junhua024-chai-12-full-202

developer_uid: junhua024
submission_id: junhua024-chai-12-full-202_v1
model_name: junhua024-chai-12-full-202_v1
model_group: junhua024/chai_12_full_2
status: torndown
timestamp: 2025-07-28T13:27:36+00:00
num_battles: 5923
num_wins: 3214
celo_rating: 1294.27
family_friendly_score: 0.531
family_friendly_standard_error: 0.00705746413380897
submission_type: basic
model_repo: junhua024/chai_12_full_202
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 2048
max_output_tokens: 64
reward_model: default
display_name: junhua024-chai-12-full-202_v1
is_internal_developer: False
language_model: junhua024/chai_12_full_202
model_size: 13B
ranking_group: single
us_pacific_date: 2025-07-28
win_ratio: 0.5426304237717373
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "You are an empathetic conversational AI. You understand the user's feelings and respond with warmth, compassion, and sincerity. Each of your responses should be fewer than 64 tokens long.", '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 junhua024-chai-12-full-202-v1-mkmlizer
Waiting for job on junhua024-chai-12-full-202-v1-mkmlizer to finish
Failed to get response for submission junhua024-chai-19cl-full-0022_v7: HTTPConnectionPool(host='junhua024-chai-19cl-full-0022-v7-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-12-full-202-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-12-full-202-v1-mkmlizer: ║                                                                     ║
junhua024-chai-12-full-202-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-12-full-202-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-12-full-202-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-12-full-202-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-12-full-202-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-12-full-202-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-12-full-202-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-12-full-202-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-12-full-202-v1-mkmlizer: ║                                                                     ║
junhua024-chai-12-full-202-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-12-full-202-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-12-full-202-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-12-full-202-v1-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-12-full-202-v1-mkmlizer: ║                                                                     ║
junhua024-chai-12-full-202-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-12-full-202-v1-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-12-full-202-v1-mkmlizer: ║                                                                     ║
junhua024-chai-12-full-202-v1-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-12-full-202-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-12-full-202-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-12-full-202-v1-mkmlizer: ║                                                                     ║
junhua024-chai-12-full-202-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-12-full-202-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-12-full-202-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-12-full-202-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-12-full-202-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-12-full-202-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-12-full-202-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-12-full-202-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-12-full-202-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-12-full-202-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-12-full-202-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-12-full-202-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-12-full-202-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-12-full-202-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-12-full-202-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-12-full-202-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-12-full-202-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-12-full-202-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-12-full-202-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-12-full-202-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-12-full-202-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-12-full-202-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-12-full-202-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-12-full-202-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-12-full-202-v1-mkmlizer: Downloaded to shared memory in 130.705s
junhua024-chai-12-full-202-v1-mkmlizer: Checking if junhua024/chai_12_full_202 already exists in ChaiML
junhua024-chai-12-full-202-v1-mkmlizer: Creating repo ChaiML/chai_12_full_202 and uploading /tmp/tmpki3sf_6z to it
Failed to get response for submission junhua024-chai-19cl-full-0022_v7: HTTPConnectionPool(host='junhua024-chai-19cl-full-0022-v7-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-12-full-202-v1-mkmlizer: 
  0%|          | 0/26 [00:00<?, ?it/s]
  4%|▍         | 1/26 [00:05<02:11,  5.25s/it]
  8%|▊         | 2/26 [00:06<01:12,  3.01s/it]
 12%|█▏        | 3/26 [00:09<01:08,  2.97s/it]
 15%|█▌        | 4/26 [00:11<00:53,  2.41s/it]
 19%|█▉        | 5/26 [00:12<00:44,  2.13s/it]
 23%|██▎       | 6/26 [00:14<00:39,  1.99s/it]
 27%|██▋       | 7/26 [00:16<00:37,  1.99s/it]
 31%|███       | 8/26 [00:18<00:34,  1.91s/it]
 35%|███▍      | 9/26 [00:19<00:31,  1.85s/it]
 38%|███▊      | 10/26 [00:21<00:28,  1.76s/it]
 42%|████▏     | 11/26 [00:23<00:29,  1.94s/it]
 46%|████▌     | 12/26 [00:25<00:26,  1.87s/it]
 50%|█████     | 13/26 [00:28<00:27,  2.11s/it]
 54%|█████▍    | 14/26 [00:30<00:26,  2.21s/it]
 58%|█████▊    | 15/26 [00:32<00:21,  2.00s/it]
 62%|██████▏   | 16/26 [00:33<00:19,  1.92s/it]
 65%|██████▌   | 17/26 [00:35<00:15,  1.77s/it]
 69%|██████▉   | 18/26 [00:36<00:13,  1.72s/it]
 73%|███████▎  | 19/26 [00:38<00:12,  1.76s/it]
 77%|███████▋  | 20/26 [00:40<00:10,  1.77s/it]
 81%|████████  | 21/26 [00:43<00:10,  2.02s/it]
 85%|████████▍ | 22/26 [00:46<00:09,  2.33s/it]
 88%|████████▊ | 23/26 [00:47<00:06,  2.13s/it]
 92%|█████████▏| 24/26 [00:49<00:03,  1.95s/it]
 96%|█████████▌| 25/26 [00:50<00:01,  1.82s/it]
100%|██████████| 26/26 [00:52<00:00,  1.63s/it]
100%|██████████| 26/26 [00:52<00:00,  2.01s/it]
junhua024-chai-12-full-202-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpki3sf_6z, device:0
junhua024-chai-12-full-202-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission junhua024-chai-12-full-201_v1: HTTPConnectionPool(host='junhua024-chai-12-full-201-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-gy-exp241-sft-gy-_3670_v1: HTTPConnectionPool(host='chaiml-gy-exp241-sft-gy-3670-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-12-full-202-v1-mkmlizer: quantized model in 166.340s
junhua024-chai-12-full-202-v1-mkmlizer: Processed model junhua024/chai_12_full_202 in 386.641s
junhua024-chai-12-full-202-v1-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-12-full-202-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-12-full-202-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-12-full-202-v1/nvidia
junhua024-chai-12-full-202-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-12-full-202-v1/nvidia/special_tokens_map.json
junhua024-chai-12-full-202-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-12-full-202-v1/nvidia/config.json
junhua024-chai-12-full-202-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-12-full-202-v1/nvidia/tokenizer_config.json
junhua024-chai-12-full-202-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-12-full-202-v1/nvidia/tokenizer.json
Job junhua024-chai-12-full-202-v1-mkmlizer completed after 417.13s with status: succeeded
Stopping job with name junhua024-chai-12-full-202-v1-mkmlizer
Pipeline stage MKMLizer completed in 417.64s
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 junhua024-chai-12-full-202-v1
Waiting for inference service junhua024-chai-12-full-202-v1 to be ready
Failed to get response for submission junhua024-chai-12-full-201_v1: HTTPConnectionPool(host='junhua024-chai-12-full-201-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Unable to record family friendly update due to error: HTTPConnectionPool(host='chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by ConnectTimeoutError(<urllib3.connection.HTTPConnection object at 0x7ac3fe9b5050>, 'Connection to chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com timed out. (connect timeout=12.0)'))
Retrying (%r) after connection broken by '%r': %s
Inference service junhua024-chai-12-full-202-v1 ready after 201.57262563705444s
Pipeline stage MKMLDeployer completed in 202.22s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9534847736358643s
Received healthy response to inference request in 1.118238925933838s
Received healthy response to inference request in 1.6849181652069092s
Received healthy response to inference request in 1.224116325378418s
Received healthy response to inference request in 1.8409669399261475s
5 requests
0 failed requests
5th percentile: 1.139414405822754
10th percentile: 1.1605898857116699
20th percentile: 1.2029408454895019
30th percentile: 1.3162766933441161
40th percentile: 1.5005974292755127
50th percentile: 1.6849181652069092
60th percentile: 1.7473376750946046
70th percentile: 1.8097571849822998
80th percentile: 2.063470506668091
90th percentile: 2.5084776401519777
95th percentile: 2.7309812068939205
99th percentile: 2.9089840602874757
mean time: 1.7643450260162354
Pipeline stage StressChecker completed in 10.90s
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 1.15s
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 0.80s
Shutdown handler de-registered
junhua024-chai-12-full-202_v1 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3258.52s
Shutdown handler de-registered
junhua024-chai-12-full-202_v1 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-12-full-202_v1 status is now torndown due to DeploymentManager action