submission_id: fizzarolli-llama-3-lust-_7285_v3
developer_uid: Fizzarolli
status: torndown
model_repo: Fizzarolli/llama-3-lust-8b-v0.2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.1, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': '<|description|>{bot_name}\n{memory}</s>\n', 'prompt_template': '<|message|>User\n{prompt}</s>\n<|message|>{bot_name}\n', 'bot_template': '<|message|>{bot_name}\n{message}</s>\n', 'user_template': '<|message|>User\n{message}</s>\n', 'response_template': '<|message|>{bot_name}\n', 'truncate_by_message': False}
reward_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}
timestamp: 2024-04-22T02:55:14+00:00
model_name: fizzarolli-llama-3-lust2_8389
model_eval_status: success
model_group: Fizzarolli/llama-3-lust-
num_battles: 5961
num_wins: 2964
celo_rating: 1141.78
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: 64
display_name: fizzarolli-llama-3-lust2_8389
ineligible_reason: propriety_total_count < 800
language_model: Fizzarolli/llama-3-lust-8b-v0.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-21
win_ratio: 0.4972320080523402
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name fizzarolli-llama-3-lust-7285-v3-mkmlizer
Waiting for job on fizzarolli-llama-3-lust-7285-v3-mkmlizer to finish
fizzarolli-llama-3-lust-7285-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
fizzarolli-llama-3-lust-7285-v3-mkmlizer: ║ _____ __ __ ║
fizzarolli-llama-3-lust-7285-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
fizzarolli-llama-3-lust-7285-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
fizzarolli-llama-3-lust-7285-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
fizzarolli-llama-3-lust-7285-v3-mkmlizer: ║ /___/ ║
fizzarolli-llama-3-lust-7285-v3-mkmlizer: ║ ║
fizzarolli-llama-3-lust-7285-v3-mkmlizer: ║ Version: 0.8.10 ║
fizzarolli-llama-3-lust-7285-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
fizzarolli-llama-3-lust-7285-v3-mkmlizer: ║ ║
fizzarolli-llama-3-lust-7285-v3-mkmlizer: ║ The license key for the current software has been verified as ║
fizzarolli-llama-3-lust-7285-v3-mkmlizer: ║ belonging to: ║
fizzarolli-llama-3-lust-7285-v3-mkmlizer: ║ ║
fizzarolli-llama-3-lust-7285-v3-mkmlizer: ║ Chai Research Corp. ║
fizzarolli-llama-3-lust-7285-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
fizzarolli-llama-3-lust-7285-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
fizzarolli-llama-3-lust-7285-v3-mkmlizer: ║ ║
fizzarolli-llama-3-lust-7285-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
fizzarolli-llama-3-lust-7285-v3-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.
fizzarolli-llama-3-lust-7285-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
fizzarolli-llama-3-lust-7285-v3-mkmlizer: Downloaded to shared memory in 20.610s
fizzarolli-llama-3-lust-7285-v3-mkmlizer: quantizing model to /dev/shm/model_cache
fizzarolli-llama-3-lust-7285-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
fizzarolli-llama-3-lust-7285-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:01, 120.60it/s] Loading 0: 83%|████████▎ | 242/291 [00:02<00:00, 120.83it/s] Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 30.00it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
fizzarolli-llama-3-lust-7285-v3-mkmlizer: Processed model Fizzarolli/llama-3-lust-8b-v0.2 in 39.463s
fizzarolli-llama-3-lust-7285-v3-mkmlizer: creating bucket guanaco-mkml-models
fizzarolli-llama-3-lust-7285-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
fizzarolli-llama-3-lust-7285-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/fizzarolli-llama-3-lust-7285-v3
fizzarolli-llama-3-lust-7285-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/fizzarolli-llama-3-lust-7285-v3/config.json
fizzarolli-llama-3-lust-7285-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/fizzarolli-llama-3-lust-7285-v3/special_tokens_map.json
fizzarolli-llama-3-lust-7285-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/fizzarolli-llama-3-lust-7285-v3/tokenizer_config.json
fizzarolli-llama-3-lust-7285-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/fizzarolli-llama-3-lust-7285-v3/tokenizer.json
fizzarolli-llama-3-lust-7285-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/fizzarolli-llama-3-lust-7285-v3/flywheel_model.0.safetensors
fizzarolli-llama-3-lust-7285-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
fizzarolli-llama-3-lust-7285-v3-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.
fizzarolli-llama-3-lust-7285-v3-mkmlizer: warnings.warn(
fizzarolli-llama-3-lust-7285-v3-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.
fizzarolli-llama-3-lust-7285-v3-mkmlizer: warnings.warn(
fizzarolli-llama-3-lust-7285-v3-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.
fizzarolli-llama-3-lust-7285-v3-mkmlizer: warnings.warn(
fizzarolli-llama-3-lust-7285-v3-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()
fizzarolli-llama-3-lust-7285-v3-mkmlizer: return self.fget.__get__(instance, owner)()
fizzarolli-llama-3-lust-7285-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
fizzarolli-llama-3-lust-7285-v3-mkmlizer: Saving duration: 0.248s
fizzarolli-llama-3-lust-7285-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.742s
fizzarolli-llama-3-lust-7285-v3-mkmlizer: creating bucket guanaco-reward-models
fizzarolli-llama-3-lust-7285-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
fizzarolli-llama-3-lust-7285-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/fizzarolli-llama-3-lust-7285-v3_reward
fizzarolli-llama-3-lust-7285-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/fizzarolli-llama-3-lust-7285-v3_reward/config.json
fizzarolli-llama-3-lust-7285-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/fizzarolli-llama-3-lust-7285-v3_reward/tokenizer_config.json
fizzarolli-llama-3-lust-7285-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/fizzarolli-llama-3-lust-7285-v3_reward/special_tokens_map.json
fizzarolli-llama-3-lust-7285-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/fizzarolli-llama-3-lust-7285-v3_reward/merges.txt
fizzarolli-llama-3-lust-7285-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/fizzarolli-llama-3-lust-7285-v3_reward/vocab.json
fizzarolli-llama-3-lust-7285-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/fizzarolli-llama-3-lust-7285-v3_reward/tokenizer.json
fizzarolli-llama-3-lust-7285-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/fizzarolli-llama-3-lust-7285-v3_reward/reward.tensors
Job fizzarolli-llama-3-lust-7285-v3-mkmlizer completed after 63.55s with status: succeeded
Stopping job with name fizzarolli-llama-3-lust-7285-v3-mkmlizer
Pipeline stage MKMLizer completed in 68.42s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service fizzarolli-llama-3-lust-7285-v3
Waiting for inference service fizzarolli-llama-3-lust-7285-v3 to be ready
Inference service fizzarolli-llama-3-lust-7285-v3 ready after 40.372432470321655s
Pipeline stage ISVCDeployer completed in 48.05s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1009902954101562s
Received healthy response to inference request in 1.2215850353240967s
Received healthy response to inference request in 1.2108373641967773s
Received healthy response to inference request in 1.574594497680664s
Received healthy response to inference request in 1.249800682067871s
5 requests
0 failed requests
5th percentile: 1.2129868984222412
10th percentile: 1.215136432647705
20th percentile: 1.2194355010986329
30th percentile: 1.2272281646728516
40th percentile: 1.2385144233703613
50th percentile: 1.249800682067871
60th percentile: 1.3797182083129882
70th percentile: 1.5096357345581055
80th percentile: 1.6798736572265627
90th percentile: 1.8904319763183595
95th percentile: 1.9957111358642576
99th percentile: 2.0799344635009764
mean time: 1.471561574935913
Pipeline stage StressChecker completed in 7.99s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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
fizzarolli-llama-3-lust-_7285_v3 status is now deployed due to DeploymentManager action
fizzarolli-llama-3-lust-_7285_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of fizzarolli-llama-3-lust-_7285_v3
Running pipeline stage ISVCDeleter
Checking if service fizzarolli-llama-3-lust-7285-v3 is running
Tearing down inference service fizzarolli-llama-3-lust-7285-v3
Toredown service fizzarolli-llama-3-lust-7285-v3
Pipeline stage ISVCDeleter completed in 3.44s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key fizzarolli-llama-3-lust-7285-v3/config.json from bucket guanaco-mkml-models
Deleting key fizzarolli-llama-3-lust-7285-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key fizzarolli-llama-3-lust-7285-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key fizzarolli-llama-3-lust-7285-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key fizzarolli-llama-3-lust-7285-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key fizzarolli-llama-3-lust-7285-v3_reward/config.json from bucket guanaco-reward-models
Deleting key fizzarolli-llama-3-lust-7285-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key fizzarolli-llama-3-lust-7285-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key fizzarolli-llama-3-lust-7285-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key fizzarolli-llama-3-lust-7285-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key fizzarolli-llama-3-lust-7285-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key fizzarolli-llama-3-lust-7285-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.45s
fizzarolli-llama-3-lust-_7285_v3 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics