rica40325-filter-mulsft_36664

developer_uid: rica40325

submission_id: rica40325-filter-mulsft_36664_v3

model_name: rica40325-filter-mulsft_36664_v3

model_group: rica40325/filter-mulsft-

status: torndown

timestamp: 2025-06-24T12:50:31+00:00

num_battles: 7812

num_wins: 3351

celo_rating: 1239.52

family_friendly_score: 0.5424

family_friendly_standard_error: 0.0070455977744972075

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

latencies: [{'batch_size': 1, 'throughput': 0.5993042527633997, 'latency_mean': 1.6684981715679168, 'latency_p50': 1.6616073846817017, 'latency_p90': 1.8259747505187989}, {'batch_size': 3, 'throughput': 1.0913305764437187, 'latency_mean': 2.7365042865276337, 'latency_p50': 2.710023880004883, 'latency_p90': 3.010512852668762}, {'batch_size': 5, 'throughput': 1.3081091979936605, 'latency_mean': 3.8041553616523744, 'latency_p50': 3.7746130228042603, 'latency_p90': 4.290639400482178}, {'batch_size': 6, 'throughput': 1.3665392686509577, 'latency_mean': 4.363025233745575, 'latency_p50': 4.353713750839233, 'latency_p90': 4.900848436355591}, {'batch_size': 8, 'throughput': 1.4207012449398067, 'latency_mean': 5.588887726068497, 'latency_p50': 5.609935879707336, 'latency_p90': 6.288690900802612}, {'batch_size': 10, 'throughput': 1.4622209426217858, 'latency_mean': 6.778645449876786, 'latency_p50': 6.802155494689941, 'latency_p90': 7.615538287162781}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rica40325-filter-mulsft_36664_v3

is_internal_developer: False

language_model: rica40325/filter-mulsft-v5-200

model_size: 13B

ranking_group: single

throughput_3p7s: 1.3

us_pacific_date: 2025-06-24

win_ratio: 0.4289554531490015

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': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', '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 rica40325-filter-mulsft-36664-v3-mkmlizer
Waiting for job on rica40325-filter-mulsft-36664-v3-mkmlizer to finish
Failed to get response for submission chaiml-giyu-disabled-hu_13897_v2: ('http://chaiml-giyu-disabled-hu-13897-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
rica40325-filter-mulsft-36664-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-filter-mulsft-36664-v3-mkmlizer: ║                                                                     ║
rica40325-filter-mulsft-36664-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rica40325-filter-mulsft-36664-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rica40325-filter-mulsft-36664-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rica40325-filter-mulsft-36664-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rica40325-filter-mulsft-36664-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rica40325-filter-mulsft-36664-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rica40325-filter-mulsft-36664-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rica40325-filter-mulsft-36664-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rica40325-filter-mulsft-36664-v3-mkmlizer: ║                                                                     ║
rica40325-filter-mulsft-36664-v3-mkmlizer: ║  Version: 0.29.3                                                    ║
rica40325-filter-mulsft-36664-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rica40325-filter-mulsft-36664-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rica40325-filter-mulsft-36664-v3-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-filter-mulsft-36664-v3-mkmlizer: ║                                                                     ║
rica40325-filter-mulsft-36664-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-filter-mulsft-36664-v3-mkmlizer: ║  belonging to:                                                      ║
rica40325-filter-mulsft-36664-v3-mkmlizer: ║                                                                     ║
rica40325-filter-mulsft-36664-v3-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-filter-mulsft-36664-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-filter-mulsft-36664-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rica40325-filter-mulsft-36664-v3-mkmlizer: ║                                                                     ║
rica40325-filter-mulsft-36664-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-filter-mulsft-36664-v3-mkmlizer: Downloaded to shared memory in 67.615s
rica40325-filter-mulsft-36664-v3-mkmlizer: Checking if rica40325/filter-mulsft-v5-200 already exists in ChaiML
rica40325-filter-mulsft-36664-v3-mkmlizer: Creating repo ChaiML/filter-mulsft-v5-200 and uploading /tmp/tmpfelcaamq to it
Failed to get response for submission chaiml-giyu-disabled-hu_13897_v2: ('http://chaiml-giyu-disabled-hu-13897-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission chaiml-giyu-disabled-hu_13897_v2: ('http://chaiml-giyu-disabled-hu-13897-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
rica40325-filter-mulsft-36664-v3-mkmlizer: 
  0%|          | 0/12 [00:00<?, ?it/s]
  8%|▊         | 1/12 [00:08<01:32,  8.43s/it]
 17%|█▋        | 2/12 [00:13<01:04,  6.48s/it]
 25%|██▌       | 3/12 [00:20<00:59,  6.66s/it]
 33%|███▎      | 4/12 [00:26<00:50,  6.27s/it]
 42%|████▏     | 5/12 [00:30<00:39,  5.60s/it]
 50%|█████     | 6/12 [00:38<00:39,  6.55s/it]
 58%|█████▊    | 7/12 [00:43<00:29,  5.99s/it]
 67%|██████▋   | 8/12 [00:47<00:21,  5.30s/it]
 75%|███████▌  | 9/12 [00:51<00:14,  4.87s/it]
 83%|████████▎ | 10/12 [00:55<00:09,  4.66s/it]
 92%|█████████▏| 11/12 [00:57<00:03,  3.67s/it]
100%|██████████| 12/12 [00:57<00:00,  2.75s/it]
100%|██████████| 12/12 [00:57<00:00,  4.81s/it]
rica40325-filter-mulsft-36664-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfelcaamq, device:0
rica40325-filter-mulsft-36664-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-filter-mulsft-36664-v3-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-v3-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
rica40325-filter-mulsft-36664-v3-mkmlizer: quantized model in 39.049s
rica40325-filter-mulsft-36664-v3-mkmlizer: Processed model rica40325/filter-mulsft-v5-200 in 213.452s
rica40325-filter-mulsft-36664-v3-mkmlizer: creating bucket guanaco-mkml-models
rica40325-filter-mulsft-36664-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-filter-mulsft-36664-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-filter-mulsft-36664-v3
rica40325-filter-mulsft-36664-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-filter-mulsft-36664-v3/config.json
rica40325-filter-mulsft-36664-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-filter-mulsft-36664-v3/special_tokens_map.json
rica40325-filter-mulsft-36664-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-filter-mulsft-36664-v3/tokenizer_config.json
rica40325-filter-mulsft-36664-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-filter-mulsft-36664-v3/tokenizer.json
rica40325-filter-mulsft-36664-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-filter-mulsft-36664-v3/flywheel_model.0.safetensors
rica40325-filter-mulsft-36664-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:07, 44.77it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:07, 49.64it/s]
Loading 0:   6%|▌         | 20/363 [00:01<00:28, 12.00it/s]
Loading 0:   7%|▋         | 25/363 [00:01<00:21, 15.61it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.78it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 27.17it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:09, 32.84it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:24, 12.72it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:19, 15.51it/s]
Loading 0:  17%|█▋        | 63/363 [00:03<00:14, 20.42it/s]
Loading 0:  19%|█▉        | 70/363 [00:03<00:11, 25.59it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:09, 30.11it/s]
Loading 0:  23%|██▎       | 82/363 [00:04<00:21, 12.95it/s]
Loading 0:  24%|██▍       | 88/363 [00:04<00:16, 16.73it/s]
Loading 0:  26%|██▌       | 95/363 [00:04<00:12, 21.94it/s]
Loading 0:  28%|██▊       | 102/363 [00:04<00:09, 26.83it/s]
Loading 0:  30%|███       | 109/363 [00:05<00:08, 30.64it/s]
Loading 0:  31%|███▏      | 114/363 [00:06<00:19, 13.03it/s]
Loading 0:  33%|███▎      | 119/363 [00:06<00:15, 15.81it/s]
Loading 0:  35%|███▍      | 126/363 [00:06<00:11, 20.60it/s]
Loading 0:  37%|███▋      | 133/363 [00:06<00:09, 25.33it/s]
Loading 0:  39%|███▊      | 140/363 [00:06<00:07, 30.39it/s]
Loading 0:  40%|███▉      | 145/363 [00:07<00:16, 13.22it/s]
Loading 0:  42%|████▏     | 151/363 [00:07<00:12, 16.88it/s]
Loading 0:  44%|████▎     | 158/363 [00:07<00:09, 21.98it/s]
Loading 0:  45%|████▌     | 165/363 [00:08<00:07, 27.34it/s]
Loading 0:  47%|████▋     | 172/363 [00:08<00:05, 32.60it/s]
Loading 0:  49%|████▉     | 178/363 [00:09<00:13, 13.84it/s]
Loading 0:  50%|█████     | 182/363 [00:09<00:11, 15.65it/s]
Loading 0:  52%|█████▏    | 189/363 [00:09<00:08, 20.33it/s]
Loading 0:  54%|█████▍    | 196/363 [00:09<00:06, 24.99it/s]
Loading 0:  56%|█████▌    | 203/363 [00:09<00:05, 29.82it/s]
Loading 0:  57%|█████▋    | 208/363 [00:11<00:12, 12.04it/s]
Loading 0:  59%|█████▉    | 214/363 [00:11<00:09, 15.27it/s]
Loading 0:  61%|██████    | 221/363 [00:11<00:07, 19.90it/s]
Loading 0:  63%|██████▎   | 228/363 [00:11<00:05, 24.64it/s]
Loading 0:  65%|██████▍   | 235/363 [00:11<00:04, 29.24it/s]
Loading 0:  66%|██████▌   | 240/363 [00:12<00:09, 13.12it/s]
Loading 0:  67%|██████▋   | 245/363 [00:12<00:07, 15.60it/s]
Loading 0:  69%|██████▉   | 252/363 [00:12<00:05, 20.20it/s]
Loading 0:  71%|███████▏  | 259/363 [00:13<00:04, 24.78it/s]
Loading 0:  73%|███████▎  | 266/363 [00:13<00:03, 30.09it/s]
Loading 0:  75%|███████▍  | 271/363 [00:14<00:07, 13.02it/s]
Loading 0:  76%|███████▋  | 277/363 [00:14<00:05, 16.52it/s]
                                                            
Job rica40325-filter-mulsft-36664-v3-mkmlizer completed after 248.08s with status: succeeded
Stopping job with name rica40325-filter-mulsft-36664-v3-mkmlizer
Pipeline stage MKMLizer completed in 248.57s
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 rica40325-filter-mulsft-36664-v3
Waiting for inference service rica40325-filter-mulsft-36664-v3 to be ready
Failed to get response for submission chaiml-giyu-disabled-hu_13897_v2: ('http://chaiml-giyu-disabled-hu-13897-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service rica40325-filter-mulsft-36664-v3 ready after 130.48265027999878s
Pipeline stage MKMLDeployer completed in 131.19s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4363765716552734s
Received healthy response to inference request in 2.235698938369751s
Received healthy response to inference request in 1.730884313583374s
Received healthy response to inference request in 1.5879135131835938s
Received healthy response to inference request in 1.6180245876312256s
5 requests
0 failed requests
5th percentile: 1.5939357280731201
10th percentile: 1.5999579429626465
20th percentile: 1.6120023727416992
30th percentile: 1.6405965328216552
40th percentile: 1.6857404232025146
50th percentile: 1.730884313583374
60th percentile: 1.9328101634979247
70th percentile: 2.1347360134124753
80th percentile: 2.2758344650268554
90th percentile: 2.3561055183410646
95th percentile: 2.396241044998169
99th percentile: 2.4283494663238527
mean time: 1.9217795848846435
Pipeline stage StressChecker completed in 11.26s
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 0.80s
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 0.67s
Shutdown handler de-registered
rica40325-filter-mulsft_36664_v3 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 5178.68s
Shutdown handler de-registered
rica40325-filter-mulsft_36664_v3 status is now inactive due to auto deactivation removed underperforming models
rica40325-filter-mulsft_36664_v3 status is now torndown due to DeploymentManager action