developer_uid: Azazelle
submission_id: undi95-llama-3-lewdplay-_3862_v9
model_name: undi95-llama-3-lewdplay-_3862_v9
model_group: Undi95/Llama-3-LewdPlay-
status: torndown
timestamp: 2024-07-06T00:11:02+00:00
num_battles: 34600
num_wins: 17361
celo_rating: 1184.28
family_friendly_score: 0.0
submission_type: basic
model_repo: Undi95/Llama-3-LewdPlay-8B-evo
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: undi95-llama-3-lewdplay-_3862_v9
is_internal_developer: False
language_model: Undi95/Llama-3-LewdPlay-8B-evo
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-05
win_ratio: 0.5017630057803468
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<eot_id>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
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'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name undi95-llama-3-lewdplay-3862-v9-mkmlizer
Waiting for job on undi95-llama-3-lewdplay-3862-v9-mkmlizer to finish
undi95-llama-3-lewdplay-3862-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
undi95-llama-3-lewdplay-3862-v9-mkmlizer: ║     _____            __           __                                ║
undi95-llama-3-lewdplay-3862-v9-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
undi95-llama-3-lewdplay-3862-v9-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
undi95-llama-3-lewdplay-3862-v9-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
undi95-llama-3-lewdplay-3862-v9-mkmlizer: ║       /___/                                                         ║
undi95-llama-3-lewdplay-3862-v9-mkmlizer: ║                                                                     ║
undi95-llama-3-lewdplay-3862-v9-mkmlizer: ║  Version: 0.8.14                                                    ║
undi95-llama-3-lewdplay-3862-v9-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
undi95-llama-3-lewdplay-3862-v9-mkmlizer: ║  https://mk1.ai                                                     ║
undi95-llama-3-lewdplay-3862-v9-mkmlizer: ║                                                                     ║
undi95-llama-3-lewdplay-3862-v9-mkmlizer: ║  The license key for the current software has been verified as      ║
undi95-llama-3-lewdplay-3862-v9-mkmlizer: ║  belonging to:                                                      ║
undi95-llama-3-lewdplay-3862-v9-mkmlizer: ║                                                                     ║
undi95-llama-3-lewdplay-3862-v9-mkmlizer: ║  Chai Research Corp.                                                ║
undi95-llama-3-lewdplay-3862-v9-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
undi95-llama-3-lewdplay-3862-v9-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
undi95-llama-3-lewdplay-3862-v9-mkmlizer: ║                                                                     ║
undi95-llama-3-lewdplay-3862-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
undi95-llama-3-lewdplay-3862-v9-mkmlizer: Downloaded to shared memory in 28.231s
undi95-llama-3-lewdplay-3862-v9-mkmlizer: quantizing model to /dev/shm/model_cache
undi95-llama-3-lewdplay-3862-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
undi95-llama-3-lewdplay-3862-v9-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:05<13:03,  2.71s/it]
Loading 0:   4%|▍         | 13/291 [00:05<01:27,  3.18it/s]
Loading 0:   8%|▊         | 24/291 [00:05<00:38,  6.91it/s]
Loading 0:  14%|█▎        | 40/291 [00:05<00:17, 14.15it/s]
Loading 0:  18%|█▊        | 51/291 [00:05<00:12, 19.99it/s]
Loading 0:  23%|██▎       | 67/291 [00:05<00:07, 30.99it/s]
Loading 0:  27%|██▋       | 79/291 [00:06<00:05, 39.10it/s]
Loading 0:  32%|███▏      | 94/291 [00:06<00:03, 52.00it/s]
Loading 0:  36%|███▋      | 106/291 [00:06<00:03, 60.15it/s]
Loading 0:  41%|████      | 118/291 [00:06<00:02, 70.31it/s]
Loading 0:  45%|████▍     | 130/291 [00:06<00:02, 78.88it/s]
Loading 0:  49%|████▉     | 142/291 [00:06<00:01, 83.00it/s]
Loading 0:  53%|█████▎    | 155/291 [00:06<00:01, 93.30it/s]
Loading 0:  57%|█████▋    | 167/291 [00:07<00:02, 44.39it/s]
Loading 0:  61%|██████    | 177/291 [00:07<00:02, 51.06it/s]
Loading 0:  66%|██████▌   | 191/291 [00:07<00:01, 65.04it/s]
Loading 0:  69%|██████▉   | 202/291 [00:07<00:01, 72.25it/s]
Loading 0:  73%|███████▎  | 213/291 [00:07<00:01, 74.84it/s]
Loading 0:  78%|███████▊  | 226/291 [00:07<00:00, 86.48it/s]
Loading 0:  82%|████████▏ | 238/291 [00:08<00:00, 91.57it/s]
Loading 0:  86%|████████▌ | 249/291 [00:08<00:00, 88.09it/s]
Loading 0:  90%|████████▉ | 261/291 [00:08<00:00, 95.82it/s]
Loading 0:  94%|█████████▍| 274/291 [00:08<00:00, 100.40it/s]
Loading 0:  98%|█████████▊| 285/291 [00:08<00:00, 94.64it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
undi95-llama-3-lewdplay-3862-v9-mkmlizer: quantized model in 25.719s
undi95-llama-3-lewdplay-3862-v9-mkmlizer: Processed model Undi95/Llama-3-LewdPlay-8B-evo in 53.950s
undi95-llama-3-lewdplay-3862-v9-mkmlizer: creating bucket guanaco-mkml-models
undi95-llama-3-lewdplay-3862-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
undi95-llama-3-lewdplay-3862-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/undi95-llama-3-lewdplay-3862-v9
undi95-llama-3-lewdplay-3862-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/undi95-llama-3-lewdplay-3862-v9/tokenizer_config.json
undi95-llama-3-lewdplay-3862-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/undi95-llama-3-lewdplay-3862-v9/special_tokens_map.json
undi95-llama-3-lewdplay-3862-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/undi95-llama-3-lewdplay-3862-v9/config.json
undi95-llama-3-lewdplay-3862-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/undi95-llama-3-lewdplay-3862-v9/tokenizer.json
undi95-llama-3-lewdplay-3862-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/undi95-llama-3-lewdplay-3862-v9/flywheel_model.0.safetensors
undi95-llama-3-lewdplay-3862-v9-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
undi95-llama-3-lewdplay-3862-v9-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
undi95-llama-3-lewdplay-3862-v9-mkmlizer:   warnings.warn(
undi95-llama-3-lewdplay-3862-v9-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
undi95-llama-3-lewdplay-3862-v9-mkmlizer:   warnings.warn(
undi95-llama-3-lewdplay-3862-v9-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
undi95-llama-3-lewdplay-3862-v9-mkmlizer:   warnings.warn(
undi95-llama-3-lewdplay-3862-v9-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.
undi95-llama-3-lewdplay-3862-v9-mkmlizer:   warnings.warn(
undi95-llama-3-lewdplay-3862-v9-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()
undi95-llama-3-lewdplay-3862-v9-mkmlizer:   return self.fget.__get__(instance, owner)()
undi95-llama-3-lewdplay-3862-v9-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
undi95-llama-3-lewdplay-3862-v9-mkmlizer: Saving duration: 0.401s
undi95-llama-3-lewdplay-3862-v9-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.539s
undi95-llama-3-lewdplay-3862-v9-mkmlizer: creating bucket guanaco-reward-models
undi95-llama-3-lewdplay-3862-v9-mkmlizer: Bucket 's3://guanaco-reward-models/' created
undi95-llama-3-lewdplay-3862-v9-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v9_reward
undi95-llama-3-lewdplay-3862-v9-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v9_reward/config.json
undi95-llama-3-lewdplay-3862-v9-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v9_reward/special_tokens_map.json
undi95-llama-3-lewdplay-3862-v9-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v9_reward/tokenizer_config.json
undi95-llama-3-lewdplay-3862-v9-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v9_reward/merges.txt
undi95-llama-3-lewdplay-3862-v9-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v9_reward/vocab.json
undi95-llama-3-lewdplay-3862-v9-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v9_reward/tokenizer.json
Job undi95-llama-3-lewdplay-3862-v9-mkmlizer completed after 84.5s with status: succeeded
Stopping job with name undi95-llama-3-lewdplay-3862-v9-mkmlizer
Pipeline stage MKMLizer completed in 85.30s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service undi95-llama-3-lewdplay-3862-v9
Waiting for inference service undi95-llama-3-lewdplay-3862-v9 to be ready
Inference service undi95-llama-3-lewdplay-3862-v9 ready after 40.34247446060181s
Pipeline stage ISVCDeployer completed in 47.17s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0774786472320557s
Received healthy response to inference request in 1.3380305767059326s
Received healthy response to inference request in 1.2085893154144287s
Received healthy response to inference request in 1.286677598953247s
Received healthy response to inference request in 1.3509318828582764s
5 requests
0 failed requests
5th percentile: 1.2242069721221924
10th percentile: 1.2398246288299561
20th percentile: 1.2710599422454834
30th percentile: 1.2969481945037842
40th percentile: 1.3174893856048584
50th percentile: 1.3380305767059326
60th percentile: 1.34319109916687
70th percentile: 1.3483516216278075
80th percentile: 1.4962412357330324
90th percentile: 1.7868599414825441
95th percentile: 1.9321692943572997
99th percentile: 2.0484167766571044
mean time: 1.4523416042327881
Pipeline stage StressChecker completed in 8.00s
undi95-llama-3-lewdplay-_3862_v9 status is now deployed due to DeploymentManager action
undi95-llama-3-lewdplay-_3862_v9 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of undi95-llama-3-lewdplay-_3862_v9
Running pipeline stage ISVCDeleter
Checking if service undi95-llama-3-lewdplay-3862-v9 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.88s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key undi95-llama-3-lewdplay-3862-v9/config.json from bucket guanaco-mkml-models
Deleting key undi95-llama-3-lewdplay-3862-v9/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key undi95-llama-3-lewdplay-3862-v9/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key undi95-llama-3-lewdplay-3862-v9/tokenizer.json from bucket guanaco-mkml-models
Deleting key undi95-llama-3-lewdplay-3862-v9/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key undi95-llama-3-lewdplay-3862-v9_reward/config.json from bucket guanaco-reward-models
Deleting key undi95-llama-3-lewdplay-3862-v9_reward/merges.txt from bucket guanaco-reward-models
Deleting key undi95-llama-3-lewdplay-3862-v9_reward/reward.tensors from bucket guanaco-reward-models
Deleting key undi95-llama-3-lewdplay-3862-v9_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key undi95-llama-3-lewdplay-3862-v9_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key undi95-llama-3-lewdplay-3862-v9_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key undi95-llama-3-lewdplay-3862-v9_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.40s
undi95-llama-3-lewdplay-_3862_v9 status is now torndown due to DeploymentManager action