theskullery-aura-llama

submission_id: theskullery-aura-llama_v1

developer_uid: Steelskull

best_of: 4

celo_rating: 1161.11

display_name: theskullery-aura-llama_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': 0.9, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 90, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}

is_internal_developer: False

language_model: TheSkullery/Aura-llama

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_eval_status: success

model_group: TheSkullery/Aura-llama

model_name: theskullery-aura-llama_v1

model_num_parameters: 10647605248.0

model_repo: TheSkullery/Aura-llama

model_size: 11B

num_battles: 7704

num_wins: 3805

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: 2024-05-27T07:51:00+00:00

us_pacific_date: 2024-05-27

win_ratio: 0.4938992731048806

Resubmit model

Running pipeline stage MKMLizer
Starting job with name theskullery-aura-llama-v1-mkmlizer
Waiting for job on theskullery-aura-llama-v1-mkmlizer to finish
theskullery-aura-llama-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
theskullery-aura-llama-v1-mkmlizer: ║     _____            __           __                                ║
theskullery-aura-llama-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
theskullery-aura-llama-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
theskullery-aura-llama-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
theskullery-aura-llama-v1-mkmlizer: ║       /___/                                                         ║
theskullery-aura-llama-v1-mkmlizer: ║                                                                     ║
theskullery-aura-llama-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
theskullery-aura-llama-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
theskullery-aura-llama-v1-mkmlizer: ║  https://mk1.ai                                                     ║
theskullery-aura-llama-v1-mkmlizer: ║                                                                     ║
theskullery-aura-llama-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
theskullery-aura-llama-v1-mkmlizer: ║  belonging to:                                                      ║
theskullery-aura-llama-v1-mkmlizer: ║                                                                     ║
theskullery-aura-llama-v1-mkmlizer: ║  Chai Research Corp.                                                ║
theskullery-aura-llama-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
theskullery-aura-llama-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
theskullery-aura-llama-v1-mkmlizer: ║                                                                     ║
theskullery-aura-llama-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
theskullery-aura-llama-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.
theskullery-aura-llama-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
theskullery-aura-llama-v1-mkmlizer: Downloaded to shared memory in 58.116s
theskullery-aura-llama-v1-mkmlizer: quantizing model to /dev/shm/model_cache
theskullery-aura-llama-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
theskullery-aura-llama-v1-mkmlizer: 
Loading 0:   0%|          | 0/399 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 12/399 [00:00<00:03, 110.57it/s]
Loading 0:   6%|▌         | 24/399 [00:00<00:03, 107.87it/s]
Loading 0:  10%|▉         | 39/399 [00:00<00:02, 123.70it/s]
Loading 0:  13%|█▎        | 52/399 [00:00<00:02, 121.29it/s]
Loading 0:  17%|█▋        | 67/399 [00:00<00:02, 123.41it/s]
Loading 0:  21%|██        | 82/399 [00:00<00:02, 131.26it/s]
Loading 0:  24%|██▍       | 96/399 [00:00<00:02, 124.06it/s]
Loading 0:  28%|██▊       | 111/399 [00:00<00:02, 131.49it/s]
Loading 0:  31%|███▏      | 125/399 [00:01<00:02, 121.98it/s]
Loading 0:  35%|███▌      | 140/399 [00:01<00:02, 127.93it/s]
Loading 0:  38%|███▊      | 153/399 [00:01<00:01, 126.58it/s]
Loading 0:  42%|████▏     | 166/399 [00:01<00:01, 127.17it/s]
Loading 0:  45%|████▌     | 180/399 [00:01<00:01, 126.92it/s]
Loading 0:  48%|████▊     | 193/399 [00:01<00:03, 57.53it/s] 
Loading 0:  52%|█████▏    | 207/399 [00:02<00:02, 68.90it/s]
Loading 0:  56%|█████▌    | 222/399 [00:02<00:02, 83.32it/s]
Loading 0:  59%|█████▊    | 234/399 [00:02<00:01, 89.86it/s]
Loading 0:  62%|██████▏   | 248/399 [00:02<00:01, 100.71it/s]
Loading 0:  65%|██████▌   | 261/399 [00:02<00:01, 106.07it/s]
Loading 0:  69%|██████▉   | 276/399 [00:02<00:01, 117.10it/s]
Loading 0:  73%|███████▎  | 290/399 [00:02<00:00, 115.92it/s]
Loading 0:  77%|███████▋  | 306/399 [00:02<00:00, 122.62it/s]
Loading 0:  81%|████████  | 323/399 [00:02<00:00, 129.94it/s]
Loading 0:  84%|████████▍ | 337/399 [00:03<00:00, 129.27it/s]
Loading 0:  88%|████████▊ | 351/399 [00:03<00:00, 128.20it/s]
Loading 0:  92%|█████████▏| 368/399 [00:03<00:00, 134.60it/s]
Loading 0:  96%|█████████▌| 383/399 [00:03<00:00, 133.99it/s]
Loading 0:  99%|█████████▉| 397/399 [00:08<00:00,  8.46it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
theskullery-aura-llama-v1-mkmlizer: quantized model in 27.320s
theskullery-aura-llama-v1-mkmlizer: Processed model TheSkullery/Aura-llama in 88.686s
theskullery-aura-llama-v1-mkmlizer: creating bucket guanaco-mkml-models
theskullery-aura-llama-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
theskullery-aura-llama-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/theskullery-aura-llama-v1
theskullery-aura-llama-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/theskullery-aura-llama-v1/tokenizer.json
theskullery-aura-llama-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/theskullery-aura-llama-v1/special_tokens_map.json
theskullery-aura-llama-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/theskullery-aura-llama-v1/tokenizer_config.json
theskullery-aura-llama-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/theskullery-aura-llama-v1/config.json
theskullery-aura-llama-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/theskullery-aura-llama-v1/flywheel_model.0.safetensors
theskullery-aura-llama-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
theskullery-aura-llama-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.
theskullery-aura-llama-v1-mkmlizer:   warnings.warn(
theskullery-aura-llama-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.
theskullery-aura-llama-v1-mkmlizer:   warnings.warn(
theskullery-aura-llama-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.
theskullery-aura-llama-v1-mkmlizer:   warnings.warn(
theskullery-aura-llama-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()
theskullery-aura-llama-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
theskullery-aura-llama-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
theskullery-aura-llama-v1-mkmlizer: Saving duration: 0.405s
theskullery-aura-llama-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 146.814s
theskullery-aura-llama-v1-mkmlizer: creating bucket guanaco-reward-models
theskullery-aura-llama-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
theskullery-aura-llama-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/theskullery-aura-llama-v1_reward
theskullery-aura-llama-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/theskullery-aura-llama-v1_reward/special_tokens_map.json
theskullery-aura-llama-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/theskullery-aura-llama-v1_reward/merges.txt
theskullery-aura-llama-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/theskullery-aura-llama-v1_reward/vocab.json
theskullery-aura-llama-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/theskullery-aura-llama-v1_reward/tokenizer_config.json
theskullery-aura-llama-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/theskullery-aura-llama-v1_reward/config.json
theskullery-aura-llama-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/theskullery-aura-llama-v1_reward/tokenizer.json
theskullery-aura-llama-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/theskullery-aura-llama-v1_reward/reward.tensors
Job theskullery-aura-llama-v1-mkmlizer completed after 266.51s with status: succeeded
Stopping job with name theskullery-aura-llama-v1-mkmlizer
Pipeline stage MKMLizer completed in 270.86s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service theskullery-aura-llama-v1
Waiting for inference service theskullery-aura-llama-v1 to be ready
Inference service theskullery-aura-llama-v1 ready after 40.20586395263672s
Pipeline stage ISVCDeployer completed in 47.95s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4544408321380615s
Received healthy response to inference request in 1.4415779113769531s
Received healthy response to inference request in 1.3441798686981201s
Received healthy response to inference request in 2.7393195629119873s
Received healthy response to inference request in 1.1431233882904053s
5 requests
0 failed requests
5th percentile: 1.1833346843719483
10th percentile: 1.2235459804534912
20th percentile: 1.303968572616577
30th percentile: 1.3636594772338868
40th percentile: 1.40261869430542
50th percentile: 1.4415779113769531
60th percentile: 1.8467230796813965
70th percentile: 2.25186824798584
80th percentile: 2.5114165782928466
90th percentile: 2.625368070602417
95th percentile: 2.6823438167572022
99th percentile: 2.72792441368103
mean time: 1.8245283126831056
Pipeline stage StressChecker completed in 9.72s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
theskullery-aura-llama_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
theskullery-aura-llama_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of theskullery-aura-llama_v1
Running pipeline stage ISVCDeleter
Checking if service theskullery-aura-llama-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.48s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key theskullery-aura-llama-v1/config.json from bucket guanaco-mkml-models
Deleting key theskullery-aura-llama-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key theskullery-aura-llama-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key theskullery-aura-llama-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key theskullery-aura-llama-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key theskullery-aura-llama-v1_reward/config.json from bucket guanaco-reward-models
Deleting key theskullery-aura-llama-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key theskullery-aura-llama-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key theskullery-aura-llama-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key theskullery-aura-llama-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key theskullery-aura-llama-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key theskullery-aura-llama-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.63s
theskullery-aura-llama_v1 status is now torndown due to DeploymentManager action