developer_uid: robert_irvine
submission_id: neversleep-llama-3-lumim_7274_v2
model_name: neversleep-llama-3-lumim_7274_v2
model_group: NeverSleep/Llama-3-Lumim
status: torndown
timestamp: 2024-05-02T16:58:23+00:00
num_battles: 22446
num_wins: 10819
celo_rating: 1149.34
family_friendly_score: 0.0
submission_type: basic
model_repo: NeverSleep/Llama-3-Lumimaid-8B-v0.1
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: neversleep-llama-3-lumim_7274_v2
is_internal_developer: True
language_model: NeverSleep/Llama-3-Lumimaid-8B-v0.1
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-02
win_ratio: 0.48200124743829637
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>', '<|start_header_id|>', '\n\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': '<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nThis is an entertaining conversation. Engage in a chat with {user_name} while staying in character. Try to flirt with {user_name}. Engage in *roleplay* actions. Describe the scene dramatically. You are {bot_name} with persona: {memory}', 'prompt_template': 'Example conversation:\n{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
model_eval_status: pending
reward_formatter: {'bot_template': 'Bot: {message}\n', 'memory_template': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-llama-3-lumim-7274-v2-mkmlizer
Waiting for job on neversleep-llama-3-lumim-7274-v2-mkmlizer to finish
neversleep-llama-3-lumim-7274-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-llama-3-lumim-7274-v2-mkmlizer: ║     _____            __           __                                ║
neversleep-llama-3-lumim-7274-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
neversleep-llama-3-lumim-7274-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
neversleep-llama-3-lumim-7274-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
neversleep-llama-3-lumim-7274-v2-mkmlizer: ║       /___/                                                         ║
neversleep-llama-3-lumim-7274-v2-mkmlizer: ║                                                                     ║
neversleep-llama-3-lumim-7274-v2-mkmlizer: ║  Version: 0.8.10                                                    ║
neversleep-llama-3-lumim-7274-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
neversleep-llama-3-lumim-7274-v2-mkmlizer: ║                                                                     ║
neversleep-llama-3-lumim-7274-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
neversleep-llama-3-lumim-7274-v2-mkmlizer: ║  belonging to:                                                      ║
neversleep-llama-3-lumim-7274-v2-mkmlizer: ║                                                                     ║
neversleep-llama-3-lumim-7274-v2-mkmlizer: ║  Chai Research Corp.                                                ║
neversleep-llama-3-lumim-7274-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
neversleep-llama-3-lumim-7274-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
neversleep-llama-3-lumim-7274-v2-mkmlizer: ║                                                                     ║
neversleep-llama-3-lumim-7274-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-llama-3-lumim-7274-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.
neversleep-llama-3-lumim-7274-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
neversleep-llama-3-lumim-7274-v2-mkmlizer: Downloaded to shared memory in 14.202s
neversleep-llama-3-lumim-7274-v2-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-llama-3-lumim-7274-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-llama-3-lumim-7274-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:03<09:35,  1.99s/it]
Loading 0:  57%|█████▋    | 166/291 [00:05<00:03, 40.56it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
neversleep-llama-3-lumim-7274-v2-mkmlizer: quantized model in 17.091s
neversleep-llama-3-lumim-7274-v2-mkmlizer: Processed model NeverSleep/Llama-3-Lumimaid-8B-v0.1 in 32.177s
neversleep-llama-3-lumim-7274-v2-mkmlizer: creating bucket guanaco-mkml-models
neversleep-llama-3-lumim-7274-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-llama-3-lumim-7274-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-llama-3-lumim-7274-v2
neversleep-llama-3-lumim-7274-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-7274-v2/special_tokens_map.json
neversleep-llama-3-lumim-7274-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-7274-v2/tokenizer_config.json
neversleep-llama-3-lumim-7274-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-7274-v2/config.json
neversleep-llama-3-lumim-7274-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-7274-v2/tokenizer.json
neversleep-llama-3-lumim-7274-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-llama-3-lumim-7274-v2/flywheel_model.0.safetensors
neversleep-llama-3-lumim-7274-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
neversleep-llama-3-lumim-7274-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.
neversleep-llama-3-lumim-7274-v2-mkmlizer:   warnings.warn(
neversleep-llama-3-lumim-7274-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.
neversleep-llama-3-lumim-7274-v2-mkmlizer:   warnings.warn(
neversleep-llama-3-lumim-7274-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.
neversleep-llama-3-lumim-7274-v2-mkmlizer:   warnings.warn(
neversleep-llama-3-lumim-7274-v2-mkmlizer: Saving duration: 0.227s
neversleep-llama-3-lumim-7274-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.573s
neversleep-llama-3-lumim-7274-v2-mkmlizer: creating bucket guanaco-reward-models
neversleep-llama-3-lumim-7274-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-llama-3-lumim-7274-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-llama-3-lumim-7274-v2_reward
neversleep-llama-3-lumim-7274-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-llama-3-lumim-7274-v2_reward/config.json
neversleep-llama-3-lumim-7274-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-llama-3-lumim-7274-v2_reward/special_tokens_map.json
neversleep-llama-3-lumim-7274-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-llama-3-lumim-7274-v2_reward/tokenizer_config.json
neversleep-llama-3-lumim-7274-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-llama-3-lumim-7274-v2_reward/merges.txt
neversleep-llama-3-lumim-7274-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-llama-3-lumim-7274-v2_reward/vocab.json
neversleep-llama-3-lumim-7274-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-llama-3-lumim-7274-v2_reward/tokenizer.json
neversleep-llama-3-lumim-7274-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-llama-3-lumim-7274-v2_reward/reward.tensors
Job neversleep-llama-3-lumim-7274-v2-mkmlizer completed after 57.48s with status: succeeded
Stopping job with name neversleep-llama-3-lumim-7274-v2-mkmlizer
Pipeline stage MKMLizer completed in 58.85s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.30s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-llama-3-lumim-7274-v2
Waiting for inference service neversleep-llama-3-lumim-7274-v2 to be ready
Inference service neversleep-llama-3-lumim-7274-v2 ready after 40.619651079177856s
Pipeline stage ISVCDeployer completed in 46.79s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.027519702911377s
Received healthy response to inference request in 1.1874897480010986s
Received healthy response to inference request in 1.2417068481445312s
Received healthy response to inference request in 1.2108900547027588s
Received healthy response to inference request in 1.3537287712097168s
5 requests
0 failed requests
5th percentile: 1.1921698093414306
10th percentile: 1.1968498706817627
20th percentile: 1.2062099933624268
30th percentile: 1.2170534133911133
40th percentile: 1.2293801307678223
50th percentile: 1.2417068481445312
60th percentile: 1.2865156173706054
70th percentile: 1.3313243865966797
80th percentile: 1.488486957550049
90th percentile: 1.758003330230713
95th percentile: 1.8927615165710447
99th percentile: 2.0005680656433107
mean time: 1.4042670249938964
Pipeline stage StressChecker completed in 9.59s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.12s
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 0.24s
%s, retrying in %s seconds...
neversleep-llama-3-lumim_7274_v2 status is now deployed due to DeploymentManager action
%s, retrying in %s seconds...
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
neversleep-llama-3-lumim_7274_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of neversleep-llama-3-lumim_7274_v2
Running pipeline stage ISVCDeleter
Checking if service neversleep-llama-3-lumim-7274-v2 is running
Tearing down inference service neversleep-llama-3-lumim-7274-v2
Toredown service neversleep-llama-3-lumim-7274-v2
Pipeline stage ISVCDeleter completed in 3.43s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key neversleep-llama-3-lumim-7274-v2/config.json from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-7274-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-7274-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-7274-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-7274-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key neversleep-llama-3-lumim-7274-v2_reward/config.json from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-7274-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-7274-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-7274-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-7274-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-7274-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-7274-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.86s
neversleep-llama-3-lumim_7274_v2 status is now torndown due to DeploymentManager action