submission_id: theskullery-aura-llama-a_3696_v1
developer_uid: Steelskull
best_of: 4
celo_rating: 1095.33
display_name: theskullery-aura-llama-a_3696_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-Abliterated-v3
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: TheSkullery/Aura-Llama-A
model_name: theskullery-aura-llama-a_3696_v1
model_num_parameters: 10647605248.0
model_repo: TheSkullery/Aura-Llama-Abliterated-v3
model_size: 11B
num_battles: 7623
num_wins: 2972
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: 2024-05-27T07:51:39+00:00
us_pacific_date: 2024-05-27
win_ratio: 0.38987275350911715
Resubmit model
Running pipeline stage MKMLizer
Starting job with name theskullery-aura-llama-a-3696-v1-mkmlizer
Waiting for job on theskullery-aura-llama-a-3696-v1-mkmlizer to finish
theskullery-aura-llama-a-3696-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
theskullery-aura-llama-a-3696-v1-mkmlizer: ║     _____            __           __                                ║
theskullery-aura-llama-a-3696-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
theskullery-aura-llama-a-3696-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
theskullery-aura-llama-a-3696-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
theskullery-aura-llama-a-3696-v1-mkmlizer: ║       /___/                                                         ║
theskullery-aura-llama-a-3696-v1-mkmlizer: ║                                                                     ║
theskullery-aura-llama-a-3696-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
theskullery-aura-llama-a-3696-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
theskullery-aura-llama-a-3696-v1-mkmlizer: ║  https://mk1.ai                                                     ║
theskullery-aura-llama-a-3696-v1-mkmlizer: ║                                                                     ║
theskullery-aura-llama-a-3696-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
theskullery-aura-llama-a-3696-v1-mkmlizer: ║  belonging to:                                                      ║
theskullery-aura-llama-a-3696-v1-mkmlizer: ║                                                                     ║
theskullery-aura-llama-a-3696-v1-mkmlizer: ║  Chai Research Corp.                                                ║
theskullery-aura-llama-a-3696-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
theskullery-aura-llama-a-3696-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
theskullery-aura-llama-a-3696-v1-mkmlizer: ║                                                                     ║
theskullery-aura-llama-a-3696-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
theskullery-aura-llama-a-3696-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-a-3696-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
theskullery-aura-llama-a-3696-v1-mkmlizer: Downloaded to shared memory in 209.751s
theskullery-aura-llama-a-3696-v1-mkmlizer: quantizing model to /dev/shm/model_cache
theskullery-aura-llama-a-3696-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
theskullery-aura-llama-a-3696-v1-mkmlizer: 
Loading 0:   0%|          | 0/399 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/399 [00:04<15:18,  2.31s/it]
Loading 0:   4%|▎         | 14/399 [00:04<01:36,  3.99it/s]
Loading 0:   7%|▋         | 27/399 [00:04<00:40,  9.14it/s]
Loading 0:  10%|█         | 41/399 [00:04<00:22, 16.18it/s]
Loading 0:  14%|█▎        | 54/399 [00:05<00:14, 24.38it/s]
Loading 0:  17%|█▋        | 66/399 [00:05<00:12, 27.08it/s]
Loading 0:  19%|█▉        | 77/399 [00:05<00:09, 34.80it/s]
Loading 0:  23%|██▎       | 90/399 [00:05<00:06, 46.33it/s]
Loading 0:  26%|██▋       | 105/399 [00:05<00:04, 59.91it/s]
Loading 0:  30%|██▉       | 119/399 [00:05<00:03, 72.90it/s]
Loading 0:  33%|███▎      | 132/399 [00:05<00:03, 81.90it/s]
Loading 0:  36%|███▋      | 145/399 [00:06<00:02, 91.75it/s]
Loading 0:  40%|███▉      | 159/399 [00:06<00:02, 98.72it/s]
Loading 0:  43%|████▎     | 171/399 [00:06<00:03, 66.16it/s]
Loading 0:  46%|████▌     | 184/399 [00:06<00:02, 77.10it/s]
Loading 0:  49%|████▉     | 195/399 [00:06<00:02, 81.60it/s]
Loading 0:  53%|█████▎    | 211/399 [00:06<00:01, 97.05it/s]
Loading 0:  56%|█████▌    | 223/399 [00:06<00:01, 98.62it/s]
Loading 0:  60%|█████▉    | 239/399 [00:07<00:01, 111.16it/s]
Loading 0:  63%|██████▎   | 252/399 [00:07<00:01, 110.72it/s]
Loading 0:  67%|██████▋   | 266/399 [00:07<00:01, 115.68it/s]
Loading 0:  70%|██████▉   | 279/399 [00:07<00:01, 67.90it/s] 
Loading 0:  74%|███████▎  | 294/399 [00:07<00:01, 81.10it/s]
Loading 0:  76%|███████▋  | 305/399 [00:07<00:01, 81.47it/s]
Loading 0:  80%|████████  | 321/399 [00:08<00:00, 96.44it/s]
Loading 0:  83%|████████▎ | 333/399 [00:08<00:00, 98.57it/s]
Loading 0:  87%|████████▋ | 348/399 [00:08<00:00, 109.15it/s]
Loading 0:  90%|█████████ | 361/399 [00:08<00:00, 110.38it/s]
Loading 0:  93%|█████████▎| 373/399 [00:08<00:00, 71.97it/s] 
Loading 0:  96%|█████████▌| 384/399 [00:08<00:00, 77.19it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
theskullery-aura-llama-a-3696-v1-mkmlizer: quantized model in 27.723s
theskullery-aura-llama-a-3696-v1-mkmlizer: Processed model TheSkullery/Aura-Llama-Abliterated-v3 in 240.743s
theskullery-aura-llama-a-3696-v1-mkmlizer: creating bucket guanaco-mkml-models
theskullery-aura-llama-a-3696-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
theskullery-aura-llama-a-3696-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/theskullery-aura-llama-a-3696-v1
theskullery-aura-llama-a-3696-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/theskullery-aura-llama-a-3696-v1/config.json
theskullery-aura-llama-a-3696-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/theskullery-aura-llama-a-3696-v1/tokenizer_config.json
theskullery-aura-llama-a-3696-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/theskullery-aura-llama-a-3696-v1/special_tokens_map.json
theskullery-aura-llama-a-3696-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/theskullery-aura-llama-a-3696-v1/flywheel_model.0.safetensors
theskullery-aura-llama-a-3696-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
theskullery-aura-llama-a-3696-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-a-3696-v1-mkmlizer:   warnings.warn(
theskullery-aura-llama-a-3696-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-a-3696-v1-mkmlizer:   warnings.warn(
theskullery-aura-llama-a-3696-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-a-3696-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
theskullery-aura-llama-a-3696-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
theskullery-aura-llama-a-3696-v1-mkmlizer: Saving duration: 0.397s
theskullery-aura-llama-a-3696-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.707s
theskullery-aura-llama-a-3696-v1-mkmlizer: creating bucket guanaco-reward-models
theskullery-aura-llama-a-3696-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
theskullery-aura-llama-a-3696-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/theskullery-aura-llama-a-3696-v1_reward
theskullery-aura-llama-a-3696-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/theskullery-aura-llama-a-3696-v1_reward/special_tokens_map.json
theskullery-aura-llama-a-3696-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/theskullery-aura-llama-a-3696-v1_reward/tokenizer_config.json
theskullery-aura-llama-a-3696-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/theskullery-aura-llama-a-3696-v1_reward/merges.txt
theskullery-aura-llama-a-3696-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/theskullery-aura-llama-a-3696-v1_reward/config.json
theskullery-aura-llama-a-3696-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/theskullery-aura-llama-a-3696-v1_reward/vocab.json
theskullery-aura-llama-a-3696-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/theskullery-aura-llama-a-3696-v1_reward/tokenizer.json
theskullery-aura-llama-a-3696-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/theskullery-aura-llama-a-3696-v1_reward/reward.tensors
Job theskullery-aura-llama-a-3696-v1-mkmlizer completed after 276.95s with status: succeeded
Stopping job with name theskullery-aura-llama-a-3696-v1-mkmlizer
Pipeline stage MKMLizer completed in 277.69s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service theskullery-aura-llama-a-3696-v1
Waiting for inference service theskullery-aura-llama-a-3696-v1 to be ready
Inference service theskullery-aura-llama-a-3696-v1 ready after 40.20535898208618s
Pipeline stage ISVCDeployer completed in 45.98s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2781901359558105s
Received healthy response to inference request in 1.0846176147460938s
Received healthy response to inference request in 1.2260503768920898s
Received healthy response to inference request in 1.0102119445800781s
Received healthy response to inference request in 0.7767634391784668s
5 requests
0 failed requests
5th percentile: 0.823453140258789
10th percentile: 0.8701428413391114
20th percentile: 0.9635222434997559
30th percentile: 1.0250930786132812
40th percentile: 1.0548553466796875
50th percentile: 1.0846176147460938
60th percentile: 1.1411907196044921
70th percentile: 1.1977638244628905
80th percentile: 1.4364783287048342
90th percentile: 1.8573342323303224
95th percentile: 2.0677621841430662
99th percentile: 2.2361045455932618
mean time: 1.2751667022705078
Pipeline stage StressChecker completed in 7.01s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
theskullery-aura-llama-a_3696_v1 status is now deployed due to DeploymentManager action
theskullery-aura-llama-a_3696_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of theskullery-aura-llama-a_3696_v1
Running pipeline stage ISVCDeleter
Checking if service theskullery-aura-llama-a-3696-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.92s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key theskullery-aura-llama-a-3696-v1/config.json from bucket guanaco-mkml-models
Deleting key theskullery-aura-llama-a-3696-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key theskullery-aura-llama-a-3696-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key theskullery-aura-llama-a-3696-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key theskullery-aura-llama-a-3696-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key theskullery-aura-llama-a-3696-v1_reward/config.json from bucket guanaco-reward-models
Deleting key theskullery-aura-llama-a-3696-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key theskullery-aura-llama-a-3696-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key theskullery-aura-llama-a-3696-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key theskullery-aura-llama-a-3696-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key theskullery-aura-llama-a-3696-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key theskullery-aura-llama-a-3696-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.42s
theskullery-aura-llama-a_3696_v1 status is now torndown due to DeploymentManager action