submission_id: bbchicago-brt-8b-l3-v0-1_v2
developer_uid: Bbbrun0
status: inactive
model_repo: BBChicago/Brt-8B-L3_v0.1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.1, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, '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}
reward_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}
timestamp: 2024-06-05T09:18:59+00:00
model_name: bbchicago-brt-8b-l3-v0-1_v2
model_eval_status: success
model_group: BBChicago/Brt-8B-L3_v0.1
num_battles: 21113
num_wins: 11662
celo_rating: 1212.81
safety_score: 0.89
propriety_score: 0.6787878787878788
propriety_total_count: 660.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: bbchicago-brt-8b-l3-v0-1_v2
ineligible_reason: propriety_total_count < 5000
language_model: BBChicago/Brt-8B-L3_v0.1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-05
win_ratio: 0.5523611045327523
Resubmit model
Running pipeline stage MKMLizer
Starting job with name bbchicago-brt-8b-l3-v0-1-v2-mkmlizer
Waiting for job on bbchicago-brt-8b-l3-v0-1-v2-mkmlizer to finish
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: ║ _____ __ __ ║
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: ║ /___/ ║
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: ║ Version: 0.8.14 ║
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: ║ https://mk1.ai ║
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: ║ belonging to: ║
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: ║ Chai Research Corp. ║
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: Downloaded to shared memory in 18.504s
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:29, 2.38s/it] Loading 0: 8%|▊ | 23/291 [00:04<00:41, 6.50it/s] Loading 0: 16%|█▌ | 46/291 [00:04<00:15, 15.38it/s] Loading 0: 22%|██▏ | 63/291 [00:05<00:10, 20.87it/s] Loading 0: 29%|██▉ | 85/291 [00:05<00:06, 33.47it/s] Loading 0: 36%|███▌ | 105/291 [00:05<00:03, 46.96it/s] Loading 0: 45%|████▍ | 130/291 [00:05<00:02, 68.15it/s] Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 84.66it/s] Loading 0: 58%|█████▊ | 169/291 [00:06<00:01, 73.77it/s] Loading 0: 66%|██████▋ | 193/291 [00:06<00:01, 96.32it/s] Loading 0: 73%|███████▎ | 213/291 [00:06<00:00, 112.33it/s] Loading 0: 80%|████████ | 234/291 [00:06<00:00, 130.12it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 146.22it/s] Loading 0: 95%|█████████▍| 276/291 [00:06<00:00, 95.11it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: quantized model in 20.788s
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: Processed model BBChicago/Brt-8B-L3_v0.1 in 40.251s
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v0-1-v2
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v0-1-v2/config.json
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v0-1-v2/special_tokens_map.json
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v0-1-v2/tokenizer_config.json
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v0-1-v2/tokenizer.json
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v0-1-v2/flywheel_model.0.safetensors
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: return self.fget.__get__(instance, owner)()
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: Saving duration: 0.214s
bbchicago-brt-8b-l3-v0-1-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 2.886s
Job bbchicago-brt-8b-l3-v0-1-v2-mkmlizer completed after 62.46s with status: succeeded
Stopping job with name bbchicago-brt-8b-l3-v0-1-v2-mkmlizer
Pipeline stage MKMLizer completed in 66.74s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-brt-8b-l3-v0-1-v2
Waiting for inference service bbchicago-brt-8b-l3-v0-1-v2 to be ready
Inference service bbchicago-brt-8b-l3-v0-1-v2 ready after 40.24020195007324s
Pipeline stage ISVCDeployer completed in 48.32s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1897130012512207s
Received healthy response to inference request in 1.276479959487915s
Received healthy response to inference request in 1.2971811294555664s
Received healthy response to inference request in 1.263223648071289s
Received healthy response to inference request in 1.262556552886963s
5 requests
0 failed requests
5th percentile: 1.262689971923828
10th percentile: 1.2628233909606934
20th percentile: 1.263090229034424
30th percentile: 1.2658749103546143
40th percentile: 1.2711774349212646
50th percentile: 1.276479959487915
60th percentile: 1.2847604274749755
70th percentile: 1.293040895462036
80th percentile: 1.4756875038146975
90th percentile: 1.832700252532959
95th percentile: 2.01120662689209
99th percentile: 2.1540117263793945
mean time: 1.4578308582305908
Pipeline stage StressChecker completed in 8.06s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.03s
M-Eval Dataset for topic stay_in_character is loaded
bbchicago-brt-8b-l3-v0-1_v2 status is now deployed due to DeploymentManager action
bbchicago-brt-8b-l3-v0-1_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics