bbchicago-test-lora-007

submission_id: bbchicago-test-lora-007_v1

developer_uid: Bbbrun0

best_of: 16

celo_rating: 1187.25

display_name: bbchicago-test-lora-007_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_Lora_007

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_eval_status: success

model_group: BBChicago/Test_Lora_007

model_name: bbchicago-test-lora-007_v1

model_num_parameters: 8030261248.0

model_repo: BBChicago/Test_Lora_007

model_size: 8B

num_battles: 21415

num_wins: 10872

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: 2024-06-13T10:09:32+00:00

us_pacific_date: 2024-06-13

win_ratio: 0.5076815316367033

Resubmit model

Running pipeline stage MKMLizer
Starting job with name bbchicago-test-lora-007-v1-mkmlizer
Waiting for job on bbchicago-test-lora-007-v1-mkmlizer to finish
bbchicago-test-lora-007-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-test-lora-007-v1-mkmlizer: ║     _____            __           __                                ║
bbchicago-test-lora-007-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
bbchicago-test-lora-007-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
bbchicago-test-lora-007-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
bbchicago-test-lora-007-v1-mkmlizer: ║       /___/                                                         ║
bbchicago-test-lora-007-v1-mkmlizer: ║                                                                     ║
bbchicago-test-lora-007-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
bbchicago-test-lora-007-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
bbchicago-test-lora-007-v1-mkmlizer: ║  https://mk1.ai                                                     ║
bbchicago-test-lora-007-v1-mkmlizer: ║                                                                     ║
bbchicago-test-lora-007-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
bbchicago-test-lora-007-v1-mkmlizer: ║  belonging to:                                                      ║
bbchicago-test-lora-007-v1-mkmlizer: ║                                                                     ║
bbchicago-test-lora-007-v1-mkmlizer: ║  Chai Research Corp.                                                ║
bbchicago-test-lora-007-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
bbchicago-test-lora-007-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
bbchicago-test-lora-007-v1-mkmlizer: ║                                                                     ║
bbchicago-test-lora-007-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-test-lora-007-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-lora-007-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
bbchicago-test-lora-007-v1-mkmlizer: Downloaded to shared memory in 40.681s
bbchicago-test-lora-007-v1-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-test-lora-007-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-test-lora-007-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<10:43,  2.23s/it]
Loading 0:   5%|▌         | 15/291 [00:04<01:01,  4.47it/s]
Loading 0:  11%|█         | 32/291 [00:04<00:22, 11.49it/s]
Loading 0:  17%|█▋        | 50/291 [00:04<00:11, 20.95it/s]
Loading 0:  22%|██▏       | 64/291 [00:05<00:09, 24.78it/s]
Loading 0:  27%|██▋       | 78/291 [00:05<00:06, 34.13it/s]
Loading 0:  33%|███▎      | 96/291 [00:05<00:04, 48.75it/s]
Loading 0:  39%|███▉      | 114/291 [00:05<00:02, 64.42it/s]
Loading 0:  45%|████▌     | 132/291 [00:05<00:01, 80.73it/s]
Loading 0:  52%|█████▏    | 150/291 [00:05<00:01, 96.61it/s]
Loading 0:  57%|█████▋    | 166/291 [00:06<00:01, 74.16it/s]
Loading 0:  63%|██████▎   | 184/291 [00:06<00:01, 89.00it/s]
Loading 0:  69%|██████▉   | 202/291 [00:06<00:00, 103.85it/s]
Loading 0:  76%|███████▌  | 220/291 [00:06<00:00, 117.55it/s]
Loading 0:  82%|████████▏ | 238/291 [00:06<00:00, 129.99it/s]
Loading 0:  88%|████████▊ | 256/291 [00:06<00:00, 138.09it/s]
Loading 0:  93%|█████████▎| 272/291 [00:06<00:00, 91.44it/s] 
Loading 0:  98%|█████████▊| 285/291 [00:07<00:00, 98.56it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-test-lora-007-v1-mkmlizer: quantized model in 22.804s
bbchicago-test-lora-007-v1-mkmlizer: Processed model BBChicago/Test_Lora_007 in 66.101s
bbchicago-test-lora-007-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-test-lora-007-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-test-lora-007-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-test-lora-007-v1
bbchicago-test-lora-007-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-test-lora-007-v1/special_tokens_map.json
bbchicago-test-lora-007-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-test-lora-007-v1/config.json
bbchicago-test-lora-007-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-test-lora-007-v1/tokenizer_config.json
bbchicago-test-lora-007-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-test-lora-007-v1/tokenizer.json
bbchicago-test-lora-007-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-test-lora-007-v1/flywheel_model.0.safetensors
bbchicago-test-lora-007-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
bbchicago-test-lora-007-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-lora-007-v1-mkmlizer:   warnings.warn(
bbchicago-test-lora-007-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-lora-007-v1-mkmlizer:   warnings.warn(
bbchicago-test-lora-007-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-lora-007-v1-mkmlizer:   warnings.warn(
bbchicago-test-lora-007-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-lora-007-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
bbchicago-test-lora-007-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-test-lora-007-v1-mkmlizer: Saving duration: 0.390s
bbchicago-test-lora-007-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.095s
bbchicago-test-lora-007-v1-mkmlizer: creating bucket guanaco-reward-models
bbchicago-test-lora-007-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-test-lora-007-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-test-lora-007-v1_reward
bbchicago-test-lora-007-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-test-lora-007-v1_reward/special_tokens_map.json
bbchicago-test-lora-007-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-test-lora-007-v1_reward/tokenizer_config.json
bbchicago-test-lora-007-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-test-lora-007-v1_reward/merges.txt
bbchicago-test-lora-007-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-test-lora-007-v1_reward/vocab.json
bbchicago-test-lora-007-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-test-lora-007-v1_reward/config.json
bbchicago-test-lora-007-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-test-lora-007-v1_reward/tokenizer.json
bbchicago-test-lora-007-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-test-lora-007-v1_reward/reward.tensors
Job bbchicago-test-lora-007-v1-mkmlizer completed after 93.97s with status: succeeded
Stopping job with name bbchicago-test-lora-007-v1-mkmlizer
Pipeline stage MKMLizer completed in 97.58s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-test-lora-007-v1
Waiting for inference service bbchicago-test-lora-007-v1 to be ready
Inference service bbchicago-test-lora-007-v1 ready after 40.25684094429016s
Pipeline stage ISVCDeployer completed in 47.96s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.230865955352783s
Received healthy response to inference request in 1.2695105075836182s
Received healthy response to inference request in 1.2749817371368408s
Received healthy response to inference request in 1.2589094638824463s
Received healthy response to inference request in 1.2507858276367188s
5 requests
0 failed requests
5th percentile: 1.2524105548858642
10th percentile: 1.2540352821350098
20th percentile: 1.2572847366333009
30th percentile: 1.2610296726226806
40th percentile: 1.2652700901031495
50th percentile: 1.2695105075836182
60th percentile: 1.2716989994049073
70th percentile: 1.2738874912261964
80th percentile: 1.4661585807800295
90th percentile: 1.8485122680664063
95th percentile: 2.0396891117095945
99th percentile: 2.1926305866241456
mean time: 1.4570106983184814
Pipeline stage StressChecker completed in 7.95s
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-007_v1 status is now deployed due to DeploymentManager action
bbchicago-test-lora-007_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of bbchicago-test-lora-007_v1
Running pipeline stage ISVCDeleter
Checking if service bbchicago-test-lora-007-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.59s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key bbchicago-test-lora-007-v1/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-test-lora-007-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key bbchicago-test-lora-007-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key bbchicago-test-lora-007-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key bbchicago-test-lora-007-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key bbchicago-test-lora-007-v1_reward/config.json from bucket guanaco-reward-models
Deleting key bbchicago-test-lora-007-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key bbchicago-test-lora-007-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key bbchicago-test-lora-007-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key bbchicago-test-lora-007-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key bbchicago-test-lora-007-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key bbchicago-test-lora-007-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.54s
bbchicago-test-lora-007_v1 status is now torndown due to DeploymentManager action