developer_uid: rirv938
submission_id: chaiml-llama31-mer-v2-_44570_v68
model_name: chaiml-llama31-mer-v2-_44570_v68
model_group: ChaiML/llama31-mer-v2-tr
status: inactive
timestamp: 2026-02-06T00:16:59+00:00
num_battles: 11226
num_wins: 5675
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/llama31-mer-v2-try1-new8m-filterv3-full-512seq-bestep-572
model_architecture: LlamaForSequenceClassification
model_num_parameters: 8030261248.0
best_of: 1
max_input_tokens: 1024
max_output_tokens: 1
reward_model: default
display_name: chaiml-llama31-mer-v2-_44570_v68
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/llama31-mer-v2-try1-new8m-filterv3-full-512seq-bestep-572
model_size: 8B
ranking_group: single
us_pacific_date: 2026-02-05
win_ratio: 0.5055228932834491
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': 1, 'max_output_tokens': 1}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '', 'truncate_by_message': True}
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 chaiml-llama31-mer-v2-44570-v68-mkmlizer
Waiting for job on chaiml-llama31-mer-v2-44570-v68-mkmlizer to finish
chaiml-llama-8b-202503-16869-v35-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-llama-8b-202503-16869-v35-mkmlizer: bash: no job control in this shell
chaiml-llama31-mer-v2-44570-v68-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-llama31-mer-v2-44570-v68-mkmlizer: bash: no job control in this shell
chaiml-llama-8b-202503-16869-v35-mkmlizer: /root/miniconda3/envs/nvidia/lib/python3.11/site-packages/mk1/__init__.py:1: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
chaiml-llama-8b-202503-16869-v35-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-llama-8b-202503-16869-v35-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-202503-16869-v35-mkmlizer: ║                                                                     ║
chaiml-llama-8b-202503-16869-v35-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-llama-8b-202503-16869-v35-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-llama-8b-202503-16869-v35-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-llama-8b-202503-16869-v35-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-llama-8b-202503-16869-v35-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-llama-8b-202503-16869-v35-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-llama-8b-202503-16869-v35-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-llama-8b-202503-16869-v35-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-llama-8b-202503-16869-v35-mkmlizer: ║                                                                     ║
chaiml-llama-8b-202503-16869-v35-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-llama-8b-202503-16869-v35-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-llama-8b-202503-16869-v35-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-llama-8b-202503-16869-v35-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-llama-8b-202503-16869-v35-mkmlizer: ║                                                                     ║
chaiml-llama-8b-202503-16869-v35-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-llama-8b-202503-16869-v35-mkmlizer: ║  belonging to:                                                      ║
chaiml-llama-8b-202503-16869-v35-mkmlizer: ║                                                                     ║
chaiml-llama-8b-202503-16869-v35-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-llama-8b-202503-16869-v35-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-llama-8b-202503-16869-v35-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-llama-8b-202503-16869-v35-mkmlizer: ║                                                                     ║
chaiml-llama-8b-202503-16869-v35-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama31-mer-v2-44570-v68-mkmlizer: /root/miniconda3/envs/nvidia/lib/python3.11/site-packages/mk1/__init__.py:1: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
chaiml-llama31-mer-v2-44570-v68-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-llama31-mer-v2-44570-v68-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama31-mer-v2-44570-v68-mkmlizer: ║                                                                     ║
chaiml-llama31-mer-v2-44570-v68-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-llama31-mer-v2-44570-v68-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-llama31-mer-v2-44570-v68-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-llama31-mer-v2-44570-v68-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-llama31-mer-v2-44570-v68-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-llama31-mer-v2-44570-v68-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-llama31-mer-v2-44570-v68-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-llama31-mer-v2-44570-v68-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-llama31-mer-v2-44570-v68-mkmlizer: ║                                                                     ║
chaiml-llama31-mer-v2-44570-v68-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-llama31-mer-v2-44570-v68-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-llama31-mer-v2-44570-v68-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-llama31-mer-v2-44570-v68-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-llama31-mer-v2-44570-v68-mkmlizer: ║                                                                     ║
chaiml-llama31-mer-v2-44570-v68-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-llama31-mer-v2-44570-v68-mkmlizer: ║  belonging to:                                                      ║
chaiml-llama31-mer-v2-44570-v68-mkmlizer: ║                                                                     ║
chaiml-llama31-mer-v2-44570-v68-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-llama31-mer-v2-44570-v68-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-llama31-mer-v2-44570-v68-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-llama31-mer-v2-44570-v68-mkmlizer: ║                                                                     ║
chaiml-llama31-mer-v2-44570-v68-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama31-mer-v2-44570-v68-mkmlizer: Downloaded to shared memory in 14.696s
chaiml-llama31-mer-v2-44570-v68-mkmlizer: Checking if ChaiML/llama31-mer-v2-try1-new8m-filterv3-full-512seq-bestep-572 already exists in ChaiML
chaiml-llama31-mer-v2-44570-v68-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpuq4jjxbe, device:0
chaiml-llama31-mer-v2-44570-v68-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama-8b-202503-16869-v35-mkmlizer: Downloaded to shared memory in 21.274s
chaiml-llama-8b-202503-16869-v35-mkmlizer: Checking if ChaiML/llama_8b_202503_1m_nemo_safety already exists in ChaiML
chaiml-llama-8b-202503-16869-v35-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpq1hckwr7, device:0
chaiml-llama-8b-202503-16869-v35-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama31-mer-v2-44570-v68-mkmlizer: 
Loading 0:   0%|          | 0.00/291 [00:00<?, ?it/s]
Loading 0:  16%|█▌        | 46.0/291 [00:01<00:05, 43.9it/s]
Loading 0:  16%|█▌        | 46.0/291 [00:01<00:05, 43.9it/s]
Loading 0:  29%|██▊       | 83.0/291 [00:02<00:05, 39.8it/s]
Loading 0:  29%|██▊       | 83.0/291 [00:02<00:05, 39.8it/s]
Loading 0:  44%|████▎     | 127/291 [00:03<00:03, 41.4it/s] 
Loading 0:  44%|████▎     | 127/291 [00:03<00:03, 41.4it/s]
Loading 0:  59%|█████▉    | 172/291 [00:04<00:02, 42.8it/s]
Loading 0:  59%|█████▉    | 172/291 [00:04<00:02, 42.8it/s]
Loading 0:  71%|███████   | 206/291 [00:05<00:02, 39.6it/s]
Loading 0:  71%|███████   | 206/291 [00:05<00:02, 39.6it/s]
Loading 0:  85%|████████▌ | 248/291 [00:06<00:01, 39.8it/s]
Loading 0:  85%|████████▌ | 248/291 [00:06<00:01, 39.8it/s]
Loading 0:  99%|█████████▊| 287/291 [00:07<00:00, 39.0it/s]
Loading 0:  99%|█████████▊| 287/291 [00:07<00:00, 39.0it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 38.8it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 38.8it/s]
                                                           

Loading 0: 100%|██████████| 291/291 [00:07<00:00, 40.0it/s]
chaiml-llama-8b-202503-16869-v35-mkmlizer: 
Loading 0:   0%|          | 0.00/291 [00:00<?, ?it/s]
Loading 0:  13%|█▎        | 37.0/291 [00:01<00:07, 34.0it/s]
Loading 0:  13%|█▎        | 37.0/291 [00:01<00:07, 34.0it/s]
Loading 0:  24%|██▍       | 71.0/291 [00:02<00:06, 33.9it/s]
Loading 0:  24%|██▍       | 71.0/291 [00:02<00:06, 33.9it/s]
Loading 0:  33%|███▎      | 95.0/291 [00:03<00:06, 28.6it/s]
Loading 0:  33%|███▎      | 95.0/291 [00:03<00:06, 28.6it/s]
Loading 0:  45%|████▍     | 130/291 [00:04<00:05, 31.0it/s] 
Loading 0:  45%|████▍     | 130/291 [00:04<00:05, 31.0it/s]
Loading 0:  54%|█████▍    | 158/291 [00:05<00:04, 29.8it/s]
Loading 0:  54%|█████▍    | 158/291 [00:05<00:04, 29.8it/s]
Loading 0:  65%|██████▍   | 188/291 [00:06<00:03, 29.8it/s]
Loading 0:  65%|██████▍   | 188/291 [00:06<00:03, 29.8it/s]
Loading 0:  76%|███████▌  | 221/291 [00:07<00:02, 29.9it/s]
Loading 0:  76%|███████▌  | 221/291 [00:07<00:02, 29.9it/s]
Loading 0:  88%|████████▊ | 257/291 [00:08<00:01, 30.9it/s]
Loading 0:  88%|████████▊ | 257/291 [00:08<00:01, 30.9it/s]
Loading 0:  99%|█████████▊| 287/291 [00:09<00:00, 29.8it/s]
Loading 0:  99%|█████████▊| 287/291 [00:09<00:00, 29.8it/s]
Loading 0: 100%|██████████| 291/291 [00:09<00:00, 29.7it/s]
Loading 0: 100%|██████████| 291/291 [00:09<00:00, 29.7it/s]
                                                           

Loading 0: 100%|██████████| 291/291 [00:09<00:00, 30.3it/s]
chaiml-llama31-mer-v2-44570-v68-mkmlizer: quantized model in 18.054s
chaiml-llama31-mer-v2-44570-v68-mkmlizer: Processed model ChaiML/llama31-mer-v2-try1-new8m-filterv3-full-512seq-bestep-572 in 32.751s
chaiml-llama31-mer-v2-44570-v68-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama31-mer-v2-44570-v68-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama31-mer-v2-44570-v68-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama31-mer-v2-44570-v68/nvidia
chaiml-llama31-mer-v2-44570-v68-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama31-mer-v2-44570-v68/nvidia/config.json
chaiml-llama-8b-202503-16869-v35-mkmlizer: quantized model in 21.686s
chaiml-llama31-mer-v2-44570-v68-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama31-mer-v2-44570-v68/nvidia/special_tokens_map.json
chaiml-llama-8b-202503-16869-v35-mkmlizer: Processed model ChaiML/llama_8b_202503_1m_nemo_safety in 42.960s
chaiml-llama31-mer-v2-44570-v68-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama31-mer-v2-44570-v68/nvidia/tokenizer_config.json
chaiml-llama-8b-202503-16869-v35-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama31-mer-v2-44570-v68-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama31-mer-v2-44570-v68/nvidia/tokenizer.json
chaiml-llama-8b-202503-16869-v35-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-202503-16869-v35-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-202503-16869-v35/nvidia
chaiml-llama-8b-202503-16869-v35-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama-8b-202503-16869-v35/nvidia/config.json
chaiml-llama-8b-202503-16869-v35-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-202503-16869-v35/nvidia/special_tokens_map.json
chaiml-llama-8b-202503-16869-v35-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama-8b-202503-16869-v35/nvidia/tokenizer_config.json
chaiml-llama-8b-202503-16869-v35-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama-8b-202503-16869-v35/nvidia/tokenizer.json
chaiml-llama31-mer-v2-44570-v68-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama31-mer-v2-44570-v68/nvidia/flywheel_model.0.safetensors
Job chaiml-llama31-mer-v2-44570-v68-mkmlizer completed after 123.83s with status: succeeded
Stopping job with name chaiml-llama31-mer-v2-44570-v68-mkmlizer
Pipeline stage MKMLizer completed in 125.30s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.36s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-llama31-mer-v2-44570-v68
Waiting for inference service chaiml-llama31-mer-v2-44570-v68 to be ready
chaiml-llama-8b-202503-16869-v35-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama-8b-202503-16869-v35/nvidia/flywheel_model.0.safetensors
Job chaiml-llama-8b-202503-16869-v35-mkmlizer completed after 144.21s with status: succeeded
Stopping job with name chaiml-llama-8b-202503-16869-v35-mkmlizer
Pipeline stage MKMLizer completed in 145.79s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.38s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-llama-8b-202503-16869-v35
Waiting for inference service chaiml-llama-8b-202503-16869-v35 to be ready
Inference service chaiml-llama31-mer-v2-44570-v68 ready after 162.23174905776978s
Pipeline stage MKMLDeployer completed in 163.62s
run pipeline stage %s
Running pipeline stage StressChecker
Inference service chaiml-llama-8b-202503-16869-v35 ready after 152.93235731124878s
Pipeline stage MKMLDeployer completed in 154.33s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 6.111316919326782s
Received healthy response to inference request in 4.018789529800415s
Received healthy response to inference request in 4.111780881881714s
Received healthy response to inference request in 5.805490970611572s
Received healthy response to inference request in 4.6345226764678955s
Received healthy response to inference request in 7.415199279785156s
Received healthy response to inference request in 6.451483488082886s
Received healthy response to inference request in 6.650815725326538s
Received healthy response to inference request in 4.4973838329315186s
5 requests
0 failed requests
5th percentile: 4.524811601638794
10th percentile: 4.5522393703460695
20th percentile: 4.6070949077606205
30th percentile: 4.8687163352966305
40th percentile: 5.337103652954101
50th percentile: 5.805490970611572
60th percentile: 5.927821350097656
70th percentile: 6.050151729583741
80th percentile: 6.179350233078003
90th percentile: 6.315416860580444
95th percentile: 6.383450174331665
99th percentile: 6.4378768253326415
mean time: 5.500039577484131
%s, retrying in %s seconds...
Received healthy response to inference request in 8.002172231674194s
5 requests
0 failed requests
5th percentile: 4.037387800216675
10th percentile: 4.055986070632935
20th percentile: 4.093182611465454
30th percentile: 4.619587850570679
40th percentile: 5.635201787948609
50th percentile: 6.650815725326538
60th percentile: 6.9565691471099855
70th percentile: 7.262322568893432
80th percentile: 7.532593870162964
90th percentile: 7.767383050918579
95th percentile: 7.884777641296386
99th percentile: 7.978693313598633
mean time: 6.0397515296936035
Received healthy response to inference request in 4.481780052185059s
%s, retrying in %s seconds...
Received healthy response to inference request in 4.407252311706543s
Received healthy response to inference request in 6.037752866744995s
Received healthy response to inference request in 3.3308634757995605s
Received healthy response to inference request in 5.251110792160034s
Received healthy response to inference request in 4.076992034912109s
Received healthy response to inference request in 6.252051115036011s
Received healthy response to inference request in 4.531184911727905s
Received healthy response to inference request in 2.764632225036621s
5 requests
0 failed requests
5th percentile: 2.877878475189209
10th percentile: 2.991124725341797
20th percentile: 3.217617225646973
30th percentile: 3.5610467910766603
40th percentile: 4.021413421630859
50th percentile: 4.481780052185059
60th percentile: 5.104169178009033
70th percentile: 5.7265583038330075
80th percentile: 6.080612516403198
90th percentile: 6.166331815719604
95th percentile: 6.209191465377808
99th percentile: 6.24347918510437
mean time: 4.573415946960449
Pipeline stage StressChecker completed in 60.04s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Received healthy response to inference request in 4.317544221878052s
5 requests
0 failed requests
triggered trigger_guanaco_pipeline args=%s
5th percentile: 4.125102472305298
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 1.76s
10th percentile: 4.173212909698487
run pipeline stage %s
20th percentile: 4.269433784484863
Running pipeline stage TriggerMKMLProfilingPipeline
30th percentile: 4.33548583984375
run_pipeline:run_in_cloud %s
40th percentile: 4.371369075775147
starting trigger_guanaco_pipeline args=%s
50th percentile: 4.407252311706543
60th percentile: 4.4568253517150875
70th percentile: 4.506398391723633
triggered trigger_guanaco_pipeline args=%s
80th percentile: 4.675170087814331
Pipeline stage TriggerMKMLProfilingPipeline completed in 2.01s
90th percentile: 4.963140439987183
Shutdown handler de-registered
95th percentile: 5.107125616073608
chaiml-llama31-mer-v2-_44570_v68 status is now deployed due to DeploymentManager action
99th percentile: 5.222313756942749
chaiml-llama31-mer-v2-_44570_v68 status is now inactive due to auto deactivation removed underperforming models