52%|█████▏ | 189/363 [00:10<00:09, 18.87it/s] Loading 0: 54%|█████▍ | 196/363 [00:10<00:07, 23.46it/s] Loading 0: 56%|█████▌ | 203/363 [00:10<00:05, 27.66it/s] Loading 0: 57%|█████▋ | 208/363 [00:11<00:12, 12.30it/s] Loading 0: 59%|█████▉ | 214/363 [00:11<00:09, 15.51it/s] Loading 0: 61%|██████ | 221/363 [00:12<00:07, 19.93it/s] Loading 0: 63%|██████▎ | 228/363 [00:12<00:05, 24.41it/s] Loading 0: 65%|██████▍ | 235/363 [00:12<00:04, 28.85it/s] Loading 0: 66%|██████▌ | 240/363 [00:13<00:09, 12.56it/s] Loading 0: 67%|██████▋ | 245/363 [00:13<00:07, 14.99it/s] Loading 0: 69%|██████▉ | 252/363 [00:13<00:05, 19.54it/s] Loading 0: 71%|███████▏ | 259/363 [00:13<00:04, 23.94it/s] Loading 0: 73%|███████▎ | 266/363 [00:14<00:03, 27.97it/s] Loading 0: 75%|███████▍ | 271/363 [00:15<00:07, 12.53it/s] Loading 0: 76%|███████▋ | 277/363 [00:15<00:05, 15.61it/s]
Job rica40325-filter-mulsft-88200-v2-mkmlizer completed after 145.81s with status: succeeded
Stopping job with name rica40325-filter-mulsft-88200-v2-mkmlizer
Pipeline stage MKMLizer completed in 146.31s
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-88200-v2
Waiting for inference service rica40325-filter-mulsft-88200-v2 to be ready
Inference service rica40325-filter-mulsft-88200-v2 ready after 120.56228828430176s
Pipeline stage MKMLDeployer completed in 121.15s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.322706937789917s
Received healthy response to inference request in 1.697554111480713s
Received healthy response to inference request in 1.5435097217559814s
Received healthy response to inference request in 1.722264051437378s
Received healthy response to inference request in 1.4850890636444092s
5 requests
0 failed requests
5th percentile: 1.4967731952667236
10th percentile: 1.508457326889038
20th percentile: 1.531825590133667
30th percentile: 1.5743185997009277
40th percentile: 1.6359363555908204
50th percentile: 1.697554111480713
60th percentile: 1.707438087463379
70th percentile: 1.7173220634460449
80th percentile: 1.8423526287078857
90th percentile: 2.0825297832489014
95th percentile: 2.202618360519409
99th percentile: 2.2986892223358155
mean time: 1.7542247772216797
Pipeline stage StressChecker completed in 10.25s
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 0.73s
Shutdown handler de-registered
rica40325-filter-mulsft_88200_v2 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
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 2877.33s
Shutdown handler de-registered
rica40325-filter-mulsft_88200_v2 status is now inactive due to auto deactivation removed underperforming models
rica40325-filter-mulsft_88200_v2 status is now torndown due to DeploymentManager action