developer_uid: robert_irvine
submission_id: vicgalle-roleplay-llama-3-8b_v17
model_name: vicgalle-roleplay-llama-3-8b_v17
model_group: vicgalle/Roleplay-Llama-
status: torndown
timestamp: 2024-05-02T17:11:13+00:00
num_battles: 19389
num_wins: 9431
celo_rating: 1152.04
family_friendly_score: 0.0
submission_type: basic
model_repo: vicgalle/Roleplay-Llama-3-8B
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: vicgalle-roleplay-llama-3-8b_v17
is_internal_developer: True
language_model: vicgalle/Roleplay-Llama-3-8B
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-02
win_ratio: 0.4864098200010315
generation_params: {'temperature': 1.0, '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. You are {bot_name} who has persona: {memory}. 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<|eot_id|>', 'prompt_template': '<|start_header_id|>system<|end_header_id|>\n\nExample 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}
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'}
model_eval_status: pending
Resubmit model
Running pipeline stage MKMLizer
Starting job with name vicgalle-roleplay-llama-3-8b-v17-mkmlizer
Waiting for job on vicgalle-roleplay-llama-3-8b-v17-mkmlizer to finish
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: ║     _____            __           __                                ║
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: ║       /___/                                                         ║
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: ║                                                                     ║
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: ║  Version: 0.8.10                                                    ║
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: ║                                                                     ║
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: ║  The license key for the current software has been verified as      ║
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: ║  belonging to:                                                      ║
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: ║                                                                     ║
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: ║  Chai Research Corp.                                                ║
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: ║                                                                     ║
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
vicgalle-roleplay-llama-3-8b-v17-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.
vicgalle-roleplay-llama-3-8b-v17-mkmlizer:   warnings.warn(warning_message, FutureWarning)
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: Downloaded to shared memory in 25.933s
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: quantizing model to /dev/shm/model_cache
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: Saving flywheel model at /dev/shm/model_cache
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  30%|██▉       | 86/291 [00:01<00:02, 85.07it/s]
Loading 0:  64%|██████▍   | 187/291 [00:02<00:01, 93.52it/s]
Loading 0:  99%|█████████▊| 287/291 [00:09<00:00, 25.35it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: quantized model in 21.587s
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: Processed model vicgalle/Roleplay-Llama-3-8B in 48.925s
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: creating bucket guanaco-mkml-models
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v17
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v17/config.json
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v17/tokenizer_config.json
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v17/special_tokens_map.json
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v17/tokenizer.json
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v17/flywheel_model.0.safetensors
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
vicgalle-roleplay-llama-3-8b-v17-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.
vicgalle-roleplay-llama-3-8b-v17-mkmlizer:   warnings.warn(
vicgalle-roleplay-llama-3-8b-v17-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.
vicgalle-roleplay-llama-3-8b-v17-mkmlizer:   warnings.warn(
vicgalle-roleplay-llama-3-8b-v17-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.
vicgalle-roleplay-llama-3-8b-v17-mkmlizer:   warnings.warn(
vicgalle-roleplay-llama-3-8b-v17-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()
vicgalle-roleplay-llama-3-8b-v17-mkmlizer:   return self.fget.__get__(instance, owner)()
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: creating bucket guanaco-reward-models
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: Bucket 's3://guanaco-reward-models/' created
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v17_reward
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v17_reward/tokenizer_config.json
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v17_reward/special_tokens_map.json
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v17_reward/merges.txt
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v17_reward/config.json
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v17_reward/vocab.json
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v17_reward/tokenizer.json
vicgalle-roleplay-llama-3-8b-v17-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v17_reward/reward.tensors
Job vicgalle-roleplay-llama-3-8b-v17-mkmlizer completed after 77.46s with status: succeeded
Stopping job with name vicgalle-roleplay-llama-3-8b-v17-mkmlizer
Pipeline stage MKMLizer completed in 78.52s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.23s
Running pipeline stage ISVCDeployer
Creating inference service vicgalle-roleplay-llama-3-8b-v17
Waiting for inference service vicgalle-roleplay-llama-3-8b-v17 to be ready
Inference service vicgalle-roleplay-llama-3-8b-v17 ready after 40.43973708152771s
Pipeline stage ISVCDeployer completed in 46.57s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.064483880996704s
Received healthy response to inference request in 1.1842687129974365s
Received healthy response to inference request in 1.1785054206848145s
Received healthy response to inference request in 1.177783489227295s
Received healthy response to inference request in 1.1751689910888672s
5 requests
0 failed requests
5th percentile: 1.1756918907165528
10th percentile: 1.1762147903442384
20th percentile: 1.1772605895996093
30th percentile: 1.1779278755187987
40th percentile: 1.1782166481018066
50th percentile: 1.1785054206848145
60th percentile: 1.1808107376098633
70th percentile: 1.1831160545349122
80th percentile: 1.3603117465972903
90th percentile: 1.712397813796997
95th percentile: 1.8884408473968504
99th percentile: 2.0292752742767335
mean time: 1.3560420989990234
Pipeline stage StressChecker completed in 8.79s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.11s
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 0.21s
%s, retrying in %s seconds...
vicgalle-roleplay-llama-3-8b_v17 status is now deployed due to DeploymentManager action
%s, retrying in %s seconds...
vicgalle-roleplay-llama-3-8b_v17 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of vicgalle-roleplay-llama-3-8b_v17
Running pipeline stage ISVCDeleter
Checking if service vicgalle-roleplay-llama-3-8b-v17 is running
Tearing down inference service vicgalle-roleplay-llama-3-8b-v17
Toredown service vicgalle-roleplay-llama-3-8b-v17
Pipeline stage ISVCDeleter completed in 7.20s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key vicgalle-roleplay-llama-3-8b-v17/config.json from bucket guanaco-mkml-models
Deleting key vicgalle-roleplay-llama-3-8b-v17/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key vicgalle-roleplay-llama-3-8b-v17/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key vicgalle-roleplay-llama-3-8b-v17/tokenizer.json from bucket guanaco-mkml-models
Deleting key vicgalle-roleplay-llama-3-8b-v17/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key vicgalle-roleplay-llama-3-8b-v17_reward/config.json from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v17_reward/merges.txt from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v17_reward/reward.tensors from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v17_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v17_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v17_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v17_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.83s
vicgalle-roleplay-llama-3-8b_v17 status is now torndown due to DeploymentManager action