bbchicago-l3-8b-fusion-m_6762

submission_id: bbchicago-l3-8b-fusion-m_6762_v1

developer_uid: Bbbrun0

best_of: 16

celo_rating: 1193.06

display_name: bbchicago-l3-8b-fusion-m_6762_v1

family_friendly_score: 0.0

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}

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': 512, 'best_of': 16, 'max_output_tokens': 64}

is_internal_developer: False

language_model: BBChicago/L3-8B-fusion-math-enhance-v0.0.3

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_eval_status: success

model_group: BBChicago/L3-8B-fusion-m

model_name: bbchicago-l3-8b-fusion-m_6762_v1

model_num_parameters: 8030261248.0

model_repo: BBChicago/L3-8B-fusion-math-enhance-v0.0.3

model_size: 8B

num_battles: 10053

num_wins: 5160

ranking_group: single

reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

status: torndown

submission_type: basic

timestamp: 2024-06-05T02:35:59+00:00

us_pacific_date: 2024-06-04

win_ratio: 0.5132796180244703

Resubmit model

Running pipeline stage MKMLizer
Starting job with name bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer
Waiting for job on bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer to finish
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: ║     _____            __           __                                ║
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: ║       /___/                                                         ║
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: ║                                                                     ║
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: ║  https://mk1.ai                                                     ║
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: ║                                                                     ║
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: ║  belonging to:                                                      ║
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: ║                                                                     ║
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: ║  Chai Research Corp.                                                ║
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: ║                                                                     ║
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-l3-8b-fusion-m-6762-v1-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-l3-8b-fusion-m-6762-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: Downloaded to shared memory in 26.744s
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:01, 200.80it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:01, 190.42it/s]
Loading 0:  23%|██▎       | 66/291 [00:00<00:01, 205.70it/s]
Loading 0:  30%|██▉       | 87/291 [00:00<00:02, 98.08it/s] 
Loading 0:  38%|███▊      | 111/291 [00:00<00:01, 125.33it/s]
Loading 0:  45%|████▌     | 131/291 [00:00<00:01, 139.15it/s]
Loading 0:  54%|█████▎    | 156/291 [00:01<00:00, 163.17it/s]
Loading 0:  62%|██████▏   | 179/291 [00:01<00:00, 176.73it/s]
Loading 0:  69%|██████▊   | 200/291 [00:01<00:00, 112.45it/s]
Loading 0:  76%|███████▌  | 220/291 [00:01<00:00, 126.49it/s]
Loading 0:  83%|████████▎ | 242/291 [00:01<00:00, 145.17it/s]
Loading 0:  91%|█████████ | 265/291 [00:01<00:00, 160.99it/s]
Loading 0:  99%|█████████▊| 287/291 [00:06<00:00, 13.55it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: quantized model in 19.309s
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: Processed model BBChicago/L3-8B-fusion-math-enhance-v0.0.3 in 46.993s
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-l3-8b-fusion-m-6762-v1
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-l3-8b-fusion-m-6762-v1/special_tokens_map.json
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-l3-8b-fusion-m-6762-v1/config.json
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-l3-8b-fusion-m-6762-v1/tokenizer_config.json
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-l3-8b-fusion-m-6762-v1/tokenizer.json
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-l3-8b-fusion-m-6762-v1/flywheel_model.0.safetensors
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
bbchicago-l3-8b-fusion-m-6762-v1-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-l3-8b-fusion-m-6762-v1-mkmlizer:   warnings.warn(
bbchicago-l3-8b-fusion-m-6762-v1-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-l3-8b-fusion-m-6762-v1-mkmlizer:   warnings.warn(
bbchicago-l3-8b-fusion-m-6762-v1-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-l3-8b-fusion-m-6762-v1-mkmlizer:   warnings.warn(
bbchicago-l3-8b-fusion-m-6762-v1-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-l3-8b-fusion-m-6762-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: Saving duration: 0.223s
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.008s
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: creating bucket guanaco-reward-models
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-l3-8b-fusion-m-6762-v1_reward
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-l3-8b-fusion-m-6762-v1_reward/config.json
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-l3-8b-fusion-m-6762-v1_reward/merges.txt
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-l3-8b-fusion-m-6762-v1_reward/vocab.json
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-l3-8b-fusion-m-6762-v1_reward/special_tokens_map.json
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-l3-8b-fusion-m-6762-v1_reward/tokenizer_config.json
bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-l3-8b-fusion-m-6762-v1_reward/tokenizer.json
Job bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer completed after 73.02s with status: succeeded
Stopping job with name bbchicago-l3-8b-fusion-m-6762-v1-mkmlizer
Pipeline stage MKMLizer completed in 78.21s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-l3-8b-fusion-m-6762-v1
Waiting for inference service bbchicago-l3-8b-fusion-m-6762-v1 to be ready
Inference service bbchicago-l3-8b-fusion-m-6762-v1 ready after 70.43319082260132s
Pipeline stage ISVCDeployer completed in 77.78s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1719298362731934s
Received healthy response to inference request in 1.2232067584991455s
Received healthy response to inference request in 1.2309250831604004s
Received healthy response to inference request in 1.2315573692321777s
Received healthy response to inference request in 12.381401300430298s
5 requests
0 failed requests
5th percentile: 1.2247504234313964
10th percentile: 1.2262940883636475
20th percentile: 1.2293814182281495
30th percentile: 1.231051540374756
40th percentile: 1.2313044548034668
50th percentile: 1.2315573692321777
60th percentile: 1.6077063560485838
70th percentile: 1.98385534286499
80th percentile: 4.213824129104616
90th percentile: 8.297612714767457
95th percentile: 10.339507007598876
99th percentile: 11.973022441864014
mean time: 3.647804069519043
Pipeline stage StressChecker completed in 18.84s
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-l3-8b-fusion-m_6762_v1 status is now deployed due to DeploymentManager action
bbchicago-l3-8b-fusion-m_6762_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of bbchicago-l3-8b-fusion-m_6762_v1
Running pipeline stage ISVCDeleter
Checking if service bbchicago-l3-8b-fusion-m-6762-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.12s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key bbchicago-l3-8b-fusion-m-6762-v1/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-l3-8b-fusion-m-6762-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key bbchicago-l3-8b-fusion-m-6762-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key bbchicago-l3-8b-fusion-m-6762-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key bbchicago-l3-8b-fusion-m-6762-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key bbchicago-l3-8b-fusion-m-6762-v1_reward/config.json from bucket guanaco-reward-models
Deleting key bbchicago-l3-8b-fusion-m-6762-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key bbchicago-l3-8b-fusion-m-6762-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key bbchicago-l3-8b-fusion-m-6762-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key bbchicago-l3-8b-fusion-m-6762-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key bbchicago-l3-8b-fusion-m-6762-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key bbchicago-l3-8b-fusion-m-6762-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.54s
bbchicago-l3-8b-fusion-m_6762_v1 status is now torndown due to DeploymentManager action