submission_id: bbchicago-brt-8b-l3-v0-0_v2
developer_uid: Bbbrun0
status: inactive
model_repo: BBChicago/Brt-8B-L3_v0.0
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 80, '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: 2024-06-05T06:25:19+00:00
model_name: bbchicago-brt-8b-l3-v0-0_v1
model_eval_status: success
model_group: BBChicago/Brt-8B-L3_v0.0
num_battles: 16050
num_wins: 8859
celo_rating: 1216.1
safety_score: 0.91
propriety_score: 0.6558441558441559
propriety_total_count: 462.0
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-v0-0_v1
ineligible_reason: propriety_total_count < 5000
language_model: BBChicago/Brt-8B-L3_v0.0
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-04
win_ratio: 0.5519626168224299
Resubmit model
Running pipeline stage MKMLizer
Starting job with name bbchicago-brt-8b-l3-v0-0-v2-mkmlizer
Waiting for job on bbchicago-brt-8b-l3-v0-0-v2-mkmlizer to finish
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: ║ _____ __ __ ║
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: ║ /___/ ║
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: ║ Version: 0.8.14 ║
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: ║ https://mk1.ai ║
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: ║ belonging to: ║
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: ║ Chai Research Corp. ║
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-brt-8b-l3-v0-0-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-v0-0-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: Downloaded to shared memory in 19.959s
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 116.39it/s] Loading 0: 8%|▊ | 24/291 [00:00<00:02, 114.17it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:01, 127.23it/s] Loading 0: 20%|█▉ | 57/291 [00:00<00:01, 135.34it/s] Loading 0: 24%|██▍ | 71/291 [00:00<00:01, 130.47it/s] Loading 0: 29%|██▉ | 85/291 [00:01<00:03, 61.00it/s] Loading 0: 35%|███▌ | 102/291 [00:01<00:02, 77.62it/s] Loading 0: 39%|███▉ | 114/291 [00:01<00:02, 84.99it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 97.65it/s] Loading 0: 50%|████▉ | 145/291 [00:01<00:01, 109.48it/s] Loading 0: 54%|█████▍ | 158/291 [00:01<00:01, 109.70it/s] Loading 0: 60%|██████ | 175/291 [00:01<00:00, 123.54it/s] Loading 0: 65%|██████▍ | 189/291 [00:02<00:01, 70.12it/s] Loading 0: 69%|██████▉ | 202/291 [00:02<00:01, 78.80it/s] Loading 0: 74%|███████▍ | 216/291 [00:02<00:00, 90.18it/s] Loading 0: 79%|███████▊ | 229/291 [00:02<00:00, 97.27it/s] Loading 0: 84%|████████▍ | 244/291 [00:02<00:00, 109.15it/s] Loading 0: 88%|████████▊ | 257/291 [00:02<00:00, 107.19it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 120.04it/s] Loading 0: 99%|█████████▊| 287/291 [00:08<00:00, 8.24it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: quantized model in 19.392s
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: Processed model BBChicago/Brt-8B-L3_v0.0 in 40.659s
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v0-0-v2
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v0-0-v2/config.json
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v0-0-v2/tokenizer_config.json
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v0-0-v2/special_tokens_map.json
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v0-0-v2/tokenizer.json
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v0-0-v2/flywheel_model.0.safetensors
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
bbchicago-brt-8b-l3-v0-0-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-v0-0-v2-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v0-0-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-v0-0-v2-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v0-0-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-v0-0-v2-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: Saving duration: 0.246s
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.803s
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: creating bucket guanaco-reward-models
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-brt-8b-l3-v0-0-v2_reward
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v0-0-v2_reward/special_tokens_map.json
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v0-0-v2_reward/tokenizer_config.json
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v0-0-v2_reward/config.json
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-brt-8b-l3-v0-0-v2_reward/merges.txt
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v0-0-v2_reward/vocab.json
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v0-0-v2_reward/tokenizer.json
bbchicago-brt-8b-l3-v0-0-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-brt-8b-l3-v0-0-v2_reward/reward.tensors
Job bbchicago-brt-8b-l3-v0-0-v2-mkmlizer completed after 62.42s with status: succeeded
Stopping job with name bbchicago-brt-8b-l3-v0-0-v2-mkmlizer
Pipeline stage MKMLizer completed in 67.70s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-brt-8b-l3-v0-0-v2
Waiting for inference service bbchicago-brt-8b-l3-v0-0-v2 to be ready
Inference service bbchicago-brt-8b-l3-v0-0-v2 ready after 30.16264271736145s
Pipeline stage ISVCDeployer completed in 37.71s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.132448673248291s
Received healthy response to inference request in 1.281097412109375s
Received healthy response to inference request in 1.2536165714263916s
Received healthy response to inference request in 1.2686028480529785s
Received healthy response to inference request in 1.246277093887329s
5 requests
0 failed requests
5th percentile: 1.2477449893951416
10th percentile: 1.249212884902954
20th percentile: 1.2521486759185791
30th percentile: 1.256613826751709
40th percentile: 1.2626083374023438
50th percentile: 1.2686028480529785
60th percentile: 1.2736006736755372
70th percentile: 1.2785984992980957
80th percentile: 1.4513676643371585
90th percentile: 1.7919081687927247
95th percentile: 1.9621784210205075
99th percentile: 2.098394622802734
mean time: 1.436408519744873
Pipeline stage StressChecker completed in 7.77s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
bbchicago-brt-8b-l3-v0-0_v2 status is now deployed due to DeploymentManager action
bbchicago-brt-8b-l3-v0-0_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics