submission_id: resplendentai-kei-llama3-8b_v1
developer_uid: jeiku
status: torndown
model_repo: ResplendentAI/Kei_Llama3_8B
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', '<|eot_id|>', '<|im_end|>'], 'max_input_tokens': 512, 'best_of': 16, '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: 2024-04-23T05:46:49+00:00
model_name: resplendentai-kei-llama3-8b_v1
model_eval_status: success
model_group: ResplendentAI/Kei_Llama3
num_battles: 6898
num_wins: 3683
celo_rating: 1179.7
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: resplendentai-kei-llama3-8b_v1
ineligible_reason: propriety_total_count < 800
language_model: ResplendentAI/Kei_Llama3_8B
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-22
win_ratio: 0.5339228761959989
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name resplendentai-kei-llama3-8b-v1-mkmlizer
Waiting for job on resplendentai-kei-llama3-8b-v1-mkmlizer to finish
resplendentai-kei-llama3-8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
resplendentai-kei-llama3-8b-v1-mkmlizer: ║ _____ __ __ ║
resplendentai-kei-llama3-8b-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
resplendentai-kei-llama3-8b-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
resplendentai-kei-llama3-8b-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
resplendentai-kei-llama3-8b-v1-mkmlizer: ║ /___/ ║
resplendentai-kei-llama3-8b-v1-mkmlizer: ║ ║
resplendentai-kei-llama3-8b-v1-mkmlizer: ║ Version: 0.8.10 ║
resplendentai-kei-llama3-8b-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
resplendentai-kei-llama3-8b-v1-mkmlizer: ║ ║
resplendentai-kei-llama3-8b-v1-mkmlizer: ║ The license key for the current software has been verified as ║
resplendentai-kei-llama3-8b-v1-mkmlizer: ║ belonging to: ║
resplendentai-kei-llama3-8b-v1-mkmlizer: ║ ║
resplendentai-kei-llama3-8b-v1-mkmlizer: ║ Chai Research Corp. ║
resplendentai-kei-llama3-8b-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
resplendentai-kei-llama3-8b-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
resplendentai-kei-llama3-8b-v1-mkmlizer: ║ ║
resplendentai-kei-llama3-8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
resplendentai-kei-llama3-8b-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.
resplendentai-kei-llama3-8b-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
resplendentai-kei-llama3-8b-v1-mkmlizer: Downloaded to shared memory in 27.810s
resplendentai-kei-llama3-8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
resplendentai-kei-llama3-8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
resplendentai-kei-llama3-8b-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 56%|█████▌ | 162/291 [00:01<00:00, 161.27it/s] Loading 0: 64%|██████▍ | 187/291 [00:06<00:04, 23.33it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
resplendentai-kei-llama3-8b-v1-mkmlizer: quantized model in 18.340s
resplendentai-kei-llama3-8b-v1-mkmlizer: Processed model ResplendentAI/Kei_Llama3_8B in 47.060s
resplendentai-kei-llama3-8b-v1-mkmlizer: creating bucket guanaco-mkml-models
resplendentai-kei-llama3-8b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
resplendentai-kei-llama3-8b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/resplendentai-kei-llama3-8b-v1
resplendentai-kei-llama3-8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/resplendentai-kei-llama3-8b-v1/config.json
resplendentai-kei-llama3-8b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/resplendentai-kei-llama3-8b-v1/special_tokens_map.json
resplendentai-kei-llama3-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/resplendentai-kei-llama3-8b-v1/tokenizer_config.json
resplendentai-kei-llama3-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/resplendentai-kei-llama3-8b-v1/tokenizer.json
resplendentai-kei-llama3-8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/resplendentai-kei-llama3-8b-v1/flywheel_model.0.safetensors
resplendentai-kei-llama3-8b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
resplendentai-kei-llama3-8b-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.
resplendentai-kei-llama3-8b-v1-mkmlizer: warnings.warn(
resplendentai-kei-llama3-8b-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.
resplendentai-kei-llama3-8b-v1-mkmlizer: warnings.warn(
resplendentai-kei-llama3-8b-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.
resplendentai-kei-llama3-8b-v1-mkmlizer: warnings.warn(
resplendentai-kei-llama3-8b-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()
resplendentai-kei-llama3-8b-v1-mkmlizer: return self.fget.__get__(instance, owner)()
resplendentai-kei-llama3-8b-v1-mkmlizer: creating bucket guanaco-reward-models
resplendentai-kei-llama3-8b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
resplendentai-kei-llama3-8b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/resplendentai-kei-llama3-8b-v1_reward
resplendentai-kei-llama3-8b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/resplendentai-kei-llama3-8b-v1_reward/config.json
resplendentai-kei-llama3-8b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/resplendentai-kei-llama3-8b-v1_reward/special_tokens_map.json
resplendentai-kei-llama3-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/resplendentai-kei-llama3-8b-v1_reward/tokenizer_config.json
resplendentai-kei-llama3-8b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/resplendentai-kei-llama3-8b-v1_reward/merges.txt
resplendentai-kei-llama3-8b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/resplendentai-kei-llama3-8b-v1_reward/vocab.json
resplendentai-kei-llama3-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/resplendentai-kei-llama3-8b-v1_reward/tokenizer.json
resplendentai-kei-llama3-8b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/resplendentai-kei-llama3-8b-v1_reward/reward.tensors
Job resplendentai-kei-llama3-8b-v1-mkmlizer completed after 115.83s with status: succeeded
Stopping job with name resplendentai-kei-llama3-8b-v1-mkmlizer
Pipeline stage MKMLizer completed in 119.06s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service resplendentai-kei-llama3-8b-v1
Waiting for inference service resplendentai-kei-llama3-8b-v1 to be ready
Inference service resplendentai-kei-llama3-8b-v1 ready after 40.222676515579224s
Pipeline stage ISVCDeployer completed in 47.31s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.192352771759033s
Received healthy response to inference request in 1.2514233589172363s
Received healthy response to inference request in 1.258148431777954s
Received healthy response to inference request in 1.2448041439056396s
Received healthy response to inference request in 1.3134334087371826s
5 requests
0 failed requests
5th percentile: 1.246127986907959
10th percentile: 1.2474518299102784
20th percentile: 1.250099515914917
30th percentile: 1.25276837348938
40th percentile: 1.255458402633667
50th percentile: 1.258148431777954
60th percentile: 1.2802624225616455
70th percentile: 1.3023764133453368
80th percentile: 1.489217281341553
90th percentile: 1.840785026550293
95th percentile: 2.016568899154663
99th percentile: 2.1571959972381594
mean time: 1.4520324230194093
Pipeline stage StressChecker completed in 7.92s
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
resplendentai-kei-llama3-8b_v1 status is now deployed due to DeploymentManager action
resplendentai-kei-llama3-8b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of resplendentai-kei-llama3-8b_v1
Running pipeline stage ISVCDeleter
Checking if service resplendentai-kei-llama3-8b-v1 is running
Tearing down inference service resplendentai-kei-llama3-8b-v1
Toredown service resplendentai-kei-llama3-8b-v1
Pipeline stage ISVCDeleter completed in 3.93s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key resplendentai-kei-llama3-8b-v1/config.json from bucket guanaco-mkml-models
Deleting key resplendentai-kei-llama3-8b-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key resplendentai-kei-llama3-8b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key resplendentai-kei-llama3-8b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key resplendentai-kei-llama3-8b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key resplendentai-kei-llama3-8b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key resplendentai-kei-llama3-8b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key resplendentai-kei-llama3-8b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key resplendentai-kei-llama3-8b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key resplendentai-kei-llama3-8b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key resplendentai-kei-llama3-8b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key resplendentai-kei-llama3-8b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.77s
resplendentai-kei-llama3-8b_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics