bbchicago-test-lora-blac_4792

submission_id: bbchicago-test-lora-blac_4792_v2

developer_uid: Bbbrun0

best_of: 16

celo_rating: 1141.78

display_name: bbchicago-test-lora-blac_4792_v2

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_lora_Blackroot_LongStory

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_eval_status: success

model_group: BBChicago/test_lora_Blac

model_name: bbchicago-test-lora-blac_4792_v2

model_num_parameters: 8030261248.0

model_repo: BBChicago/test_lora_Blackroot_LongStory

model_size: 8B

num_battles: 16875

num_wins: 7781

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: 2024-06-11T09:31:36+00:00

us_pacific_date: 2024-06-11

win_ratio: 0.4610962962962963

Resubmit model

Running pipeline stage MKMLizer
Starting job with name bbchicago-test-lora-blac-4792-v2-mkmlizer
Waiting for job on bbchicago-test-lora-blac-4792-v2-mkmlizer to finish
bbchicago-test-lora-blac-4792-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-test-lora-blac-4792-v2-mkmlizer: ║     _____            __           __                                ║
bbchicago-test-lora-blac-4792-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
bbchicago-test-lora-blac-4792-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
bbchicago-test-lora-blac-4792-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
bbchicago-test-lora-blac-4792-v2-mkmlizer: ║       /___/                                                         ║
bbchicago-test-lora-blac-4792-v2-mkmlizer: ║                                                                     ║
bbchicago-test-lora-blac-4792-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
bbchicago-test-lora-blac-4792-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
bbchicago-test-lora-blac-4792-v2-mkmlizer: ║  https://mk1.ai                                                     ║
bbchicago-test-lora-blac-4792-v2-mkmlizer: ║                                                                     ║
bbchicago-test-lora-blac-4792-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
bbchicago-test-lora-blac-4792-v2-mkmlizer: ║  belonging to:                                                      ║
bbchicago-test-lora-blac-4792-v2-mkmlizer: ║                                                                     ║
bbchicago-test-lora-blac-4792-v2-mkmlizer: ║  Chai Research Corp.                                                ║
bbchicago-test-lora-blac-4792-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
bbchicago-test-lora-blac-4792-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
bbchicago-test-lora-blac-4792-v2-mkmlizer: ║                                                                     ║
bbchicago-test-lora-blac-4792-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-test-lora-blac-4792-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-test-lora-blac-4792-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
bbchicago-test-lora-blac-4792-v2-mkmlizer: Downloaded to shared memory in 14.853s
bbchicago-test-lora-blac-4792-v2-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-test-lora-blac-4792-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-test-lora-blac-4792-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:01, 203.55it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:01, 189.09it/s]
Loading 0:  23%|██▎       | 66/291 [00:00<00:01, 202.91it/s]
Loading 0:  30%|██▉       | 87/291 [00:00<00:02, 101.59it/s]
Loading 0:  38%|███▊      | 111/291 [00:00<00:01, 128.22it/s]
Loading 0:  45%|████▌     | 131/291 [00:00<00:01, 141.14it/s]
Loading 0:  54%|█████▎    | 156/291 [00:01<00:00, 163.52it/s]
Loading 0:  62%|██████▏   | 179/291 [00:01<00:00, 176.16it/s]
Loading 0:  68%|██████▊   | 199/291 [00:01<00:00, 110.96it/s]
Loading 0:  76%|███████▌  | 220/291 [00:01<00:00, 127.47it/s]
Loading 0:  82%|████████▏ | 240/291 [00:01<00:00, 142.33it/s]
Loading 0:  91%|█████████ | 264/291 [00:01<00:00, 161.05it/s]
Loading 0:  97%|█████████▋| 283/291 [00:01<00:00, 168.00it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-test-lora-blac-4792-v2-mkmlizer: quantized model in 16.804s
bbchicago-test-lora-blac-4792-v2-mkmlizer: Processed model BBChicago/test_lora_Blackroot_LongStory in 32.573s
bbchicago-test-lora-blac-4792-v2-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-test-lora-blac-4792-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-test-lora-blac-4792-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-test-lora-blac-4792-v2
bbchicago-test-lora-blac-4792-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-test-lora-blac-4792-v2/config.json
bbchicago-test-lora-blac-4792-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-test-lora-blac-4792-v2/tokenizer_config.json
bbchicago-test-lora-blac-4792-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-test-lora-blac-4792-v2/special_tokens_map.json
bbchicago-test-lora-blac-4792-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-test-lora-blac-4792-v2/tokenizer.json
bbchicago-test-lora-blac-4792-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-test-lora-blac-4792-v2/flywheel_model.0.safetensors
bbchicago-test-lora-blac-4792-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
bbchicago-test-lora-blac-4792-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-test-lora-blac-4792-v2-mkmlizer:   warnings.warn(
bbchicago-test-lora-blac-4792-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-test-lora-blac-4792-v2-mkmlizer:   warnings.warn(
bbchicago-test-lora-blac-4792-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-test-lora-blac-4792-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
bbchicago-test-lora-blac-4792-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-test-lora-blac-4792-v2-mkmlizer: Saving duration: 0.213s
bbchicago-test-lora-blac-4792-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.502s
bbchicago-test-lora-blac-4792-v2-mkmlizer: creating bucket guanaco-reward-models
bbchicago-test-lora-blac-4792-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-test-lora-blac-4792-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-test-lora-blac-4792-v2_reward
bbchicago-test-lora-blac-4792-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-test-lora-blac-4792-v2_reward/special_tokens_map.json
bbchicago-test-lora-blac-4792-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-test-lora-blac-4792-v2_reward/config.json
bbchicago-test-lora-blac-4792-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-test-lora-blac-4792-v2_reward/tokenizer_config.json
bbchicago-test-lora-blac-4792-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-test-lora-blac-4792-v2_reward/merges.txt
bbchicago-test-lora-blac-4792-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-test-lora-blac-4792-v2_reward/vocab.json
bbchicago-test-lora-blac-4792-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-test-lora-blac-4792-v2_reward/tokenizer.json
bbchicago-test-lora-blac-4792-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-test-lora-blac-4792-v2_reward/reward.tensors
Job bbchicago-test-lora-blac-4792-v2-mkmlizer completed after 52.99s with status: succeeded
Stopping job with name bbchicago-test-lora-blac-4792-v2-mkmlizer
Pipeline stage MKMLizer completed in 53.36s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-test-lora-blac-4792-v2
Waiting for inference service bbchicago-test-lora-blac-4792-v2 to be ready
Inference service bbchicago-test-lora-blac-4792-v2 ready after 40.240620851516724s
Pipeline stage ISVCDeployer completed in 45.77s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.185999631881714s
Received healthy response to inference request in 1.2186930179595947s
Received healthy response to inference request in 1.2544500827789307s
Received healthy response to inference request in 1.2190923690795898s
Received healthy response to inference request in 1.226224660873413s
5 requests
0 failed requests
5th percentile: 1.2187728881835938
10th percentile: 1.2188527584075928
20th percentile: 1.2190124988555908
30th percentile: 1.2205188274383545
40th percentile: 1.2233717441558838
50th percentile: 1.226224660873413
60th percentile: 1.2375148296356202
70th percentile: 1.248804998397827
80th percentile: 1.4407599925994874
90th percentile: 1.8133798122406006
95th percentile: 1.9996897220611571
99th percentile: 2.1487376499176025
mean time: 1.4208919525146484
Pipeline stage StressChecker completed in 7.69s
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-test-lora-blac_4792_v2 status is now deployed due to DeploymentManager action
bbchicago-test-lora-blac_4792_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of bbchicago-test-lora-blac_4792_v2
Running pipeline stage ISVCDeleter
Checking if service bbchicago-test-lora-blac-4792-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.36s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key bbchicago-test-lora-blac-4792-v2/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-test-lora-blac-4792-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key bbchicago-test-lora-blac-4792-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key bbchicago-test-lora-blac-4792-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key bbchicago-test-lora-blac-4792-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key bbchicago-test-lora-blac-4792-v2_reward/config.json from bucket guanaco-reward-models
Deleting key bbchicago-test-lora-blac-4792-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key bbchicago-test-lora-blac-4792-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key bbchicago-test-lora-blac-4792-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key bbchicago-test-lora-blac-4792-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key bbchicago-test-lora-blac-4792-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key bbchicago-test-lora-blac-4792-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.62s
bbchicago-test-lora-blac_4792_v2 status is now torndown due to DeploymentManager action