submission_id: bbchicago-test-lora-004-_7588_v1
developer_uid: Bbbrun0
best_of: 16
celo_rating: 1165.89
display_name: bbchicago-test-lora-004-_7588_v1
family_friendly_score: 0.0
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
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}
is_internal_developer: False
language_model: BBChicago/Test_Lora_004_couple_aug
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: BBChicago/Test_Lora_004_
model_name: bbchicago-test-lora-004-_7588_v1
model_num_parameters: 8030261248.0
model_repo: BBChicago/Test_Lora_004_couple_aug
model_size: 8B
num_battles: 23395
num_wins: 11351
ranking_group: single
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'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-06-18T11:28:42+00:00
us_pacific_date: 2024-06-18
win_ratio: 0.4851891429792691
Resubmit model
Running pipeline stage MKMLizer
Starting job with name bbchicago-test-lora-004-7588-v1-mkmlizer
Waiting for job on bbchicago-test-lora-004-7588-v1-mkmlizer to finish
bbchicago-test-lora-004-7588-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-test-lora-004-7588-v1-mkmlizer: ║ _____ __ __ ║
bbchicago-test-lora-004-7588-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-test-lora-004-7588-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-test-lora-004-7588-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-test-lora-004-7588-v1-mkmlizer: ║ /___/ ║
bbchicago-test-lora-004-7588-v1-mkmlizer: ║ ║
bbchicago-test-lora-004-7588-v1-mkmlizer: ║ Version: 0.8.14 ║
bbchicago-test-lora-004-7588-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-test-lora-004-7588-v1-mkmlizer: ║ https://mk1.ai ║
bbchicago-test-lora-004-7588-v1-mkmlizer: ║ ║
bbchicago-test-lora-004-7588-v1-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-test-lora-004-7588-v1-mkmlizer: ║ belonging to: ║
bbchicago-test-lora-004-7588-v1-mkmlizer: ║ ║
bbchicago-test-lora-004-7588-v1-mkmlizer: ║ Chai Research Corp. ║
bbchicago-test-lora-004-7588-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-test-lora-004-7588-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
bbchicago-test-lora-004-7588-v1-mkmlizer: ║ ║
bbchicago-test-lora-004-7588-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-test-lora-004-7588-v1-mkmlizer: Downloaded to shared memory in 64.369s
bbchicago-test-lora-004-7588-v1-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-test-lora-004-7588-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-test-lora-004-7588-v1-mkmlizer: quantized model in 27.971s
bbchicago-test-lora-004-7588-v1-mkmlizer: Processed model BBChicago/Test_Lora_004_couple_aug in 95.392s
bbchicago-test-lora-004-7588-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-test-lora-004-7588-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-test-lora-004-7588-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-test-lora-004-7588-v1
bbchicago-test-lora-004-7588-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-test-lora-004-7588-v1/config.json
bbchicago-test-lora-004-7588-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-test-lora-004-7588-v1/tokenizer_config.json
bbchicago-test-lora-004-7588-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-test-lora-004-7588-v1/special_tokens_map.json
bbchicago-test-lora-004-7588-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-test-lora-004-7588-v1/tokenizer.json
bbchicago-test-lora-004-7588-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-test-lora-004-7588-v1/flywheel_model.0.safetensors
bbchicago-test-lora-004-7588-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
bbchicago-test-lora-004-7588-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.
bbchicago-test-lora-004-7588-v1-mkmlizer: warnings.warn(
bbchicago-test-lora-004-7588-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.
bbchicago-test-lora-004-7588-v1-mkmlizer: warnings.warn(
bbchicago-test-lora-004-7588-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.
bbchicago-test-lora-004-7588-v1-mkmlizer: warnings.warn(
bbchicago-test-lora-004-7588-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()
bbchicago-test-lora-004-7588-v1-mkmlizer: return self.fget.__get__(instance, owner)()
bbchicago-test-lora-004-7588-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-test-lora-004-7588-v1-mkmlizer: Saving duration: 0.430s
bbchicago-test-lora-004-7588-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 33.027s
bbchicago-test-lora-004-7588-v1-mkmlizer: creating bucket guanaco-reward-models
bbchicago-test-lora-004-7588-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-test-lora-004-7588-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-test-lora-004-7588-v1_reward
bbchicago-test-lora-004-7588-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-test-lora-004-7588-v1_reward/config.json
bbchicago-test-lora-004-7588-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-test-lora-004-7588-v1_reward/tokenizer_config.json
bbchicago-test-lora-004-7588-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-test-lora-004-7588-v1_reward/special_tokens_map.json
bbchicago-test-lora-004-7588-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-test-lora-004-7588-v1_reward/merges.txt
bbchicago-test-lora-004-7588-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-test-lora-004-7588-v1_reward/vocab.json
bbchicago-test-lora-004-7588-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-test-lora-004-7588-v1_reward/tokenizer.json
bbchicago-test-lora-004-7588-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-test-lora-004-7588-v1_reward/reward.tensors
Job bbchicago-test-lora-004-7588-v1-mkmlizer completed after 225.6s with status: succeeded
Stopping job with name bbchicago-test-lora-004-7588-v1-mkmlizer
Pipeline stage MKMLizer completed in 228.60s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-test-lora-004-7588-v1
Waiting for inference service bbchicago-test-lora-004-7588-v1 to be ready
Inference service bbchicago-test-lora-004-7588-v1 ready after 40.199585914611816s
Pipeline stage ISVCDeployer completed in 47.47s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1447367668151855s
Received healthy response to inference request in 14.068211317062378s
Received healthy response to inference request in 1.3500785827636719s
Received healthy response to inference request in 1.3014085292816162s
Received healthy response to inference request in 1.2928130626678467s
5 requests
0 failed requests
5th percentile: 1.2945321559906007
10th percentile: 1.2962512493133544
20th percentile: 1.2996894359588622
30th percentile: 1.3111425399780274
40th percentile: 1.3306105613708497
50th percentile: 1.3500785827636719
60th percentile: 1.6679418563842772
70th percentile: 1.9858051300048827
80th percentile: 4.529431676864626
90th percentile: 9.298821496963502
95th percentile: 11.683516407012938
99th percentile: 13.59127233505249
mean time: 4.031449651718139
Pipeline stage StressChecker completed in 20.80s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
bbchicago-test-lora-004-_7588_v1 status is now deployed due to DeploymentManager action
bbchicago-test-lora-004-_7588_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of bbchicago-test-lora-004-_7588_v1
Running pipeline stage ISVCDeleter
Checking if service bbchicago-test-lora-004-7588-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.21s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key bbchicago-test-lora-004-7588-v1/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-test-lora-004-7588-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key bbchicago-test-lora-004-7588-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key bbchicago-test-lora-004-7588-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key bbchicago-test-lora-004-7588-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key bbchicago-test-lora-004-7588-v1_reward/config.json from bucket guanaco-reward-models
Deleting key bbchicago-test-lora-004-7588-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key bbchicago-test-lora-004-7588-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key bbchicago-test-lora-004-7588-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key bbchicago-test-lora-004-7588-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key bbchicago-test-lora-004-7588-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key bbchicago-test-lora-004-7588-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.91s
bbchicago-test-lora-004-_7588_v1 status is now torndown due to DeploymentManager action