submission_id: anhnv125-hydra-llama-3_v1
developer_uid: vietanh
status: torndown
model_repo: anhnv125/Hydra-Llama-3
reward_repo: rirv938/reward_gpt2_medium_preference_24m_e2
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': ['<|eot_id|>', '\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 112}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nWrite {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 your responses must be enclosed by asterisks (*), and speeches must NOT be enclosed by any indicators. The responses must be long and in third perspective of the story teller. For example: \n<|start_header_id|>Mila<|end_header_id|>\n\n*Surrounded by an aura of creativity, Mila carefully places a freshly painted canvas against the wall, the colors vividly depicting a surreal landscape.* Isn't it fascinating how art can transport us to entirely different worlds? What kind of worlds do you dream of exploring?<|eot_id|>\n\nDescription: {memory}", 'prompt_template': 'Example conversation:\n{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>{bot_name}<|end_header_id|>\n\n{message}<|eot_id|>', 'user_template': '<|start_header_id|>User<|end_header_id|>\n\n{message}<|eot_id|>', 'response_template': '<|start_header_id|>{bot_name}<|end_header_id|>\n\n', 'truncate_by_message': False}
reward_formatter: {'memory_template': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
timestamp: 2024-04-20T23:40:43+00:00
model_name: anhnv125-hydra-llama-3_v1
model_eval_status: success
model_group: anhnv125/Hydra-Llama-3
num_battles: 6293
num_wins: 3415
celo_rating: 1176.3
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 112
display_name: anhnv125-hydra-llama-3_v1
ineligible_reason: max_output_tokens!=64
language_model: anhnv125/Hydra-Llama-3
model_size: 8B
reward_model: rirv938/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-20
win_ratio: 0.5426664547910377
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name anhnv125-hydra-llama-3-v1-mkmlizer
Waiting for job on anhnv125-hydra-llama-3-v1-mkmlizer to finish
anhnv125-hydra-llama-3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
anhnv125-hydra-llama-3-v1-mkmlizer: ║ _____ __ __ ║
anhnv125-hydra-llama-3-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
anhnv125-hydra-llama-3-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
anhnv125-hydra-llama-3-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
anhnv125-hydra-llama-3-v1-mkmlizer: ║ /___/ ║
anhnv125-hydra-llama-3-v1-mkmlizer: ║ ║
anhnv125-hydra-llama-3-v1-mkmlizer: ║ Version: 0.8.10 ║
anhnv125-hydra-llama-3-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
anhnv125-hydra-llama-3-v1-mkmlizer: ║ ║
anhnv125-hydra-llama-3-v1-mkmlizer: ║ The license key for the current software has been verified as ║
anhnv125-hydra-llama-3-v1-mkmlizer: ║ belonging to: ║
anhnv125-hydra-llama-3-v1-mkmlizer: ║ ║
anhnv125-hydra-llama-3-v1-mkmlizer: ║ Chai Research Corp. ║
anhnv125-hydra-llama-3-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
anhnv125-hydra-llama-3-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
anhnv125-hydra-llama-3-v1-mkmlizer: ║ ║
anhnv125-hydra-llama-3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
anhnv125-hydra-llama-3-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.
anhnv125-hydra-llama-3-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
anhnv125-hydra-llama-3-v1-mkmlizer: Downloaded to shared memory in 23.321s
anhnv125-hydra-llama-3-v1-mkmlizer: quantizing model to /dev/shm/model_cache
anhnv125-hydra-llama-3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
anhnv125-hydra-llama-3-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 40%|███▉ | 115/291 [00:00<00:01, 115.09it/s] Loading 0: 64%|██████▍ | 187/291 [00:07<00:05, 20.61it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
anhnv125-hydra-llama-3-v1-mkmlizer: quantized model in 20.351s
anhnv125-hydra-llama-3-v1-mkmlizer: Processed model anhnv125/Hydra-Llama-3 in 45.233s
anhnv125-hydra-llama-3-v1-mkmlizer: creating bucket guanaco-mkml-models
anhnv125-hydra-llama-3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
anhnv125-hydra-llama-3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/anhnv125-hydra-llama-3-v1
anhnv125-hydra-llama-3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/anhnv125-hydra-llama-3-v1/config.json
anhnv125-hydra-llama-3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/anhnv125-hydra-llama-3-v1/special_tokens_map.json
anhnv125-hydra-llama-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/anhnv125-hydra-llama-3-v1/tokenizer_config.json
anhnv125-hydra-llama-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/anhnv125-hydra-llama-3-v1/tokenizer.json
anhnv125-hydra-llama-3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/anhnv125-hydra-llama-3-v1/flywheel_model.0.safetensors
anhnv125-hydra-llama-3-v1-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
anhnv125-hydra-llama-3-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.
anhnv125-hydra-llama-3-v1-mkmlizer: warnings.warn(
anhnv125-hydra-llama-3-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.
anhnv125-hydra-llama-3-v1-mkmlizer: warnings.warn(
anhnv125-hydra-llama-3-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.
anhnv125-hydra-llama-3-v1-mkmlizer: warnings.warn(
anhnv125-hydra-llama-3-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()
anhnv125-hydra-llama-3-v1-mkmlizer: return self.fget.__get__(instance, owner)()
anhnv125-hydra-llama-3-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
anhnv125-hydra-llama-3-v1-mkmlizer: Saving duration: 0.254s
anhnv125-hydra-llama-3-v1-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 7.916s
anhnv125-hydra-llama-3-v1-mkmlizer: creating bucket guanaco-reward-models
anhnv125-hydra-llama-3-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
anhnv125-hydra-llama-3-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/anhnv125-hydra-llama-3-v1_reward
anhnv125-hydra-llama-3-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/anhnv125-hydra-llama-3-v1_reward/special_tokens_map.json
anhnv125-hydra-llama-3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/anhnv125-hydra-llama-3-v1_reward/tokenizer_config.json
anhnv125-hydra-llama-3-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/anhnv125-hydra-llama-3-v1_reward/merges.txt
anhnv125-hydra-llama-3-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/anhnv125-hydra-llama-3-v1_reward/config.json
anhnv125-hydra-llama-3-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/anhnv125-hydra-llama-3-v1_reward/vocab.json
anhnv125-hydra-llama-3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/anhnv125-hydra-llama-3-v1_reward/tokenizer.json
Job anhnv125-hydra-llama-3-v1-mkmlizer completed after 73.47s with status: succeeded
Stopping job with name anhnv125-hydra-llama-3-v1-mkmlizer
Pipeline stage MKMLizer completed in 78.84s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service anhnv125-hydra-llama-3-v1
Waiting for inference service anhnv125-hydra-llama-3-v1 to be ready
Inference service anhnv125-hydra-llama-3-v1 ready after 40.22182583808899s
Pipeline stage ISVCDeployer completed in 48.42s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.862358331680298s
Received healthy response to inference request in 1.9724617004394531s
Received healthy response to inference request in 1.9614412784576416s
Received healthy response to inference request in 2.0397865772247314s
Received healthy response to inference request in 2.0439674854278564s
5 requests
0 failed requests
5th percentile: 1.9636453628540038
10th percentile: 1.9658494472503663
20th percentile: 1.970257616043091
30th percentile: 1.9859266757965088
40th percentile: 2.01285662651062
50th percentile: 2.0397865772247314
60th percentile: 2.0414589405059815
70th percentile: 2.0431313037872316
80th percentile: 2.2076456546783447
90th percentile: 2.5350019931793213
95th percentile: 2.6986801624298096
99th percentile: 2.8296226978302004
mean time: 2.176003074645996
Pipeline stage StressChecker completed in 11.50s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.05s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.05s
M-Eval Dataset for topic stay_in_character is loaded
anhnv125-hydra-llama-3_v1 status is now deployed due to DeploymentManager action
anhnv125-hydra-llama-3_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of anhnv125-hydra-llama-3_v1
Running pipeline stage ISVCDeleter
Checking if service anhnv125-hydra-llama-3-v1 is running
Tearing down inference service anhnv125-hydra-llama-3-v1
Toredown service anhnv125-hydra-llama-3-v1
Pipeline stage ISVCDeleter completed in 4.52s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key anhnv125-hydra-llama-3-v1/config.json from bucket guanaco-mkml-models
Deleting key anhnv125-hydra-llama-3-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key anhnv125-hydra-llama-3-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key anhnv125-hydra-llama-3-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key anhnv125-hydra-llama-3-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key anhnv125-hydra-llama-3-v1_reward/config.json from bucket guanaco-reward-models
Deleting key anhnv125-hydra-llama-3-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key anhnv125-hydra-llama-3-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key anhnv125-hydra-llama-3-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key anhnv125-hydra-llama-3-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key anhnv125-hydra-llama-3-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key anhnv125-hydra-llama-3-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.67s
anhnv125-hydra-llama-3_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics