submission_id: hyperblaze-l3-8b-soliloq_2337_v2
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': 0.1, 'stopping_words': ['\n'], '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: 2024-05-08T23:12:45+00:00
model_name: hyperblaze-l3-8b-soliloq_2337_v2
model_eval_status: success
model_group: HyperBlaze/L3-8B-Soliloq
num_battles: 17933
num_wins: 8990
celo_rating: 1177.6
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: hyperblaze-l3-8b-soliloq_2337_v2
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: 0.501310433279429
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer
Waiting for job on hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer to finish
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: ║ _____ __ __ ║
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: ║ /___/ ║
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: ║ ║
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: ║ Version: 0.8.10 ║
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: ║ ║
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: ║ belonging to: ║
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: ║ ║
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: ║ Chai Research Corp. ║
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: ║ ║
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hyperblaze-l3-8b-soliloq-2337-v2-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-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: Downloaded to shared memory in 19.733s
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 36%|███▌ | 104/291 [00:01<00:01, 102.25it/s] Loading 0: 64%|██████▍ | 187/291 [00:07<00:04, 21.92it/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-v2-mkmlizer: quantized model in 19.908s
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: Processed model HyperBlaze/L3-8B-Soliloquy-v2-SpicyMaid-Lewd-Mergetest in 40.754s
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: creating bucket guanaco-mkml-models
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hyperblaze-l3-8b-soliloq-2337-v2
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hyperblaze-l3-8b-soliloq-2337-v2/special_tokens_map.json
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hyperblaze-l3-8b-soliloq-2337-v2/tokenizer_config.json
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hyperblaze-l3-8b-soliloq-2337-v2/config.json
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hyperblaze-l3-8b-soliloq-2337-v2/tokenizer.json
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hyperblaze-l3-8b-soliloq-2337-v2/flywheel_model.0.safetensors
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hyperblaze-l3-8b-soliloq-2337-v2-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-v2-mkmlizer: warnings.warn(
hyperblaze-l3-8b-soliloq-2337-v2-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-v2-mkmlizer: warnings.warn(
hyperblaze-l3-8b-soliloq-2337-v2-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-v2-mkmlizer: warnings.warn(
hyperblaze-l3-8b-soliloq-2337-v2-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-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: Saving duration: 0.255s
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.974s
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: creating bucket guanaco-reward-models
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-2337-v2_reward
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-2337-v2_reward/config.json
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-2337-v2_reward/special_tokens_map.json
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-2337-v2_reward/tokenizer_config.json
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-2337-v2_reward/vocab.json
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-2337-v2_reward/merges.txt
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-2337-v2_reward/tokenizer.json
hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-2337-v2_reward/reward.tensors
Job hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer completed after 62.7s with status: succeeded
Stopping job with name hyperblaze-l3-8b-soliloq-2337-v2-mkmlizer
Pipeline stage MKMLizer completed in 65.91s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hyperblaze-l3-8b-soliloq-2337-v2
Waiting for inference service hyperblaze-l3-8b-soliloq-2337-v2 to be ready
Inference service hyperblaze-l3-8b-soliloq-2337-v2 ready after 40.34318470954895s
Pipeline stage ISVCDeployer completed in 47.46s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.961087942123413s
Received healthy response to inference request in 1.1601810455322266s
Received healthy response to inference request in 1.166041374206543s
Received healthy response to inference request in 1.1716973781585693s
Received healthy response to inference request in 1.1579272747039795s
5 requests
0 failed requests
5th percentile: 1.1583780288696288
10th percentile: 1.1588287830352784
20th percentile: 1.1597302913665772
30th percentile: 1.1613531112670898
40th percentile: 1.1636972427368164
50th percentile: 1.166041374206543
60th percentile: 1.1683037757873536
70th percentile: 1.1705661773681642
80th percentile: 1.3295754909515383
90th percentile: 1.6453317165374757
95th percentile: 1.8032098293304442
99th percentile: 1.9295123195648194
mean time: 1.3233870029449464
Pipeline stage StressChecker completed in 7.31s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.03s
M-Eval Dataset for topic stay_in_character is loaded
hyperblaze-l3-8b-soliloq_2337_v2 status is now deployed due to DeploymentManager action
hyperblaze-l3-8b-soliloq_2337_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hyperblaze-l3-8b-soliloq_2337_v2
Running pipeline stage ISVCDeleter
Checking if service hyperblaze-l3-8b-soliloq-2337-v2 is running
Tearing down inference service hyperblaze-l3-8b-soliloq-2337-v2
Toredown service hyperblaze-l3-8b-soliloq-2337-v2
Pipeline stage ISVCDeleter completed in 5.50s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
admin requested tearing down of inferenceillusionist-m7-_8467_v1
Cleaning model data from model cache
Running pipeline stage ISVCDeleter
Deleting key hyperblaze-l3-8b-soliloq-2337-v2/config.json from bucket guanaco-mkml-models
Checking if service inferenceillusionist-m7-8467-v1 is running
Deleting key hyperblaze-l3-8b-soliloq-2337-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hyperblaze-l3-8b-soliloq-2337-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hyperblaze-l3-8b-soliloq-2337-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hyperblaze-l3-8b-soliloq-2337-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hyperblaze-l3-8b-soliloq-2337-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hyperblaze-l3-8b-soliloq-2337-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hyperblaze-l3-8b-soliloq-2337-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hyperblaze-l3-8b-soliloq-2337-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hyperblaze-l3-8b-soliloq-2337-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hyperblaze-l3-8b-soliloq-2337-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hyperblaze-l3-8b-soliloq-2337-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.74s
hyperblaze-l3-8b-soliloq_2337_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics