developer_uid: Hastagaras
submission_id: hastagaras-l3-bakau-8b_v1
model_name: hastagaras-l3-bakau-8b_v1
model_group: Hastagaras/L3-Bakau-8B
status: torndown
timestamp: 2024-04-27T02:20:03+00:00
num_battles: 6504
num_wins: 3529
celo_rating: 1185.89
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/L3-Bakau-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-l3-bakau-8b_v1
is_internal_developer: False
language_model: Hastagaras/L3-Bakau-8B
model_size: 8B
ranking_group: single
us_pacific_date: 2024-04-26
win_ratio: 0.5425891758917589
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', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|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. Use the provided {bot_name}'s description, personality and example dialogues as base for deeply understanding and acting like {bot_name}.\n\nActions and narrations must be enclosed in asterisks (*). The responses must be long and in third perspective of the story teller.\n\nDescription: {memory}<|eot_id|>", 'prompt_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {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", 'prompt_template': '{prompt}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
model_eval_status: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-l3-bakau-8b-v1-mkmlizer
Waiting for job on hastagaras-l3-bakau-8b-v1-mkmlizer to finish
hastagaras-l3-bakau-8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-l3-bakau-8b-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-l3-bakau-8b-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-l3-bakau-8b-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-l3-bakau-8b-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-l3-bakau-8b-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-l3-bakau-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-bakau-8b-v1-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-l3-bakau-8b-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-l3-bakau-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-bakau-8b-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-l3-bakau-8b-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-l3-bakau-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-bakau-8b-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-l3-bakau-8b-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-l3-bakau-8b-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-l3-bakau-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-bakau-8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-l3-bakau-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.
hastagaras-l3-bakau-8b-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-l3-bakau-8b-v1-mkmlizer: Downloaded to shared memory in 33.002s
hastagaras-l3-bakau-8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-l3-bakau-8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-l3-bakau-8b-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<09:42,  2.01s/it]
Loading 0:  42%|████▏     | 122/291 [00:05<00:05, 30.39it/s]
Loading 0:  94%|█████████▍| 274/291 [00:06<00:00, 62.36it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-l3-bakau-8b-v1-mkmlizer: quantized model in 17.640s
hastagaras-l3-bakau-8b-v1-mkmlizer: Processed model Hastagaras/L3-Bakau-8B in 51.757s
hastagaras-l3-bakau-8b-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-l3-bakau-8b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-l3-bakau-8b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-l3-bakau-8b-v1
hastagaras-l3-bakau-8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-l3-bakau-8b-v1/config.json
hastagaras-l3-bakau-8b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-l3-bakau-8b-v1/special_tokens_map.json
hastagaras-l3-bakau-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-l3-bakau-8b-v1/tokenizer_config.json
hastagaras-l3-bakau-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-l3-bakau-8b-v1/tokenizer.json
hastagaras-l3-bakau-8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-l3-bakau-8b-v1/flywheel_model.0.safetensors
hastagaras-l3-bakau-8b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-l3-bakau-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.
hastagaras-l3-bakau-8b-v1-mkmlizer:   warnings.warn(
hastagaras-l3-bakau-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.
hastagaras-l3-bakau-8b-v1-mkmlizer:   warnings.warn(
hastagaras-l3-bakau-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.
hastagaras-l3-bakau-8b-v1-mkmlizer:   warnings.warn(
hastagaras-l3-bakau-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()
hastagaras-l3-bakau-8b-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-l3-bakau-8b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-l3-bakau-8b-v1-mkmlizer: Saving duration: 0.261s
hastagaras-l3-bakau-8b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.243s
hastagaras-l3-bakau-8b-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-l3-bakau-8b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-l3-bakau-8b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-l3-bakau-8b-v1_reward
hastagaras-l3-bakau-8b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-l3-bakau-8b-v1_reward/config.json
hastagaras-l3-bakau-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-l3-bakau-8b-v1_reward/tokenizer_config.json
hastagaras-l3-bakau-8b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-l3-bakau-8b-v1_reward/vocab.json
hastagaras-l3-bakau-8b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-l3-bakau-8b-v1_reward/special_tokens_map.json
hastagaras-l3-bakau-8b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-l3-bakau-8b-v1_reward/merges.txt
hastagaras-l3-bakau-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-l3-bakau-8b-v1_reward/tokenizer.json
hastagaras-l3-bakau-8b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-l3-bakau-8b-v1_reward/reward.tensors
Job hastagaras-l3-bakau-8b-v1-mkmlizer completed after 83.38s with status: succeeded
Stopping job with name hastagaras-l3-bakau-8b-v1-mkmlizer
Pipeline stage MKMLizer completed in 87.88s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-l3-bakau-8b-v1
Waiting for inference service hastagaras-l3-bakau-8b-v1 to be ready
Inference service hastagaras-l3-bakau-8b-v1 ready after 30.206609964370728s
Pipeline stage ISVCDeployer completed in 37.91s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1696054935455322s
Received healthy response to inference request in 1.2717087268829346s
Received healthy response to inference request in 1.2299118041992188s
Received healthy response to inference request in 1.3031480312347412s
Received healthy response to inference request in 1.2707011699676514s
5 requests
0 failed requests
5th percentile: 1.2380696773529052
10th percentile: 1.2462275505065918
20th percentile: 1.262543296813965
30th percentile: 1.270902681350708
40th percentile: 1.2713057041168212
50th percentile: 1.2717087268829346
60th percentile: 1.2842844486236573
70th percentile: 1.2968601703643798
80th percentile: 1.4764395236968997
90th percentile: 1.823022508621216
95th percentile: 1.9963140010833738
99th percentile: 2.1349471950531007
mean time: 1.4490150451660155
Pipeline stage StressChecker completed in 7.86s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
%s, retrying in %s seconds...
hastagaras-l3-bakau-8b_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
%s, retrying in %s seconds...
hastagaras-l3-bakau-8b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-l3-bakau-8b_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-l3-bakau-8b-v1 is running
Tearing down inference service hastagaras-l3-bakau-8b-v1
Toredown service hastagaras-l3-bakau-8b-v1
Pipeline stage ISVCDeleter completed in 3.45s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-l3-bakau-8b-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-bakau-8b-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-l3-bakau-8b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-bakau-8b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-bakau-8b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-l3-bakau-8b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-bakau-8b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-l3-bakau-8b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-l3-bakau-8b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-bakau-8b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-bakau-8b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-bakau-8b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.81s
hastagaras-l3-bakau-8b_v1 status is now torndown due to DeploymentManager action