chaiml-djinn-wishmaster_81119

developer_uid: chai_backend_admin
submission_id: chaiml-djinn-wishmaster_81119_v1
model_name: chaiml-djinn-wishmaster_81119_v1
model_group: ChaiML/Djinn-Wishmaster2
status: inactive
timestamp: 2026-01-10T04:57:01+00:00
num_battles: 15724
num_wins: 7513
celo_rating: 9999.0
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/Djinn-Wishmaster260110041143_sft
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
display_name: chaiml-djinn-wishmaster_81119_v1
is_internal_developer: True
language_model: ChaiML/Djinn-Wishmaster260110041143_sft
model_size: 24B
ranking_group: single
us_pacific_date: 2026-01-09
win_ratio: 0.47780462986517425
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', '</s>', '####\n', '####', 'You:'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}</s>\n', 'user_template': 'You: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
Connection pool is full, discarding connection: %s. Connection pool size: %s
run pipeline %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-djinn-wishmaster-81119-v1-mkmlizer
Waiting for job on chaiml-djinn-wishmaster-81119-v1-mkmlizer to finish
chaiml-djinn-wishmaster-81119-v1-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-djinn-wishmaster-81119-v1-mkmlizer: bash: no job control in this shell
chaiml-djinn-wishmaster-81119-v1-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-djinn-wishmaster-81119-v1-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-djinn-wishmaster-81119-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-djinn-wishmaster-81119-v1-mkmlizer: ║                                                                     ║
chaiml-djinn-wishmaster-81119-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-djinn-wishmaster-81119-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-djinn-wishmaster-81119-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-djinn-wishmaster-81119-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-djinn-wishmaster-81119-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-djinn-wishmaster-81119-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-djinn-wishmaster-81119-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-djinn-wishmaster-81119-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-djinn-wishmaster-81119-v1-mkmlizer: ║                                                                     ║
chaiml-djinn-wishmaster-81119-v1-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-djinn-wishmaster-81119-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-djinn-wishmaster-81119-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-djinn-wishmaster-81119-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-djinn-wishmaster-81119-v1-mkmlizer: ║                                                                     ║
chaiml-djinn-wishmaster-81119-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-djinn-wishmaster-81119-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-djinn-wishmaster-81119-v1-mkmlizer: ║                                                                     ║
chaiml-djinn-wishmaster-81119-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-djinn-wishmaster-81119-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-djinn-wishmaster-81119-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-djinn-wishmaster-81119-v1-mkmlizer: ║                                                                     ║
chaiml-djinn-wishmaster-81119-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-djinn-wishmaster-81119-v1-mkmlizer: Downloaded to shared memory in 66.163s
chaiml-djinn-wishmaster-81119-v1-mkmlizer: Checking if ChaiML/Djinn-Wishmaster260110041143_sft already exists in ChaiML
chaiml-djinn-wishmaster-81119-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8nacw8ai, device:0
chaiml-djinn-wishmaster-81119-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-djinn-wishmaster-81119-v1-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   9%|▉         | 33.0/363 [00:01<00:11, 29.5it/s]
Loading 0:   9%|▉         | 33.0/363 [00:01<00:11, 29.5it/s]
Loading 0:  15%|█▌        | 55.0/363 [00:02<00:12, 24.3it/s]
Loading 0:  15%|█▌        | 55.0/363 [00:02<00:12, 24.3it/s]
Loading 0:  20%|█▉        | 71.0/363 [00:03<00:14, 20.7it/s]
Loading 0:  20%|█▉        | 71.0/363 [00:03<00:14, 20.7it/s]
Loading 0:  27%|██▋       | 99.0/363 [00:04<00:11, 23.4it/s]
Loading 0:  27%|██▋       | 99.0/363 [00:04<00:11, 23.4it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:09, 24.8it/s] 
Loading 0:  35%|███▍      | 127/363 [00:05<00:09, 24.8it/s]
Loading 0:  43%|████▎     | 156/363 [00:06<00:08, 25.8it/s]
Loading 0:  43%|████▎     | 156/363 [00:06<00:08, 25.8it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:06, 26.7it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:06, 26.7it/s]
Loading 0:  52%|█████▏    | 187/363 [00:20<00:06, 26.7it/s]
Loading 0:  55%|█████▌    | 201/363 [00:20<00:33, 4.77it/s]
Loading 0:  55%|█████▌    | 201/363 [00:20<00:33, 4.77it/s]
Loading 0:  62%|██████▏   | 224/363 [00:21<00:22, 6.25it/s]
Loading 0:  62%|██████▏   | 224/363 [00:21<00:22, 6.25it/s]
Loading 0:  70%|██████▉   | 253/363 [00:22<00:12, 8.65it/s]
Loading 0:  70%|██████▉   | 253/363 [00:22<00:12, 8.65it/s]
Loading 0:  77%|███████▋  | 280/363 [00:23<00:07, 11.0it/s]
Loading 0:  77%|███████▋  | 280/363 [00:23<00:07, 11.0it/s]
Loading 0:  84%|████████▍ | 306/363 [00:24<00:04, 13.3it/s]
Loading 0:  84%|████████▍ | 306/363 [00:24<00:04, 13.3it/s]
Loading 0:  93%|█████████▎| 336/363 [00:25<00:01, 16.2it/s]
Loading 0:  93%|█████████▎| 336/363 [00:25<00:01, 16.2it/s]
Loading 0: 100%|█████████▉| 362/363 [00:26<00:00, 18.2it/s]
Loading 0: 100%|█████████▉| 362/363 [00:26<00:00, 18.2it/s]
Loading 0: 100%|██████████| 363/363 [00:26<00:00, 18.2it/s]
                                                           

Loading 0: 100%|██████████| 363/363 [00:26<00:00, 13.5it/s]
chaiml-djinn-wishmaster-81119-v1-mkmlizer: The tokenizer you are loading from '/tmp/tmp8nacw8ai' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue.
chaiml-djinn-wishmaster-81119-v1-mkmlizer: quantized model in 43.695s
chaiml-djinn-wishmaster-81119-v1-mkmlizer: Processed model ChaiML/Djinn-Wishmaster260110041143_sft in 109.859s
chaiml-djinn-wishmaster-81119-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-djinn-wishmaster-81119-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-djinn-wishmaster-81119-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-djinn-wishmaster-81119-v1/nvidia
chaiml-djinn-wishmaster-81119-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-djinn-wishmaster-81119-v1/nvidia/config.json
chaiml-djinn-wishmaster-81119-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-djinn-wishmaster-81119-v1/nvidia/special_tokens_map.json
chaiml-djinn-wishmaster-81119-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-djinn-wishmaster-81119-v1/nvidia/tokenizer_config.json
chaiml-djinn-wishmaster-81119-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-djinn-wishmaster-81119-v1/nvidia/tokenizer.json
chaiml-djinn-wishmaster-81119-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-djinn-wishmaster-81119-v1/nvidia/flywheel_model.1.safetensors
chaiml-djinn-wishmaster-81119-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-djinn-wishmaster-81119-v1/nvidia/flywheel_model.0.safetensors
Job chaiml-djinn-wishmaster-81119-v1-mkmlizer completed after 165.88s with status: succeeded
Stopping job with name chaiml-djinn-wishmaster-81119-v1-mkmlizer
Pipeline stage MKMLizer completed in 167.21s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-djinn-wishmaster-81119-v1
Waiting for inference service chaiml-djinn-wishmaster-81119-v1 to be ready
Inference service chaiml-djinn-wishmaster-81119-v1 ready after 170.67277932167053s
Pipeline stage MKMLDeployer completed in 171.16s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.415902614593506s
Received healthy response to inference request in 2.2961740493774414s
Received healthy response to inference request in 2.436244010925293s
Received healthy response to inference request in 1.9013011455535889s
Received healthy response to inference request in 2.3209595680236816s
5 requests
0 failed requests
5th percentile: 1.9802757263183595
10th percentile: 2.05925030708313
20th percentile: 2.217199468612671
30th percentile: 2.3011311531066894
40th percentile: 2.3110453605651857
50th percentile: 2.3209595680236816
60th percentile: 2.3589367866516113
70th percentile: 2.396914005279541
80th percentile: 2.419970893859863
90th percentile: 2.4281074523925783
95th percentile: 2.4321757316589356
99th percentile: 2.4354303550720213
mean time: 2.274116277694702
Pipeline stage StressChecker completed in 12.42s
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 0.59s
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
chaiml-djinn-wishmaster_81119_v1 status is now deployed due to DeploymentManager action
chaiml-djinn-wishmaster_81119_v1 status is now inactive due to auto deactivation removed underperforming models