wespro-dr-erp-samantha-l_6764

submission_id: wespro-dr-erp-samantha-l_6764_v1

developer_uid: WesPro

best_of: 4

celo_rating: 1168.05

display_name: wespro-dr-erp-samantha-l_6764_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': 4, 'max_output_tokens': 64}

is_internal_developer: False

language_model: WesPro/Dr.eRP.Samantha-Llama3_8B

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_eval_status: success

model_group: WesPro/Dr.eRP.Samantha-L

model_name: wespro-dr-erp-samantha-l_6764_v1

model_num_parameters: 8030261248.0

model_repo: WesPro/Dr.eRP.Samantha-Llama3_8B

model_size: 8B

num_battles: 17009

num_wins: 8504

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: 2024-06-05T19:49:57+00:00

us_pacific_date: 2024-06-05

win_ratio: 0.4999706037979893

Resubmit model

Running pipeline stage MKMLizer
Starting job with name wespro-dr-erp-samantha-l-6764-v1-mkmlizer
Waiting for job on wespro-dr-erp-samantha-l-6764-v1-mkmlizer to finish
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: ║     _____            __           __                                ║
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: ║       /___/                                                         ║
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: ║                                                                     ║
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: ║  https://mk1.ai                                                     ║
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: ║                                                                     ║
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: ║  belonging to:                                                      ║
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: ║                                                                     ║
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: ║  Chai Research Corp.                                                ║
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: ║                                                                     ║
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
wespro-dr-erp-samantha-l-6764-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.
wespro-dr-erp-samantha-l-6764-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: Downloaded to shared memory in 41.047s
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: quantizing model to /dev/shm/model_cache
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<09:52,  2.05s/it]
Loading 0:   5%|▌         | 15/291 [00:04<00:57,  4.83it/s]
Loading 0:  11%|█▏        | 33/291 [00:04<00:20, 12.77it/s]
Loading 0:  18%|█▊        | 51/291 [00:04<00:10, 22.80it/s]
Loading 0:  22%|██▏       | 65/291 [00:04<00:08, 25.77it/s]
Loading 0:  27%|██▋       | 78/291 [00:04<00:06, 34.22it/s]
Loading 0:  33%|███▎      | 95/291 [00:05<00:04, 48.34it/s]
Loading 0:  38%|███▊      | 112/291 [00:05<00:02, 63.85it/s]
Loading 0:  44%|████▎     | 127/291 [00:05<00:02, 76.88it/s]
Loading 0:  48%|████▊     | 141/291 [00:05<00:01, 87.16it/s]
Loading 0:  54%|█████▍    | 158/291 [00:05<00:01, 103.26it/s]
Loading 0:  59%|█████▉    | 173/291 [00:05<00:01, 67.02it/s] 
Loading 0:  64%|██████▍   | 186/291 [00:05<00:01, 76.98it/s]
Loading 0:  70%|███████   | 204/291 [00:06<00:00, 94.03it/s]
Loading 0:  76%|███████▋  | 222/291 [00:06<00:00, 109.49it/s]
Loading 0:  82%|████████▏ | 240/291 [00:06<00:00, 122.65it/s]
Loading 0:  89%|████████▊ | 258/291 [00:06<00:00, 133.29it/s]
Loading 0:  94%|█████████▍| 274/291 [00:06<00:00, 81.09it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: quantized model in 18.886s
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: Processed model WesPro/Dr.eRP.Samantha-Llama3_8B in 60.994s
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: creating bucket guanaco-mkml-models
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/wespro-dr-erp-samantha-l-6764-v1
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/wespro-dr-erp-samantha-l-6764-v1/config.json
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/wespro-dr-erp-samantha-l-6764-v1/special_tokens_map.json
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/wespro-dr-erp-samantha-l-6764-v1/tokenizer_config.json
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/wespro-dr-erp-samantha-l-6764-v1/tokenizer.json
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/wespro-dr-erp-samantha-l-6764-v1/flywheel_model.0.safetensors
wespro-dr-erp-samantha-l-6764-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.
wespro-dr-erp-samantha-l-6764-v1-mkmlizer:   warnings.warn(
wespro-dr-erp-samantha-l-6764-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.
wespro-dr-erp-samantha-l-6764-v1-mkmlizer:   warnings.warn(
wespro-dr-erp-samantha-l-6764-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()
wespro-dr-erp-samantha-l-6764-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: Saving duration: 0.318s
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.648s
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: creating bucket guanaco-reward-models
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/wespro-dr-erp-samantha-l-6764-v1_reward
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/wespro-dr-erp-samantha-l-6764-v1_reward/config.json
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/wespro-dr-erp-samantha-l-6764-v1_reward/special_tokens_map.json
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/wespro-dr-erp-samantha-l-6764-v1_reward/tokenizer_config.json
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/wespro-dr-erp-samantha-l-6764-v1_reward/merges.txt
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/wespro-dr-erp-samantha-l-6764-v1_reward/vocab.json
wespro-dr-erp-samantha-l-6764-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/wespro-dr-erp-samantha-l-6764-v1_reward/tokenizer.json
Job wespro-dr-erp-samantha-l-6764-v1-mkmlizer completed after 94.67s with status: succeeded
Stopping job with name wespro-dr-erp-samantha-l-6764-v1-mkmlizer
Pipeline stage MKMLizer completed in 98.23s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service wespro-dr-erp-samantha-l-6764-v1
Waiting for inference service wespro-dr-erp-samantha-l-6764-v1 to be ready
Inference service wespro-dr-erp-samantha-l-6764-v1 ready after 90.85068845748901s
Pipeline stage ISVCDeployer completed in 97.95s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.038616180419922s
Received healthy response to inference request in 1.1250338554382324s
Received healthy response to inference request in 1.1324031352996826s
Received healthy response to inference request in 1.1186881065368652s
Received healthy response to inference request in 1.1178641319274902s
5 requests
0 failed requests
5th percentile: 1.1180289268493653
10th percentile: 1.1181937217712403
20th percentile: 1.1185233116149902
30th percentile: 1.1199572563171387
40th percentile: 1.1224955558776855
50th percentile: 1.1250338554382324
60th percentile: 1.1279815673828124
70th percentile: 1.1309292793273926
80th percentile: 1.3136457443237306
90th percentile: 1.6761309623718263
95th percentile: 1.857373571395874
99th percentile: 2.0023676586151122
mean time: 1.3065210819244384
Pipeline stage StressChecker completed in 7.19s
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
wespro-dr-erp-samantha-l_6764_v1 status is now deployed due to DeploymentManager action
wespro-dr-erp-samantha-l_6764_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of wespro-dr-erp-samantha-l_6764_v1
Running pipeline stage ISVCDeleter
Checking if service wespro-dr-erp-samantha-l-6764-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.84s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key wespro-dr-erp-samantha-l-6764-v1/config.json from bucket guanaco-mkml-models
Deleting key wespro-dr-erp-samantha-l-6764-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key wespro-dr-erp-samantha-l-6764-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key wespro-dr-erp-samantha-l-6764-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key wespro-dr-erp-samantha-l-6764-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key wespro-dr-erp-samantha-l-6764-v1_reward/config.json from bucket guanaco-reward-models
Deleting key wespro-dr-erp-samantha-l-6764-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key wespro-dr-erp-samantha-l-6764-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key wespro-dr-erp-samantha-l-6764-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key wespro-dr-erp-samantha-l-6764-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key wespro-dr-erp-samantha-l-6764-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key wespro-dr-erp-samantha-l-6764-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.10s
wespro-dr-erp-samantha-l_6764_v1 status is now torndown due to DeploymentManager action