bbchicago-test-l3-8b-instruct

submission_id: bbchicago-test-l3-8b-instruct_v1

developer_uid: Bbbrun0

best_of: 16

celo_rating: 1178.8

display_name: bbchicago-test-l3-8b-instruct_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/test-L3-8B-instruct

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_eval_status: success

model_group: BBChicago/test-L3-8B-ins

model_name: bbchicago-test-l3-8b-instruct_v1

model_num_parameters: 8030261248.0

model_repo: BBChicago/test-L3-8B-instruct

model_size: 8B

num_battles: 8849

num_wins: 4405

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: 2024-06-11T04:14:41+00:00

us_pacific_date: 2024-06-10

win_ratio: 0.49779636117075377

Resubmit model

Running pipeline stage MKMLizer
Starting job with name bbchicago-test-l3-8b-instruct-v1-mkmlizer
Waiting for job on bbchicago-test-l3-8b-instruct-v1-mkmlizer to finish
bbchicago-test-l3-8b-instruct-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-test-l3-8b-instruct-v1-mkmlizer: ║     _____            __           __                                ║
bbchicago-test-l3-8b-instruct-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
bbchicago-test-l3-8b-instruct-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
bbchicago-test-l3-8b-instruct-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
bbchicago-test-l3-8b-instruct-v1-mkmlizer: ║       /___/                                                         ║
bbchicago-test-l3-8b-instruct-v1-mkmlizer: ║                                                                     ║
bbchicago-test-l3-8b-instruct-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
bbchicago-test-l3-8b-instruct-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
bbchicago-test-l3-8b-instruct-v1-mkmlizer: ║  https://mk1.ai                                                     ║
bbchicago-test-l3-8b-instruct-v1-mkmlizer: ║                                                                     ║
bbchicago-test-l3-8b-instruct-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
bbchicago-test-l3-8b-instruct-v1-mkmlizer: ║  belonging to:                                                      ║
bbchicago-test-l3-8b-instruct-v1-mkmlizer: ║                                                                     ║
bbchicago-test-l3-8b-instruct-v1-mkmlizer: ║  Chai Research Corp.                                                ║
bbchicago-test-l3-8b-instruct-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
bbchicago-test-l3-8b-instruct-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
bbchicago-test-l3-8b-instruct-v1-mkmlizer: ║                                                                     ║
bbchicago-test-l3-8b-instruct-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-test-l3-8b-instruct-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-test-l3-8b-instruct-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
bbchicago-test-l3-8b-instruct-v1-mkmlizer: Downloaded to shared memory in 59.651s
bbchicago-test-l3-8b-instruct-v1-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-test-l3-8b-instruct-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-test-l3-8b-instruct-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:01, 200.12it/s]
Loading 0:  15%|█▌        | 44/291 [00:00<00:01, 210.27it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:01, 209.74it/s]
Loading 0:  30%|███       | 88/291 [00:00<00:01, 105.36it/s]
Loading 0:  38%|███▊      | 111/291 [00:00<00:01, 131.27it/s]
Loading 0:  45%|████▌     | 131/291 [00:00<00:01, 144.84it/s]
Loading 0:  54%|█████▎    | 156/291 [00:00<00:00, 168.43it/s]
Loading 0:  62%|██████▏   | 179/291 [00:01<00:00, 182.03it/s]
Loading 0:  69%|██████▊   | 200/291 [00:01<00:00, 113.46it/s]
Loading 0:  76%|███████▌  | 220/291 [00:01<00:00, 128.23it/s]
Loading 0:  83%|████████▎ | 242/291 [00:01<00:00, 146.91it/s]
Loading 0:  91%|█████████ | 265/291 [00:01<00:00, 161.99it/s]
Loading 0:  99%|█████████▊| 287/291 [00:06<00:00, 14.04it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-test-l3-8b-instruct-v1-mkmlizer: quantized model in 16.690s
bbchicago-test-l3-8b-instruct-v1-mkmlizer: Processed model BBChicago/test-L3-8B-instruct in 78.151s
bbchicago-test-l3-8b-instruct-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-test-l3-8b-instruct-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-test-l3-8b-instruct-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-test-l3-8b-instruct-v1
bbchicago-test-l3-8b-instruct-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-test-l3-8b-instruct-v1/tokenizer.json
bbchicago-test-l3-8b-instruct-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-test-l3-8b-instruct-v1/flywheel_model.0.safetensors
bbchicago-test-l3-8b-instruct-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
bbchicago-test-l3-8b-instruct-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-test-l3-8b-instruct-v1-mkmlizer:   warnings.warn(
bbchicago-test-l3-8b-instruct-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-test-l3-8b-instruct-v1-mkmlizer:   warnings.warn(
bbchicago-test-l3-8b-instruct-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-test-l3-8b-instruct-v1-mkmlizer:   warnings.warn(
bbchicago-test-l3-8b-instruct-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-test-l3-8b-instruct-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
bbchicago-test-l3-8b-instruct-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-test-l3-8b-instruct-v1-mkmlizer: Saving duration: 0.214s
bbchicago-test-l3-8b-instruct-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 2.787s
bbchicago-test-l3-8b-instruct-v1-mkmlizer: creating bucket guanaco-reward-models
bbchicago-test-l3-8b-instruct-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-test-l3-8b-instruct-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-test-l3-8b-instruct-v1_reward
bbchicago-test-l3-8b-instruct-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-test-l3-8b-instruct-v1_reward/special_tokens_map.json
bbchicago-test-l3-8b-instruct-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-test-l3-8b-instruct-v1_reward/tokenizer_config.json
bbchicago-test-l3-8b-instruct-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-test-l3-8b-instruct-v1_reward/merges.txt
bbchicago-test-l3-8b-instruct-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-test-l3-8b-instruct-v1_reward/vocab.json
bbchicago-test-l3-8b-instruct-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-test-l3-8b-instruct-v1_reward/tokenizer.json
bbchicago-test-l3-8b-instruct-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-test-l3-8b-instruct-v1_reward/config.json
bbchicago-test-l3-8b-instruct-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-test-l3-8b-instruct-v1_reward/reward.tensors
Job bbchicago-test-l3-8b-instruct-v1-mkmlizer completed after 103.52s with status: succeeded
Stopping job with name bbchicago-test-l3-8b-instruct-v1-mkmlizer
Pipeline stage MKMLizer completed in 106.70s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-test-l3-8b-instruct-v1
Waiting for inference service bbchicago-test-l3-8b-instruct-v1 to be ready
Inference service bbchicago-test-l3-8b-instruct-v1 ready after 30.168657302856445s
Pipeline stage ISVCDeployer completed in 37.66s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.225522518157959s
Received healthy response to inference request in 1.2622992992401123s
Received healthy response to inference request in 1.2495040893554688s
Received healthy response to inference request in 1.2580177783966064s
Received healthy response to inference request in 1.2310082912445068s
5 requests
0 failed requests
5th percentile: 1.2347074508666993
10th percentile: 1.2384066104888916
20th percentile: 1.2458049297332763
30th percentile: 1.2512068271636962
40th percentile: 1.2546123027801515
50th percentile: 1.2580177783966064
60th percentile: 1.2597303867340088
70th percentile: 1.2614429950714112
80th percentile: 1.454943943023682
90th percentile: 1.8402332305908204
95th percentile: 2.0328778743743894
99th percentile: 2.186993589401245
mean time: 1.4452703952789308
Pipeline stage StressChecker completed in 7.88s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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-test-l3-8b-instruct_v1 status is now deployed due to DeploymentManager action
bbchicago-test-l3-8b-instruct_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of bbchicago-test-l3-8b-instruct_v1
Running pipeline stage ISVCDeleter
Checking if service bbchicago-test-l3-8b-instruct-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.92s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key bbchicago-test-l3-8b-instruct-v1/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-test-l3-8b-instruct-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key bbchicago-test-l3-8b-instruct-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key bbchicago-test-l3-8b-instruct-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key bbchicago-test-l3-8b-instruct-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key bbchicago-test-l3-8b-instruct-v1_reward/config.json from bucket guanaco-reward-models
Deleting key bbchicago-test-l3-8b-instruct-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key bbchicago-test-l3-8b-instruct-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key bbchicago-test-l3-8b-instruct-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key bbchicago-test-l3-8b-instruct-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key bbchicago-test-l3-8b-instruct-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key bbchicago-test-l3-8b-instruct-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.55s
bbchicago-test-l3-8b-instruct_v1 status is now torndown due to DeploymentManager action