developer_uid: Hastagaras
submission_id: hastagaras-l3-bakau-8b_v2
model_name: hastagaras-l3-bakau-8b_v1
model_group: Hastagaras/L3-Bakau-8B
status: torndown
timestamp: 2024-04-27T02:50:54+00:00
num_battles: 7429
num_wins: 4060
celo_rating: 1190.59
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: 0.5465069322923678
generation_params: {'temperature': 0.85, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 1.05, 'stopping_words': ['\n', '<|eot_id|>', '\n{user_name}:', '\n{char_name}:'], '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're {bot_name} in this uncensored fictional roleplay between {bot_name} and {user_name}. Non-verbal actions and gestures are described between asterisks, e.g. *waves hello* or *moves closer*. Thoughts and inner monologue are written inside backticks, e.g. `I wonder what they'll say next.`\n\n{memory}<|eot_id|>", 'prompt_template': "<|start_header_id|>user<|end_header_id|>\n\n{user_name}: Let's begin the roleplay.<|eot_id|><|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-v2-mkmlizer
Waiting for job on hastagaras-l3-bakau-8b-v2-mkmlizer to finish
hastagaras-l3-bakau-8b-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-l3-bakau-8b-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-l3-bakau-8b-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-l3-bakau-8b-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-l3-bakau-8b-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-l3-bakau-8b-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-l3-bakau-8b-v2-mkmlizer: ║                                                                     ║
hastagaras-l3-bakau-8b-v2-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-l3-bakau-8b-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-l3-bakau-8b-v2-mkmlizer: ║                                                                     ║
hastagaras-l3-bakau-8b-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-l3-bakau-8b-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-l3-bakau-8b-v2-mkmlizer: ║                                                                     ║
hastagaras-l3-bakau-8b-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-l3-bakau-8b-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-l3-bakau-8b-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-l3-bakau-8b-v2-mkmlizer: ║                                                                     ║
hastagaras-l3-bakau-8b-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-l3-bakau-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-l3-bakau-8b-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-l3-bakau-8b-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:03<09:23,  1.95s/it]
Loading 0:  42%|████▏     | 122/291 [00:05<00:05, 31.52it/s]
Loading 0:  97%|█████████▋| 283/291 [00:06<00:00, 66.39it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-l3-bakau-8b-v2-mkmlizer: quantized model in 17.199s
hastagaras-l3-bakau-8b-v2-mkmlizer: Processed model Hastagaras/L3-Bakau-8B in 36.246s
hastagaras-l3-bakau-8b-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-l3-bakau-8b-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-l3-bakau-8b-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-l3-bakau-8b-v2
hastagaras-l3-bakau-8b-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-l3-bakau-8b-v2/config.json
hastagaras-l3-bakau-8b-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-l3-bakau-8b-v2/special_tokens_map.json
hastagaras-l3-bakau-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-l3-bakau-8b-v2/tokenizer_config.json
hastagaras-l3-bakau-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-l3-bakau-8b-v2/tokenizer.json
hastagaras-l3-bakau-8b-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-l3-bakau-8b-v2/flywheel_model.0.safetensors
hastagaras-l3-bakau-8b-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-l3-bakau-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-l3-bakau-8b-v2-mkmlizer:   warnings.warn(
hastagaras-l3-bakau-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-l3-bakau-8b-v2-mkmlizer:   warnings.warn(
hastagaras-l3-bakau-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-l3-bakau-8b-v2-mkmlizer:   warnings.warn(
hastagaras-l3-bakau-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-l3-bakau-8b-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-l3-bakau-8b-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-l3-bakau-8b-v2-mkmlizer: Saving duration: 0.231s
hastagaras-l3-bakau-8b-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.284s
hastagaras-l3-bakau-8b-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-l3-bakau-8b-v2_reward/reward.tensors
Job hastagaras-l3-bakau-8b-v2-mkmlizer completed after 62.93s with status: succeeded
Stopping job with name hastagaras-l3-bakau-8b-v2-mkmlizer
Pipeline stage MKMLizer completed in 66.85s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-l3-bakau-8b-v2
Waiting for inference service hastagaras-l3-bakau-8b-v2 to be ready
Inference service hastagaras-l3-bakau-8b-v2 ready after 30.161091566085815s
Pipeline stage ISVCDeployer completed in 38.11s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0311899185180664s
Received healthy response to inference request in 0.9608049392700195s
Received healthy response to inference request in 1.252274990081787s
Received healthy response to inference request in 1.1827917098999023s
Received healthy response to inference request in 1.3033185005187988s
5 requests
0 failed requests
5th percentile: 1.005202293395996
10th percentile: 1.0495996475219727
20th percentile: 1.1383943557739258
30th percentile: 1.1966883659362793
40th percentile: 1.2244816780090333
50th percentile: 1.252274990081787
60th percentile: 1.2726923942565918
70th percentile: 1.2931097984313964
80th percentile: 1.4488927841186525
90th percentile: 1.7400413513183595
95th percentile: 1.8856156349182127
99th percentile: 2.0020750617980956
mean time: 1.3460760116577148
Pipeline stage StressChecker completed in 7.30s
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
%s, retrying in %s seconds...
hastagaras-l3-bakau-8b_v2 status is now deployed due to DeploymentManager action
%s, retrying in %s seconds...
hastagaras-l3-bakau-8b_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-l3-bakau-8b_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-l3-bakau-8b-v2 is running
Tearing down inference service hastagaras-l3-bakau-8b-v2
Toredown service hastagaras-l3-bakau-8b-v2
Pipeline stage ISVCDeleter completed in 3.24s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-l3-bakau-8b-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-bakau-8b-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-l3-bakau-8b-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-bakau-8b-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-bakau-8b-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-l3-bakau-8b-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-bakau-8b-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-l3-bakau-8b-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-l3-bakau-8b-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-bakau-8b-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-bakau-8b-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-bakau-8b-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.22s
hastagaras-l3-bakau-8b_v2 status is now torndown due to DeploymentManager action