submission_id: hyperblaze-l3-8b-soliloq_6192_v1
developer_uid: HyperBlaze
status: inactive
model_repo: HyperBlaze/L3-8B-Soliloquy-TheSpice-Hermes2pro-merge-v1
reward_repo: ChaiML/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': ['\n'], 'max_input_tokens': 512, '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: 2024-05-08T19:44:35+00:00
model_name: hyperblaze-l3-8b-soliloq_6192_v1
model_eval_status: success
double_thumbs_up: 259
thumbs_up: 349
thumbs_down: 139
num_battles: 19849
num_wins: 9854
celo_rating: 1166.81
entertaining: 6.8
stay_in_character: 8.54
user_preference: 7.46
safety_score: 0.94
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: hyperblaze-l3-8b-soliloq_6192_v1
double_thumbs_up_ratio: 0.3467202141900937
feedback_count: 747
ineligible_reason: None
language_model: HyperBlaze/L3-8B-Soliloquy-TheSpice-Hermes2pro-merge-v1
model_score: 7.6000000000000005
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.46720214190093706
thumbs_down_ratio: 0.18607764390896922
thumbs_up_ratio: 0.8139223560910308
us_pacific_date: 2024-05-08
win_ratio: 0.49644818378759636
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer
Waiting for job on hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer to finish
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: ║ _____ __ __ ║
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: ║ /___/ ║
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: ║ ║
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: ║ Version: 0.8.10 ║
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: ║ ║
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: ║ belonging to: ║
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: ║ ║
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: ║ Chai Research Corp. ║
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: ║ ║
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hyperblaze-l3-8b-soliloq-6192-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-6192-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: Downloaded to shared memory in 22.680s
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 46%|████▋ | 135/291 [00:01<00:01, 134.28it/s] Loading 0: 64%|██████▍ | 187/291 [00:06<00:04, 22.18it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: quantized model in 18.956s
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: Processed model HyperBlaze/L3-8B-Soliloquy-TheSpice-Hermes2pro-merge-v1 in 42.646s
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: creating bucket guanaco-mkml-models
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hyperblaze-l3-8b-soliloq-6192-v1
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hyperblaze-l3-8b-soliloq-6192-v1/config.json
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hyperblaze-l3-8b-soliloq-6192-v1/tokenizer_config.json
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hyperblaze-l3-8b-soliloq-6192-v1/special_tokens_map.json
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hyperblaze-l3-8b-soliloq-6192-v1/tokenizer.json
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hyperblaze-l3-8b-soliloq-6192-v1/flywheel_model.0.safetensors
hyperblaze-l3-8b-soliloq-6192-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-6192-v1-mkmlizer: warnings.warn(
hyperblaze-l3-8b-soliloq-6192-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-6192-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: Saving duration: 0.253s
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.723s
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: creating bucket guanaco-reward-models
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-6192-v1_reward
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-6192-v1_reward/config.json
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-6192-v1_reward/merges.txt
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-6192-v1_reward/tokenizer_config.json
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-6192-v1_reward/special_tokens_map.json
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-6192-v1_reward/vocab.json
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-6192-v1_reward/tokenizer.json
hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-6192-v1_reward/reward.tensors
Job hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer completed after 72.95s with status: succeeded
Stopping job with name hyperblaze-l3-8b-soliloq-6192-v1-mkmlizer
Pipeline stage MKMLizer completed in 76.29s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hyperblaze-l3-8b-soliloq-6192-v1
Waiting for inference service hyperblaze-l3-8b-soliloq-6192-v1 to be ready
Inference service hyperblaze-l3-8b-soliloq-6192-v1 ready after 30.194279670715332s
Pipeline stage ISVCDeployer completed in 37.66s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0119190216064453s
Received healthy response to inference request in 1.1261613368988037s
Received healthy response to inference request in 1.089540958404541s
Received healthy response to inference request in 1.1157350540161133s
Received healthy response to inference request in 1.1122314929962158s
5 requests
0 failed requests
5th percentile: 1.094079065322876
10th percentile: 1.098617172241211
20th percentile: 1.1076933860778808
30th percentile: 1.1129322052001953
40th percentile: 1.1143336296081543
50th percentile: 1.1157350540161133
60th percentile: 1.1199055671691895
70th percentile: 1.1240760803222656
80th percentile: 1.3033128738403321
90th percentile: 1.6576159477233887
95th percentile: 1.834767484664917
99th percentile: 1.9764887142181395
mean time: 1.2911175727844237
Pipeline stage StressChecker completed in 7.12s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
hyperblaze-l3-8b-soliloq_6192_v1 status is now deployed due to DeploymentManager action
hyperblaze-l3-8b-soliloq_6192_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics