submission_id: hyperblaze-l3-8b-soliloq_2337_v1
developer_uid: HyperBlaze
status: torndown
model_repo: HyperBlaze/L3-8B-Soliloquy-v2-SpicyMaid-Lewd-Mergetest
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.8, 'top_p': 0.95, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.7, 'frequency_penalty': 0.15, 'stopping_words': ['\n', 'user:', 'you:'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}
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}
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: 2024-05-08T23:08:43+00:00
model_name: Soliloquy-SpicyMaidLewd-test
model_eval_status: success
model_group: HyperBlaze/L3-8B-Soliloq
num_battles: 19741
num_wins: 9911
celo_rating: 1177.36
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
display_name: Soliloquy-SpicyMaidLewd-test
ineligible_reason: propriety_total_count < 800
language_model: HyperBlaze/L3-8B-Soliloquy-v2-SpicyMaid-Lewd-Mergetest
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-08
win_ratio: 0.5020515678030495
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer
Waiting for job on hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer to finish
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: ║ _____ __ __ ║
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: ║ /___/ ║
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: ║ ║
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: ║ Version: 0.8.10 ║
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: ║ ║
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: ║ belonging to: ║
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: ║ ║
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: ║ Chai Research Corp. ║
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: ║ ║
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hyperblaze-l3-8b-soliloq-2337-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.
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: Downloaded to shared memory in 25.230s
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 44%|████▎ | 127/291 [00:01<00:01, 125.44it/s] Loading 0: 64%|██████▍ | 187/291 [00:07<00:04, 21.40it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: quantized model in 19.599s
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: Processed model HyperBlaze/L3-8B-Soliloquy-v2-SpicyMaid-Lewd-Mergetest in 45.842s
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: creating bucket guanaco-mkml-models
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hyperblaze-l3-8b-soliloq-2337-v1
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hyperblaze-l3-8b-soliloq-2337-v1/config.json
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hyperblaze-l3-8b-soliloq-2337-v1/special_tokens_map.json
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hyperblaze-l3-8b-soliloq-2337-v1/tokenizer_config.json
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hyperblaze-l3-8b-soliloq-2337-v1/tokenizer.json
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hyperblaze-l3-8b-soliloq-2337-v1/flywheel_model.0.safetensors
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hyperblaze-l3-8b-soliloq-2337-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.
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: warnings.warn(
hyperblaze-l3-8b-soliloq-2337-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.
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: warnings.warn(
hyperblaze-l3-8b-soliloq-2337-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.
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: warnings.warn(
hyperblaze-l3-8b-soliloq-2337-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()
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: Saving duration: 0.241s
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.811s
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: creating bucket guanaco-reward-models
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-2337-v1_reward
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-2337-v1_reward/tokenizer_config.json
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-2337-v1_reward/special_tokens_map.json
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-2337-v1_reward/merges.txt
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-2337-v1_reward/config.json
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-2337-v1_reward/vocab.json
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-2337-v1_reward/tokenizer.json
hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-2337-v1_reward/reward.tensors
Job hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer completed after 74.34s with status: succeeded
Stopping job with name hyperblaze-l3-8b-soliloq-2337-v1-mkmlizer
Pipeline stage MKMLizer completed in 77.61s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hyperblaze-l3-8b-soliloq-2337-v1
Waiting for inference service hyperblaze-l3-8b-soliloq-2337-v1 to be ready
Inference service hyperblaze-l3-8b-soliloq-2337-v1 ready after 30.210546016693115s
Pipeline stage ISVCDeployer completed in 38.01s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9485454559326172s
Received healthy response to inference request in 1.156503438949585s
Received healthy response to inference request in 1.2386209964752197s
Received healthy response to inference request in 1.1776213645935059s
Received healthy response to inference request in 1.1731722354888916s
5 requests
0 failed requests
5th percentile: 1.1598371982574462
10th percentile: 1.1631709575653075
20th percentile: 1.1698384761810303
30th percentile: 1.1740620613098145
40th percentile: 1.17584171295166
50th percentile: 1.1776213645935059
60th percentile: 1.2020212173461915
70th percentile: 1.226421070098877
80th percentile: 1.3806058883666994
90th percentile: 1.6645756721496583
95th percentile: 1.8065605640411375
99th percentile: 1.9201484775543212
mean time: 1.3388926982879639
Pipeline stage StressChecker completed in 7.49s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
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
hyperblaze-l3-8b-soliloq_2337_v1 status is now deployed due to DeploymentManager action
hyperblaze-l3-8b-soliloq_2337_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hyperblaze-l3-8b-soliloq_2337_v1
Running pipeline stage ISVCDeleter
Checking if service hyperblaze-l3-8b-soliloq-2337-v1 is running
Tearing down inference service hyperblaze-l3-8b-soliloq-2337-v1
Toredown service hyperblaze-l3-8b-soliloq-2337-v1
Pipeline stage ISVCDeleter completed in 3.71s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hyperblaze-l3-8b-soliloq-2337-v1/config.json from bucket guanaco-mkml-models
Deleting key hyperblaze-l3-8b-soliloq-2337-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hyperblaze-l3-8b-soliloq-2337-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hyperblaze-l3-8b-soliloq-2337-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hyperblaze-l3-8b-soliloq-2337-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hyperblaze-l3-8b-soliloq-2337-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hyperblaze-l3-8b-soliloq-2337-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hyperblaze-l3-8b-soliloq-2337-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hyperblaze-l3-8b-soliloq-2337-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hyperblaze-l3-8b-soliloq-2337-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hyperblaze-l3-8b-soliloq-2337-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hyperblaze-l3-8b-soliloq-2337-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.00s
hyperblaze-l3-8b-soliloq_2337_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics