developer_uid: Hastagaras
submission_id: hastagaras-l3-bakaroko-8b_v1
model_name: hastagaras-l3-bakaroko-8b_v1
model_group: Hastagaras/L3-Bakaroko-8
status: torndown
timestamp: 2024-04-24T16:28:41+00:00
num_battles: 6745
num_wins: 3385
celo_rating: 1155.37
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/L3-Bakaroko-8B
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: hastagaras-l3-bakaroko-8b_v1
is_internal_developer: False
language_model: Hastagaras/L3-Bakaroko-8B
model_size: 8B
ranking_group: single
us_pacific_date: 2024-04-24
win_ratio: 0.5018532246108228
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|eot_id|>', '\n{user_name}:'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|start_header_id|>system<|end_header_id|>\n\nImagine you are {bot_name}, a character based on the provided description. You are talking to {user_name}. Be yourself, think, and respond naturally. Describe what you see, feel, and think in detail. Each of your responses must follow this format:\n\n*Action in asterisks*\n\n"Speech in quotes"\n\nFor example:\n\n{bot_name}: "Greetings {user_name}! I\\\'m the brave knight {bot_name}."\n\n*straightens posture and rests hand on sword hilt* \n\n"What quest shall we embark upon today?"\n\nWrite your next reply based on the below information:\n\n{memory}\n\n', 'prompt_template': '{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': 'Memory: {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-bakaroko-8b-v1-mkmlizer
Waiting for job on hastagaras-l3-bakaroko-8b-v1-mkmlizer to finish
Stopping job with name hastagaras-l3-bakaroko-8b-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-l3-bakaroko-8b-v1-mkmlizer
Waiting for job on hastagaras-l3-bakaroko-8b-v1-mkmlizer to finish
hastagaras-l3-bakaroko-8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-l3-bakaroko-8b-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-l3-bakaroko-8b-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-l3-bakaroko-8b-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-l3-bakaroko-8b-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-l3-bakaroko-8b-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-l3-bakaroko-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-bakaroko-8b-v1-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-l3-bakaroko-8b-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-l3-bakaroko-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-bakaroko-8b-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-l3-bakaroko-8b-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-l3-bakaroko-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-bakaroko-8b-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-l3-bakaroko-8b-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-l3-bakaroko-8b-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-l3-bakaroko-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-bakaroko-8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-l3-bakaroko-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-bakaroko-8b-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-l3-bakaroko-8b-v1-mkmlizer: Downloaded to shared memory in 37.363s
hastagaras-l3-bakaroko-8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-l3-bakaroko-8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-l3-bakaroko-8b-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:03<09:36,  1.99s/it]
Loading 0:  42%|████▏     | 122/291 [00:05<00:05, 29.94it/s]
Loading 0:  85%|████████▌ | 248/291 [00:06<00:00, 54.90it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-l3-bakaroko-8b-v1-mkmlizer: quantized model in 18.423s
hastagaras-l3-bakaroko-8b-v1-mkmlizer: Processed model Hastagaras/L3-Bakaroko-8B in 56.793s
hastagaras-l3-bakaroko-8b-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-l3-bakaroko-8b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-l3-bakaroko-8b-v1/special_tokens_map.json
hastagaras-l3-bakaroko-8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-l3-bakaroko-8b-v1/config.json
hastagaras-l3-bakaroko-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-l3-bakaroko-8b-v1/tokenizer_config.json
hastagaras-l3-bakaroko-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-l3-bakaroko-8b-v1/tokenizer.json
hastagaras-l3-bakaroko-8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-l3-bakaroko-8b-v1/flywheel_model.0.safetensors
hastagaras-l3-bakaroko-8b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-l3-bakaroko-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-bakaroko-8b-v1-mkmlizer:   warnings.warn(
hastagaras-l3-bakaroko-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-bakaroko-8b-v1-mkmlizer:   warnings.warn(
hastagaras-l3-bakaroko-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-bakaroko-8b-v1-mkmlizer:   warnings.warn(
hastagaras-l3-bakaroko-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-bakaroko-8b-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-l3-bakaroko-8b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-l3-bakaroko-8b-v1-mkmlizer: Saving duration: 0.276s
hastagaras-l3-bakaroko-8b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.492s
hastagaras-l3-bakaroko-8b-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-l3-bakaroko-8b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-l3-bakaroko-8b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-l3-bakaroko-8b-v1_reward
hastagaras-l3-bakaroko-8b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-l3-bakaroko-8b-v1_reward/config.json
hastagaras-l3-bakaroko-8b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-l3-bakaroko-8b-v1_reward/special_tokens_map.json
hastagaras-l3-bakaroko-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-l3-bakaroko-8b-v1_reward/tokenizer_config.json
hastagaras-l3-bakaroko-8b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-l3-bakaroko-8b-v1_reward/merges.txt
hastagaras-l3-bakaroko-8b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-l3-bakaroko-8b-v1_reward/vocab.json
hastagaras-l3-bakaroko-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-l3-bakaroko-8b-v1_reward/tokenizer.json
hastagaras-l3-bakaroko-8b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-l3-bakaroko-8b-v1_reward/reward.tensors
Job hastagaras-l3-bakaroko-8b-v1-mkmlizer completed after 147.42s with status: succeeded
Stopping job with name hastagaras-l3-bakaroko-8b-v1-mkmlizer
Pipeline stage MKMLizer completed in 151.63s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-l3-bakaroko-8b-v1
Waiting for inference service hastagaras-l3-bakaroko-8b-v1 to be ready
Inference service hastagaras-l3-bakaroko-8b-v1 ready after 30.268014430999756s
Pipeline stage ISVCDeployer completed in 38.05s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0573830604553223s
Received healthy response to inference request in 1.2535600662231445s
Received healthy response to inference request in 1.264648675918579s
Received healthy response to inference request in 1.233609676361084s
Received healthy response to inference request in 1.242804765701294s
5 requests
0 failed requests
5th percentile: 1.235448694229126
10th percentile: 1.237287712097168
20th percentile: 1.2409657478332519
30th percentile: 1.244955825805664
40th percentile: 1.2492579460144042
50th percentile: 1.2535600662231445
60th percentile: 1.2579955101013183
70th percentile: 1.2624309539794922
80th percentile: 1.423195552825928
90th percentile: 1.740289306640625
95th percentile: 1.8988361835479735
99th percentile: 2.0256736850738526
mean time: 1.4104012489318847
Pipeline stage StressChecker completed in 7.76s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.06s
hastagaras-l3-bakaroko-8b_v1 status is now deployed due to DeploymentManager action
hastagaras-l3-bakaroko-8b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-l3-bakaroko-8b_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-l3-bakaroko-8b-v1 is running
Tearing down inference service hastagaras-l3-bakaroko-8b-v1
Toredown service hastagaras-l3-bakaroko-8b-v1
Pipeline stage ISVCDeleter completed in 3.81s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-l3-bakaroko-8b-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-bakaroko-8b-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-l3-bakaroko-8b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-bakaroko-8b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-bakaroko-8b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-l3-bakaroko-8b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-bakaroko-8b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-l3-bakaroko-8b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-l3-bakaroko-8b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-bakaroko-8b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-bakaroko-8b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-bakaroko-8b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.03s
hastagaras-l3-bakaroko-8b_v1 status is now torndown due to DeploymentManager action