developer_uid: RandomForest1024
submission_id: randomforest1024-v25_v3
model_name: randomforest1024-v25_v3
model_group: RandomForest1024/V25
status: torndown
timestamp: 2025-02-10T15:54:22+00:00
num_battles: 10840
num_wins: 5094
celo_rating: 1243.84
family_friendly_score: 0.5938
family_friendly_standard_error: 0.006945524602216884
submission_type: basic
model_repo: RandomForest1024/V25
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
display_name: randomforest1024-v25_v3
is_internal_developer: False
language_model: RandomForest1024/V25
model_size: 13B
ranking_group: single
us_pacific_date: 2025-02-10
win_ratio: 0.46992619926199264
generation_params: {'temperature': 0.7, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 50, 'presence_penalty': 0.3, 'frequency_penalty': 0.3, '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': '{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 randomforest1024-v25-v3-mkmlizer
Waiting for job on randomforest1024-v25-v3-mkmlizer to finish
randomforest1024-v25-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
randomforest1024-v25-v3-mkmlizer: ║     _____            __           __                                ║
randomforest1024-v25-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
randomforest1024-v25-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
randomforest1024-v25-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
randomforest1024-v25-v3-mkmlizer: ║       /___/                                                         ║
randomforest1024-v25-v3-mkmlizer: ║                                                                     ║
randomforest1024-v25-v3-mkmlizer: ║  Version: 0.11.12                                                   ║
randomforest1024-v25-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
randomforest1024-v25-v3-mkmlizer: ║  https://mk1.ai                                                     ║
randomforest1024-v25-v3-mkmlizer: ║                                                                     ║
randomforest1024-v25-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
randomforest1024-v25-v3-mkmlizer: ║  belonging to:                                                      ║
randomforest1024-v25-v3-mkmlizer: ║                                                                     ║
randomforest1024-v25-v3-mkmlizer: ║  Chai Research Corp.                                                ║
randomforest1024-v25-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
randomforest1024-v25-v3-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
randomforest1024-v25-v3-mkmlizer: ║                                                                     ║
randomforest1024-v25-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
randomforest1024-v25-v3-mkmlizer: Downloaded to shared memory in 32.602s
randomforest1024-v25-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp07r3eiat, device:0
randomforest1024-v25-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
randomforest1024-v25-v3-mkmlizer: quantized model in 35.280s
randomforest1024-v25-v3-mkmlizer: Processed model RandomForest1024/V25 in 67.883s
randomforest1024-v25-v3-mkmlizer: creating bucket guanaco-mkml-models
randomforest1024-v25-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
randomforest1024-v25-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/randomforest1024-v25-v3
randomforest1024-v25-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/randomforest1024-v25-v3/config.json
randomforest1024-v25-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/randomforest1024-v25-v3/special_tokens_map.json
randomforest1024-v25-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/randomforest1024-v25-v3/tokenizer_config.json
randomforest1024-v25-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/randomforest1024-v25-v3/tokenizer.json
randomforest1024-v25-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/randomforest1024-v25-v3/flywheel_model.0.safetensors
randomforest1024-v25-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 31.28it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 52.78it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:06, 49.68it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:06, 50.87it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 53.18it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 48.75it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:06, 48.83it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:06, 50.63it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 44.65it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 35.30it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 34.28it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 41.21it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 41.68it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 42.03it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:05, 46.95it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 46.18it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:05, 45.77it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:04, 54.25it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 48.22it/s]
Loading 0:  33%|███▎      | 121/363 [00:02<00:05, 46.89it/s]
Loading 0:  35%|███▍      | 127/363 [00:02<00:05, 42.25it/s]
Loading 0:  37%|███▋      | 134/363 [00:02<00:04, 48.33it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:04, 48.77it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 34.76it/s]
Loading 0:  42%|████▏     | 151/363 [00:03<00:05, 35.42it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 38.22it/s]
Loading 0:  44%|████▍     | 161/363 [00:03<00:05, 38.17it/s]
Loading 0:  46%|████▌     | 166/363 [00:03<00:05, 38.80it/s]
Loading 0:  47%|████▋     | 171/363 [00:03<00:04, 40.79it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 36.56it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 43.57it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:03, 44.49it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 45.45it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 44.52it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 44.01it/s]
Loading 0:  58%|█████▊    | 210/363 [00:04<00:03, 47.46it/s]
Loading 0:  59%|█████▉    | 215/363 [00:04<00:03, 47.10it/s]
Loading 0:  61%|██████    | 222/363 [00:05<00:02, 47.65it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:03, 35.21it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:03, 34.27it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 39.86it/s]
Loading 0:  67%|██████▋   | 242/363 [00:05<00:02, 40.77it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:02, 41.92it/s]
Loading 0:  70%|██████▉   | 253/363 [00:05<00:02, 42.23it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 42.52it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 48.02it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:01, 46.76it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:01, 45.20it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 49.77it/s]
Loading 0:  80%|███████▉  | 289/363 [00:06<00:01, 48.16it/s]
Loading 0:  81%|████████  | 294/363 [00:06<00:01, 46.41it/s]
Loading 0:  82%|████████▏ | 299/363 [00:06<00:01, 46.12it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:23,  2.54it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:16,  3.28it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:11,  4.27it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:06,  7.09it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:03,  9.59it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:02, 12.01it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 16.84it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 20.74it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 24.23it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 30.91it/s]
Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 33.99it/s]
                                                            

Job randomforest1024-v25-v3-mkmlizer completed after 94.01s with status: succeeded
Stopping job with name randomforest1024-v25-v3-mkmlizer
Pipeline stage MKMLizer completed in 94.49s
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 randomforest1024-v25-v3
Waiting for inference service randomforest1024-v25-v3 to be ready
Inference service randomforest1024-v25-v3 ready after 190.92890191078186s
Pipeline stage MKMLDeployer completed in 191.73s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0232019424438477s
Received healthy response to inference request in 1.6384570598602295s
Received healthy response to inference request in 1.8941569328308105s
Received healthy response to inference request in 1.7121429443359375s
Received healthy response to inference request in 1.6790008544921875s
5 requests
0 failed requests
5th percentile: 1.646565818786621
10th percentile: 1.6546745777130127
20th percentile: 1.670892095565796
30th percentile: 1.6856292724609374
40th percentile: 1.6988861083984375
50th percentile: 1.7121429443359375
60th percentile: 1.7849485397338867
70th percentile: 1.8577541351318358
80th percentile: 1.919965934753418
90th percentile: 1.971583938598633
95th percentile: 1.9973929405212403
99th percentile: 2.018040142059326
mean time: 1.7893919467926025
Pipeline stage StressChecker completed in 10.36s
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 0.67s
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 0.63s
Shutdown handler de-registered
randomforest1024-v25_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 3964.16s
Shutdown handler de-registered
randomforest1024-v25_v3 status is now inactive due to auto deactivation removed underperforming models
randomforest1024-v25_v3 status is now torndown due to DeploymentManager action
randomforest1024-v25_v3 status is now torndown due to DeploymentManager action
randomforest1024-v25_v3 status is now torndown due to DeploymentManager action