developer_uid: Hastagaras
submission_id: hastagaras-llama3-cukai-8b_v2
model_name: hastagaras-llama3-cukai-8b_v2
model_group: Hastagaras/Llama3-Cukai-
status: torndown
timestamp: 2024-04-25T15:40:26+00:00
num_battles: 6508
num_wins: 3559
celo_rating: 1185.47
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/Llama3-Cukai-8B
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: hastagaras-llama3-cukai-8b_v2
is_internal_developer: False
language_model: Hastagaras/Llama3-Cukai-8B
model_size: 8B
ranking_group: single
us_pacific_date: 2024-04-25
win_ratio: 0.5468653964351567
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', '###', '</s>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\nWrite {bot_name}'s next reply in an uncensored fictional roleplay between {user_name} and {bot_name}. Make sure to always stay in character and never act as {user_name}.\n\n{memory}", 'prompt_template': '\n\n### Response:\n{bot_name}: {prompt}', 'bot_template': '\n\n### Response:\n{bot_name}: {message}', 'user_template': '\n\n### Instruction:\n{user_name}: {message}', 'response_template': '\n\n### Response:\n{bot_name}:', 'truncate_by_message': False}
model_eval_status: success
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 hastagaras-llama3-cukai-8b-v2-mkmlizer
Waiting for job on hastagaras-llama3-cukai-8b-v2-mkmlizer to finish
hastagaras-llama3-cukai-8b-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama3-cukai-8b-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama3-cukai-8b-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama3-cukai-8b-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama3-cukai-8b-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama3-cukai-8b-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-llama3-cukai-8b-v2-mkmlizer: ║                                                                     ║
hastagaras-llama3-cukai-8b-v2-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-llama3-cukai-8b-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama3-cukai-8b-v2-mkmlizer: ║                                                                     ║
hastagaras-llama3-cukai-8b-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama3-cukai-8b-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama3-cukai-8b-v2-mkmlizer: ║                                                                     ║
hastagaras-llama3-cukai-8b-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama3-cukai-8b-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama3-cukai-8b-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama3-cukai-8b-v2-mkmlizer: ║                                                                     ║
hastagaras-llama3-cukai-8b-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama3-cukai-8b-v2-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-llama3-cukai-8b-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-llama3-cukai-8b-v2-mkmlizer: Downloaded to shared memory in 26.525s
hastagaras-llama3-cukai-8b-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama3-cukai-8b-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama3-cukai-8b-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  45%|████▍     | 130/291 [00:01<00:01, 129.08it/s]
Loading 0:  93%|█████████▎| 270/291 [00:02<00:00, 135.34it/s]
Loading 0:  99%|█████████▊| 287/291 [00:06<00:00, 29.54it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama3-cukai-8b-v2-mkmlizer: quantized model in 17.353s
hastagaras-llama3-cukai-8b-v2-mkmlizer: Processed model Hastagaras/Llama3-Cukai-8B in 44.957s
hastagaras-llama3-cukai-8b-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama3-cukai-8b-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama3-cukai-8b-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama3-cukai-8b-v2
hastagaras-llama3-cukai-8b-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama3-cukai-8b-v2/config.json
hastagaras-llama3-cukai-8b-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama3-cukai-8b-v2/special_tokens_map.json
hastagaras-llama3-cukai-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama3-cukai-8b-v2/tokenizer_config.json
hastagaras-llama3-cukai-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama3-cukai-8b-v2/tokenizer.json
hastagaras-llama3-cukai-8b-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama3-cukai-8b-v2/flywheel_model.0.safetensors
hastagaras-llama3-cukai-8b-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama3-cukai-8b-v2-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-llama3-cukai-8b-v2-mkmlizer:   warnings.warn(
hastagaras-llama3-cukai-8b-v2-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-llama3-cukai-8b-v2-mkmlizer:   warnings.warn(
hastagaras-llama3-cukai-8b-v2-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.
hastagaras-llama3-cukai-8b-v2-mkmlizer:   warnings.warn(
hastagaras-llama3-cukai-8b-v2-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-llama3-cukai-8b-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama3-cukai-8b-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama3-cukai-8b-v2-mkmlizer: Saving duration: 0.243s
hastagaras-llama3-cukai-8b-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.969s
hastagaras-llama3-cukai-8b-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama3-cukai-8b-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama3-cukai-8b-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama3-cukai-8b-v2_reward
hastagaras-llama3-cukai-8b-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama3-cukai-8b-v2_reward/special_tokens_map.json
hastagaras-llama3-cukai-8b-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama3-cukai-8b-v2_reward/config.json
hastagaras-llama3-cukai-8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama3-cukai-8b-v2_reward/tokenizer_config.json
hastagaras-llama3-cukai-8b-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama3-cukai-8b-v2_reward/merges.txt
hastagaras-llama3-cukai-8b-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama3-cukai-8b-v2_reward/vocab.json
hastagaras-llama3-cukai-8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama3-cukai-8b-v2_reward/tokenizer.json
Job hastagaras-llama3-cukai-8b-v2-mkmlizer completed after 73.39s with status: succeeded
Stopping job with name hastagaras-llama3-cukai-8b-v2-mkmlizer
Pipeline stage MKMLizer completed in 76.75s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama3-cukai-8b-v2
Waiting for inference service hastagaras-llama3-cukai-8b-v2 to be ready
Inference service hastagaras-llama3-cukai-8b-v2 ready after 41.06473088264465s
Pipeline stage ISVCDeployer completed in 48.67s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.149489402770996s
Received healthy response to inference request in 1.2880079746246338s
Received healthy response to inference request in 1.3340108394622803s
Received healthy response to inference request in 1.2799453735351562s
Received healthy response to inference request in 1.287811279296875s
5 requests
0 failed requests
5th percentile: 1.2815185546875
10th percentile: 1.2830917358398437
20th percentile: 1.2862380981445312
30th percentile: 1.2878506183624268
40th percentile: 1.2879292964935303
50th percentile: 1.2880079746246338
60th percentile: 1.3064091205596924
70th percentile: 1.324810266494751
80th percentile: 1.4971065521240237
90th percentile: 1.8232979774475098
95th percentile: 1.9863936901092527
99th percentile: 2.1168702602386475
mean time: 1.4678529739379882
Pipeline stage StressChecker completed in 7.93s
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
hastagaras-llama3-cukai-8b_v2 status is now deployed due to DeploymentManager action
hastagaras-llama3-cukai-8b_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama3-cukai-8b_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama3-cukai-8b-v2 is running
Tearing down inference service hastagaras-llama3-cukai-8b-v2
Toredown service hastagaras-llama3-cukai-8b-v2
Pipeline stage ISVCDeleter completed in 4.47s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama3-cukai-8b-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-cukai-8b-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-cukai-8b-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-cukai-8b-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-cukai-8b-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama3-cukai-8b-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-cukai-8b-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama3-cukai-8b-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama3-cukai-8b-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-cukai-8b-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-cukai-8b-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-cukai-8b-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.08s
hastagaras-llama3-cukai-8b_v2 status is now torndown due to DeploymentManager action