submission_id: neversleep-llama-3-lumim_6375_v3
developer_uid: Undi95
status: torndown
model_repo: NeverSleep/Llama-3-Lumimaid-8B-v1.1
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': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n", 'prompt_template': '{prompt}\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", 'prompt_template': '{prompt}\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-04-26T00:17:52+00:00
model_name: neversleep-llama-3-lumim_6375_v3
model_eval_status: success
model_group: NeverSleep/Llama-3-Lumim
num_battles: 7526
num_wins: 3967
celo_rating: 1172.16
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: neversleep-llama-3-lumim_6375_v3
ineligible_reason: propriety_total_count < 800
language_model: NeverSleep/Llama-3-Lumimaid-8B-v1.1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-25
win_ratio: 0.5271060324209408
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-llama-3-lumim-6375-v3-mkmlizer
Waiting for job on neversleep-llama-3-lumim-6375-v3-mkmlizer to finish
neversleep-llama-3-lumim-6375-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-llama-3-lumim-6375-v3-mkmlizer: ║ _____ __ __ ║
neversleep-llama-3-lumim-6375-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-llama-3-lumim-6375-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-llama-3-lumim-6375-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-llama-3-lumim-6375-v3-mkmlizer: ║ /___/ ║
neversleep-llama-3-lumim-6375-v3-mkmlizer: ║ ║
neversleep-llama-3-lumim-6375-v3-mkmlizer: ║ Version: 0.8.10 ║
neversleep-llama-3-lumim-6375-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-llama-3-lumim-6375-v3-mkmlizer: ║ ║
neversleep-llama-3-lumim-6375-v3-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-llama-3-lumim-6375-v3-mkmlizer: ║ belonging to: ║
neversleep-llama-3-lumim-6375-v3-mkmlizer: ║ ║
neversleep-llama-3-lumim-6375-v3-mkmlizer: ║ Chai Research Corp. ║
neversleep-llama-3-lumim-6375-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-llama-3-lumim-6375-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-llama-3-lumim-6375-v3-mkmlizer: ║ ║
neversleep-llama-3-lumim-6375-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-llama-3-lumim-6375-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.
neversleep-llama-3-lumim-6375-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
neversleep-llama-3-lumim-6375-v3-mkmlizer: Downloaded to shared memory in 11.440s
neversleep-llama-3-lumim-6375-v3-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-llama-3-lumim-6375-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-llama-3-lumim-6375-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:02, 2.09s/it] Loading 0: 57%|█████▋ | 166/291 [00:05<00:03, 39.19it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
neversleep-llama-3-lumim-6375-v3-mkmlizer: quantized model in 17.360s
neversleep-llama-3-lumim-6375-v3-mkmlizer: Processed model NeverSleep/Llama-3-Lumimaid-8B-v1.1 in 29.810s
neversleep-llama-3-lumim-6375-v3-mkmlizer: creating bucket guanaco-mkml-models
neversleep-llama-3-lumim-6375-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-llama-3-lumim-6375-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-llama-3-lumim-6375-v3
neversleep-llama-3-lumim-6375-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-6375-v3/config.json
neversleep-llama-3-lumim-6375-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-6375-v3/tokenizer_config.json
neversleep-llama-3-lumim-6375-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-6375-v3/special_tokens_map.json
neversleep-llama-3-lumim-6375-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-6375-v3/tokenizer.json
neversleep-llama-3-lumim-6375-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-llama-3-lumim-6375-v3/flywheel_model.0.safetensors
neversleep-llama-3-lumim-6375-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
neversleep-llama-3-lumim-6375-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.
neversleep-llama-3-lumim-6375-v3-mkmlizer: warnings.warn(
neversleep-llama-3-lumim-6375-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.
neversleep-llama-3-lumim-6375-v3-mkmlizer: warnings.warn(
neversleep-llama-3-lumim-6375-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.
neversleep-llama-3-lumim-6375-v3-mkmlizer: warnings.warn(
neversleep-llama-3-lumim-6375-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()
neversleep-llama-3-lumim-6375-v3-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-llama-3-lumim-6375-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-llama-3-lumim-6375-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-llama-3-lumim-6375-v3_reward/reward.tensors
Job neversleep-llama-3-lumim-6375-v3-mkmlizer completed after 52.84s with status: succeeded
Stopping job with name neversleep-llama-3-lumim-6375-v3-mkmlizer
Pipeline stage MKMLizer completed in 55.96s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-llama-3-lumim-6375-v3
Waiting for inference service neversleep-llama-3-lumim-6375-v3 to be ready
Inference service neversleep-llama-3-lumim-6375-v3 ready after 30.189049243927002s
Pipeline stage ISVCDeployer completed in 37.35s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0404446125030518s
Received healthy response to inference request in 1.2403347492218018s
Received healthy response to inference request in 1.2544355392456055s
Received healthy response to inference request in 1.2325584888458252s
Received healthy response to inference request in 1.2137196063995361s
5 requests
0 failed requests
5th percentile: 1.217487382888794
10th percentile: 1.2212551593780518
20th percentile: 1.2287907123565673
30th percentile: 1.2341137409210206
40th percentile: 1.237224245071411
50th percentile: 1.2403347492218018
60th percentile: 1.2459750652313233
70th percentile: 1.2516153812408448
80th percentile: 1.4116373538970948
90th percentile: 1.7260409832000734
95th percentile: 1.8832427978515625
99th percentile: 2.009004249572754
mean time: 1.396298599243164
Pipeline stage StressChecker completed in 7.59s
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
neversleep-llama-3-lumim_6375_v3 status is now deployed due to DeploymentManager action
neversleep-llama-3-lumim_6375_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of neversleep-llama-3-lumim_6375_v3
Running pipeline stage ISVCDeleter
Checking if service neversleep-llama-3-lumim-6375-v3 is running
Tearing down inference service neversleep-llama-3-lumim-6375-v3
Toredown service neversleep-llama-3-lumim-6375-v3
Pipeline stage ISVCDeleter completed in 3.94s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key neversleep-llama-3-lumim-6375-v3/config.json from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-6375-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-6375-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-6375-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-6375-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key neversleep-llama-3-lumim-6375-v3_reward/config.json from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-6375-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-6375-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-6375-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-6375-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-6375-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-6375-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.08s
neversleep-llama-3-lumim_6375_v3 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics