wespro-daringrp-l3ama-8b

submission_id: wespro-daringrp-l3ama-8b_v1
developer_uid: WesPro
best_of: 4
celo_rating: 1181.02
display_name: wespro-daringrp-l3ama-8b_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/DaringRP-L3ama-8B
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: WesPro/DaringRP-L3ama-8B
model_name: wespro-daringrp-l3ama-8b_v1
model_num_parameters: 8030261248.0
model_repo: WesPro/DaringRP-L3ama-8B
model_size: 8B
num_battles: 20325
num_wins: 10007
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: 2024-06-04T17:01:35+00:00
us_pacific_date: 2024-06-04
win_ratio: 0.49234932349323496
Resubmit model
Running pipeline stage MKMLizer
Starting job with name wespro-daringrp-l3ama-8b-v1-mkmlizer
Waiting for job on wespro-daringrp-l3ama-8b-v1-mkmlizer to finish
Stopping job with name wespro-daringrp-l3ama-8b-v1-mkmlizer
%s, retrying in %s seconds...
Stopping job with name wespro-daringrp-l3ama-8b-v1-mkmlizer
%s, retrying in %s seconds...
Stopping job with name wespro-daringrp-l3ama-8b-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name wespro-daringrp-l3ama-8b-v1-mkmlizer
Waiting for job on wespro-daringrp-l3ama-8b-v1-mkmlizer to finish
wespro-daringrp-l3ama-8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║     _____            __           __                                ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║       /___/                                                         ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║                                                                     ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║  https://mk1.ai                                                     ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║                                                                     ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║  belonging to:                                                      ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║                                                                     ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║  Chai Research Corp.                                                ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║                                                                     ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
wespro-daringrp-l3ama-8b-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-daringrp-l3ama-8b-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
wespro-daringrp-l3ama-8b-v1-mkmlizer: Downloaded to shared memory in 29.149s
wespro-daringrp-l3ama-8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
wespro-daringrp-l3ama-8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
wespro-daringrp-l3ama-8b-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 8/291 [00:00<00:03, 79.33it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:02, 102.27it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:02, 98.36it/s] 
Loading 0:  16%|█▋        | 48/291 [00:00<00:02, 114.01it/s]
Loading 0:  21%|██        | 60/291 [00:00<00:02, 109.31it/s]
Loading 0:  26%|██▌       | 75/291 [00:00<00:01, 117.53it/s]
Loading 0:  30%|██▉       | 87/291 [00:00<00:01, 112.89it/s]
Loading 0:  35%|███▌      | 102/291 [00:00<00:01, 119.84it/s]
Loading 0:  40%|███▉      | 115/291 [00:01<00:01, 117.37it/s]
Loading 0:  44%|████▎     | 127/291 [00:01<00:01, 115.44it/s]
Loading 0:  49%|████▉     | 143/291 [00:01<00:01, 118.18it/s]
Loading 0:  53%|█████▎    | 155/291 [00:01<00:01, 105.50it/s]
Loading 0:  58%|█████▊    | 170/291 [00:01<00:01, 115.36it/s]
Loading 0:  63%|██████▎   | 182/291 [00:01<00:00, 110.71it/s]
Loading 0:  67%|██████▋   | 194/291 [00:07<00:15,  6.45it/s] 
Loading 0:  70%|███████   | 204/291 [00:08<00:10,  8.42it/s]
Loading 0:  76%|███████▌  | 220/291 [00:08<00:05, 12.80it/s]
Loading 0:  79%|███████▉  | 231/291 [00:08<00:03, 16.55it/s]
Loading 0:  85%|████████▍ | 247/291 [00:08<00:01, 24.06it/s]
Loading 0:  89%|████████▉ | 259/291 [00:08<00:01, 30.48it/s]
Loading 0:  94%|█████████▍| 274/291 [00:08<00:00, 40.89it/s]
Loading 0:  98%|█████████▊| 286/291 [00:08<00:00, 48.87it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
wespro-daringrp-l3ama-8b-v1-mkmlizer: quantized model in 25.264s
wespro-daringrp-l3ama-8b-v1-mkmlizer: Processed model WesPro/DaringRP-L3ama-8B in 57.383s
wespro-daringrp-l3ama-8b-v1-mkmlizer: creating bucket guanaco-mkml-models
wespro-daringrp-l3ama-8b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
wespro-daringrp-l3ama-8b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/wespro-daringrp-l3ama-8b-v1
wespro-daringrp-l3ama-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/wespro-daringrp-l3ama-8b-v1/tokenizer_config.json
wespro-daringrp-l3ama-8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/wespro-daringrp-l3ama-8b-v1/config.json
wespro-daringrp-l3ama-8b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/wespro-daringrp-l3ama-8b-v1/special_tokens_map.json
wespro-daringrp-l3ama-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/wespro-daringrp-l3ama-8b-v1/tokenizer.json
wespro-daringrp-l3ama-8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/wespro-daringrp-l3ama-8b-v1/flywheel_model.0.safetensors
wespro-daringrp-l3ama-8b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
wespro-daringrp-l3ama-8b-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.
wespro-daringrp-l3ama-8b-v1-mkmlizer:   warnings.warn(
wespro-daringrp-l3ama-8b-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-daringrp-l3ama-8b-v1-mkmlizer:   warnings.warn(
wespro-daringrp-l3ama-8b-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-daringrp-l3ama-8b-v1-mkmlizer:   warnings.warn(
wespro-daringrp-l3ama-8b-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-daringrp-l3ama-8b-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
wespro-daringrp-l3ama-8b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
wespro-daringrp-l3ama-8b-v1-mkmlizer: Saving duration: 0.640s
wespro-daringrp-l3ama-8b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 14.006s
wespro-daringrp-l3ama-8b-v1-mkmlizer: creating bucket guanaco-reward-models
wespro-daringrp-l3ama-8b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
wespro-daringrp-l3ama-8b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/wespro-daringrp-l3ama-8b-v1_reward
wespro-daringrp-l3ama-8b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/wespro-daringrp-l3ama-8b-v1_reward/config.json
wespro-daringrp-l3ama-8b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/wespro-daringrp-l3ama-8b-v1_reward/merges.txt
wespro-daringrp-l3ama-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/wespro-daringrp-l3ama-8b-v1_reward/tokenizer_config.json
wespro-daringrp-l3ama-8b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/wespro-daringrp-l3ama-8b-v1_reward/special_tokens_map.json
wespro-daringrp-l3ama-8b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/wespro-daringrp-l3ama-8b-v1_reward/vocab.json
wespro-daringrp-l3ama-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/wespro-daringrp-l3ama-8b-v1_reward/tokenizer.json
wespro-daringrp-l3ama-8b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/wespro-daringrp-l3ama-8b-v1_reward/reward.tensors
Stopping job with name wespro-daringrp-l3ama-8b-v1-mkmlizer
%s, retrying in %s seconds...
Stopping job with name wespro-daringrp-l3ama-8b-v1-mkmlizer
%s, retrying in %s seconds...
Stopping job with name wespro-daringrp-l3ama-8b-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name wespro-daringrp-l3ama-8b-v1-mkmlizer
Waiting for job on wespro-daringrp-l3ama-8b-v1-mkmlizer to finish
wespro-daringrp-l3ama-8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║     _____            __           __                                ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║       /___/                                                         ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║                                                                     ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║  https://mk1.ai                                                     ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║                                                                     ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║  belonging to:                                                      ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║                                                                     ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║  Chai Research Corp.                                                ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ║                                                                     ║
wespro-daringrp-l3ama-8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
wespro-daringrp-l3ama-8b-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-daringrp-l3ama-8b-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
wespro-daringrp-l3ama-8b-v1-mkmlizer: Downloaded to shared memory in 15.104s
wespro-daringrp-l3ama-8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
wespro-daringrp-l3ama-8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
wespro-daringrp-l3ama-8b-v1-mkmlizer: Processed model WesPro/DaringRP-L3ama-8B in 40.710s
wespro-daringrp-l3ama-8b-v1-mkmlizer: creating bucket guanaco-mkml-models
wespro-daringrp-l3ama-8b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
wespro-daringrp-l3ama-8b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/wespro-daringrp-l3ama-8b-v1
wespro-daringrp-l3ama-8b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/wespro-daringrp-l3ama-8b-v1/special_tokens_map.json
wespro-daringrp-l3ama-8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/wespro-daringrp-l3ama-8b-v1/config.json
wespro-daringrp-l3ama-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/wespro-daringrp-l3ama-8b-v1/tokenizer_config.json
wespro-daringrp-l3ama-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/wespro-daringrp-l3ama-8b-v1/tokenizer.json
wespro-daringrp-l3ama-8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/wespro-daringrp-l3ama-8b-v1/flywheel_model.0.safetensors
wespro-daringrp-l3ama-8b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
wespro-daringrp-l3ama-8b-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.
wespro-daringrp-l3ama-8b-v1-mkmlizer:   warnings.warn(
wespro-daringrp-l3ama-8b-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-daringrp-l3ama-8b-v1-mkmlizer:   warnings.warn(
wespro-daringrp-l3ama-8b-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-daringrp-l3ama-8b-v1-mkmlizer:   warnings.warn(
wespro-daringrp-l3ama-8b-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-daringrp-l3ama-8b-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
wespro-daringrp-l3ama-8b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
wespro-daringrp-l3ama-8b-v1-mkmlizer: Saving duration: 0.400s
wespro-daringrp-l3ama-8b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.746s
wespro-daringrp-l3ama-8b-v1-mkmlizer: creating bucket guanaco-reward-models
wespro-daringrp-l3ama-8b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
wespro-daringrp-l3ama-8b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/wespro-daringrp-l3ama-8b-v1_reward
wespro-daringrp-l3ama-8b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/wespro-daringrp-l3ama-8b-v1_reward/config.json
wespro-daringrp-l3ama-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/wespro-daringrp-l3ama-8b-v1_reward/tokenizer.json
wespro-daringrp-l3ama-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/wespro-daringrp-l3ama-8b-v1_reward/tokenizer_config.json
wespro-daringrp-l3ama-8b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/wespro-daringrp-l3ama-8b-v1_reward/special_tokens_map.json
wespro-daringrp-l3ama-8b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/wespro-daringrp-l3ama-8b-v1_reward/vocab.json
wespro-daringrp-l3ama-8b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/wespro-daringrp-l3ama-8b-v1_reward/merges.txt
wespro-daringrp-l3ama-8b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/wespro-daringrp-l3ama-8b-v1_reward/reward.tensors
Job wespro-daringrp-l3ama-8b-v1-mkmlizer completed after 64.61s with status: succeeded
Stopping job with name wespro-daringrp-l3ama-8b-v1-mkmlizer
Pipeline stage MKMLizer completed in 266.64s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service wespro-daringrp-l3ama-8b-v1
Ignoring service wespro-daringrp-l3ama-8b-v1 already deployed
Waiting for inference service wespro-daringrp-l3ama-8b-v1 to be ready
Inference service wespro-daringrp-l3ama-8b-v1 ready after 10.097408771514893s
Pipeline stage ISVCDeployer completed in 16.17s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.376732587814331s
Received healthy response to inference request in 1.4572336673736572s
Received healthy response to inference request in 1.3795387744903564s
%s, retrying in %s seconds...
Received healthy response to inference request in 1.6107048988342285s
Received healthy response to inference request in 1.3584811687469482s
Received healthy response to inference request in 1.1412856578826904s
Received healthy response to inference request in 1.3911364078521729s
Received healthy response to inference request in 1.2723197937011719s
5 requests
0 failed requests
5th percentile: 1.1674924850463868
10th percentile: 1.193699312210083
20th percentile: 1.2461129665374755
30th percentile: 1.2895520687103272
40th percentile: 1.3240166187286377
50th percentile: 1.3584811687469482
60th percentile: 1.3715432643890382
70th percentile: 1.3846053600311279
80th percentile: 1.435050106048584
90th percentile: 1.5228775024414063
95th percentile: 1.5667912006378173
99th percentile: 1.6019221591949462
mean time: 1.3547855854034423
Pipeline stage StressChecker completed in 32.19s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.05s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.06s
M-Eval Dataset for topic stay_in_character is loaded
wespro-daringrp-l3ama-8b_v1 status is now deployed due to DeploymentManager action
wespro-daringrp-l3ama-8b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of wespro-daringrp-l3ama-8b_v1
Running pipeline stage ISVCDeleter
Checking if service wespro-daringrp-l3ama-8b-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.58s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key wespro-daringrp-l3ama-8b-v1/config.json from bucket guanaco-mkml-models
Deleting key wespro-daringrp-l3ama-8b-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key wespro-daringrp-l3ama-8b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key wespro-daringrp-l3ama-8b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key wespro-daringrp-l3ama-8b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key wespro-daringrp-l3ama-8b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key wespro-daringrp-l3ama-8b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key wespro-daringrp-l3ama-8b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key wespro-daringrp-l3ama-8b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key wespro-daringrp-l3ama-8b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key wespro-daringrp-l3ama-8b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key wespro-daringrp-l3ama-8b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.80s
wespro-daringrp-l3ama-8b_v1 status is now torndown due to DeploymentManager action