developer_uid: Azazelle
submission_id: undi95-llama-3-lewdplay_3862_v10
model_name: undi95-lewdplay-evo
model_group: Undi95/Llama-3-LewdPlay-
status: torndown
timestamp: 2024-07-06T01:03:22+00:00
num_battles: 31154
num_wins: 14934
celo_rating: 1169.33
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-lewdplay-evo
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: 0.47936059575014445
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-v10-mkmlizer
Waiting for job on undi95-llama-3-lewdplay-3862-v10-mkmlizer to finish
undi95-llama-3-lewdplay-3862-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
undi95-llama-3-lewdplay-3862-v10-mkmlizer: ║     _____            __           __                                ║
undi95-llama-3-lewdplay-3862-v10-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
undi95-llama-3-lewdplay-3862-v10-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
undi95-llama-3-lewdplay-3862-v10-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
undi95-llama-3-lewdplay-3862-v10-mkmlizer: ║       /___/                                                         ║
undi95-llama-3-lewdplay-3862-v10-mkmlizer: ║                                                                     ║
undi95-llama-3-lewdplay-3862-v10-mkmlizer: ║  Version: 0.8.14                                                    ║
undi95-llama-3-lewdplay-3862-v10-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
undi95-llama-3-lewdplay-3862-v10-mkmlizer: ║  https://mk1.ai                                                     ║
undi95-llama-3-lewdplay-3862-v10-mkmlizer: ║                                                                     ║
undi95-llama-3-lewdplay-3862-v10-mkmlizer: ║  The license key for the current software has been verified as      ║
undi95-llama-3-lewdplay-3862-v10-mkmlizer: ║  belonging to:                                                      ║
undi95-llama-3-lewdplay-3862-v10-mkmlizer: ║                                                                     ║
undi95-llama-3-lewdplay-3862-v10-mkmlizer: ║  Chai Research Corp.                                                ║
undi95-llama-3-lewdplay-3862-v10-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
undi95-llama-3-lewdplay-3862-v10-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
undi95-llama-3-lewdplay-3862-v10-mkmlizer: ║                                                                     ║
undi95-llama-3-lewdplay-3862-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
undi95-llama-3-lewdplay-3862-v10-mkmlizer: Downloaded to shared memory in 18.920s
undi95-llama-3-lewdplay-3862-v10-mkmlizer: quantizing model to /dev/shm/model_cache
undi95-llama-3-lewdplay-3862-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
undi95-llama-3-lewdplay-3862-v10-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:25,  2.37s/it]
Loading 0:   4%|▍         | 13/291 [00:04<01:16,  3.63it/s]
Loading 0:   8%|▊         | 24/291 [00:04<00:34,  7.84it/s]
Loading 0:  14%|█▎        | 40/291 [00:05<00:15, 15.92it/s]
Loading 0:  18%|█▊        | 51/291 [00:05<00:10, 22.29it/s]
Loading 0:  23%|██▎       | 67/291 [00:05<00:06, 34.29it/s]
Loading 0:  27%|██▋       | 79/291 [00:05<00:04, 42.98it/s]
Loading 0:  32%|███▏      | 94/291 [00:05<00:03, 56.67it/s]
Loading 0:  36%|███▋      | 106/291 [00:05<00:02, 64.96it/s]
Loading 0:  42%|████▏     | 121/291 [00:05<00:02, 79.00it/s]
Loading 0:  46%|████▌     | 133/291 [00:05<00:01, 84.25it/s]
Loading 0:  51%|█████     | 148/291 [00:05<00:01, 96.38it/s]
Loading 0:  55%|█████▌    | 161/291 [00:06<00:01, 99.70it/s]
Loading 0:  59%|█████▉    | 173/291 [00:06<00:02, 49.97it/s]
Loading 0:  64%|██████▎   | 185/291 [00:06<00:01, 58.56it/s]
Loading 0:  68%|██████▊   | 198/291 [00:06<00:01, 69.94it/s]
Loading 0:  73%|███████▎  | 211/291 [00:06<00:00, 80.89it/s]
Loading 0:  76%|███████▋  | 222/291 [00:07<00:00, 83.79it/s]
Loading 0:  82%|████████▏ | 238/291 [00:07<00:00, 98.47it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:00, 99.23it/s]
Loading 0:  91%|█████████ | 265/291 [00:07<00:00, 108.82it/s]
Loading 0:  95%|█████████▌| 277/291 [00:07<00:00, 107.32it/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-v10-mkmlizer: quantized model in 23.983s
undi95-llama-3-lewdplay-3862-v10-mkmlizer: Processed model Undi95/Llama-3-LewdPlay-8B-evo in 42.903s
undi95-llama-3-lewdplay-3862-v10-mkmlizer: creating bucket guanaco-mkml-models
undi95-llama-3-lewdplay-3862-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
undi95-llama-3-lewdplay-3862-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/undi95-llama-3-lewdplay-3862-v10
undi95-llama-3-lewdplay-3862-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/undi95-llama-3-lewdplay-3862-v10/config.json
undi95-llama-3-lewdplay-3862-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/undi95-llama-3-lewdplay-3862-v10/tokenizer_config.json
undi95-llama-3-lewdplay-3862-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/undi95-llama-3-lewdplay-3862-v10/special_tokens_map.json
undi95-llama-3-lewdplay-3862-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/undi95-llama-3-lewdplay-3862-v10/tokenizer.json
undi95-llama-3-lewdplay-3862-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/undi95-llama-3-lewdplay-3862-v10/flywheel_model.0.safetensors
undi95-llama-3-lewdplay-3862-v10-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
undi95-llama-3-lewdplay-3862-v10-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-v10-mkmlizer:   warnings.warn(
undi95-llama-3-lewdplay-3862-v10-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-v10-mkmlizer:   warnings.warn(
undi95-llama-3-lewdplay-3862-v10-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-v10-mkmlizer:   warnings.warn(
undi95-llama-3-lewdplay-3862-v10-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-v10-mkmlizer:   warnings.warn(
undi95-llama-3-lewdplay-3862-v10-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-v10-mkmlizer:   return self.fget.__get__(instance, owner)()
undi95-llama-3-lewdplay-3862-v10-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
undi95-llama-3-lewdplay-3862-v10-mkmlizer: Saving duration: 0.407s
undi95-llama-3-lewdplay-3862-v10-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.002s
undi95-llama-3-lewdplay-3862-v10-mkmlizer: creating bucket guanaco-reward-models
undi95-llama-3-lewdplay-3862-v10-mkmlizer: Bucket 's3://guanaco-reward-models/' created
undi95-llama-3-lewdplay-3862-v10-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v10_reward
undi95-llama-3-lewdplay-3862-v10-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v10_reward/config.json
undi95-llama-3-lewdplay-3862-v10-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v10_reward/special_tokens_map.json
undi95-llama-3-lewdplay-3862-v10-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v10_reward/merges.txt
undi95-llama-3-lewdplay-3862-v10-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v10_reward/vocab.json
undi95-llama-3-lewdplay-3862-v10-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v10_reward/tokenizer_config.json
undi95-llama-3-lewdplay-3862-v10-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v10_reward/tokenizer.json
undi95-llama-3-lewdplay-3862-v10-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v10_reward/reward.tensors
Job undi95-llama-3-lewdplay-3862-v10-mkmlizer completed after 108.44s with status: succeeded
Stopping job with name undi95-llama-3-lewdplay-3862-v10-mkmlizer
Pipeline stage MKMLizer completed in 109.42s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service undi95-llama-3-lewdplay-3862-v10
Waiting for inference service undi95-llama-3-lewdplay-3862-v10 to be ready
Inference service undi95-llama-3-lewdplay-3862-v10 ready after 50.229487895965576s
Pipeline stage ISVCDeployer completed in 57.59s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.072894334793091s
Received healthy response to inference request in 1.3533790111541748s
Received healthy response to inference request in 1.3113222122192383s
Received healthy response to inference request in 1.3072924613952637s
Received healthy response to inference request in 1.3810381889343262s
5 requests
0 failed requests
5th percentile: 1.3080984115600587
10th percentile: 1.3089043617248535
20th percentile: 1.3105162620544433
30th percentile: 1.3197335720062255
40th percentile: 1.3365562915802003
50th percentile: 1.3533790111541748
60th percentile: 1.3644426822662354
70th percentile: 1.3755063533782959
80th percentile: 1.519409418106079
90th percentile: 1.796151876449585
95th percentile: 1.934523105621338
99th percentile: 2.0452200889587404
mean time: 1.4851852416992188
Pipeline stage StressChecker completed in 8.26s
undi95-llama-3-lewdplay_3862_v10 status is now deployed due to DeploymentManager action
undi95-llama-3-lewdplay_3862_v10 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of undi95-llama-3-lewdplay_3862_v10
Running pipeline stage ISVCDeleter
Checking if service undi95-llama-3-lewdplay-3862-v10 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.63s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key undi95-llama-3-lewdplay-3862-v10/config.json from bucket guanaco-mkml-models
Deleting key undi95-llama-3-lewdplay-3862-v10/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key undi95-llama-3-lewdplay-3862-v10/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key undi95-llama-3-lewdplay-3862-v10/tokenizer.json from bucket guanaco-mkml-models
Deleting key undi95-llama-3-lewdplay-3862-v10/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key undi95-llama-3-lewdplay-3862-v10_reward/config.json from bucket guanaco-reward-models
Deleting key undi95-llama-3-lewdplay-3862-v10_reward/merges.txt from bucket guanaco-reward-models
Deleting key undi95-llama-3-lewdplay-3862-v10_reward/reward.tensors from bucket guanaco-reward-models
Deleting key undi95-llama-3-lewdplay-3862-v10_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key undi95-llama-3-lewdplay-3862-v10_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key undi95-llama-3-lewdplay-3862-v10_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key undi95-llama-3-lewdplay-3862-v10_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.32s
undi95-llama-3-lewdplay_3862_v10 status is now torndown due to DeploymentManager action