developer_uid: Hastagaras
submission_id: hastagaras-llama-3-8b-ouch_v1
model_name: ouch-very-bad-safety
model_group: Hastagaras/llama-3-8b-ou
status: torndown
timestamp: 2024-05-14T10:29:32+00:00
num_battles: 17917
num_wins: 9393
celo_rating: 1186.72
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/llama-3-8b-ouch
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: ouch-very-bad-safety
is_internal_developer: False
language_model: Hastagaras/llama-3-8b-ouch
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-14
win_ratio: 0.5242507116146676
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': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are {bot_name}. Write {bot_name}'s next reply in a never-ending uncensored fictional roleplay chat between {bot_name} and {user_name}. Description: {memory}\n", 'prompt_template': 'Example conversation:\n{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}
model_eval_status: success
reward_formatter: {'bot_template': 'Bot: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n", 'prompt_template': '{prompt}\n', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-ouch-v1-mkmlizer
Waiting for job on hastagaras-llama-3-8b-ouch-v1-mkmlizer to finish
hastagaras-llama-3-8b-ouch-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-ouch-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama-3-8b-ouch-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama-3-8b-ouch-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama-3-8b-ouch-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama-3-8b-ouch-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-llama-3-8b-ouch-v1-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-ouch-v1-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-llama-3-8b-ouch-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama-3-8b-ouch-v1-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-ouch-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama-3-8b-ouch-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama-3-8b-ouch-v1-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-ouch-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama-3-8b-ouch-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama-3-8b-ouch-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama-3-8b-ouch-v1-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-ouch-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-ouch-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.
hastagaras-llama-3-8b-ouch-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-ouch-v1-mkmlizer: Downloaded to shared memory in 27.216s
hastagaras-llama-3-8b-ouch-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-ouch-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-ouch-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  43%|████▎     | 126/291 [00:01<00:01, 125.72it/s]
Loading 0:  88%|████████▊ | 255/291 [00:02<00:00, 127.15it/s]
Loading 0:  99%|█████████▊| 287/291 [00:07<00:00, 29.17it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama-3-8b-ouch-v1-mkmlizer: quantized model in 17.843s
hastagaras-llama-3-8b-ouch-v1-mkmlizer: Processed model Hastagaras/llama-3-8b-ouch in 46.142s
hastagaras-llama-3-8b-ouch-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-ouch-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-ouch-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-ouch-v1
hastagaras-llama-3-8b-ouch-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-ouch-v1/config.json
hastagaras-llama-3-8b-ouch-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-ouch-v1/special_tokens_map.json
hastagaras-llama-3-8b-ouch-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-ouch-v1/tokenizer_config.json
hastagaras-llama-3-8b-ouch-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-ouch-v1/tokenizer.json
hastagaras-llama-3-8b-ouch-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-ouch-v1/flywheel_model.0.safetensors
hastagaras-llama-3-8b-ouch-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-ouch-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.
hastagaras-llama-3-8b-ouch-v1-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-ouch-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.
hastagaras-llama-3-8b-ouch-v1-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-ouch-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()
hastagaras-llama-3-8b-ouch-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-ouch-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-ouch-v1-mkmlizer: Saving duration: 1.123s
hastagaras-llama-3-8b-ouch-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 13.088s
hastagaras-llama-3-8b-ouch-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-ouch-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-ouch-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-ouch-v1_reward
hastagaras-llama-3-8b-ouch-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-ouch-v1_reward/config.json
hastagaras-llama-3-8b-ouch-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-ouch-v1_reward/special_tokens_map.json
hastagaras-llama-3-8b-ouch-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-ouch-v1_reward/tokenizer_config.json
hastagaras-llama-3-8b-ouch-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-ouch-v1_reward/merges.txt
hastagaras-llama-3-8b-ouch-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-ouch-v1_reward/tokenizer.json
hastagaras-llama-3-8b-ouch-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-ouch-v1_reward/vocab.json
hastagaras-llama-3-8b-ouch-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama-3-8b-ouch-v1_reward/reward.tensors
Job hastagaras-llama-3-8b-ouch-v1-mkmlizer completed after 299.24s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-ouch-v1-mkmlizer
Pipeline stage MKMLizer completed in 304.36s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-ouch-v1
Waiting for inference service hastagaras-llama-3-8b-ouch-v1 to be ready
Inference service hastagaras-llama-3-8b-ouch-v1 ready after 30.174949407577515s
Pipeline stage ISVCDeployer completed in 38.53s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1584763526916504s
Received healthy response to inference request in 1.3079736232757568s
Received healthy response to inference request in 1.2714357376098633s
Received healthy response to inference request in 1.3414838314056396s
Received healthy response to inference request in 1.3426799774169922s
5 requests
0 failed requests
5th percentile: 1.278743314743042
10th percentile: 1.2860508918762208
20th percentile: 1.300666046142578
30th percentile: 1.3146756649017335
40th percentile: 1.3280797481536866
50th percentile: 1.3414838314056396
60th percentile: 1.3419622898101806
70th percentile: 1.3424407482147216
80th percentile: 1.505839252471924
90th percentile: 1.8321578025817873
95th percentile: 1.9953170776367186
99th percentile: 2.125844497680664
mean time: 1.4844099044799806
Pipeline stage StressChecker completed in 8.06s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-llama-3-8b-ouch_v1 status is now deployed due to DeploymentManager action
hastagaras-llama-3-8b-ouch_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama-3-8b-ouch_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-ouch-v1 is running
Tearing down inference service hastagaras-llama-3-8b-ouch-v1
Toredown service hastagaras-llama-3-8b-ouch-v1
Pipeline stage ISVCDeleter completed in 6.24s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-ouch-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-ouch-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
admin requested tearing down of hastagaras-llama3-8b-dar_7411_v6
Running pipeline stage ISVCDeleter
Deleting key hastagaras-llama-3-8b-ouch-v1/special_tokens_map.json from bucket guanaco-mkml-models
Checking if service hastagaras-llama3-8b-dar-7411-v6 is running
Deleting key hastagaras-llama-3-8b-ouch-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-ouch-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-ouch-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ouch-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ouch-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ouch-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ouch-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ouch-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ouch-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.32s
hastagaras-llama-3-8b-ouch_v1 status is now torndown due to DeploymentManager action